{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:37:14Z","timestamp":1758587834407,"version":"3.44.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060037","type":"print"},{"value":"9783032060044","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06004-4_24","type":"book-chapter","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:21:59Z","timestamp":1758561719000},"page":"239-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Trustworthy Clinical Thinking in\u00a0MLLMs: Hierarchical Energy-based Reasoning for\u00a0interpretable MEdical Scans (HERMES)"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6519-5222","authenticated-orcid":false,"given":"Florence X.","family":"Doo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5313-382X","authenticated-orcid":false,"given":"Huiwen","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6784-764X","authenticated-orcid":false,"given":"Bradley A.","family":"Maron","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3483-8333","authenticated-orcid":false,"given":"Heng","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"24_CR1","unstructured":"Ben-Baruch, E., et al.: Asymmetric loss for multi-label classification (2021). https:\/\/arxiv.org\/abs\/2009.14119"},{"key":"24_CR2","unstructured":"Blankemeier, L., et al.: Merlin: a vision language foundation model for 3d computed tomography. arXiv preprint arXiv:2406.06512 (2024)"},{"key":"24_CR3","doi-asserted-by":"publisher","unstructured":"Chen, Y., Liu, C., Liu, X., Arcucci, R., Xiong, Z.: BIMCV-R: a landmark dataset for 3d CT text-image retrieval. In: Medical Image Computing and Computer Assisted Intervention (MICCAI) 2024. Lecture Notes in Computer Science, vol. 15011, pp. 124\u2013134. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-75489-3_12","DOI":"10.1007\/978-3-031-75489-3_12"},{"key":"24_CR4","unstructured":"Chen, Z., et al.: CheXagent: Towards a foundation model for chest x-ray interpretation. arXiv preprint arXiv:2406.09264 (2024)"},{"issue":"2","key":"24_CR5","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240320","volume":"312","author":"FX Doo","year":"2024","unstructured":"Doo, F.X., et al.: Optimal large language model characteristics to balance accuracy and energy use for sustainable medical applications. Radiology 312(2), e240320 (2024). https:\/\/doi.org\/10.1148\/radiol.240320","journal-title":"Radiology"},{"issue":"2","key":"24_CR6","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232030","volume":"310","author":"FX Doo","year":"2024","unstructured":"Doo, F.X., et al.: Environmental sustainability and AI in radiology: a double-edged sword. Radiology 310(2), e232030 (2024). https:\/\/doi.org\/10.1148\/radiol.232030","journal-title":"Radiology"},{"issue":"6","key":"24_CR7","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.acra.2016.08.012","volume":"24","author":"A Gijp","year":"2017","unstructured":"Gijp, A., Webb, E.M., Naeger, D.M.: How radiologists think: understanding fast and slow thought processing and how it can improve our teaching. Acad. Radiol. 24(6), 768\u2013771 (2017). https:\/\/doi.org\/10.1016\/j.acra.2016.08.012","journal-title":"Acad. Radiol."},{"key":"24_CR8","unstructured":"Gladstone, A., et al.: Energy-based transformers are scalable learners and thinkers. arXiv preprint arXiv:2507.02092 (2025)"},{"key":"24_CR9","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks (2017). https:\/\/arxiv.org\/abs\/1706.04599"},{"key":"24_CR10","unstructured":"Hamamci, I.E., et al.: A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities. arXiv preprint arXiv:2406.17055 (2024)"},{"key":"24_CR11","unstructured":"Hewitt, J., Geirhos, R., Kim, B.: We can\u2019t understand AI using our existing vocabulary (2025). https:\/\/arxiv.org\/abs\/2502.07586"},{"key":"24_CR12","volume-title":"Thinking, Fast and Slow","author":"D Kahneman","year":"2011","unstructured":"Kahneman, D.: Thinking, Fast and Slow. Farrar, Straus and Giroux, New York (2011)"},{"issue":"2","key":"24_CR13","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/s10278-018-0121-8","volume":"32","author":"LC Kelahan","year":"2018","unstructured":"Kelahan, L.C., Fong, A., Blumenthal, J., Kandaswamy, S., Ratwani, R.M., Filice, R.W.: The radiologist\u2019s gaze: mapping three-dimensional visual search in computed tomography of the abdomen and pelvis. J. Digit. Imaging 32(2), 234\u2013240 (2018). https:\/\/doi.org\/10.1007\/s10278-018-0121-8","journal-title":"J. Digit. Imaging"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.J.: A tutorial on energy-based learning. In: Bakir, G., Hofman, T., Sch\u00f6lkopf, B., Smola, A., Taskar, B. (eds.) Predicting Structured Data, pp. 1\u201350. MIT Press (2006)","DOI":"10.7551\/mitpress\/7443.003.0014"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)","DOI":"10.32388\/VLXB6M"},{"issue":"7956","key":"24_CR16","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor, M., et al.: Foundation models for generalist medical artificial intelligence. Nature 616(7956), 259\u2013265 (2023). https:\/\/doi.org\/10.1038\/s41586-023-05881-4","journal-title":"Nature"},{"key":"24_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1007\/978-3-319-10404-1_65","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2014","author":"HR Roth","year":"2014","unstructured":"Roth, H.R., et al.: A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 520\u2013527. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10404-1_65"},{"key":"24_CR18","unstructured":"Saab, K., et\u00a0al.: Capabilities of gemini models in medicine. arXiv preprint arXiv:2404.18416 (2024)"},{"issue":"5","key":"24_CR19","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/TMI.2016.2536809","volume":"35","author":"AAA Setio","year":"2016","unstructured":"Setio, A.A.A., et al.: Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans. Med. Imaging 35(5), 1160\u20131169 (2016). https:\/\/doi.org\/10.1109\/TMI.2016.2536809","journal-title":"IEEE Trans. Med. Imaging"},{"key":"24_CR20","unstructured":"Shen, H., et al.: Towards bidirectional human-AI alignment: a systematic review for clarifications, framework, and future directions (2024). https:\/\/arxiv.org\/abs\/2406.09264"},{"issue":"1","key":"24_CR21","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s41746-020-0273-z","volume":"3","author":"YX Tang","year":"2020","unstructured":"Tang, Y.X., et al.: Automated abnormality classification of chest radiographs using deep convolutional neural networks. NPJ Dig. Med. 3(1), 70 (2020). https:\/\/doi.org\/10.1038\/s41746-020-0273-z","journal-title":"NPJ Dig. Med."},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedCLIP: contrastive learning from unpaired medical images and text. In: 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 833\u2013846. Association for Computational Linguistics (2022). https:\/\/aclanthology.org\/2022.emnlp-main.52\/","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"24_CR23","doi-asserted-by":"publisher","unstructured":"Zhang, K., et al.: A generalist vision-language foundation model for diverse biomedical tasks. Nat. Med. 30(11), 3129\u20133141 (2024). https:\/\/doi.org\/10.1038\/s41591-024-03185-2","DOI":"10.1038\/s41591-024-03185-2"},{"key":"24_CR24","unstructured":"Zhang, S., et al.: Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"24_CR25","doi-asserted-by":"publisher","unstructured":"Zhu, W., Liu, C., Fan, W., Xie, X.: DeepLung: deep 3D dual path nets for automated pulmonary nodule detection and classification. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 673\u2013681. IEEE (2018). https:\/\/doi.org\/10.1109\/WACV.2018.00081","DOI":"10.1109\/WACV.2018.00081"}],"container-title":["Lecture Notes in Computer Science","AI for Clinical Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06004-4_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:22:06Z","timestamp":1758561726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06004-4_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"ISBN":["9783032060037","9783032060044"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06004-4_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"22 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CMLLMs","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Multimodal Large Language Models in Clinical Practice","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cmllms2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clinicalmllms.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}