{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T12:18:45Z","timestamp":1778156325662,"version":"3.51.4"},"reference-count":39,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"vor","delay-in-days":126,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Biomedical Imaging"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Lung field segmentation (LFS) in chest x\u2010rays (CXR) is a key step for the computer\u2010assisted diagnosis of respiratory diseases. However, achieving precise delineation remains challenging in images with poor contrast and superimposed anatomical structures, often resulting in imprecise lung outlines in deep learning (DL) models. Furthermore, existing models often lack generalizability, performing well on specific datasets but failing on unseen domains due to variations in imaging equipment, acquisition protocols, and patient demographics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To overcome these limitations, we propose a two\u2010phase hybrid approach for robust and generalizable LFS in CXR. The first phase employs a heuristic approach to extract and refine multiscale edge features: The Laplacian of Gaussian (LoG) filter detects closed contours that effectively highlight the overall lung shape, whereas the Canny detector captures the finer, high\u2010frequency edge details that preserve the lung outlines often missed by DL models due to overlapping structures. In the second phase, the enriched multiscale feature maps are fused along with the original contrast inputs and then used to train and evaluate various U\u2010Net architectures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed approach is evaluated on three benchmark datasets: Montgomery County (MC), Shenzhen Hospital (SH), and Japanese Society of Radiological Technology (JSRT). Experiments conducted on individual datasets using five\u2010fold cross\u2010validation and testing on a completely unseen separate test set to simulate real\u2010world settings revealed that the proposed edge\u2010assisted filters, especially the Canny filter, significantly improve segmentation performance metrics. Among all U\u2010Net variants, deep attention U\u2010Net achieved the highest performance using a consistent channel combination, attaining a dice coefficient of 0.9815, a Jaccard score of 0.9624 on the JSRT dataset. The proposed approach achieved a dice gain of +0.0011 to +0.0034 and an IoU gain of +0.009 to +0.0034 across the three datasets compared with the baseline configuration using original images. Furthermore, cross\u2010dataset validation also depicted improvement gains in dice, IoU, and other metrics, demonstrating the generalizability of the proposed approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Further cross\u2010dataset validation confirmed the framework\u2032s strong generalization capabilities, demonstrating stable performance even on unseen domains. These findings validate the proposed method as a reliable and effective solution for LFS in diverse and clinically challenging environments, offering promising benefits for respiratory diagnosis and patient care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1155\/ijbi\/6566262","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T12:04:21Z","timestamp":1778155461000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing the Generalizability of Deep Learning\u2013Based Models for Lung Field Segmentation in Chest Radiographs Using Edge\u2010Assisted Multiscale Feature Fusion"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9178-6544","authenticated-orcid":false,"given":"Tairah","family":"Andrabi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7650-7751","authenticated-orcid":false,"given":"Sajid Yousuf","family":"Bhat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"e_1_2_14_1_2","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1007\/978-3-642-16444-6_63","volume-title":"Proceedings of the International Conference on Security-Enriched Urban Computing and Smart Grid","author":"Ganguly S.","year":"2010"},{"key":"e_1_2_14_2_2","doi-asserted-by":"publisher","DOI":"10.1378\/chest.10-1302"},{"key":"e_1_2_14_3_2","first-page":"27","volume-title":"Comparative Interpretation of CT and Standard Radiography of the Chest","author":"Delrue L.","year":"2010"},{"key":"e_1_2_14_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01917-1"},{"key":"e_1_2_14_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02352-7"},{"key":"e_1_2_14_6_2","first-page":"234","volume-title":"Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger O.","year":"2015"},{"key":"e_1_2_14_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-12743-y"},{"key":"e_1_2_14_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22528"},{"key":"e_1_2_14_9_2","first-page":"2659","volume-title":"Proceedings of the 2024 27th International Conference on Computer and Information Technology","author":"Ray S. K.","year":"2024"},{"key":"e_1_2_14_10_2","article-title":"Transfer Learning-Based Segmentation of Pneumonia From Chest X-Rays Images","volume":"8","author":"Pyar K.","year":"2025","journal-title":"Journal of Applied Informatics and Technology"},{"key":"e_1_2_14_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017915"},{"key":"e_1_2_14_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10091091"},{"key":"e_1_2_14_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/math9222896"},{"key":"e_1_2_14_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-023-01848-4"},{"key":"e_1_2_14_15_2","doi-asserted-by":"publisher","DOI":"10.1080\/23311916.2023.2229571"},{"key":"e_1_2_14_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-79494-w"},{"key":"e_1_2_14_17_2","doi-asserted-by":"publisher","DOI":"10.1049\/tje2.70065"},{"key":"e_1_2_14_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10060987"},{"key":"e_1_2_14_19_2","first-page":"327","volume-title":"Proceeding of the 2023 International Conference on Cyber Management and Engineering","author":"Nimalsiri W.","year":"2023"},{"key":"e_1_2_14_20_2","doi-asserted-by":"publisher","DOI":"10.3991\/ijoe.v18i07.30807"},{"key":"e_1_2_14_21_2","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2025.2501936"},{"key":"e_1_2_14_22_2","doi-asserted-by":"publisher","DOI":"10.46649\/fjiece.v3.2.20a.29.5.2024"},{"key":"e_1_2_14_23_2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3081584"},{"key":"e_1_2_14_24_2","first-page":"532","volume-title":"Proceedings of the 2015 2nd International Conference on Signal Processing and Integrated Networks","author":"Anand S. S.","year":"2015"},{"key":"e_1_2_14_25_2","doi-asserted-by":"publisher","DOI":"10.1080\/13682199.2023.2208923"},{"key":"e_1_2_14_26_2","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/B978-0-12-336156-1.50061-6","volume-title":"Graphics Gems IV","author":"Zuiderveld K.","year":"1994"},{"key":"e_1_2_14_27_2","doi-asserted-by":"publisher","DOI":"10.3978\/j.issn.2223-4292.2014.11.20"},{"key":"e_1_2_14_28_2","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.174.1.1740071"},{"key":"e_1_2_14_29_2","doi-asserted-by":"publisher","DOI":"10.2174\/1573405618666220630151409"},{"key":"e_1_2_14_30_2","first-page":"3","volume-title":"Proceedings of the International Workshop on Deep Learning in Medical Image Analysis","author":"Zhou Z.","year":"2018"},{"key":"e_1_2_14_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"e_1_2_14_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914873"},{"key":"e_1_2_14_33_2","first-page":"658","volume-title":"Proceedings of the 2024 6th International Conference on Electrical Engineering and Information & Communication Technology","author":"Mahmud Auvy A. A.","year":"2024"},{"key":"e_1_2_14_34_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13091651"},{"key":"e_1_2_14_35_2","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2700"},{"key":"e_1_2_14_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2023.100929"},{"key":"e_1_2_14_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s43538-023-00223-4"},{"key":"e_1_2_14_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-025-03344-8"},{"key":"e_1_2_14_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-024-00981-7"}],"container-title":["International Journal of Biomedical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/ijbi\/6566262","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/ijbi\/6566262","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/ijbi\/6566262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T12:04:24Z","timestamp":1778155464000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/ijbi\/6566262"}},"subtitle":[],"editor":[{"given":"Vincenzo","family":"Positano","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/ijbi\/6566262"],"URL":"https:\/\/doi.org\/10.1155\/ijbi\/6566262","archive":["Portico"],"relation":{},"ISSN":["1687-4188","1687-4196"],"issn-type":[{"value":"1687-4188","type":"print"},{"value":"1687-4196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-10-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6566262"}}