{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T10:19:47Z","timestamp":1783419587611,"version":"3.54.6"},"reference-count":147,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00371-024-03579-w","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T04:01:31Z","timestamp":1722225691000},"page":"2953-2972","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Visual\u2013language foundation models in medicine"],"prefix":"10.1007","volume":"41","author":[{"given":"Chunyu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixiao","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouyu","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingyao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehua","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangning","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying Feng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dian","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,29]]},"reference":[{"key":"3579_CR1","doi-asserted-by":"publisher","first-page":"101213","DOI":"10.1016\/j.xcrm.2023.101213","volume":"4","author":"Z Guan","year":"2023","unstructured":"Guan, Z., Li, H., Liu, R., Cai, C., Liu, Y., Li, J., Wang, X., Huang, S., Wu, L., Liu, D., Yu, S., Wang, Z., Shu, J., Hou, X., Yang, X., Jia, W., Sheng, B.: Artificial intelligence in diabetes management: advancements, opportunities, and challenges. Cell Reports Med. 4, 101213 (2023). https:\/\/doi.org\/10.1016\/j.xcrm.2023.101213","journal-title":"Cell Reports Med."},{"key":"3579_CR2","doi-asserted-by":"publisher","first-page":"3871","DOI":"10.1007\/s00371-024-03391-6","volume":"40","author":"SG Ali","year":"2024","unstructured":"Ali, S.G., Zhang, C., Guan, Z., Chen, T., Wu, Q., Li, P., Yang, P., Ghazanfar, Z., Jung, Y., Chen, Y., Sheng, B., Tham, Y.-C., Wang, X., Wen, Y.: AI-enhanced digital technologies for myopia management: advancements, challenges, and future prospects. Vis. Comput. 40, 3871\u20133887 (2024). https:\/\/doi.org\/10.1007\/s00371-024-03391-6","journal-title":"Vis. Comput."},{"key":"3579_CR3","doi-asserted-by":"publisher","first-page":"7479","DOI":"10.3390\/app13137479","volume":"13","author":"FC Kitsios","year":"2023","unstructured":"Kitsios, F.C., Kamariotou, M., Syngelakis, A.I., Talias, M.A.: Recent advances of artificial intelligence in healthcare. A systematic literature review. Appl. Sci. 13, 7479 (2023)","journal-title":"Appl. Sci."},{"key":"3579_CR4","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E.J.: High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44 (2019)","journal-title":"Nat. Med."},{"key":"3579_CR5","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","volume":"380","author":"A Rajkomar","year":"2019","unstructured":"Rajkomar, A., Dean, J., Kohane, I.: Machine learning in medicine. N. Engl. J. Med. 380, 1347\u20131358 (2019). https:\/\/doi.org\/10.1056\/NEJMra1814259","journal-title":"N. Engl. J. Med."},{"key":"3579_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3625287","volume":"56","author":"C Patr\u00edcio","year":"2022","unstructured":"Patr\u00edcio, C., Neves, J.C., Teixeira, L.F.: Explainable deep learning methods in medical image classification: a survey. ACM Comput. Surv. 56, 1\u201341 (2022)","journal-title":"ACM Comput. Surv."},{"key":"3579_CR7","doi-asserted-by":"publisher","first-page":"e1548","DOI":"10.1002\/wsbm.1548","volume":"14","author":"D Jin","year":"2021","unstructured":"Jin, D., Sergeeva, E., Weng, W.-H., Chauhan, G., Szolovits, P.: Explainable deep learning in healthcare: a methodological survey from an attribution view. WIREs Mech Disease 14, e1548 (2021)","journal-title":"WIREs Mech Disease"},{"key":"3579_CR8","unstructured":"Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., Arx, S. von, Bernstein, M.S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E., Buch, S., Card, D., Castellon, R., Chatterji, N.S., Chen, A.S., Creel, K.A., Davis, J., Demszky, D., Donahue, C., Doumbouya, M., Durmus, E., Ermon, S., Etchemendy, J., Ethayarajh, K., Fei-Fei, L., Finn, C., Gale, T., Gillespie, L., Goel, K., Goodman, N.D., Grossman, S., Guha, N., Hashimoto, T., Henderson, P., Hewitt, J., Ho, D.E., Hong, J., Hsu, K., Huang, J., Icard, T.F., Jain, S., Jurafsky, D., Kalluri, P., Karamcheti, S., Keeling, G., Khani, F., Khattab, O., Koh, P.W., Krass, M.S., Krishna, R., Kuditipudi, R., Kumar, A., Ladhak, F., Lee, M., Lee, T., Leskovec, J., Levent, I., Li, X.L., Li, X., Ma, T., Malik, A., Manning, C.D., Mirchandani, S., Mitchell, E., Munyikwa, Z., Nair, S., Narayan, A., Narayanan, D., Newman, B., Nie, A., Niebles, J.C., Nilforoshan, H., Nyarko, J.F., Ogut, G., Orr, L.J., Papadimitriou, I., Park, J.S., Piech, C., Portelance, E., Potts, C., Raghunathan, A., Reich, R., Ren, H., Rong, F., Roohani, Y.H., Ruiz, C., Ryan, J., R\u2019e, C., Sadigh, D., Sagawa, S., Santhanam, K., Shih, A., Srinivasan, K.P., Tamkin, A., Taori, R., Thomas, A.W., Tram\u00e8r, F., Wang, R.E., Wang, W., Wu, B., Wu, J., Wu, Y., Xie, S.M., Yasunaga, M., You, J., Zaharia, M.A., Zhang, M., Zhang, T., Zhang, X., Zhang, Y., Zheng, L., Zhou, K., Liang, P.: On the opportunities and risks of foundation models. ArXiv. abs\/2108.07258, (2021)"},{"key":"3579_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02305-7","author":"M Hao","year":"2024","unstructured":"Hao, M., Gong, J., Zeng, X., Liu, C., Guo, Y., Cheng, X., Wang, T., Ma, J., Zhang, X., Song, L.: Large-scale foundation model on single-cell transcriptomics. Nat. Methods (2024). https:\/\/doi.org\/10.1038\/s41592-024-02305-7","journal-title":"Nat. Methods"},{"key":"3579_CR10","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., Schramowski, P., Kundurthy, S., Crowson, K., Schmidt, L., Kaczmarczyk, R., Jitsev, J.: LAION-5B: An open large-scale dataset for training next generation image-text models. ArXiv. abs\/2210.08402, (2022)"},{"key":"3579_CR11","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1016\/j.scib.2024.01.004","volume":"69","author":"B Sheng","year":"2024","unstructured":"Sheng, B., Guan, Z., Lim, L.L., Jiang, Z., Mathioudakis, N., Li, J., Liu, R., Bao, Y., Bee, Y.M., Wang, Y.X., Zheng, Y., Tan, G.S.W., Ji, H., Car, J., Wang, H., Klonoff, D.C., Li, H., Tham, Y.C., Wong, T.Y., Jia, W.: Large language models for diabetes care: potentials and prospects. Sci Bull (Beijing). 69, 583\u2013588 (2024). https:\/\/doi.org\/10.1016\/j.scib.2024.01.004","journal-title":"Sci Bull (Beijing)."},{"key":"3579_CR12","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. Presented at the international conference on machine learning (2022)"},{"key":"3579_CR13","doi-asserted-by":"crossref","unstructured":"Singh, A., Hu, R., Goswami, V., Couairon, G., Galuba, W., Rohrbach, M., Kiela, D.: FLAVA: a foundational language and vision alignment model. In 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). 15617\u201315629 (2021)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"3579_CR14","doi-asserted-by":"crossref","unstructured":"Thawakar, O., Shaker, A.M., Mullappilly, S.S., Cholakkal, H., Anwer, R.M., Khan, S.S., Laaksonen, J., Khan, F.S.: XrayGPT: Chest radiographs summarization using medical vision-language models. ArXiv. abs\/2306.07971, (2023)","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"3579_CR15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3369699","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2024). https:\/\/doi.org\/10.1109\/tpami.2024.3369699","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3579_CR16","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1038\/s41591-024-02959-y","volume":"30","author":"M Christensen","year":"2024","unstructured":"Christensen, M., Vukadinovic, M., Yuan, N., Ouyang, D.: Vision-language foundation model for echocardiogram interpretation. Nat. Med. 30, 1481\u20131488 (2024). https:\/\/doi.org\/10.1038\/s41591-024-02959-y","journal-title":"Nat. Med."},{"key":"3579_CR17","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1038\/s41591-024-02887-x","volume":"30","author":"C Kim","year":"2024","unstructured":"Kim, C., Gadgil, S.U., DeGrave, A.J., Omiye, J.A., Cai, Z.R., Daneshjou, R., Lee, S.I.: Transparent medical image AI via an image-text foundation model grounded in medical literature. Nat. Med. 30, 1154\u20131165 (2024). https:\/\/doi.org\/10.1038\/s41591-024-02887-x","journal-title":"Nat. Med."},{"key":"3579_CR18","doi-asserted-by":"publisher","first-page":"4542","DOI":"10.1038\/s41467-023-40260-7","volume":"14","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Wu, C., Zhang, Y., Xie, W., Wang, Y.: Knowledge-enhanced visual-language pre-training on chest radiology images. Nat. Commun. 14, 4542 (2023). https:\/\/doi.org\/10.1038\/s41467-023-40260-7","journal-title":"Nat. Commun."},{"key":"3579_CR19","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T.J., Zou, J.: A visual-language foundation model for pathology image analysis using medical twitter. Nat. Med. 29, 2307\u20132316 (2023). https:\/\/doi.org\/10.1038\/s41591-023-02504-3","journal-title":"Nat. Med."},{"key":"3579_CR20","doi-asserted-by":"crossref","unstructured":"Li, Q., Cai, W., Wang, X., Zhou, Y., Feng, D.D., Chen, M.: Medical image classification with convolutional neural network. In: 2014 13th International conference on control automation robotics & vision (ICARCV). pp. 844\u2013848 (2014)","DOI":"10.1109\/ICARCV.2014.7064414"},{"key":"3579_CR21","doi-asserted-by":"publisher","first-page":"9375","DOI":"10.1109\/ACCESS.2017.2788044","volume":"6","author":"J Ker","year":"2018","unstructured":"Ker, J., Wang, L., Rao, J., Lim, T.: Deep learning applications in medical image analysis. IEEE Access. 6, 9375\u20139389 (2018). https:\/\/doi.org\/10.1109\/ACCESS.2017.2788044","journal-title":"IEEE Access."},{"key":"3579_CR22","doi-asserted-by":"crossref","unstructured":"Pechenizkiy, M., Tsymbal, A., Puuronen, S., Pechenizkiy, O.: Class noise and supervised learning in medical domains: the effect of feature extraction. In: 19th IEEE symposium on computer-based medical systems (CBMS\u201906). pp. 708\u2013713 (2006)","DOI":"10.1109\/CBMS.2006.65"},{"key":"3579_CR23","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: 2015 IEEE international conference on computer vision (ICCV). pp. 1422\u20131430. IEEE, Santiago, Chile (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"3579_CR24","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles, http:\/\/arxiv.org\/abs\/1603.09246, (2017)"},{"key":"3579_CR25","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations, http:\/\/arxiv.org\/abs\/1803.07728, (2018)"},{"key":"3579_CR26","doi-asserted-by":"crossref","unstructured":"Feng, Z., Xu, C., Tao, D.: Self-supervised representation learning by rotation feature decoupling. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp. 10356\u201310366. IEEE, Long Beach, CA, USA (2019)","DOI":"10.1109\/CVPR.2019.01061"},{"key":"3579_CR27","unstructured":"Ballard, D.H.: Modular learning in neural networks. In: Proceedings of the sixth national conference on artificial intelligence, vol 1. pp. 279\u2013284. AAAI Press, Seattle, Washington (1987)"},{"key":"3579_CR28","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015). https:\/\/doi.org\/10.1016\/j.neunet.2014.09.003","journal-title":"Neural Netw."},{"key":"3579_CR29","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). pp. 2536\u20132544. IEEE, Las Vegas, NV, USA (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"3579_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Dollar, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). pp. 15979\u201315988. IEEE, New Orleans, LA, USA (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3579_CR31","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1145\/3458754","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., Poon, H.: Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthcare. 3, 21\u2013223 (2021). https:\/\/doi.org\/10.1145\/3458754","journal-title":"ACM Trans. Comput. Healthcare."},{"key":"3579_CR32","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C.H., Kang, J.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36, 1234\u20131240 (2020). https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinformatics"},{"key":"3579_CR33","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., Hu, H.: SimMIM: A simple framework for masked image modeling. Presented at the proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"3579_CR34","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/978-3-319-46493-0_35","volume-title":"Computer Vision\u2014ECCV 2016","author":"G Larsson","year":"2016","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision\u2014ECCV 2016, pp. 577\u2013593. Springer International Publishing, Cham (2016)"},{"key":"3579_CR35","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision\u2014ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision\u2014ECCV 2016, pp. 649\u2013666. Springer International Publishing, Cham (2016)"},{"key":"3579_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Split-brain autoencoders: unsupervised learning by cross-channel prediction. Presented at the proceedings of the IEEE conference on computer vision and pattern recognition (2017)","DOI":"10.1109\/CVPR.2017.76"},{"key":"3579_CR37","doi-asserted-by":"publisher","first-page":"113326","DOI":"10.1109\/ACCESS.2021.3104515","volume":"9","author":"I Zeger","year":"2021","unstructured":"Zeger, I., Grgic, S., Vukovic, J., Sisul, G.: Grayscale image colorization methods: overview and evaluation. IEEE Access. 9, 113326\u2013113346 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3104515","journal-title":"IEEE Access."},{"key":"3579_CR38","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE computer society conference on computer vision and pattern recognition - vol 2 (CVPR\u201906). pp. 1735\u20131742. IEEE, New York, NY, USA (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"3579_CR39","first-page":"9912","volume-title":"Advances in Neural Information Processing Systems","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, pp. 9912\u20139924. Curran Associates, Inc, Glasgow (2020)"},{"key":"3579_CR40","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. Presented at the proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"3579_CR41","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th international conference on machine learning. pp. 1597\u20131607. PMLR (2020)"},{"key":"3579_CR42","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3390\/informatics8030059","volume":"8","author":"A Chowdhury","year":"2021","unstructured":"Chowdhury, A., Rosenthal, J., Waring, J., Umeton, R.: applying self-supervised learning to medicine: review of the state of the art and medical implementations. Informatics. 8, 59 (2021). https:\/\/doi.org\/10.3390\/informatics8030059","journal-title":"Informatics."},{"key":"3579_CR43","first-page":"596","volume-title":"Advances in Neural Information Processing Systems","author":"K Sohn","year":"2020","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.A., Cubuk, E.D., Kurakin, A., Li, C.-L.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems, pp. 596\u2013608. Curran Associates, Inc, Glasgow (2020)"},{"key":"3579_CR44","doi-asserted-by":"crossref","unstructured":"Cai, Z., Ravichandran, A., Maji, S., Fowlkes, C., Tu, Z., Soatto, S.: Exponential moving average normalization for self-supervised and semi-supervised learning. Presented at the proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00026"},{"key":"3579_CR45","first-page":"22243","volume-title":"Advances in Neural Information Processing Systems","author":"T Chen","year":"2020","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. In: Advances in Neural Information Processing Systems, pp. 22243\u201322255. Curran Associates Inc, Glasglow (2020)"},{"key":"3579_CR46","first-page":"25697","volume":"35","author":"Z Cai","year":"2022","unstructured":"Cai, Z., Ravichandran, A., Favaro, P., Wang, M., Modolo, D., Bhotika, R., Tu, Z., Soatto, S.: Semi-supervised Vision transformers at scale. Adv. Neural. Inf. Process. Syst. 35, 25697\u201325710 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3579_CR47","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-031-20056-4_35","volume-title":"Computer Vision\u2014ECCV 2022","author":"Z Weng","year":"2022","unstructured":"Weng, Z., Yang, X., Li, A., Wu, Z., Jiang, Y.-G.: Semi-supervised vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2014ECCV 2022, pp. 605\u2013620. Springer Nature Switzerland, Cham (2022)"},{"key":"3579_CR48","unstructured":"APTOS\u202f: Eye preprocessing in diabetic retinopathy, https:\/\/kaggle.com\/code\/ratthachat\/aptos-eye-preprocessing-in-diabetic-retinopathy"},{"key":"3579_CR49","doi-asserted-by":"publisher","first-page":"106236","DOI":"10.1016\/j.cmpb.2021.106236","volume":"208","author":"F P\u00e9rez-Garc\u00eda","year":"2021","unstructured":"P\u00e9rez-Garc\u00eda, F., Sparks, R., Ourselin, S.: TorchIO: a python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput. Methods Programs Biomed. 208, 106236 (2021). https:\/\/doi.org\/10.1016\/j.cmpb.2021.106236","journal-title":"Comput. Methods Programs Biomed."},{"key":"3579_CR50","doi-asserted-by":"publisher","first-page":"104616","DOI":"10.1016\/j.jbi.2024.104616","volume":"151","author":"H Oss Boll","year":"2024","unstructured":"Oss Boll, H., Amirahmadi, A., Ghazani, M.M., de Morais, W.O., de Freitas, E.P., Soliman, A., Etminani, F., Byttner, S., Recamonde-Mendoza, M.: Graph neural networks for clinical risk prediction based on electronic health records: a survey. J. Biomed. Inform. 151, 104616 (2024). https:\/\/doi.org\/10.1016\/j.jbi.2024.104616","journal-title":"J. Biomed. Inform."},{"key":"3579_CR51","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. Presented at the proceedings of the IEEE\/CVF international conference on computer vision (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"3579_CR52","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2023","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y., Yang, Z., Zhang, Y., Tao, D.: A Survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45, 87\u2013110 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3152247","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3579_CR53","doi-asserted-by":"crossref","unstructured":"Khare, Y., Bagal, V., Mathew, M., Devi, A., Priyakumar, U.D., Jawahar, C.: MMBERT: multimodal BERT pretraining for improved medical VQA. In: 2021 IEEE 18th international symposium on biomedical imaging (ISBI). pp. 1033\u20131036. IEEE, Nice, France (2021)","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"3579_CR54","unstructured":"Zhou, H.-Y., Lian, C., Wang, L., Yu, Y.: Advancing radiograph representation learning with masked record modeling, http:\/\/arxiv.org\/abs\/2301.13155, (2023)"},{"key":"3579_CR55","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data, http:\/\/arxiv.org\/abs\/2308.02463, (2023)"},{"key":"3579_CR56","doi-asserted-by":"crossref","unstructured":"Yan, B., Sun, Y., Tan, W., Gu, Z., He, R., Chen, S., Pang, M.: Expertise-informed generative AI enables ultra-high data efficiency for building generalist medical foundation model, https:\/\/www.researchsquare.com\/article\/rs-3766549\/v1, (2024)","DOI":"10.21203\/rs.3.rs-3766549\/v1"},{"key":"3579_CR57","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","volume":"622","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y., Chia, M.A., Wagner, S.K., Ayhan, M.S., Williamson, D.J., Struyven, R.R., Liu, T., Xu, M., Lozano, M.G., Woodward-Court, P., Kihara, Y., Altmann, A., Lee, A.Y., Topol, E.J., Denniston, A.K., Alexander, D.C., Keane, P.A.: A foundation model for generalizable disease detection from retinal images. Nature 622, 156\u2013163 (2023). https:\/\/doi.org\/10.1038\/s41586-023-06555-x","journal-title":"Nature"},{"key":"3579_CR58","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th international conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"3579_CR59","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., Chen, B., Zhang, A., Williamson, D.F.K., Chen, R.J., Ding, T., Le, L.P., Chuang, Y.-S., Mahmood, F.: visual language pretrained multiple instance zero-shot transfer for histopathology images. Presented at the proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"3579_CR60","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/978-3-031-19809-0_39","volume-title":"Computer Vision\u2014ECCV 2022","author":"P M\u00fcller","year":"2022","unstructured":"M\u00fcller, P., Kaissis, G., Zou, C., Rueckert, D.: Joint learning of\u00a0localized representations from\u00a0medical images and\u00a0reports. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2014ECCV 2022, pp. 685\u2013701. Springer Nature Switzerland, Cham (2022)"},{"key":"3579_CR61","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedCLIP: Contrastive learning from unpaired medical images and text, http:\/\/arxiv.org\/abs\/2210.10163, (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"3579_CR62","doi-asserted-by":"publisher","unstructured":"Yan, B., Pei, M.: Clinical-BERT: vision-language pre-training for radiograph diagnosis and reports generation. Proceedings of the AAAI conference on artificial intelligence. vol.36, pp. 2982\u20132990 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i3.20204","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"3579_CR63","doi-asserted-by":"publisher","first-page":"6070","DOI":"10.1109\/JBHI.2022.3207502","volume":"26","author":"JH Moon","year":"2022","unstructured":"Moon, J.H., Lee, H., Shin, W., Kim, Y.-H., Choi, E.: Multi-modal understanding and generation for medical images and text via vision-language pre-training. IEEE J. Biomed. Health Inform. 26, 6070\u20136080 (2022). https:\/\/doi.org\/10.1109\/JBHI.2022.3207502","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"3579_CR64","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, G., Wan, X.: Align, reason and learn: enhancing medical vision-and-language pre-training with knowledge. In: Proceedings of the 30th ACM international conference on multimedia. pp. 5152\u20135161. Association for Computing Machinery, New York, NY, USA (2022)","DOI":"10.1145\/3503161.3547948"},{"key":"3579_CR65","first-page":"525","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2023","author":"W Lin","year":"2023","unstructured":"Lin, W., Zhao, Z., Zhang, X., Wu, C., Zhang, Y., Wang, Y., Xie, W.: PMC-CLIP: contrastive language-image pre-training using biomedical documents. In: Greenspan, H., Madabhushi, A., Mousavi, P., Salcudean, S., Duncan, J., Syeda-Mahmood, T., Taylor, R. (eds.) Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2023, pp. 525\u2013536. Springer Nature Switzerland, Cham (2023)"},{"key":"3579_CR66","first-page":"1","volume-title":"Computer Vision\u2014ECCV 2022","author":"B Boecking","year":"2022","unstructured":"Boecking, B., Usuyama, N., Bannur, S., Castro, D.C., Schwaighofer, A., Hyland, S., Wetscherek, M., Naumann, T., Nori, A., Alvarez-Valle, J., Poon, H., Oktay, O.: Making the most of text semantics to improve biomedical vision-language processing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2014ECCV 2022, pp. 1\u201321. Springer Nature Switzerland, Cham (2022)"},{"key":"3579_CR67","first-page":"374","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2023","author":"P Li","year":"2023","unstructured":"Li, P., Liu, G., He, J., Zhao, Z., Zhong, S.: Masked vision and language pre-training with unimodal and multimodal contrastive losses for medical visual question answering. In: Greenspan, H., Madabhushi, A., Mousavi, P., Salcudean, S., Duncan, J., Syeda-Mahmood, T., Taylor, R. (eds.) Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2023, pp. 374\u2013383. Springer Nature Switzerland, Cham (2023)"},{"key":"3579_CR68","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03384-5","author":"B Qian","year":"2024","unstructured":"Qian, B., Wang, X., Guan, Z., Yang, D., Ran, A., Li, T., Wang, Z., Wen, Y., Shu, X., Xie, J., Liu, S., Xing, G., Silva-Rodr\u00edguez, J., Kobbi, R., Li, P., Chen, T., Bi, L., Kim, J., Jia, W., Li, H., Qin, J., Zhang, P., Cheng, C.-Y., Heng, P.-A., Wong, T.Y., Cheung, C.Y., Tham, Y.-C., Thalmann, N.M., Sheng, B.: HRDC challenge: a public benchmark for hypertension and hypertensive retinopathy classification from fundus images. Vis. Comput. (2024). https:\/\/doi.org\/10.1007\/s00371-024-03384-5","journal-title":"Vis. Comput."},{"key":"3579_CR69","doi-asserted-by":"publisher","first-page":"100929","DOI":"10.1016\/j.patter.2024.100929","volume":"5","author":"B Qian","year":"2024","unstructured":"Qian, B., Chen, H., Wang, X., Guan, Z., Li, T., Jin, Y., Wu, Y., Wen, Y., Che, H., Kwon, G., Kim, J., Choi, S., Shin, S., Krause, F., Unterdechler, M., Hou, J., Feng, R., Li, Y., El Habib, D.M., Yang, D., Wu, Q., Zhang, P., Yang, X., Cai, Y., Tan, G.S.W., Cheung, C.Y., Jia, W., Li, H., Tham, Y.C., Wong, T.Y., Sheng, B.: DRAC 2022: a public benchmark for diabetic retinopathy analysis on ultra-wide optical coherence tomography angiography images. Patterns. 5, 100929 (2024). https:\/\/doi.org\/10.1016\/j.patter.2024.100929","journal-title":"Patterns."},{"key":"3579_CR70","doi-asserted-by":"publisher","first-page":"3242","DOI":"10.1038\/s41467-021-23458-5","volume":"12","author":"L Dai","year":"2021","unstructured":"Dai, L., Wu, L., Li, H., Cai, C., Wu, Q., Kong, H., Liu, R., Wang, X., Hou, X., Liu, Y., Long, X., Wen, Y., Lu, L., Shen, Y., Chen, Y., Shen, D., Yang, X., Zou, H., Sheng, B., Jia, W.: A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12, 3242 (2021). https:\/\/doi.org\/10.1038\/s41467-021-23458-5","journal-title":"Nat. Commun."},{"key":"3579_CR71","unstructured":"Qiu, J., Wu, J., Wei, H., Shi, P., Zhang, M., Sun, Y., Li, L., Liu, H., Liu, H., Hou, S., Zhao, Y., Shi, X., Xian, J., Qu, X., Zhu, S., Pan, L., Chen, X., Zhang, X., Jiang, S., Wang, K., Yang, C., Chen, M., Fan, S., Hu, J., Lv, A., Miao, H., Guo, L., Zhang, S., Pei, C., Fan, X., Lei, J., Wei, T., Duan, J., Liu, C., Xia, X., Xiong, S., Li, J., Lo, B., Tham, Y.C., Wong, T.Y., Wang, N., Yuan, W.: VisionFM: a multi-modal multi-task vision foundation model for generalist ophthalmic artificial intelligence, http:\/\/arxiv.org\/abs\/2310.04992, (2023)"},{"key":"3579_CR72","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y., Dollar, P., Girshick, R.: Segment anything. Presented at the proceedings of the IEEE\/CVF international conference on computer vision (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3579_CR73","doi-asserted-by":"crossref","unstructured":"Gong, S., Zhong, Y., Ma, W., Li, J., Wang, Z., Zhang, J., Heng, P.-A., Dou, Q.: 3DSAM-adapter: holistic adaptation of SAM from 2D to 3D for promptable medical image segmentation, http:\/\/arxiv.org\/abs\/2306.13465, (2023)","DOI":"10.1016\/j.media.2024.103324"},{"key":"3579_CR74","unstructured":"Wang, H., Guo, S., Ye, J., Deng, Z., Cheng, J., Li, T., Chen, J., Su, Y., Huang, Z., Shen, Y., Fu, B., Zhang, S., He, J., Qiao, Y.: SAM-Med3D, http:\/\/arxiv.org\/abs\/2310.15161, (2023)"},{"key":"3579_CR75","unstructured":"Cheng, J., Ye, J., Deng, Z., Chen, J., Li, T., Wang, H., Su, Y., Huang, Z., Chen, J., Jiang, L., Sun, H., He, J., Zhang, S., Zhu, M., Qiao, Y.: SAM-Med2D, http:\/\/arxiv.org\/abs\/2308.16184, (2023)"},{"key":"3579_CR76","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15, 654 (2024). https:\/\/doi.org\/10.1038\/s41467-024-44824-z","journal-title":"Nat. Commun."},{"key":"3579_CR77","first-page":"27922","volume":"36","author":"DMH Nguyen","year":"2023","unstructured":"Nguyen, D.M.H., Nguyen, H., Diep, N., Pham, T.N., Cao, T., Nguyen, B., Swoboda, P., Ho, N., Albarqouni, S., Xie, P., Sonntag, D., Niepert, M.: LVM-med: learning large-scale self-supervised vision models for medical imaging via second-order graph matching. Adv. Neural Inform. Process. Syst. 36, 27922\u201327950 (2023)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"3579_CR78","doi-asserted-by":"crossref","unstructured":"Ma, Y., Hua, Y., Deng, H., Song, T., Wang, H., Xue, Z., Cao, H., Ma, R., Guan, H.: Self-supervised vessel segmentation via adversarial learning. Presented at the proceedings of the IEEE\/CVF international conference on computer vision (2021)","DOI":"10.1109\/ICCV48922.2021.00744"},{"key":"3579_CR79","doi-asserted-by":"publisher","first-page":"103202","DOI":"10.1016\/j.media.2024.103202","volume":"96","author":"J Jiao","year":"2024","unstructured":"Jiao, J., Zhou, J., Li, X., Xia, M., Huang, Y., Huang, L., Wang, N., Zhang, X., Zhou, S., Wang, Y., Guo, Y.: USFM: a universal ultrasound foundation model generalized to tasks and organs towards label efficient image analysis. Med. Image Anal. 96, 103202 (2024). https:\/\/doi.org\/10.1016\/j.media.2024.103202","journal-title":"Med. Image Anal."},{"key":"3579_CR80","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1109\/TAI.2022.3147440","volume":"4","author":"Z Fang","year":"2023","unstructured":"Fang, Z., Bai, J., Guo, X., Wang, X., Gao, F., Yang, H.-Y., Kong, B., Hou, Y., Cao, K., Song, Q., Xia, J., Yin, Y.: Annotation-efficient COVID-19 pneumonia lesion segmentation using error-aware unified semisupervised and active learning. IEEE Trans. Artif. Intell. 4, 255\u2013267 (2023). https:\/\/doi.org\/10.1109\/TAI.2022.3147440","journal-title":"IEEE Trans. Artif. Intell."},{"key":"3579_CR81","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.compbiomed.2018.05.011","volume":"98","author":"N Tomita","year":"2018","unstructured":"Tomita, N., Cheung, Y.Y., Hassanpour, S.: Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Comput. Biol. Med. 98, 8\u201315 (2018). https:\/\/doi.org\/10.1016\/j.compbiomed.2018.05.011","journal-title":"Comput. Biol. Med."},{"key":"3579_CR82","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03418-y","author":"X Wang","year":"2024","unstructured":"Wang, X., Guan, Z., Qian, B., Chen, T., Wu, Q.: A deep learning system for the detection of optic disc neovascularization in diabetic retinopathy using optical coherence tomography angiography images. Vis. Comput. (2024). https:\/\/doi.org\/10.1007\/s00371-024-03418-y","journal-title":"Vis. Comput."},{"key":"3579_CR83","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1038\/s41591-023-02702-z","volume":"30","author":"L Dai","year":"2024","unstructured":"Dai, L., Sheng, B., Chen, T., Wu, Q., Liu, R., Cai, C., Wu, L., Yang, D., Hamzah, H., Liu, Y., Wang, X., Guan, Z., Yu, S., Li, T., Tang, Z., Ran, A., Che, H., Chen, H., Zheng, Y., Shu, J., Huang, S., Wu, C., Lin, S., Liu, D., Li, J., Wang, Z., Meng, Z., Shen, J., Hou, X., Deng, C., Ruan, L., Lu, F., Chee, M., Quek, T.C., Srinivasan, R., Raman, R., Sun, X., Wang, Y.X., Wu, J., Jin, H., Dai, R., Shen, D., Yang, X., Guo, M., Zhang, C., Cheung, C.Y., Tan, G.S.W., Tham, Y.-C., Cheng, C.-Y., Li, H., Wong, T.Y., Jia, W.: A deep learning system for predicting time to progression of diabetic retinopathy. Nat. Med. 30, 584\u2013594 (2024). https:\/\/doi.org\/10.1038\/s41591-023-02702-z","journal-title":"Nat. Med."},{"key":"3579_CR84","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., Lample, G.: LLaMA: Open and efficient foundation language models, http:\/\/arxiv.org\/abs\/2302.13971, (2023)"},{"key":"3579_CR85","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1007\/s10439-023-03172-7","volume":"51","author":"SS Biswas","year":"2023","unstructured":"Biswas, S.S.: Role of Chat GPT in public health. Ann. Biomed. Eng. 51, 868\u2013869 (2023). https:\/\/doi.org\/10.1007\/s10439-023-03172-7","journal-title":"Ann. Biomed. Eng."},{"key":"3579_CR86","doi-asserted-by":"publisher","first-page":"e917","DOI":"10.1016\/S2589-7500(23)00201-7","volume":"5","author":"BK Betzler","year":"2023","unstructured":"Betzler, B.K., Chen, H., Cheng, C.-Y., Lee, C.S., Ning, G., Song, S.J., Lee, A.Y., Kawasaki, R., Van Wijngaarden, P., Grzybowski, A., He, M., Li, D., Ran Ran, A., Ting, D.S.W., Teo, K., Ruamviboonsuk, P., Sivaprasad, S., Chaudhary, V., Tadayoni, R., Wang, X., Cheung, C.Y., Zheng, Y., Wang, Y.X., Tham, Y.C., Wong, T.Y.: Large language models and their impact in ophthalmology. Lancet Digital Health. 5, e917\u2013e924 (2023). https:\/\/doi.org\/10.1016\/S2589-7500(23)00201-7","journal-title":"Lancet Digital Health."},{"key":"3579_CR87","unstructured":"Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Hou, L., Clark, K., Pfohl, S., Cole-Lewis, H., Neal, D., Schaekermann, M., Wang, A., Amin, M., Lachgar, S., Mansfield, P., Prakash, S., Green, B., Dominowska, E., Arcas, B.A. y, Tomasev, N., Liu, Y., Wong, R., Semturs, C., Mahdavi, S.S., Barral, J., Webster, D., Corrado, G.S., Matias, Y., Azizi, S., Karthikesalingam, A., Natarajan, V.: Towards expert-level medical question answering with large language models, http:\/\/arxiv.org\/abs\/2305.09617, (2023)"},{"key":"3579_CR88","doi-asserted-by":"publisher","first-page":"e107","DOI":"10.1016\/S2589-7500(23)00021-3","volume":"5","author":"SB Patel","year":"2023","unstructured":"Patel, S.B., Lam, K.: ChatGPT: the future of discharge summaries? The Lancet Digital Health. 5, e107\u2013e108 (2023). https:\/\/doi.org\/10.1016\/S2589-7500(23)00021-3","journal-title":"The Lancet Digital Health."},{"key":"3579_CR89","doi-asserted-by":"publisher","first-page":"e179","DOI":"10.1016\/S2589-7500(23)00048-1","volume":"5","author":"SR Ali","year":"2023","unstructured":"Ali, S.R., Dobbs, T.D., Hutchings, H.A., Whitaker, I.S.: Using ChatGPT to write patient clinic letters. Lancet Digital Health. 5, e179\u2013e181 (2023). https:\/\/doi.org\/10.1016\/S2589-7500(23)00048-1","journal-title":"Lancet Digital Health."},{"key":"3579_CR90","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhao, Z., Ouyang, X., Wang, Q., Shen, D.: ChatCAD: interactive computer-aided diagnosis on medical image using large language models, http:\/\/arxiv.org\/abs\/2302.07257, (2023)","DOI":"10.1038\/s44172-024-00271-8"},{"key":"3579_CR91","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3398350","author":"Z Zhao","year":"2024","unstructured":"Zhao, Z., Wang, S., Gu, J., Zhu, Y., Mei, L., Zhuang, Z., Cui, Z., Wang, Q., Shen, D.: ChatCAD+: towards a universal and reliable interactive CAD using LLMs. IEEE Trans. Med. Imaging (2024). https:\/\/doi.org\/10.1109\/TMI.2024.3398350","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3579_CR92","doi-asserted-by":"crossref","unstructured":"Tang, X., Zou, A., Zhang, Z., Li, Z., Zhao, Y., Zhang, X., Cohan, A., Gerstein, M.: MedAgents: large language models as collaborators for zero-shot medical reasoning, http:\/\/arxiv.org\/abs\/2311.10537, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.33"},{"key":"3579_CR93","doi-asserted-by":"publisher","unstructured":"Lee, P., Bubeck, S., Petro, J.: Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N. Engl. J. Med. (2023). https:\/\/doi.org\/10.1056\/NEJMsr2214184","DOI":"10.1056\/NEJMsr2214184"},{"key":"3579_CR94","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.ajo.2023.05.024","volume":"254","author":"LZ Cai","year":"2023","unstructured":"Cai, L.Z., Shaheen, A., Jin, A., Fukui, R., Yi, J.S., Yannuzzi, N., Alabiad, C.: Performance of generative large language models on ophthalmology board-style questions. Am. J. Ophthalmol. 254, 141\u2013149 (2023). https:\/\/doi.org\/10.1016\/j.ajo.2023.05.024","journal-title":"Am. J. Ophthalmol."},{"key":"3579_CR95","doi-asserted-by":"publisher","first-page":"100324","DOI":"10.1016\/j.xops.2023.100324","volume":"3","author":"F Antaki","year":"2023","unstructured":"Antaki, F., Touma, S., Milad, D., El-Khoury, J., Duval, R.: Evaluating the performance of ChatGPT in ophthalmology: an analysis of its successes and shortcomings. Ophthalmol. Sci. 3, 100324 (2023). https:\/\/doi.org\/10.1016\/j.xops.2023.100324","journal-title":"Ophthalmol. Sci."},{"key":"3579_CR96","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.18653\/v1\/2023.findings-emnlp.83","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Xing, X., Lin, J., Zheng, H., Wang, Z., Liu, Q., Xu, X.: SoulChat: improving LLMs\u2019 empathy, listening, and comfort abilities through fine-tuning with multi-turn empathy conversations. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 1170\u20131183. Association for Computational Linguistics, Singapore (2023)"},{"key":"3579_CR97","unstructured":"Gemini Team., Reid, M., Savinov, N., Teplyashin, D., Dmitry, Lepikhin, Lillicrap, T., Alayrac, J., Soricut, R., Lazaridou, A., Firat, O., Schrittwieser, J., Antonoglou, I., Anil, R., Borgeaud, S., Dai, A., Millican, K., Dyer, E., Glaese, M., Sottiaux, T., Lee, B., Viola, F., Reynolds, M., Xu, Y., Molloy, J., Chen, J., Isard, M., Barham, P., Hennigan, T., McIlroy, R., Johnson, M., Schalkwyk, J., Collins, E., Rutherford, E., Moreira, E., Ayoub, K., Goel, M., Meyer, C., Thornton, G., Yang, Z., Michalewski, H., Abbas, Z., Schucher, N., Anand, A., Ives, R., Keeling, J., Lenc, K., Haykal, S., Shakeri, S., Shyam, P., Chowdhery, A., Ring, R., Spencer, S., Sezener, E., Vilnis, L., Chang, O., Morioka, N., Tucker, G., Zheng, C., Woodman, O., Attaluri, N., Kocisky, T., Eltyshev, E., Chen, X., Chung, T., Selo, V., Brahma, S., Georgiev, P., Slone, A., Zhu, Z., Lottes, J., Qiao, S., Caine, B., Riedel, S., Tomala, A., Chadwick, M., Love, J., Choy, P., Mittal, S., Houlsby, N., Tang, Y., Lamm, M., Bai, L., Zhang, Q., He, L., Cheng, Y., Humphreys, P., Li, Y., Brin, S., Cassirer, A., Miao, Y., Zilka, L., Tobin, T., Xu, K., Proleev, L., Sohn, D., Magni, A., Hendricks, L.A., Gao, I., Ontanon, S., Bunyan, O., Byrd, N., Sharma, A., Zhang, B., Pinto, M., Sinha, R., Mehta, H., Jia, D., Caelles, S., Webson, A., Morris, A., Roelofs, B., Ding, Y., Strudel, R., Xiong, X., Ritter, M., Dehghani, M., Chaabouni, R., Karmarkar, A., Lai, G., Mentzer, F., Xu, B., Li, Y., Zhang, Y., Paine, T.L., Goldin, A., Neyshabur, B., Baumli, K., Levskaya, A., Laskin, M., Jia, W., Rae, J.W., Xiao, K., He, A., Giordano, S., Yagati, L., Lespiau, J.-B., Natsev, P., Ganapathy, S., Liu, F., Martins, D., Chen, N., Xu, Y., Barnes, M., May, R., Vezer, A., Oh, J., Franko, K., Bridgers, S., Zhao, R., Wu, B., Mustafa, B., Sechrist, S., Parisotto, E., Pillai, T.S., Larkin, C., Gu, C., Sorokin, C., Krikun, M., Guseynov, A., Landon, J., Datta, R., Pritzel, A., Thacker, P., Yang, F., Hui, K., Hauth, A., Yeh, C.-K., Barker, D., Mao-Jones, J., Austin, S., Sheahan, H., Schuh, P., Svensson, J., Jain, R., Ramasesh, V., Briukhov, A., Chung, D.-W., von Glehn, T., Butterfield, C., Jhakra, P., Wiethoff, M., Frye, J., Grimstad, J., Changpinyo, B., Lan, C.L., Bortsova, A., Wu, Y., Voigtlaender, P., Sainath, T., Gu, S., Smith, C., Hawkins, W., Cao, K., Besley, J., Srinivasan, S., Omernick, M., Gaffney, C., Surita, G., Burnell, R., Damoc, B., Ahn, J., Brock, A., Pajarskas, M., Petrushkina, A., Noury, S., Blanco, L., Swersky, K., Ahuja, A., Avrahami, T., Misra, V., de Liedekerke, R., Iinuma, M., Polozov, A., York, S., Driessche, G. van den, Michel, P., Chiu, J., Blevins, R., Gleicher, Z., Recasens, A., Rrustemi, A., Gribovskaya, E., Roy, A., Gworek, W., Arnold, S.M.R., Lee, L., Lee-Thorp, J., Maggioni, M., Piqueras, E., Badola, K., Vikram, S., Gonzalez, L., Baddepudi, A., Senter, E., Devlin, J., Qin, J., Azzam, M., Trebacz, M., Polacek, M., Krishnakumar, K., Chang, S., Tung, M., Penchev, I., Joshi, R., Olszewska, K., Muir, C., Wirth, M., Hartman, A.J., Newlan, J., Kashem, S., Bolina, V., Dabir, E., van Amersfoort, J., Ahmed, Z., Cobon-Kerr, J., Kamath, A., Hrafnkelsson, A.M., Hou, L., Mackinnon, I., Frechette, A., Noland, E., Si, X., Taropa, E., Li, D., Crone, P., Gulati, A., Cevey, S., Adler, J., Ma, A., Silver, D., Tokumine, S., Powell, R., Lee, S., Vodrahalli, K., Hassan, S., Mincu, D., Yang, A., Levine, N., Brennan, J., Wang, M., Hodkinson, S., Zhao, J., Lipschultz, J., Pope, A., Chang, M.B., Li, C., Shafey, L.E., Paganini, M., Douglas, S., Bohnet, B., Pardo, F., Odoom, S., Rosca, M., Santos, C.N. dos, Soparkar, K., Guez, A., Hudson, T., Hansen, S., Asawaroengchai, C., Addanki, R., Yu, T., Stokowiec, W., Khan, M., Gilmer, J., Lee, J., Bostock, C.G., Rong, K., Caton, J., Pejman, P., Pavetic, F., Brown, G., Sharma, V., Lu\u010di\u0107, M., Samuel, R., Djolonga, J., Mandhane, A., Sj\u00f6sund, L.L., Buchatskaya, E., White, E., Clay, N., Jiang, J., Lim, H., Hemsley, R., Cankara, Z., Labanowski, J., De Cao, N., Steiner, D., Hashemi, S.H., Austin, J., Gergely, A., Blyth, T., Stanton, J., Shivakumar, K., Siddhant, A., Andreassen, A., Araya, C., Sethi, N., Shivanna, R., Hand, S., Bapna, A., Khodaei, A., Miech, A., Tanzer, G., Swing, A., Thakoor, S., Aroyo, L., Pan, Z., Nado, Z., Sygnowski, J., Winkler, S., Yu, D., Saleh, M., Maggiore, L., Bansal, Y., Garcia, X., Kazemi, M., Patil, P., Dasgupta, I., Barr, I., Giang, M., Kagohara, T., Danihelka, I., Marathe, A., Feinberg, V., Elhawaty, M., Ghelani, N., Horgan, D., Miller, H., Walker, L., Tanburn, R., Tariq, M., Shrivastava, D., Xia, F., Wang, Q., Chiu, C.-C., Ashwood, Z., Baatarsukh, K., Samangooei, S., Kaufman, R.L., Alcober, F., Stjerngren, A., Komarek, P., Tsihlas, K., Boral, A., Comanescu, R., Chen, J., Liu, R., Welty, C., Bloxwich, D., Chen, C., Sun, Y., Feng, F., Mauger, M., Dotiwalla, X., Hellendoorn, V., Sharman, M., Zheng, I., Haridasan, K., Barth-Maron, G., Swanson, C., Rogozi\u0144ska, D., Andreev, A., Rubenstein, P.K., Sang, R., Hurt, D., Elsayed, G., Wang, R., Lacey, D., Ili\u0107, A., Zhao, Y., Iwanicki, A., Lince, A., Chen, A., Lyu, C., Lebsack, C., Griffith, J., Gaba, M., Sandhu, P., Chen, P., Koop, A., Rajwar, R., Yeganeh, S.H., Chang, S., Zhu, R., Radpour, S., Davoodi, E., Lei, V.I., Xu, Y., Toyama, D., Segal, C., Wicke, M., Lin, H., Bulanova, A., Badia, A.P., Raki\u0107evi\u0107, N., Sprechmann, P., Filos, A., Hou, S., Campos, V., Kassner, N., Sachan, D., Fortunato, M., Iwuanyanwu, C., Nikolaev, V., Lakshminarayanan, B., Jazayeri, S., Varadarajan, M., Tekur, C., Fritz, D., Khalman, M., Reitter, D., Dasgupta, K., Sarcar, S., Ornduff, T., Snaider, J., Huot, F., Jia, J., Kemp, R., Trdin, N., Vijayakumar, A., Kim, L., Angermueller, C., Lao, L., Liu, T., Zhang, H., Engel, D., Greene, S., White, A., Austin, J., Taylor, L., Ashraf, S., Liu, D., Georgaki, M., Cai, I., Kulizhskaya, Y., Goenka, S., Saeta, B., Xu, Y., Frank, C., de Cesare, D., Robenek, B., Richardson, H., Alnahlawi, M., Yew, C., Ponnapalli, P., Tagliasacchi, M., Korchemniy, A., Kim, Y., Li, D., Rosgen, B., Levin, K., Wiesner, J., Banzal, P., Srinivasan, P., Yu, H., \u00dcnl\u00fc, \u00c7., Reid, D., Tung, Z., Finchelstein, D., Kumar, R., Elisseeff, A., Huang, J., Zhang, M., Aguilar, R., Gim\u00e9nez, M., Xia, J., Dousse, O., Gierke, W., Yates, D., Jalan, K., Li, L., Latorre-Chimoto, E., Nguyen, D.D., Durden, K., Kallakuri, P., Liu, Y., Johnson, M., Tsai, T., Talbert, A., Liu, J., Neitz, A., Elkind, C., Selvi, M., Jasarevic, M., Soares, L.B., Cui, A., Wang, P., Wang, A.W., Ye, X., Kallarackal, K., Loher, L., Lam, H., Broder, J., Holtmann-Rice, D., Martin, N., Ramadhana, B., Shukla, M., Basu, S., Mohan, A., Fernando, N., Fiedel, N., Paterson, K., Li, H., Garg, A., Park, J., Choi, D., Wu, D., Singh, S., Zhang, Z., Globerson, A., Yu, L., Carpenter, J., Quitry, F. de C., Radebaugh, C., Lin, C.-C., Tudor, A., Shroff, P., Garmon, D., Du, D., Vats, N., Lu, H., Iqbal, S., Yakubovich, A., Tripuraneni, N., Manyika, J., Qureshi, H., Hua, N., Ngani, C., Raad, M.A., Forbes, H., Stanway, J., Sundararajan, M., Ungureanu, V., Bishop, C., Li, Y., Venkatraman, B., Li, B., Thornton, C., Scellato, S., Gupta, N., Wang, Y., Tenney, I., Wu, X., Shenoy, A., Carvajal, G., Wright, D.G., Bariach, B., Xiao, Z., Hawkins, P., Dalmia, S., Farabet, C., Valenzuela, P., Yuan, Q., Agarwal, A., Chen, M., Kim, W., Hulse, B., Dukkipati, N., Paszke, A., Bolt, A., Choo, K., Beattie, J., Prendki, J., Vashisht, H., Santamaria-Fernandez, R., Cobo, L.C., Wilkiewicz, J., Madras, D., Elqursh, A., Uy, G., Ramirez, K., Harvey, M., Liechty, T., Zen, H., Seibert, J., Hu, C.H., Khorlin, A., Le, M., Aharoni, A., Li, M., Wang, L., Kumar, S., Casagrande, N., Hoover, J., Badawy, D.E., Soergel, D., Vnukov, D., Miecnikowski, M., Simsa, J., Kumar, P., Sellam, T., Vlasic, D., Daruki, S., Shabat, N., Zhang, J., Su, G., Zhang, J., Liu, J., Sun, Y., Palmer, E., Ghaffarkhah, A., Xiong, X., Cotruta, V., Fink, M., Dixon, L., Sreevatsa, A., Goedeckemeyer, A., Dimitriev, A., Jafari, M., Crocker, R., FitzGerald, N., Kumar, A., Ghemawat, S., Philips, I., Liu, F., Liang, Y., Sterneck, R., Repina, A., Wu, M., Knight, L., Georgiev, M., Lee, H., Askham, H., Chakladar, A., Louis, A., Crous, C., Cate, H., Petrova, D., Quinn, M., Owusu-Afriyie, D., Singhal, A., Wei, N., Kim, S., Vincent, D., Nasr, M., Choquette-Choo, C.A., Tojo, R., Lu, S., Casas, D. de L., Cheng, Y., Bolukbasi, T., Lee, K., Fatehi, S., Ananthanarayanan, R., Patel, M., Kaed, C., Li, J., Belle, S.R., Chen, Z., Konzelmann, J., P\u00f5der, S., Garg, R., Koverkathu, V., Brown, A., Dyer, C., Liu, R., Nova, A., Xu, J., Walton, A., Parrish, A., Epstein, M., McCarthy, S., Petrov, S., Hassabis, D., Kavukcuoglu, K., Dean, J., Vinyals, O.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context, http:\/\/arxiv.org\/abs\/2403.05530, (2024)"},{"key":"3579_CR98","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.-M., Xu, L., Ma, L., Yang, Y., Wu, X.-M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th international symposium on biomedical imaging (ISBI). pp. 1650\u20131654 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"3579_CR99","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: PathVQA: 30000+ questions for medical visual question answering, http:\/\/arxiv.org\/abs\/2003.10286, (2020)","DOI":"10.36227\/techrxiv.13127537.v1"},{"key":"3579_CR100","unstructured":"Ben Abacha, A., Sarrouti, M., Demner-Fushman, D., Hasan, S.A., M\u00fcller, H. eds: Overview of the VQA-Med task at imageCLEF 2021: visual question answering and generation in the medical domain. Proceedings of the CLEF 2021 conference and labs of the evaluation forum - working notes."},{"key":"3579_CR101","unstructured":"Yang, L., Xu, S., Sellergren, A., Kohlberger, T., Zhou, Y., Ktena, I., Kiraly, A., Ahmed, F., Hormozdiari, F., Jaroensri, T., Wang, E., Wulczyn, E., Jamil, F., Guidroz, T., Lau, C., Qiao, S., Liu, Y., Goel, A., Park, K., Agharwal, A., George, N., Wang, Y., Tanno, R., Barrett, D.G.T., Weng, W.-H., Mahdavi, S.S., Saab, K., Tu, T., Kalidindi, S.R., Etemadi, M., Cuadros, J., Sorensen, G., Matias, Y., Chou, K., Corrado, G., Barral, J., Shetty, S., Fleet, D., Eslami, S.M.A., Tse, D., Prabhakara, S., McLean, C., Steiner, D., Pilgrim, R., Kelly, C., Azizi, S., Golden, D.: Advancing multimodal medical capabilities of Gemini, http:\/\/arxiv.org\/abs\/2405.03162, (2024)"},{"key":"3579_CR102","doi-asserted-by":"crossref","unstructured":"Thawkar, O., Shaker, A., Mullappilly, S.S., Cholakkal, H., Anwer, R.M., Khan, S., Laaksonen, J., Khan, F.S.: XrayGPT: chest radiographs summarization using medical vision-language models, http:\/\/arxiv.org\/abs\/2306.07971, (2023)","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"3579_CR103","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu, A.J., Ting, D.S.J., Elangovan, K., Gutierrez, L., Tan, T.F., Ting, D.S.W.: Large language models in medicine. Nat. Med. 29, 1930\u20131940 (2023). https:\/\/doi.org\/10.1038\/s41591-023-02448-8","journal-title":"Nat. Med."},{"key":"3579_CR104","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1089\/heq.2018.0037","volume":"2","author":"J Guo","year":"2018","unstructured":"Guo, J., Li, B.: The application of medical artificial intelligence technology in rural areas of developing countries. Health Equity. 2, 174\u2013181 (2018). https:\/\/doi.org\/10.1089\/heq.2018.0037","journal-title":"Health Equity."},{"key":"3579_CR105","doi-asserted-by":"publisher","first-page":"100905","DOI":"10.1016\/j.lanwpc.2023.100905","volume":"41","author":"X Wang","year":"2023","unstructured":"Wang, X., Sanders, H.M., Liu, Y., Seang, K., Tran, B.X., Atanasov, A.G., Qiu, Y., Tang, S., Car, J., Wang, Y.X., Wong, T.Y., Tham, Y.C., Chung, K.C.: ChatGPT: promise and challenges for deployment in low- and middle-income countries. Lancet Reg. Health West Pac. 41, 100905 (2023). https:\/\/doi.org\/10.1016\/j.lanwpc.2023.100905","journal-title":"Lancet Reg. Health West Pac."},{"key":"3579_CR106","unstructured":"He, Y., Huang, F., Jiang, X., Nie, Y., Wang, M., Wang, J., Chen, H.: Foundation model for advancing healthcare: challenges, opportunities, and future directions. ArXiv. abs\/2404.03264, (2024)"},{"key":"3579_CR107","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2019-100081","author":"M Sujan","year":"2019","unstructured":"Sujan, M., Furniss, D., Grundy, K., Grundy, H., Nelson, D., Elliott, M., White, S., Habli, I., Reynolds, N.: Human factors challenges for the safe use of artificial intelligence in patient care. BMJ Health Care Inform. (2019). https:\/\/doi.org\/10.1136\/bmjhci-2019-100081","journal-title":"BMJ Health Care Inform."},{"key":"3579_CR108","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","volume":"183","author":"JW Ayers","year":"2023","unstructured":"Ayers, J.W., Poliak, A., Dredze, M., Leas, E.C., Zhu, Z., Kelley, J.B., Faix, D.J., Goodman, A.M., Longhurst, C.A., Hogarth, M., Smith, D.M.: Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern. Med. 183, 589\u2013596 (2023). https:\/\/doi.org\/10.1001\/jamainternmed.2023.1838","journal-title":"JAMA Intern. Med."},{"key":"3579_CR109","unstructured":"Xu, R., Baracaldo, N., Joshi, J.B.D.: Privacy-preserving machine learning: methods, challenges and directions. ArXiv. abs\/2108.04417, (2021)"},{"key":"3579_CR110","doi-asserted-by":"publisher","first-page":"216:1","DOI":"10.1145\/3653676","volume":"20","author":"J Liu","year":"2024","unstructured":"Liu, J., Zhou, J., Tian, J., Sun, W.: Recoverable privacy-preserving image classification through noise-like adversarial examples. ACM Trans. Multimed. Comput. Commun. Appl. 20, 216:1-216:27 (2024). https:\/\/doi.org\/10.1145\/3653676","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"3579_CR111","doi-asserted-by":"crossref","unstructured":"Moon, S., Lee, W.H.: Privacy-preserving federated learning in healthcare, In\u00a02023 International Conference on Electronics, Information, and Communication (ICEIC) pp. 1\u20134 (2023). IEEE.","DOI":"10.1109\/ICEIC57457.2023.10049966"},{"key":"3579_CR112","doi-asserted-by":"publisher","first-page":"e13600","DOI":"10.2196\/13600","volume":"21","author":"M Jones","year":"2019","unstructured":"Jones, M., Johnson, M., Shervey, M., Dudley, J.T., Zimmerman, N.: Privacy-preserving methods for feature engineering using blockchain: review, evaluation, and proof of concept. J. Med. Internet Res. 21, e13600 (2019). https:\/\/doi.org\/10.2196\/13600","journal-title":"J. Med. Internet Res."},{"issue":"3\u20134","key":"3579_CR113","first-page":"211","volume":"9","author":"D Cynthia","year":"2014","unstructured":"Cynthia, D., Aaron, R.: The algorithmic foundations of differential privacy. Found. Trends\u00ae Theor. Comput. Sci. 9(3\u20134), 211 (2014)","journal-title":"Found. Trends\u00ae Theor. Comput. Sci."},{"key":"3579_CR114","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","volume":"366","author":"Z Obermeyer","year":"2019","unstructured":"Obermeyer, Z., Powers, B., Vogeli, C., Mullainathan, S.: Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 447\u2013453 (2019). https:\/\/doi.org\/10.1126\/science.aax2342","journal-title":"Science"},{"key":"3579_CR115","unstructured":"Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017)"},{"key":"3579_CR116","unstructured":"Samek, W., Wiegand, T., M\u00fcller, K.-R.: Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. ArXiv. abs\/1708.08296, (2017)"},{"key":"3579_CR117","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2019","unstructured":"Arrieta, A.B., Rodr\u00edguez, N.D., Ser, J.D., Bennetot, A., Tabik, S., Barbado, A., Garc\u00eda, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., Herrera, F.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion. 58, 82\u2013115 (2019)","journal-title":"Inf. Fusion."},{"key":"3579_CR118","unstructured":"Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions, Advances in neural information processing systems,\u00a030 (2017)"},{"key":"3579_CR119","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s41746-024-01127-3","volume":"7","author":"L Goetz","year":"2024","unstructured":"Goetz, L., Seedat, N., Vandersluis, R., van der Schaar, M.: Generalization-a key challenge for responsible AI in patient-facing clinical applications. NPJ Digit Med. 7, 126 (2024). https:\/\/doi.org\/10.1038\/s41746-024-01127-3","journal-title":"NPJ Digit Med."},{"key":"3579_CR120","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64, 107\u2013115 (2021)","journal-title":"Commun. ACM"},{"key":"3579_CR121","first-page":"2261","volume":"23","author":"A Damour","year":"2020","unstructured":"Damour, A., Heller, K.A., Moldovan, D.I., Adlam, B., Alipanahi, B., Beutel, A., Chen, C., Deaton, J., Eisenstein, J., Hoffman, M.D., Hormozdiari, F., Houlsby, N., Hou, S., Jerfel, G., Karthikesalingam, A., Lucic, M., Ma, Y.-A., McLean, C.Y., Mincu, D., Mitani, A., Montanari, A., Nado, Z., Natarajan, V., Nielson, C., Osborne, T.F., Raman, R., Ramasamy, K., Sayres, R., Schrouff, J., Seneviratne, M.G., Sequeira, S., Suresh, H., Veitch, V., Vladymyrov, M., Wang, X., Webster, K., Yadlowsky, S., Yun, T., Zhai, X., Sculley, D.: Underspecification presents challenges for credibility in modern machine learning. J. Mach. Learn. Res. 23, 2261\u201322661 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"3579_CR122","first-page":"4349","volume":"29","author":"T Bolukbasi","year":"2016","unstructured":"Bolukbasi, T., Chang, K.-W., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. Adv. Neural Inform. Process. Syst. 29, 4349\u20134357 (2016)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"3579_CR123","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1001\/jama.2016.17217","volume":"316","author":"AL Beam","year":"2016","unstructured":"Beam, A.L., Kohane, I.S.: Translating artificial intelligence into clinical care. JAMA 316, 2368\u20132369 (2016). https:\/\/doi.org\/10.1001\/jama.2016.17217","journal-title":"JAMA"},{"key":"3579_CR124","doi-asserted-by":"publisher","first-page":"e489","DOI":"10.1016\/s2589-7500(20)30186-2","volume":"2","author":"J Futoma","year":"2020","unstructured":"Futoma, J., Simons, M., Panch, T., Doshi-Velez, F., Celi, L.A.: The myth of generalisability in clinical research and machine learning in health care. Lancet Digit Health. 2, e489\u2013e492 (2020). https:\/\/doi.org\/10.1016\/s2589-7500(20)30186-2","journal-title":"Lancet Digit Health."},{"key":"3579_CR125","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Kai, L., Li, F.-F.: ImageNet: a large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255 (2009). Ieee","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3579_CR126","unstructured":"Rajpurkar, P., Irvin, J.A., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D.Y., Bagul, A., Langlotz, C., Shpanskaya, K.S., Lungren, M.P., Ng, A.: CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. ArXiv. abs\/1711.05225, (2017)"},{"issue":"6","key":"3579_CR127","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1109\/JSTARS.2014.2329330","volume":"7","author":"Y Chen","year":"2014","unstructured":"Chen, Y., Lin, Z., Zhao, X., Wang, G., Gu, Y.: Deep learning-based classification of hyperspectral data. IEEE J. Sel. Topics Appl. Earth Obs. Rem. Sens. 7(6), 2094\u20132107 (2014)","journal-title":"IEEE J. Sel. Topics Appl. Earth Obs. Rem. Sens."},{"key":"3579_CR128","unstructured":"Yang, L., Wang, Y., Gao, M., Shrivastava, A., Weinberger, K.Q., Chao, W.L., Lim, S.N.: Deep co-training with task decomposition for semi-supervised domain adaptation. In\u00a0Proceedings of the IEEE\/CVF international conference on computer vision\u00a0(pp. 8906-8916)"},{"key":"3579_CR129","doi-asserted-by":"crossref","unstructured":"Shin, H.-C., Tenenholtz, N.A., Rogers, J.K., Schwarz, C.G., Senjem, M.L., Gunter, J.L., Andriole, K.P., Michalski, M.H.: Medical image synthesis for data augmentation and anonymization using generative adversarial networks. ArXiv. abs\/1807.10225, (2018)","DOI":"10.1007\/978-3-030-00536-8_1"},{"key":"3579_CR130","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s40708-016-0042-6","volume":"3","author":"A Holzinger","year":"2016","unstructured":"Holzinger, A.: Interactive machine learning for health informatics: when do we need the human-in-the-loop? Brain Inform. 3, 119\u2013131 (2016). https:\/\/doi.org\/10.1007\/s40708-016-0042-6","journal-title":"Brain Inform."},{"issue":"5","key":"3579_CR131","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/MC.2023.3240450","volume":"56","author":"A Majeed","year":"2023","unstructured":"Majeed, A., Hwang, S.O.: Data-centric artificial intelligence, preprocessing, and the quest for transformative artificial intelligence systems development. Computer 56(5), 109\u2013115 (2023)","journal-title":"Computer"},{"key":"3579_CR132","unstructured":"Yutong Bai, Jieru Mei, Alan Yuille, Cihang Xie: Are transformers more robust than CNNs?.In Proceedings of the 35th international conference on neural information processing systems. (2024)"},{"key":"3579_CR133","doi-asserted-by":"publisher","first-page":"e196972","DOI":"10.1001\/jamanetworkopen.2019.6972","volume":"2","author":"L Wang","year":"2019","unstructured":"Wang, L., Sha, L., Lakin, J.R., Bynum, J., Bates, D.W., Hong, P., Zhou, L.: Development and validation of a deep learning algorithm for mortality prediction in selecting patients with dementia for earlier palliative care interventions. JAMA Netw. Open 2, e196972 (2019). https:\/\/doi.org\/10.1001\/jamanetworkopen.2019.6972","journal-title":"JAMA Netw. Open"},{"key":"3579_CR134","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.202311-2185OC","author":"M Thillai","year":"2024","unstructured":"Thillai, M., Oldham, J.M., Ruggiero, A., Kanavati, F., McLellan, T., Saini, G., Johnson, S.R., Ble, F.X., Azim, A., Ostridge, K., Platt, A., Belvisi, M., Maher, T.M., Molyneaux, P.L.: Deep learning-based segmentation of CT scans predicts disease progression and mortality in IPF. Am. J. Respir. Crit. Care Med. (2024). https:\/\/doi.org\/10.1164\/rccm.202311-2185OC","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"3579_CR135","doi-asserted-by":"publisher","DOI":"10.1172\/jci157968","author":"F Li","year":"2022","unstructured":"Li, F., Su, Y., Lin, F., Li, Z., Song, Y., Nie, S., Xu, J., Chen, L., Chen, S., Li, H., Xue, K., Che, H., Chen, Z., Yang, B., Zhang, H., Ge, M., Zhong, W., Yang, C., Chen, L., Wang, F., Jia, Y., Li, W., Wu, Y., Li, Y., Gao, Y., Zhou, Y., Zhang, K., Zhang, X.: A deep-learning system predicts glaucoma incidence and progression using retinal photographs. J. Clin. Invest. (2022). https:\/\/doi.org\/10.1172\/jci157968","journal-title":"J. Clin. Invest."},{"key":"3579_CR136","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/s41551-021-00745-6","volume":"5","author":"K Zhang","year":"2021","unstructured":"Zhang, K., Liu, X., Xu, J., Yuan, J., Cai, W., Chen, T., Wang, K., Gao, Y., Nie, S., Xu, X., Qin, X., Su, Y., Xu, W., Olvera, A., Xue, K., Li, Z., Zhang, M., Zeng, X., Zhang, C.L., Li, O., Zhang, E.E., Zhu, J., Xu, Y., Kermany, D., Zhou, K., Pan, Y., Li, S., Lai, I.F., Chi, Y., Wang, C., Pei, M., Zang, G., Zhang, Q., Lau, J., Lam, D., Zou, X., Wumaier, A., Wang, J., Shen, Y., Hou, F.F., Zhang, P., Xu, T., Zhou, Y., Wang, G.: Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images. Nat Biomed Eng. 5, 533\u2013545 (2021). https:\/\/doi.org\/10.1038\/s41551-021-00745-6","journal-title":"Nat Biomed Eng."},{"key":"3579_CR137","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev, N., Glorot, X., Rae, J.W., Zielinski, M., Askham, H., Saraiva, A., Mottram, A., Meyer, C., Ravuri, S., Protsyuk, I., Connell, A., Hughes, C.O., Karthikesalingam, A., Cornebise, J., Montgomery, H., Rees, G., Laing, C., Baker, C.R., Peterson, K., Reeves, R., Hassabis, D., King, D., Suleyman, M., Back, T., Nielson, C., Ledsam, J.R., Mohamed, S.: A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 572, 116\u2013119 (2019). https:\/\/doi.org\/10.1038\/s41586-019-1390-1","journal-title":"Nature"},{"key":"3579_CR138","doi-asserted-by":"crossref","unstructured":"Madhu, A., Kumaraswamy, S.: Data augmentation using generative adversarial network for environmental sound classification.\u00a0In\u00a02019 27th European signal processing conference (EUSIPCO), pp. 1\u20135 (2019). IEEE","DOI":"10.23919\/EUSIPCO.2019.8902819"},{"key":"3579_CR139","doi-asserted-by":"crossref","unstructured":"Dunmore, A., Jang-Jaccard, J., Sabrina, F., Kwak, J.: A comprehensive survey of generative adversarial networks (GANs) in cybersecurity intrusion detection, IEEE (2023)","DOI":"10.1109\/ACCESS.2023.3296707"},{"key":"3579_CR140","doi-asserted-by":"crossref","unstructured":"Zemouri, R., L\u00e9vesque, M., \u00c9, B., Kirouac, M., Lafleur, F., Bernier, S., Merkhouf, A.: Recent research and applications in variational autoencoders for industrial prognosis and health management: a survey. In\u00a02022 Prognostics and health management conference (PHM-2022 London), pp. 193\u2013203 (2022). IEEE.","DOI":"10.1109\/PHM2022-London52454.2022.00042"},{"key":"3579_CR141","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","volume":"3","author":"N Rieke","year":"2020","unstructured":"Rieke, N., Hancox, J., Li, W., Milletar\u00ec, F., Roth, H.R., Albarqouni, S., Bakas, S., Galtier, M.N., Landman, B.A., Maier-Hein, K., Ourselin, S., Sheller, M., Summers, R.M., Trask, A., Xu, D., Baust, M., Cardoso, M.J.: The future of digital health with federated learning. NPJ Digit Med. 3, 119 (2020). https:\/\/doi.org\/10.1038\/s41746-020-00323-1","journal-title":"NPJ Digit Med."},{"key":"3579_CR142","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.ijmedinf.2018.01.007","volume":"112","author":"TS Brisimi","year":"2018","unstructured":"Brisimi, T.S., Chen, R., Mela, T., Olshevsky, A., Paschalidis, I.C., Shi, W.: Federated learning of predictive models from federated electronic health records. Int. J. Med. Inform. 112, 59\u201367 (2018). https:\/\/doi.org\/10.1016\/j.ijmedinf.2018.01.007","journal-title":"Int. J. Med. Inform."},{"key":"3579_CR143","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1038\/s41746-024-01097-6","volume":"7","author":"C Silcox","year":"2024","unstructured":"Silcox, C., Zimlichmann, E., Huber, K., Rowen, N., Saunders, R., McClellan, M., Kahn, C.N., Salzberg, C.A., Bates, D.W.: The potential for artificial intelligence to transform healthcare: perspectives from international health leaders. NPJ Digital Med. 7, 88 (2024). https:\/\/doi.org\/10.1038\/s41746-024-01097-6","journal-title":"NPJ Digital Med."},{"key":"3579_CR144","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M., Blau, H.M., Thrun, S.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115\u2013118 (2017). https:\/\/doi.org\/10.1038\/nature21056","journal-title":"Nature"},{"key":"3579_CR145","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1038\/nbt.3780","volume":"35","author":"BK Beaulieu-Jones","year":"2017","unstructured":"Beaulieu-Jones, B.K., Greene, C.S.: Reproducibility of computational workflows is automated using continuous analysis. Nat. Biotechnol. 35, 342\u2013346 (2017). https:\/\/doi.org\/10.1038\/nbt.3780","journal-title":"Nat. Biotechnol."},{"key":"3579_CR146","doi-asserted-by":"crossref","unstructured":"Butt, H.A., Ahad, A., Wasim, M., Madeira, F., Chamran, M.K.: 5G and IoT for intelligent healthcare: AI and machine learning approaches\u2014a review. Presented at the Smart objects and technologies for social good (2024)","DOI":"10.1007\/978-3-031-52524-7_8"},{"key":"3579_CR147","doi-asserted-by":"publisher","first-page":"e2348422","DOI":"10.1001\/jamanetworkopen.2023.48422","volume":"6","author":"A Youssef","year":"2023","unstructured":"Youssef, A., Ng, M.Y., Long, J., Hernandez-Boussard, T., Shah, N., Miner, A., Larson, D., Langlotz, C.P.: Organizational factors in clinical data sharing for artificial intelligence in health care. JAMA Netw. Open 6, e2348422 (2023). https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.48422","journal-title":"JAMA Netw. Open"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03579-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03579-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03579-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T11:31:07Z","timestamp":1741001467000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03579-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,29]]},"references-count":147,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["3579"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03579-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,29]]},"assertion":[{"value":"11 July 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}