{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T14:29:49Z","timestamp":1776090589921,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031723834","type":"print"},{"value":"9783031723841","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\/978-3-031-72384-1_18","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T11:02:53Z","timestamp":1727866973000},"page":"184-194","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing Human-Computer Interaction in\u00a0Chest X-Ray Analysis Using Vision and\u00a0Language Model with\u00a0Eye Gaze Patterns"],"prefix":"10.1007","author":[{"given":"Yunsoo","family":"Kim","sequence":"first","affiliation":[]},{"given":"Jinge","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yusuf","family":"Abdulle","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Honghan","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"18_CR1","unstructured":"Bae, S., Kyung, D., Ryu, J., Cho, E., Lee, G., Kweon, S., Oh, J., Ji, L., Chang, E., Kim, T., et\u00a0al.: Ehrxqa: A multi-modal question answering dataset for electronic health records with chest x-ray images. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"18_CR2","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s13244-016-0534-1","volume":"8","author":"AP Brady","year":"2017","unstructured":"Brady, A.P.: Error and discrepancy in radiology: inevitable or avoidable? Insights into imaging 8, 171\u2013182 (2017)","journal-title":"Insights into imaging"},{"key":"18_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102285","volume":"127","author":"FM Calisto","year":"2022","unstructured":"Calisto, F.M., Santiago, C., Nunes, N., Nascimento, J.C.: Breastscreening-ai: Evaluating medical intelligent agents for human-ai interactions. Artificial Intelligence in Medicine 127, 102285 (2022)","journal-title":"Artificial Intelligence in Medicine"},{"key":"18_CR4","first-page":"16344","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems 35, 16344\u201316359 (2022)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"18_CR5","unstructured":"He, P., Gao, J., Chen, W.: Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543 (2021)"},{"key":"18_CR6","unstructured":"Hsieh, C., Ouyang, C., Nascimento, J.C., Pereira, J., Jorge, J., Moreira, C.: Mimic-eye: Integrating mimic datasets with reflacx and eye gaze for multimodal deep learning applications (2023)"},{"key":"18_CR7","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Hwang, E.J., Lee, J.H., Kim, J.H., Lim, W.H., Goo, J.M., Park, C.M.: Deep learning computer-aided detection system for pneumonia in febrile neutropenia patients: a diagnostic cohort study. BMC Pulmonary Medicine 21(1), \u00a0406 (2021). https:\/\/doi.org\/10.1186\/s12890-021-01768-0, https:\/\/doi.org\/10.1186\/s12890-021-01768-0","DOI":"10.1186\/s12890-021-01768-0"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Ji, C., Du, C., Zhang, Q., Wang, S., Ma, C., Xie, J., Zhou, Y., He, H., Shen, D.: Mammo-net: Integrating gaze supervision and interactive information in multi-view mammogram classification. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 68\u201378. Springer (2023)","DOI":"10.1007\/978-3-031-43990-2_7"},{"key":"18_CR10","unstructured":"Lee, S., Youn, J., Kim, M., Yoon, S.H.: Cxr-llava: Multimodal large language model for interpreting chest x-ray images. arXiv preprint arXiv:2310.18341 (2023)"},{"key":"18_CR11","unstructured":"Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., Gao, J.: Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, Y., Wang, Z., Liang, X., Liu, L., Wang, L., Cui, L., Tu, Z., Wang, L., Zhou, L.: A comprehensive study of gpt-4v\u2019s multimodal capabilities in medical imaging. medRxiv pp. 2023\u201311 (2023)","DOI":"10.1101\/2023.11.03.23298067"},{"key":"18_CR13","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out. pp. 74\u201381 (2004)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Liu, F., Shareghi, E., Meng, Z., Basaldella, M., Collier, N.: Self-alignment pretraining for biomedical entity representations. arXiv preprint arXiv:2010.11784 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.334"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"18_CR16","unstructured":"Liu, H., Li, C., Li, Y., Li, B., Zhang, Y., Shen, S., Lee, Y.J.: Llava-next: Improved reasoning, ocr, and world knowledge (January 2024), https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"18_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Ma, C., Zhao, L., Chen, Y., Wang, S., Guo, L., Zhang, T., Shen, D., Jiang, X., Liu, T.: Eye-gaze-guided vision transformer for rectifying shortcut learning. IEEE Transactions on Medical Imaging (2023)","DOI":"10.1109\/TMI.2023.3287572"},{"key":"18_CR19","unstructured":"OpenAI: Gpt-4 (2023), https:\/\/www.openai.com\/gpt-4"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Patel, B.N., Rosenberg, L., Willcox, G., Baltaxe, D., Lyons, M., Irvin, J., Rajpurkar, P., Amrhein, T., Gupta, R., Halabi, S., Langlotz, C., Lo, E., Mammarappallil, J., Mariano, A.J., Riley, G., Seekins, J., Shen, L., Zucker, E., Lungren, M.P.: Human\u2013machine partnership with artificial intelligence for chest radiograph diagnosis. npj Digital Medicine 2(1), \u00a0111 (2019). https:\/\/doi.org\/10.1038\/s41746-019-0189-7, https:\/\/doi.org\/10.1038\/s41746-019-0189-7","DOI":"10.1038\/s41746-019-0189-7"},{"key":"18_CR21","doi-asserted-by":"publisher","unstructured":"Qin, C., Yao, D., Shi, Y., Song, Z.: Computer-aided detection in chest radiography based on artificial intelligence: a survey. BioMedical Engineering OnLine 17(1), \u00a0113 (2018). https:\/\/doi.org\/10.1186\/s12938-018-0544-y, https:\/\/doi.org\/10.1186\/s12938-018-0544-y","DOI":"10.1186\/s12938-018-0544-y"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Shaheed, K., Szczuko, P., Abbas, Q., Hussain, A., Albathan, M.: Computer-aided diagnosis of covid-19 from chest x-ray images using hybrid-features and random forest classifier. Healthcare 11(6) (2023). https:\/\/doi.org\/10.3390\/healthcare11060837, https:\/\/www.mdpi.com\/2227-9032\/11\/6\/837","DOI":"10.3390\/healthcare11060837"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Tu, T., Azizi, S., Driess, D., Schaekermann, M., Amin, M., Chang, P.C., Carroll, A., Lau, C., Tanno, R., Ktena, I., et\u00a0al.: Towards generalist biomedical ai. arXiv preprint arXiv:2307.14334 (2023)","DOI":"10.1056\/AIoa2300138"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Ushio, A., Camacho-Collados, J.: T-ner: an all-round python library for transformer-based named entity recognition. arXiv preprint arXiv:2209.12616 (2022)","DOI":"10.18653\/v1\/2021.eacl-demos.7"},{"issue":"7","key":"18_CR26","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1109\/TMI.2022.3146973","volume":"41","author":"S Wang","year":"2022","unstructured":"Wang, S., Ouyang, X., Liu, T., Wang, Q., Shen, D.: Follow my eye: Using gaze to supervise computer-aided diagnosis. IEEE Transactions on Medical Imaging 41(7), 1688\u20131698 (2022)","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Wei, C.H., Peng, Y., Leaman, R., Davis, A.P., Mattingly, C.J., Li, J., Wiegers, T.C., Lu, Z.: Assessing the state of the art in biomedical relation extraction: overview of the biocreative v chemical-disease relation (cdr) task. Database 2016 (2016)","DOI":"10.1093\/database\/baw032"},{"key":"18_CR28","unstructured":"Wu, J., Kim, Y., Keller, E.C., Chow, J., Levine, A.P., Pontikos, N., Ibrahim, Z., Taylor, P., Williams, M.C., Wu, H.: Exploring multimodal large language models for radiology report error-checking. arXiv preprint arXiv:2312.13103 (2023)"},{"key":"18_CR29","unstructured":"Wu, J., Kim, Y., Wu, H.: Hallucination benchmark in medical visual question answering. arXiv preprint arXiv:2401.05827 (2024)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Yildirim, N., Richardson, H., Wetscherek, M.T., Bajwa, J., Jacob, J., Pinnock, M.A., Harris, S., de\u00a0Castro, D.C., Bannur, S., Hyland, S.L., et\u00a0al.: Multimodal healthcare ai: Identifying and designing clinically relevant vision-language applications for radiology. arXiv preprint arXiv:2402.14252 (2024)","DOI":"10.1145\/3613904.3642013"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Wang, S., Wang, Q., Shen, D.: Mining gaze for contrastive learning toward computer-assisted diagnosis. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 7543\u20137551 (2024)","DOI":"10.1609\/aaai.v38i7.28586"}],"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\/978-3-031-72384-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T11:15:01Z","timestamp":1727867701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72384-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723834","9783031723841"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72384-1_18","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"}}]}}