{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T12:03:56Z","timestamp":1784894636889,"version":"3.55.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62541611"],"award-info":[{"award-number":["62541611"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"crossref","award":["LQN26F020069"],"award-info":[{"award-number":["LQN26F020069"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ningbo Public Welfare Science and Technology Program Project","award":["2025S181"],"award-info":[{"award-number":["2025S181"]}]},{"name":"Ningbo Science and Technology Special Projects","award":["2025Z124"],"award-info":[{"award-number":["2025Z124"]}]},{"name":"Ningbo Special Talent Support Program","award":["2025 S-237-05"],"award-info":[{"award-number":["2025 S-237-05"]}]},{"name":"Key Programs of Ningbo Municipal Natural Science Foundationn","award":["2024J021"],"award-info":[{"award-number":["2024J021"]}]},{"name":"Key Project of the Zhejiang Provincial Natural Science Foundation","award":["LZ26F020010"],"award-info":[{"award-number":["LZ26F020010"]}]},{"name":"Key R&D Program of Ningbo National High-Tech Zone","award":["2025CX050008"],"award-info":[{"award-number":["2025CX050008"]}]},{"name":"Yuyao Key Research and Development Plan","award":["2025JH03010002"],"award-info":[{"award-number":["2025JH03010002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00371-026-04622-8","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T14:29:26Z","timestamp":1784125766000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3D brain image anomaly detection using anomaly-guided large vision-language models"],"prefix":"10.1007","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5226-8515","authenticated-orcid":false,"given":"Kun","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8867-3888","authenticated-orcid":false,"given":"Zhiwang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5372-5083","authenticated-orcid":false,"given":"Yipeng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinqiu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaji","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2055-2553","authenticated-orcid":false,"given":"Shiting","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"4622_CR1","unstructured":"Zhu, D., Chen, J., Shen, X.: Minigpt-4: enhancing vision-language understanding with advanced large language models, (2023). arXiv preprint arXiv:2304.10592"},{"key":"4622_CR2","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023). arXiv:2301.12597"},{"key":"4622_CR3","unstructured":"Su, Y., Lan, T., Li, H.: Pandagpt: one model to instruction-follow them all, (2023). arXiv preprint arXiv:2305.16355"},{"key":"4622_CR4","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhu, B., Zhu, G., et\u00a0al.: Anomalygpt: detecting industrial anomalies using large vision-language models (2023). arXiv:2308.15366","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"4622_CR5","doi-asserted-by":"crossref","unstructured":"Huang, Z., Hu, J., Li, X.: SIDA: social media image deepfake detection, localization and explanation with large multimodal model. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), pp. 2025. (2025)","DOI":"10.1109\/CVPR52734.2025.02685"},{"key":"4622_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, X., Wang, X.: Holmes-vau: towards long-term video anomaly understanding at any granularity, (2024). arXiv preprint arXiv:2412.06171","DOI":"10.1109\/CVPR52734.2025.01292"},{"key":"4622_CR7","doi-asserted-by":"crossref","unstructured":"You, Z., Cui, L., Shen, Y.: A unified model for multi-class anomaly detection, (2022). arXiv:2206.03687","DOI":"10.52202\/068431-0330"},{"key":"4622_CR8","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440. (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"4622_CR9","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"4622_CR10","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4622_CR11","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"4622_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G.: Masked-attention mask transformer for universal image segmentation, (2022). arXiv:2112.01527","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"4622_CR13","doi-asserted-by":"crossref","unstructured":"Defard, T., Setkov, A., Loesch, A., Audigier, R.: Padim: a patch distribution modeling framework for anomaly detection and localization. In: International conference on pattern recognition, pp. 475\u2013489. Springer (2021)","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"4622_CR14","doi-asserted-by":"crossref","unstructured":"Roth, K., Pemula, L., Zepeda, J.: Towards total recall in industrial anomaly detection, (2022). arXiv:2106.08265","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"4622_CR15","doi-asserted-by":"crossref","unstructured":"Deng, H., Li, X.: Anomaly detection via reverse distillation from one-class embedding, (2022). arXiv:2201.10703","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"4622_CR16","doi-asserted-by":"crossref","unstructured":"Lv, J., Hu, Y., Fu, Q.: Cm-mlp: cascade multi-scale mlp with axial context relation encoder for edge segmentation of medical image. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1100\u20131107. IEEE (2022)","DOI":"10.1109\/BIBM55620.2022.9995348"},{"key":"4622_CR17","unstructured":"Zhou, Q., Pang, G., Tian, Y., He, S., Chen, J.: Anomalyclip: object-agnostic prompt learning for zero-shot anomaly detection. In: The Twelfth International Conference on Learning Representations, (2023)"},{"issue":"1","key":"4622_CR18","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1038\/s41746-025-01964-w","volume":"8","author":"Z Zhao","year":"2025","unstructured":"Zhao, Z., Zhang, Y., Wu, C., et al.: Large-vocabulary segmentation for medical images with text prompts. NPJ Digit. Med. 8(1), 566 (2025)","journal-title":"NPJ Digit. Med."},{"key":"4622_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhang, Z., Wen, S., et\u00a0al.: Boosting remote semantic segmentation using vision-and-language foundation model: Q. zhang et al. The Visual Computer 41(9), 6687\u20136700 (2025)","DOI":"10.1007\/s00371-025-03968-9"},{"key":"4622_CR20","unstructured":"Baid, U., Ghodasara, S., Mohan, S., Bilello, M.: The rsna-asnr-miccai brats 2021 benchmark on brain tumor segmentation and radiogenomic classification, (2021). arXiv:2107.02314"},{"key":"4622_CR21","unstructured":"LaBella, D., Adewole, M., Alonso-Basanta, M., et\u00a0al.: The asnr-miccai brain tumor segmentation (brats) challenge 2023: intracranial meningioma (2023). arXiv:2305.07642"},{"key":"4622_CR22","unstructured":"Moawad, A.W., Janas, A., Baid, U.: The brain tumor segmentation (brats-mets) challenge 2023: Brain metastasis segmentation on pre-treatment mri, (2023)"},{"key":"4622_CR23","unstructured":"Kazerooni, A.F., Khalili, N., Liu, X.: The brain tumor segmentation (brats) challenge 2023: focus on pediatrics (cbtn-connect-dipgr-asnr-miccai brats-peds) (2023)"},{"key":"4622_CR24","unstructured":"Adewole, M., Rudie, J.D., Gbadamosi, A.: The brain tumor segmentation (brats) challenge 2023: glioma segmentation in sub-saharan africa patient population (brats-africa) (2023)"},{"issue":"1","key":"4622_CR25","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1038\/s41597-022-01875-5","volume":"9","author":"MR Hernandez Petzsche","year":"2022","unstructured":"Hernandez Petzsche, M.R., de la Rosa, E., Hanning, U., et al.: Isles 2022: a multi-center magnetic resonance imaging stroke lesion segmentation dataset. Sci. data 9(1), 762 (2022)","journal-title":"Sci. data"},{"issue":"11","key":"4622_CR26","doi-asserted-by":"publisher","first-page":"2556","DOI":"10.1109\/TMI.2019.2905770","volume":"38","author":"HJ Kuijf","year":"2019","unstructured":"Kuijf, H.J., Biesbroek, J.M., De Bresser, J., et al.: Standardized assessment of automatic segmentation of white matter hyperintensities and results of the wmh segmentation challenge. IEEE Trans. Med. Imaging 38(11), 2556\u20132568 (2019). https:\/\/doi.org\/10.1109\/TMI.2019.2905770","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4622_CR27","doi-asserted-by":"crossref","unstructured":"Gao, S., Guo, J., Su, L.: Cmedbench: a comprehensive benchmark for efficient medical large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 21198\u201321206. (2026)","DOI":"10.1609\/aaai.v40i25.39264"},{"key":"4622_CR28","unstructured":"Achiam, J., Adler, S., Agarwal, S.: Gpt-4 technical report, (2023). arXiv preprint arXiv:2303.08774"},{"key":"4622_CR29","unstructured":"Yang, A., Li, A., Yang, B., et\u00a0al.: Qwen3 technical report (2025). arXiv:2505.09388"},{"key":"4622_CR30","unstructured":"Anthropic: the claude 3 model family: Opus, sonnet, haiku. https:\/\/api.semanticscholar.org\/CorpusID:268232499"},{"key":"4622_CR31","unstructured":"Team, G., Anil, R., Borgeaud, S.: Gemini: a family of highly capable multimodal models, (2023). arXiv preprint arXiv:2312.11805"},{"key":"4622_CR32","unstructured":"Team, L., Xu, W., Chan, H.P.: Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning, (2025). arXiv:2506.07044"},{"key":"4622_CR33","doi-asserted-by":"crossref","unstructured":"Rui, S., Chen, L., Tang, Z., Wang, L.: Multi-modal vision pre-training for medical image analysis, (2025). arXiv:2410.10604","DOI":"10.1109\/CVPR52734.2025.00487"},{"key":"4622_CR34","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA (2002). https:\/\/doi.org\/10.3115\/1073083.1073135. https:\/\/aclanthology.org\/P02-1040\/","DOI":"10.3115\/1073083.1073135"},{"key":"4622_CR35","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain (2004). https:\/\/aclanthology.org\/W04-1013\/"},{"key":"4622_CR36","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Goldstein, J., Lavie, A., Lin, C.Y., Voss, C. (eds.) Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372. Association for Computational Linguistics, Ann Arbor, Michigan (2005). https:\/\/aclanthology.org\/W05-0909\/"},{"key":"4622_CR37","unstructured":"Zhang, T., Kishore, V., Wu, F.: Bertscore: evaluating text generation with bert, (2020). arXiv:1904.09675"},{"key":"4622_CR38","unstructured":"Chiang, W.L., Li, Z., Lin, Z., et\u00a0al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04622-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04622-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04622-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T11:39:24Z","timestamp":1784893164000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04622-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":38,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["4622"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04622-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"3 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"413"}}