{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T17:29:53Z","timestamp":1768238993740,"version":"3.49.0"},"reference-count":48,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0111102"],"award-info":[{"award-number":["2021ZD0111102"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022TQ0049"],"award-info":[{"award-number":["2022TQ0049"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["75N92020C00008"],"award-info":[{"award-number":["75N92020C00008"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["75N92020C00021"],"award-info":[{"award-number":["75N92020C00021"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Accurate and robust medical image analysis plays a critical role in disease screening, diagnosis, and prognosis. However, its development is often constrained by data scarcity, privacy concerns, and domain discrepancies. To address these challenges, we propose TransMedVision\u2014a transitional training framework tailored for cross\u2010domain few\u2010shot medical image analysis tasks. The framework consists of three stages: (1) initializing the model with a vision backbone pretrained on large\u2010scale natural image datasets; (2) performing short\u2010term transitional training on intermediate medical image datasets to reduce the representation gap between natural and medical domains, while stabilizing feature learning; and (3) fine\u2010tuning on the target few\u2010shot CT dataset to obtain the final classifier. By preserving general visual features and gradually adapting them to medical domains, TransMedVision enhances both cross\u2010domain transfer accuracy and training stability. In cross\u2010domain few\u2010shot COVID\u201019 pneumonia CT classification tasks, TransMedVision achieves state\u2010of\u2010the\u2010art performance (Accuracy = 0.9113, F1 = 0.9032, AUC = 0.9514). All datasets, code, and models are publicly released via\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/01Matrix\/TransMedVision\">https:\/\/github.com\/01Matrix\/TransMedVision<\/jats:ext-link>\n                    to facilitate reproducibility and future research.\n                  <\/jats:p>","DOI":"10.1002\/cpe.70482","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T05:42:35Z","timestamp":1765258955000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TransMedVision: Improving Medical Image Analysis Under Data Scarcity With Transferable Visual Representations"],"prefix":"10.1002","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7118-1038","authenticated-orcid":false,"given":"Hongwang","family":"Xiao","sequence":"first","affiliation":[{"name":"Peking University  Beijing China"},{"name":"Beijing Academy of Artificial Intelligence  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiwei","family":"Ye","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Shu","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Victoria University  Melbourne Victoria Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"key":"e_1_2_14_2_1","first-page":"391","volume-title":"Machine Learning for Health","author":"Zhang Y.","year":"2022"},{"key":"e_1_2_14_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551\u2010022\u201000936\u20109"},{"key":"e_1_2_14_4_1","first-page":"3478","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Azizi S.","year":"2021"},{"key":"e_1_2_14_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_14_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-93030-0"},{"key":"e_1_2_14_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-05539-7"},{"key":"e_1_2_14_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-19544-3"},{"key":"e_1_2_14_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00108"},{"key":"e_1_2_14_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3528222"},{"key":"e_1_2_14_11_1","first-page":"1097","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems \u2010 Volume 1 (NIPS'12)","author":"Krizhevsky A.","year":"2012"},{"key":"e_1_2_14_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_14_13_1","unstructured":"F. N.Iandola S.Han M. W.Moskewicz K.Ashraf W. J.Dally andK.Keutzer \u201cSqueezeNet: AlexNet\u2010Level Accuracy With 50x Fewer Parameters and <0.5MB Model Size \u201d arXiv preprint arXiv:1602.07360 (2016) https:\/\/doi.org\/10.48550\/arXiv.1602.07360."},{"key":"e_1_2_14_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13755\u2010020\u201000135\u20103"},{"key":"e_1_2_14_15_1","volume-title":"Proceedings of International Conference on Learning Representations","author":"Dosovitskiy A.","year":"2021"},{"key":"e_1_2_14_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102762"},{"key":"e_1_2_14_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_14_18_1","first-page":"9620","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Chen X.","year":"2021"},{"key":"e_1_2_14_19_1","volume-title":"Proceedings of International Conference on Learning Representations","author":"Bao H.","year":"2022"},{"key":"e_1_2_14_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_2_14_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"e_1_2_14_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"e_1_2_14_23_1","first-page":"6000","volume-title":"In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17)","author":"Vaswani A.","year":"2017"},{"key":"e_1_2_14_24_1","first-page":"2790","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Houlsby N.","year":"2019"},{"key":"e_1_2_14_25_1","unstructured":"E. J.Hu Y.Shen P.Wallis et al. \u201cLoRA: Low\u2010Rank Adaptation of Large Language Models \u201d2021."},{"key":"e_1_2_14_26_1","unstructured":"R. K.Mahabadi J.Henderson andS.Ruder \u201cCompacter: Efficient Low\u2010Rank Hypercomplex Adapter Layers \u201d2021 https:\/\/doi.org\/10.48550\/arXiv.2106.04647."},{"key":"e_1_2_14_27_1","doi-asserted-by":"crossref","unstructured":"B.Lester R.Al\u2010Rfou andN.Constant \u201cThe Power of Scale for Parameter\u2010Efficient Prompt Tuning \u201d2021 https:\/\/doi.org\/10.48550\/arXiv.2104.08691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_2_14_28_1","unstructured":"X.Liu Y.Zheng Z.Du et al. \u201cGPT Understands Too \u201d2021 https:\/\/doi.org\/10.48550\/arXiv.2103.10385."},{"key":"e_1_2_14_29_1","volume-title":"Proceedings of International Conference on Learning Representations","author":"Zhang T.","year":"2021"},{"key":"e_1_2_14_30_1","first-page":"272","volume-title":"International MICCAI Brainlesion Workshop","author":"Hatamizadeh A.","year":"2021"},{"key":"e_1_2_14_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3358295"},{"key":"e_1_2_14_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110471"},{"key":"e_1_2_14_33_1","unstructured":"J.Chen Y.Lu Q.Yu et al. \u201cTransunet: Transformers Make Strong Encoders for Medical Image Segmentation \u201d arXiv preprint arXiv:2102.04306 (2021)."},{"key":"e_1_2_14_34_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02129-z"},{"key":"e_1_2_14_35_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210315"},{"key":"e_1_2_14_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082015"},{"key":"e_1_2_14_37_1","unstructured":"J.Phang T.F\u00e9vry andS. R.Bowman \u201cSentence Encoders on STILTs: Supplementary Training on Intermediate Labeled\u2010Data Tasks \u201d2018 https:\/\/doi.org\/10.48550\/arXiv.1811.01088."},{"key":"e_1_2_14_38_1","unstructured":"X.Yang X.He J.Zhao Y.Zhang S.Zhang andP.Xie \u201cCOVID\u2010CT\u2010Dataset: A CT Scan Dataset About COVID\u201019 \u201d2020."},{"key":"e_1_2_14_39_1","doi-asserted-by":"publisher","DOI":"10.1101\/2020.04.13.20063941"},{"key":"e_1_2_14_40_1","doi-asserted-by":"crossref","unstructured":"A.Mobiny P. A.Cicalese S.Zare et al. \u201cRadiologist\u2010Level COVID\u201019 Detection Using CT Scans With Detail\u2010Oriented Capsule Networks \u201d arXiv preprint arXiv:2004.07407 (2020).","DOI":"10.1007\/978-3-030-59710-8_15"},{"key":"e_1_2_14_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/07391102.2020.1788642"},{"key":"e_1_2_14_42_1","unstructured":"J.Dodge G.Ilharco R.Schwartz A.Farhadi H.Hajishirzi andN.Smith \u201cFine\u2010Tuning Pretrained Language Models: Weight Initializations Data Orders and Early Stopping \u201d2020 https:\/\/doi.org\/10.48550\/arXiv.2002.06305."},{"key":"e_1_2_14_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104037"},{"key":"e_1_2_14_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058783"},{"key":"e_1_2_14_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2996645"},{"key":"e_1_2_14_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-07715-1"},{"key":"e_1_2_14_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105123"},{"key":"e_1_2_14_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00900-3"},{"key":"e_1_2_14_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3527357"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T04:48:59Z","timestamp":1768193339000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/cpe.70482"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70482","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,8]]},"assertion":[{"value":"2025-06-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70482"}}