{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T21:40:45Z","timestamp":1773265245832,"version":"3.50.1"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Lower limb edema is a common clinical symptom closely associated with chronic diseases such as heart failure, liver disease, and renal dysfunction. Edema severity grading is an important indicator for clinical diagnosis and disease monitoring. However, traditional assessments that rely on visual inspection and manual palpation are subjective and inconsistent, making them insufficient to meet the requirements of standardized and precise diagnostics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes a multistage deep learning framework that integrates object detection and image classification for automatic detection and grading of lower limb edema. The system architecture initially employed YOLO models to detect indentation regions, followed by image enhancement techniques to improve the representation of edema features and enhance the detection accuracy. Finally, classification models were used to categorize edema severity. To address the data imbalance issue, random rotation was applied for data augmentation, and non-target regions were removed through automatic background elimination and cropping to enhance classification performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The experimental findings demonstrated that the proposed system achieved an average classification accuracy of 87~93% across different edema severity levels, 90\u201394% for recall rates, and 93~97% for precisions for different edema stages. These results validate the feasibility and effectiveness of the automatic detection and grading classification system for lower limb edema.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed system holds the potential for both clinical decision support and home-based self-care, enhancing the accuracy and consistency of edema assessment for patients and healthcare professionals. It can facilitate smart and precision medicine based on the status of lower limb edema.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1697503","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T05:36:11Z","timestamp":1773207371000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Lower limb edema detection and grading classification using deep learning and image enhancement technologies"],"prefix":"10.3389","volume":"13","author":[{"given":"Ting-Wei","family":"Hu","sequence":"first","affiliation":[{"name":"Programs of Artificial Intelligence Technology, Innovation Frontier Institute of Research for Science and Technology, National Taipei University of Technology","place":["Taipei, Taiwan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao-Hung","family":"Wang","sequence":"additional","affiliation":[{"name":"Heart Failure Research Center, Division of Cardiology, Department of Internal Medicine, Chang Gung Memorial Hospital","place":["Keelung, Taiwan"]},{"name":"School of Medicine, Chang Gung University","place":["Taoyuan, Taiwan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Heart Failure Research Center, Division of Cardiology, Department of Internal Medicine, Chang Gung Memorial Hospital","place":["Keelung, Taiwan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-Huang","family":"Hsu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, Tamkang University","place":["New Taipei City, Taiwan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tun-Wen","family":"Pai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taipei University of Technology","place":["Taipei, Taiwan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.5334\/ejmcm.250","article-title":"Subsiding of dependent oedema following chiropractic adjustment for discogenic sciatica","volume":"5","author":"Chu","year":"2018","journal-title":"Eur J Mol Clin Med"},{"key":"ref2","volume-title":"Medical-surgical nursing","author":"Hogan","year":"2007"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3121\/cmr.2009.819","article-title":"Reliability and feasibility of methods to quantitatively assess peripheral edema","volume":"7","author":"Brodovicz","year":"2009","journal-title":"Clin Med Res"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/978-981-16-6206-5_5","volume-title":"Approach to lower limb oedema","author":"Menegatti","year":"2022"},{"key":"ref5","volume-title":"Mosby\u2019s guide to physical examination-E-book","author":"Seidel","year":"2010"},{"key":"ref6","year":"2013"},{"key":"ref7","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.4269\/ajtmh.17-0504","article-title":"Use of a novel portable three-dimensional imaging system to measure limb volume and circumference in patients with filarial lymphedema","volume":"97","author":"Yahathugoda","year":"2017","journal-title":"Am J Trop Med Hyg"},{"key":"ref9","first-page":"4387","author":"George","year":"2016"},{"key":"ref10","first-page":"5914","author":"Williams","year":"2018"},{"key":"ref11","first-page":"457","author":"Chen","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"105002","DOI":"10.1117\/1.JBO.26.10.105002","article-title":"Objective determination of peripheral edema in heart failure patients using short-wave infrared molecular chemical imaging","volume":"26","author":"Smith","year":"2021","journal-title":"J Biomed Opt"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e18372","DOI":"10.2196\/18372","article-title":"Predictive analytics for care and management of patients with acute diseases: deep learning\u2013based method to predict crucial complication phenotypes","volume":"23","author":"Sheng","year":"2021","journal-title":"J Med Internet Res"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"9375","DOI":"10.1109\/ACCESS.2017.2788044","article-title":"Deep learning applications in medical image analysis","volume":"6","author":"Ker","year":"2017","journal-title":"IEEE Access"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2425","DOI":"10.3390\/diagnostics14212425","article-title":"The detection and classification of scaphoid fractures in radiograph by using a convolutional neural network","volume":"14","author":"Yang","year":"2024","journal-title":"Diagnostics"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"107875","DOI":"10.1016\/j.compbiomed.2023.107875","article-title":"WBC YOLO-ViT: 2 way\u20142 stage white blood cell detection and classification with a combination of YOLOv5 and vision transformer","volume":"169","author":"Tarimo","year":"2024","journal-title":"Comput Biol Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"4584","DOI":"10.1038\/s41598-024-54864-6","article-title":"A multi-class brain tumor grading system based on histopathological images using a hybrid YOLO and RESNET networks","volume":"14","author":"Elazab","year":"2024","journal-title":"Sci Rep"},{"key":"ref19","author":"Wang","year":"2024"},{"key":"ref20","author":"Wang","year":"2024"},{"key":"ref21","author":"Jocher","year":"2024"},{"key":"ref22","author":"Simonyan","year":"2014"},{"key":"ref23","first-page":"770","author":"He","year":"2016"},{"key":"ref24","author":"Jocher","year":"2024"},{"key":"ref25","author":"Goodfellow","year":"2014"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1697503\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T05:36:13Z","timestamp":1773207373000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1697503\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":25,"alternative-id":["10.3389\/fmed.2026.1697503"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1697503","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]},"article-number":"1697503"}}