{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T05:23:32Z","timestamp":1779254612733,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031845246","type":"print"},{"value":"9783031845253","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-84525-3_10","type":"book-chapter","created":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T06:22:59Z","timestamp":1744438979000},"page":"113-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Language Models Meet Anomaly Detection for\u00a0Better Interpretability and\u00a0Generalizability"],"prefix":"10.1007","author":[{"given":"Jun","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Su Hwan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Felsner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Rueckert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benedikt","family":"Wiestler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia A.","family":"Schnabel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cosmin I.","family":"Bercea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"10_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1007\/978-3-030-20893-6_39","volume-title":"Computer Vision \u2013 ACCV 2018","author":"S Akcay","year":"2019","unstructured":"Akcay, S., Atapour-Abarghouei, A., Breckon, T.P.: GANomaly: semi-supervised anomaly detection via adversarial training. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 622\u2013637. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_39"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Bai, L., Islam, M., Ren, H.: Cat-ViL: co-attention gated vision-language embedding for visual question localized-answering in robotic surgery. In: Medical Image Computing and Computer-Assisted Intervention, pp. 397\u2013407. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-43996-4_38","DOI":"10.1007\/978-3-031-43996-4_38"},{"key":"10_CR3","unstructured":"Behrendt, F., Bhattacharya, D., Kr\u00fcger, J., Opfer, R., Schlaefer, A.: Patched diffusion models for unsupervised anomaly detection in brain MRI. In: International Conference on Medical Imaging with Deep Learning (2023)"},{"key":"10_CR4","unstructured":"Bercea, C.I., Neumayr, M., Rueckert, D., Schnabel, J.A.: Mask, stitch, and re-sample: enhancing robustness and generalizability in anomaly detection through automatic diffusion models. In: ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (2023)"},{"key":"10_CR5","unstructured":"Bercea, C.I., Wiestler, B., Rueckert, D., Schnabel, J.A.: Generalizing unsupervised anomaly detection: towards unbiased pathology screening. In: Medical Imaging with Deep Learning (2023)"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Bercea, C.I., Wiestler, B., Rueckert, D., Schnabel, J.A.: Reversing the abnormal: Pseudo-healthy generative networks for anomaly detection. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 293\u2013303. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-43904-9_29","DOI":"10.1007\/978-3-031-43904-9_29"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., You, S., Tezcan, K.C., Konukoglu, E.: Unsupervised lesion detection via image restoration with a normative prior. Medical Image Analysis 64, 101713 (2020)","DOI":"10.1016\/j.media.2020.101713"},{"issue":"240","key":"10_CR8","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR9","unstructured":"Dosovitskiy, A., et al..: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"10_CR10","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":"10_CR11","unstructured":"He, P., Gao, J., Chen, W.: DeBERTav3: improving deBERTa using electra-style pre-training with gradient-disentangled embedding sharing. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Knoll, F., et\u00a0al.: fastMRI: a publicly available raw k-space and DICOM dataset of knee images for accelerated MR image reconstruction using machine learning. Radiol. Artif. Intell. 2(1), e190007 (2020)","DOI":"10.1148\/ryai.2020190007"},{"issue":"2","key":"10_CR13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198","volume":"2","author":"TH Kung","year":"2023","unstructured":"Kung, T.H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepa\u00f1o, C., et al.: Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLoS Digit. Health 2(2), e0000198 (2023)","journal-title":"PLoS Digit. Health"},{"issue":"4","key":"10_CR14","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020)","journal-title":"Bioinformatics"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., et\u00a0al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the Association for Computational Linguistics, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Li, J., Li, S., Hu, Y., Tao, H.: A self-guided framework for radiology report generation. In: Medical Image Computing and Computer-Assisted Intervention, pp. 588\u2013598. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-16452-1_56","DOI":"10.1007\/978-3-031-16452-1_56"},{"key":"10_CR17","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"10_CR18","doi-asserted-by":"publisher","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: Medical Image Computing and Computer-Assisted Intervention, pp. 374\u2013383. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-43907-0_36","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"10_CR19","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"10_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-87196-3_20","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"B Liu","year":"2021","unstructured":"Liu, B., Zhan, L.-M., Wu, X.-M.: Contrastive pre-training and\u00a0representation distillation for\u00a0medical visual question answering based on\u00a0radiology images. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 210\u2013220. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_20"},{"key":"10_CR21","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., et\u00a0al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"10_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Luo, R., Sun, L., Xia, Y., Qin, T., Zhang, S., Poon, H., Liu, T.Y.: BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefing Bioinf. 23(6), bbac409 (2022)","DOI":"10.1093\/bib\/bbac409"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Nguyen, B.D., Do, T.T., Nguyen, B.X., Do, T., Tjiputra, E., Tran, Q.D.: Overcoming data limitation in medical visual question answering. In: Medical Image Computing and Computer Assisted Intervention, pp. 522\u2013530. Springer (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_57","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"10_CR25","unstructured":"OpenAI: Introducing ChatGPT (2023). https:\/\/openai.com\/blog\/chatgpt\/. Accessed 30 Nov 2022"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"8","key":"10_CR27","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"10_CR28","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.media.2019.01.010","volume":"54","author":"T Schlegl","year":"2019","unstructured":"Schlegl, T., Seeb\u00f6ck, P., Waldstein, S.M., Langs, G., Schmidt-Erfurth, U.: f-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks. Med. Image Anal. 54, 30\u201344 (2019)","journal-title":"Med. Image Anal."},{"key":"10_CR29","unstructured":"Sileo, D.: TaskSource: Structured dataset preprocessing annotations for frictionless extreme multi-task learning and evaluation. arXiv preprint arXiv:2301.05948 (2023)"},{"issue":"7972","key":"10_CR30","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K., et al.: Large language models encode clinical knowledge. Nature 620(7972), 172\u2013180 (2023)","journal-title":"Nature"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Tanida, T., M\u00fcller, P., Kaissis, G., Rueckert, D.: Interactive and explainable region-guided radiology report generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7433\u20137442 (2023)","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"10_CR32","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"10_CR33","unstructured":"Tu, T., et\u00a0al.: Towards conversational diagnostic AI. arXiv preprint arXiv:2401.05654 (2024)"},{"key":"10_CR34","doi-asserted-by":"publisher","unstructured":"Van\u00a0Sonsbeek, T., Derakhshani, M.M., Najdenkoska, I., Snoek, C.G., Worring, M.: Open-ended medical visual question answering through prefix tuning of language models. In: Medical Image Computing and Computer Assisted Intervention, pp. 726\u2013736. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-43904-9_70","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"10_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030 (2017)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Wolleb, J., Bieder, F., Sandk\u00fchler, R., Cattin, P.C.: Diffusion models for medical anomaly detection. Medical Image Computing and Computer Assisted Intervention, pp. 35\u201345 (2022)","DOI":"10.1007\/978-3-031-16452-1_4"},{"key":"10_CR38","unstructured":"Wu, X., et al.: Deltanet: Conditional medical report generation for Covid-19 diagnosis. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 2952\u20132961 (2022)"},{"key":"10_CR39","unstructured":"Zhang, X., Wu, C., Zhao, Z., Lin, W.o.: PMC-VQA: visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Zimmerer, D., Isensee, F., Petersen, J., Kohl, S., Maier-Hein, K.: Unsupervised anomaly localization using variational auto-encoders. In: Medical Image Computing and Computer Assisted Intervention, pp. 289\u2013297 (2019)","DOI":"10.1007\/978-3-030-32251-9_32"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-84525-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T06:23:20Z","timestamp":1744439000000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-84525-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031845246","9783031845253"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-84525-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"13 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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"}}]}}