{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:45:45Z","timestamp":1775263545830,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031721168","type":"print"},{"value":"9783031721175","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-72117-5_5","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:02:53Z","timestamp":1727870573000},"page":"46-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Aligning Human Knowledge with\u00a0Visual Concepts Towards Explainable Medical Image Classification"],"prefix":"10.1007","author":[{"given":"Yunhe","family":"Gao","sequence":"first","affiliation":[]},{"given":"Difei","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Mu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Dimitris","family":"Metaxas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"5_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"issue":"1","key":"5_CR2","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41746-021-00438-z","volume":"4","author":"R Aggarwal","year":"2021","unstructured":"Aggarwal, R., et al.: Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ Dig. Med. 4(1), 65 (2021)","journal-title":"NPJ Dig. Med."},{"issue":"5","key":"5_CR3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/acij.2019.10501","volume":"10","author":"W Al-Dhabyani","year":"2019","unstructured":"Al-Dhabyani, W., Gomaa, M., Khaled, H., Aly, F.: Deep learning approaches for data augmentation and classification of breast masses using ultrasound images. Int. J. Adv. Comput. Sci. Appl. 10(5), 1\u201311 (2019)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"5_CR4","doi-asserted-by":"publisher","unstructured":"Boecking, B., et\u00a0al.: Making the most of text semantics to improve biomedical vision\u2013language processing. In: European Conference on Computer Vision, pp. 1\u201321. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_1","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cai, L., Gao, J., Zhao, D.: A review of the application of deep learning in medical image classification and segmentation. Ann. Transl. Med. 8(11) (2020)","DOI":"10.21037\/atm.2020.02.44"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Cutillo, C.M., et al.: Machine intelligence in healthcare-perspectives on trustworthiness, explainability, usability, and transparency. NPJ Dig. Med. 3(1), 47 (2020)","DOI":"10.1038\/s41746-020-0254-2"},{"key":"5_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Gao, Y.: Training like a medical resident: context-prior learning toward universal medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11194\u201311204 (2024)","DOI":"10.1109\/CVPR52733.2024.01064"},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"Gao, Y., et al.: Focusnet: imbalanced large and small organ segmentation with an end-to-end deep neural network for head and neck ct images. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, 13\u201317 October 2019, Proceedings, Part III 22. pp. 829\u2013838. Springer, Heidelberg (2019). https:\/\/doi.org\/10.1007\/978-3-030-32248-9_92","DOI":"10.1007\/978-3-030-32248-9_92"},{"key":"5_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101831","volume":"67","author":"Y Gao","year":"2021","unstructured":"Gao, Y., et al.: Focusnetv 2: imbalanced large and small organ segmentation with adversarial shape constraint for head and neck ct images. Med. Image Anal. 67, 101831 (2021)","journal-title":"Med. Image Anal."},{"key":"5_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/978-3-030-87199-4_6","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Gao","year":"2021","unstructured":"Gao, Y., Zhou, M., Metaxas, D.N.: UTNet: a hybrid transformer architecture for medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 61\u201371. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87199-4_6"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR13","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916. PMLR (2021)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"5_CR15","unstructured":"Kakkad, J., Jannu, J., Sharma, K., Aggarwal, C., Medya, S.: A survey on explainability of graph neural networks. arXiv preprint arXiv:2306.01958 (2023)"},{"key":"5_CR16","unstructured":"Kather, J.N., Halama, N., Marx, A.: 100,000 histological images of human colorectal cancer and healthy tissue. Zenodo10 5281 (2018)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Khanna, N.N., et\u00a0al.: Economics of artificial intelligence in healthcare: diagnosis vs. treatment. In: Healthcare, vol.\u00a010, p.\u00a02493. MDPI (2022)","DOI":"10.3390\/healthcare10122493"},{"issue":"1","key":"5_CR18","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s12880-022-00793-7","volume":"22","author":"HE Kim","year":"2022","unstructured":"Kim, H.E., Cosa-Linan, A., Santhanam, N., Jannesari, M., Maros, M.E., Ganslandt, T.: Transfer learning for medical image classification: a literature review. BMC Med. Imaging 22(1), 69 (2022)","journal-title":"BMC Med. Imaging"},{"key":"5_CR19","unstructured":"Koh, P.W., et al.: Concept bottleneck models. In: ICML, pp. 5338\u20135348. PMLR (2020)"},{"key":"5_CR20","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"5_CR21","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. IEEE (2014)","DOI":"10.1109\/ICARCV.2014.7064414"},{"issue":"3","key":"5_CR22","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1016\/S0033-8389(01)00017-3","volume":"40","author":"L Liberman","year":"2002","unstructured":"Liberman, L., Menell, J.H.: Breast imaging reporting and data system (bi-rads). Radiol. Clin. 40(3), 409\u2013430 (2002)","journal-title":"Radiol. Clin."},{"issue":"3","key":"5_CR23","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3390\/data3030025","volume":"3","author":"P Porwal","year":"2018","unstructured":"Porwal, P., et al.: Indian diabetic retinopathy image dataset (idrid): a database for diabetic retinopathy screening research. Data 3(3), 25 (2018)","journal-title":"Data"},{"key":"5_CR24","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"5_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/978-3-319-19992-4_46","volume-title":"Information Processing in Medical Imaging","author":"W Shen","year":"2015","unstructured":"Shen, W., Zhou, M., Yang, F., Yang, C., Tian, J.: Multi-scale convolutional neural networks for lung nodule classification. In: Ourselin, S., Alexander, D.C., Westin, C.-F., Cardoso, M.J. (eds.) IPMI 2015. LNCS, vol. 9123, pp. 588\u2013599. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-19992-4_46"},{"issue":"1","key":"5_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5(1), 1\u20139 (2018)","journal-title":"Sci. Data"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Turkbey, B., et\u00a0al.: Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2. Eur. Urology 76(3), 340\u2013351 (2019)","DOI":"10.1016\/j.eururo.2019.02.033"},{"key":"5_CR29","unstructured":"Windsor, R., Jamaludin, A., Kadir, T., Zisserman, A.: Vision-language modelling for radiological imaging and reports in the low data regime. arXiv preprint arXiv:2303.17644 (2023)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Y., Panagopoulou, A., Zhou, S., Jin, D., Callison-Burch, C., Yatskar, M.: Language in a bottle: Language model guided concept bottlenecks for interpretable image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19187\u201319197 (2023)","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"5_CR31","unstructured":"Zhang, S., et\u00a0al.: Large-scale domain-specific pretraining for biomedical vision-language processing 2(3), 6 (2023). arXiv preprint arXiv:2303.00915"},{"key":"5_CR32","unstructured":"Zhang, Y., et al.: Data-centric foundation models in computational healthcare: a survey. arXiv preprint arXiv:2401.02458 (2024)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72117-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:12:23Z","timestamp":1727871143000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72117-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031721168","9783031721175"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72117-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}