{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T13:45:24Z","timestamp":1792071924554,"version":"4.4.0"},"reference-count":46,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T00:00:00Z","timestamp":1788480000000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100007210","name":"Varian Medical Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007210","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate segmentation of the left anterior descending (LAD) artery in 3D free\u2010breathing, non\u2010contrast CT is critical for cardiac dose sparing in thoracic radiotherapy. The task is inherently difficult because the LAD is extremely small, exhibits poor soft\u2010tissue contrast, and varies substantially across patients. Even manual contours show limited inter\u2010observer agreement on non\u2010contrast CT, underscoring the ambiguity of the vessel\u00a0boundaries.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop a transformer\u2010based segmentation framework that enhances LAD delineation in low\u2010contrast, imbalanced CT using local\u2010global context modeling and uncertainty\u2010guided\u00a0optimization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We propose\n                      <jats:bold>NA\u2010UNETR<\/jats:bold>\n                      , a 3D transformer\u2010based segmentation model with neighborhood attention (NA) and Dilated NA (DiNA) blocks that jointly capture fine structural detail and long\u2010range context. To address the limited availability of annotated LAD artery data, the model is pretrained on 1000 CTA volumes representing general coronary anatomy and then fine\u2010tuned using a parameter\u2010efficient adaptation strategy on 20 free\u2010breathing institutional CT scans of the LAD artery. A composite Dice\u2013Focal and Hausdorff loss, dynamically balanced via homoscedastic uncertainty, improves overlap and boundary accuracy. Preprocessing included intensity clipping, contrast enhancement, and artery\u2010centric sampling, and postprocessing refined\u00a0morphology.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>NA\u2010UNETR achieved comparable performance to SOTA with improved efficiency and boundary properties. It reached 45.64% Dice, 38.16 mm HD95, and 10.01 mm ASD, improving Dice by 3.10 percentage points over nnU\u2010Net and reducing HD95 by 2.96 mm relative to Swin UNETR, while showing the strongest boundary accuracy among all models and demonstrating improved geometric and centerline stability. On ImageCAS, it achieved 79.49% Dice, 8.89 mm HD95, and 1.02 mm ASD. Ablations confirmed that residual blocks, variable kernels, and uncertainty\u2010weighted loss each contributed to performance stability and boundary\u00a0precision.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>NA\u2010UNETR effectively balances local precision and global context, enabling accurate segmentation of thin, low\u2010contrast LAD structures. Its integration of NA, uncertainty\u2010weighted loss, and LoRA\u2010based fine\u2010tuning demonstrates a robust and computationally efficient framework for substructure\u2010level cardiac segmentation in radiotherapy\u00a0planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70653","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T07:03:17Z","timestamp":1788505397000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A neighborhood attention transformer network for enhanced 3D segmentation of the left anterior descending artery"],"prefix":"10.1002","volume":"53","author":[{"given":"Rafi Ibn","family":"Sultan","sequence":"first","affiliation":[{"name":"Department of Computer Science Wayne State University Detroit Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengyin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Henry Ford Health Detroit Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiannos","family":"Demetriou","sequence":"additional","affiliation":[{"name":"Department of Computer Science Wayne State University Detroit Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed I.","family":"Ghanem","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Henry Ford Health Detroit Michigan USA"},{"name":"Department of Clinical Oncology Alexandria University Alexandria Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua P.","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Henry Ford Health Detroit Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justine","family":"Cunningham","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Henry Ford Health Detroit Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Bagher\u2010Ebadian","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Henry Ford Health Detroit Michigan USA"},{"name":"Department of Radiology Michigan State University East Lansing Michigan USA"},{"name":"College of Medicine Michigan State University East Lansing Michigan USA"},{"name":"Department of Physics Oakland University Rochester Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxiao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science Wayne State University Detroit Michigan USA"},{"name":"Institute for AI and Data Science Wayne State University Detroit Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kundan S.","family":"Thind","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Henry Ford Health Detroit Michigan USA"},{"name":"College of Medicine Michigan State University East Lansing Michigan USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,4]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2011.34.5900"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2006.08.6595"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1209825"},{"key":"e_1_2_10_5_1","volume-title":"StatPearls [Internet]","author":"Rehman I","year":"2023"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.06.091"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.03.005"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.09.019"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.03.004"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13940"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748-717X-2-20"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2016.69.8480"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.04.026"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12872-024-04437-2"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.08.051"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.3857\/roj.2020.00094"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4890294"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.03.013"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.01.008"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.07.013"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.11.025"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2016.11.016"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: convolutional networks for biomedical image segmentation. In:Medical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2015.Springer;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2023.100520"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15237"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.05.013"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13132274"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-93889-z"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3169425"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102745"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908039"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13239-025-00775-0"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16554"},{"key":"e_1_2_10_35_1","doi-asserted-by":"crossref","unstructured":"HassaniA WaltonS LiJ LiS ShiH.Neighborhood attention transformer. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2023:6185\u20106194.","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA TangY NathV et\u00a0al.Unetr: Transformers for 3d medical image segmentation. In:Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision.2022:574\u2010584.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102287"},{"key":"e_1_2_10_38_1","doi-asserted-by":"crossref","unstructured":"KendallA GalY CipollaR.Multi\u2010task learning using uncertainty to weigh losses for scene geometry and semantics. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7482\u20137491.","DOI":"10.1109\/CVPR.2018.00781"},{"key":"e_1_2_10_39_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS\u2010A.V\u2010net: fully convolutional neural networks for volumetric medical image segmentation. In:2016 Fourth International Conference on 3D Vision (3DV).IEEE;2016:565\u2010571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_10_40_1","unstructured":"LinT\u2010Y GoyalP GirshickR HeK Doll\u00e1rP.Focal loss for dense object detection. In:Proceedings of the IEEE International Conference on Computer Vision.2017:2980\u20102988."},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2930068"},{"key":"e_1_2_10_42_1","unstructured":"HuEJ ShenY WallisP et\u00a0al.LoRA: low\u2010rank adaptation of large language models. In:International Conference on Learning Representations.2022."},{"key":"e_1_2_10_43_1","doi-asserted-by":"crossref","unstructured":"ZhouZ Rahman SiddiqueeMM TajbakhshN LiangJ.Unet++: a nested u\u2010net architecture for medical image segmentation. In:Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop DLMIA 2018 and 8th International Workshop ML\u2010CDS 2018 Held in Conjunction with MICCAI 2018 Granada Spain September 20 2018 Proceedings 4.Springer;2018:3\u201011.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_10_44_1","doi-asserted-by":"crossref","unstructured":"RoyS KoehlerG UlrichC et\u00a0al.Mednext: transformer\u2010driven scaling of convnets for medical image segmentation. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2023:405\u2010415.","DOI":"10.1007\/978-3-031-43901-8_39"},{"key":"e_1_2_10_45_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA NathV TangY YangD RothHR XuD.Swin UNETR: Swin transformers for semantic segmentation of brain tumors in mri images. In:International MICCAI Brainlesion Workshop.Springer;2021:272\u2010284.","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"e_1_2_10_46_1","doi-asserted-by":"crossref","unstructured":"HeY NathV YangD TangY MyronenkoA XuD.Swinunetr\u2010v2: stronger swin transformers with stagewise convolutions for 3d medical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2023:416\u2010426.","DOI":"10.1007\/978-3-031-43901-8_40"},{"key":"e_1_2_10_47_1","unstructured":"ZhouH\u2010Y GuoJ ZhangY YuL WangL YuY.nnFormer: interleaved transformer for volumetric segmentation.arXiv. Preprint posted online September 7 2021. doi:10.48550\/arXiv.2109.03201"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70653","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70653","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T12:54:59Z","timestamp":1792068899000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70653"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":46,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/mp.70653"],"URL":"https:\/\/doi.org\/10.1002\/mp.70653","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"2025-12-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70653"}}