{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T01:07:39Z","timestamp":1778807259348,"version":"3.51.4"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271465"],"award-info":[{"award-number":["62271465"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.media.2026.104036","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T16:38:20Z","timestamp":1773765500000},"page":"104036","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["PASS-Tr: PAtch-wise swin slice attention to leverage generalization of 2D large vision model to universal lesion detection"],"prefix":"10.1016","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8029-1498","authenticated-orcid":false,"given":"Han","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3174-3352","authenticated-orcid":false,"given":"Jingsong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0902-2321","authenticated-orcid":false,"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1415-9731","authenticated-orcid":false,"given":"Zhicheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1664-5588","authenticated-orcid":false,"given":"Xun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1353-8921","authenticated-orcid":false,"given":"Peter","family":"Sch\u00fcffler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-5611","authenticated-orcid":false,"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6881-4444","authenticated-orcid":false,"given":"S Kevin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.media.2026.104036_bib0001","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/s41746-017-0015-z","article-title":"Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration","volume":"1","author":"Arbabshirani","year":"2018","journal-title":"NPJ Digit. Med."},{"issue":"2","key":"10.1016\/j.media.2026.104036_bib0002","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans","volume":"38","author":"Armato","year":"2011","journal-title":"Med. Phys."},{"key":"10.1016\/j.media.2026.104036_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102680","article-title":"The liver tumor segmentation benchmark (lits)","volume":"84","author":"Bilic","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104036_bib0004","series-title":"MICCAI","first-page":"3","article-title":"Deep volumetric universal lesion detection using light-weight pseudo 3d convolution and surface point regression","author":"Cai","year":"2020"},{"issue":"1","key":"10.1016\/j.media.2026.104036_bib0005","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/TMI.2020.3022034","article-title":"Lesion-harvester: iteratively mining unlabeled lesions and hard-negative examples at scale","volume":"40","author":"Cai","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"2","key":"10.1016\/j.media.2026.104036_bib0006","doi-asserted-by":"crossref","DOI":"10.1148\/ryct.2020200082","article-title":"Longitudinal assessment of COVID-19 using a deep learning\u2013based quantitative CT pipeline: illustration of two cases","volume":"2","author":"Cao","year":"2020","journal-title":"Radiol. Cardiothorac. Imaging"},{"key":"10.1016\/j.media.2026.104036_bib0007","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6299","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"Carreira","year":"2017"},{"issue":"5","key":"10.1016\/j.media.2026.104036_bib0008","doi-asserted-by":"crossref","first-page":"3509","DOI":"10.1109\/TPAMI.2023.3342120","article-title":"Centernet++ for object detection","volume":"46","author":"Duan","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104036_bib0009","doi-asserted-by":"crossref","first-page":"2626","DOI":"10.1109\/TMI.2020.2996645","article-title":"Inf-net: automatic COVID-19 lung infection segmentation from CT images","volume":"39","author":"Fan","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104036_bib0010","unstructured":"Gildenblat, J., contributors, 2021. Pytorch library for CAM methods. https:\/\/github.com\/jacobgil\/pytorch-grad-cam."},{"key":"10.1016\/j.media.2026.104036_bib0011","series-title":"International MICCAI Brainlesion Workshop","first-page":"272","article-title":"Swin unetr: swin transformers for semantic segmentation of brain tumors in MRI images","author":"Hatamizadeh","year":"2021"},{"key":"10.1016\/j.media.2026.104036_bib0012","series-title":"IEEE WACV","first-page":"6202","article-title":"Hiformer: hierarchical multi-scale representations using transformers for medical image segmentation","author":"Heidari","year":"2023"},{"issue":"12","key":"10.1016\/j.media.2026.104036_bib0013","doi-asserted-by":"crossref","first-page":"3509","DOI":"10.1109\/TMI.2022.3187170","article-title":"A self supervised styleGAN for image annotation and classification with extremely limited labels","volume":"41","author":"Hochberg","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"2","key":"10.1016\/j.media.2026.104036_bib0014","doi-asserted-by":"crossref","DOI":"10.1148\/ryct.2020200075","article-title":"Serial quantitative chest ct assessment of covid-19: deep-learning approach","volume":"2","author":"Huang","year":"2020","journal-title":"Radiol. Cardiothorac. Imaging"},{"issue":"2","key":"10.1016\/j.media.2026.104036_bib0015","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"10.1016\/j.media.2026.104036_bib0016","first-page":"36722","article-title":"Amos: a large-scale abdominal multi-organ benchmark for versatile medical image segmentation","volume":"35","author":"Ji","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104036_bib0017","article-title":"Collaborative learning of dynamic and static information for medical image segmentation","volume":"125","author":"Ju","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.media.2026.104036_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101950","article-title":"Chaos challenge-combined (ct-mr) healthy abdominal organ segmentation","volume":"69","author":"Kavur","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104036_bib0019","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.media.2026.104036_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.109173","article-title":"A flexible 2.5 d medical image segmentation approach with in-slice and cross-slice attention","volume":"182","author":"Kumar","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.104036_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13619","article-title":"DN-DETR: accelerate detr training by introducing query denoising","author":"Li","year":"2022"},{"key":"10.1016\/j.media.2026.104036_bib0022","series-title":"MICCAI","first-page":"141","article-title":"Conditional training with bounding map for universal lesion detection","author":"Li","year":"2021"},{"key":"10.1016\/j.media.2026.104036_bib0023","series-title":"MICCAI","first-page":"163","article-title":"SATr: slice attention with transformer for universal lesion detection","author":"Li","year":"2022"},{"issue":"12","key":"10.1016\/j.media.2026.104036_bib0024","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","article-title":"H-denseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes","volume":"37","author":"Li","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104036_bib0025","series-title":"MICCAI","first-page":"13","article-title":"MVP-Net: multi-view fpn with position-aware attention for deep universal lesion detection","author":"Li","year":"2019"},{"key":"10.1016\/j.media.2026.104036_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102205","article-title":"Covid-19 lung infection segmentation with a novel two-stage cross-domain transfer learning framework","volume":"74","author":"Liu","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104036_bib0027","series-title":"International Conference on Medical Image Computing and Computer-assisted Intervention","first-page":"615","article-title":"Swin-uMamba: Mamba-based unet with imagenet-based pretraining","author":"Liu","year":"2024"},{"issue":"2","key":"10.1016\/j.media.2026.104036_bib0028","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1109\/TMI.2022.3226575","article-title":"Structural attention graph neural network for diagnosis and prediction of COVID-19 severity","volume":"42","author":"Liu","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104036_bib0029","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.media.2026.104036_bib0030","series-title":"MICCAI","first-page":"117","article-title":"A segmentation-assisted model for universal lesion detection with partial labels","author":"Lyu","year":"2021"},{"issue":"3","key":"10.1016\/j.media.2026.104036_bib0031","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1109\/TMI.2022.3217501","article-title":"Pseudo-label guided image synthesis for semi-supervised COVID-19 pneumonia infection segmentation","volume":"42","author":"Lyu","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.media.2026.104036_bib0032","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.media.2026.104036_bib0033","series-title":"IEEE IJCNN","first-page":"1","article-title":"Eigen-CAM: class activation map using principal components","author":"Muhammad","year":"2020"},{"key":"10.1016\/j.media.2026.104036_bib0034","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1109\/TMI.2022.3232572","article-title":"Semi-supervised CT lesion segmentation using uncertainty-based data pairing and swapmix","volume":"42","author":"Qiao","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104036_bib0035","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"9302","article-title":"Segment anything meets point tracking","author":"Raji\u010d","year":"2025"},{"key":"10.1016\/j.media.2026.104036_bib0036","series-title":"NeurIPS","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"10.1016\/j.media.2026.104036_bib0037","series-title":"MICCAI","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.media.2026.104036_bib0038","series-title":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","first-page":"1","article-title":"An efficient anchor-free universal lesion detection in ct-scans","author":"Sheoran","year":"2022"},{"key":"10.1016\/j.media.2026.104036_bib0039","series-title":"MICCAI","first-page":"515","article-title":"Weakly-supervised universal lesion segmentation with regional level set loss","author":"Tang","year":"2021"},{"key":"10.1016\/j.media.2026.104036_bib0040","series-title":"Proc. Int. Conf. Computer Vision (ICCV)","article-title":"FCOS: Fully convolutional one-stage object detection","author":"Tian","year":"2019"},{"issue":"8","key":"10.1016\/j.media.2026.104036_bib0041","doi-asserted-by":"crossref","first-page":"2653","DOI":"10.1109\/TMI.2020.3000314","article-title":"A noise-robust framework for automatic segmentation of covid-19 pneumonia lesions from ct images","volume":"39","author":"Wang","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"8","key":"10.1016\/j.media.2026.104036_bib0042","doi-asserted-by":"crossref","first-page":"2615","DOI":"10.1109\/TMI.2020.2995965","article-title":"A weakly-supervised framework for COVID-19 classification and lesion localization from chest CT","volume":"39","author":"Wang","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"5","key":"10.1016\/j.media.2026.104036_bib0043","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.230024","article-title":"TotalSegmentator: robust segmentation of 104 anatomic structures in CT images","volume":"5","author":"Wasserthal","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"10.1016\/j.media.2026.104036_bib0044","doi-asserted-by":"crossref","first-page":"3113","DOI":"10.1109\/TIP.2021.3058783","article-title":"JCS: an explainable covid-19 diagnosis system by joint classification and zsegmentation","volume":"30","author":"Wu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.media.2026.104036_bib0045","series-title":"MICCAI","first-page":"511","article-title":"3d context enhanced region-based convolutional neural network for end-to-end lesion detection","author":"Yan","year":"2018"},{"key":"10.1016\/j.media.2026.104036_bib0046","series-title":"MICCAI","first-page":"194","article-title":"Mulan: multitask universal lesion analysis network for joint lesion detection, tagging, and segmentation","author":"Yan","year":"2019"},{"key":"10.1016\/j.media.2026.104036_bib0047","series-title":"IEEE\/CVF CVPR","first-page":"9261","article-title":"Deep lesion graphs in the wild: relationship learning and organization of significant radiology image findings in a diverse large-scale lesion database","author":"Yan","year":"2018"},{"key":"10.1016\/j.media.2026.104036_bib0048","series-title":"MICCAI","first-page":"562","article-title":"Alignshift: bridging the gap of imaging thickness in 3d anisotropic volumes","author":"Yang","year":"2020"},{"key":"10.1016\/j.media.2026.104036_bib0049","series-title":"MICCAI","first-page":"571","article-title":"Asymmetric 3d context fusion for universal lesion detection","author":"Yang","year":"2021"},{"key":"10.1016\/j.media.2026.104036_bib0050","doi-asserted-by":"crossref","first-page":"2808","DOI":"10.1109\/TMI.2021.3066161","article-title":"Label-free segmentation of COVID-19 lesions in lung CT","volume":"40","author":"Yao","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104036_bib0051","first-page":"29582","article-title":"Class-aware adversarial transformers for medical image segmentation","volume":"35","author":"You","year":"2022","journal-title":"NeurIPS"},{"issue":"8","key":"10.1016\/j.media.2026.104036_bib0052","doi-asserted-by":"crossref","first-page":"10427","DOI":"10.1109\/TPAMI.2023.3240886","article-title":"SS-TBN: a semi-supervised tri-branch network for covid-19 screening and lesion segmentation","volume":"45","author":"Zeng","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104036_bib0053","unstructured":"Zhang, N., Cao, Y., Liu, B., Luo, Y., 2020a. 3d aggregated faster R-CNN for general lesion detection. arXiv: 2001.11071."},{"key":"10.1016\/j.media.2026.104036_bib0054","series-title":"MICCAI","first-page":"542","article-title":"Revisiting 3d context modeling with supervised pre-training for universal lesion detection in CT slices","author":"Zhang","year":"2020"},{"key":"10.1016\/j.media.2026.104036_bib0055","series-title":"MLMI Workshop","first-page":"470","article-title":"Lesion detection by efficiently bridging 3d context","author":"Zhang","year":"2019"},{"issue":"8","key":"10.1016\/j.media.2026.104036_bib0056","doi-asserted-by":"crossref","first-page":"2638","DOI":"10.1109\/TMI.2020.3001810","article-title":"A rapid, accurate and machine-agnostic segmentation and quantification method for CT-based COVID-19 diagnosis","volume":"39","author":"Zhou","year":"2020","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526001052?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526001052?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:10:40Z","timestamp":1778803840000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526001052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":56,"alternative-id":["S1361841526001052"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104036","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PASS-Tr: PAtch-wise swin slice attention to leverage generalization of 2D large vision model to universal lesion detection","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104036","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104036"}}