{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T23:02:44Z","timestamp":1793142164093,"version":"4.5.0"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82060051"],"award-info":[{"award-number":["82060051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82300376"],"award-info":[{"award-number":["82300376"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Aortic stenosis (AS) is a valvular heart disease that obstructs normal blood flow from the left ventricle to the aorta due to pathological changes in the valve, leading to impaired cardiac function. Echocardiography is a key diagnostic tool for AS; however, its accuracy is influenced by inter-observer variability, operator experience, and image quality, which can result in misdiagnosis. Therefore, alternative methods are needed to assist healthcare professionals in achieving more accurate diagnoses.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We proposed a deep learning model, RSMAS-Net, for the automated identification and diagnosis of AS using echocardiography. The model enhanced the ResNet50 backbone by replacing Stage 4 with Spatial and Channel Reconstruction Convolution (SCConv) and Multi-Dconv Head Transposed Attention (MDTA) modules, aiming to reduce redundant computations and improve feature extraction capabilities.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed method was evaluated on the TMED-2 echocardiography dataset, achieving an accuracy of 94.67%, an <jats:italic>F<\/jats:italic><jats:sub>1<\/jats:sub>-score of 94.37%, and an AUC of 0.95 for AS identification. Additionally, the model achieved an AUC of 0.93 for AS severity classification on TMED-2. RSMAS-Net outperformed multiple baseline models in recall, precision, parameter efficiency, and inference time. It also achieved an AUC of 0.91 on the TMED-1 dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>RSMAS-Net effectively diagnoses and classifies the severity of AS in echocardiographic images. The integration of SCConv and MDTA modules enhances diagnostic accuracy while reducing model complexity compared to the original ResNet50 architecture. These results highlight the potential of RSMAS-Net in improving AS assessment and supporting clinical decision-making.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1587307","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T05:34:35Z","timestamp":1745818475000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["RAMAS-Net: a module-optimized convolutional network model for aortic valve stenosis recognition in echocardiography"],"prefix":"10.3389","volume":"12","author":[{"given":"Yejia","family":"Gan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanzhong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoying","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaozhuang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maosheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangchun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,28]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1161\/CIRCRESAHA.113.300156","article-title":"Introduction to aortic stenosis","volume":"113","author":"Carabello","year":"2013","journal-title":"Circ Res"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1161\/01.cir.38.1s5.v-61","article-title":"Aortic stenosis","volume":"38","author":"Ross","year":"1968","journal-title":"Circulation"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1001\/jamacardio.2018.3152","article-title":"Outcomes of patients with asymptomatic aortic stenosis followed up in heart valve clinics","volume":"3","author":"Lancellotti","year":"2018","journal-title":"JAMA Cardiol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1001\/jama.2013.279194","article-title":"Asymptomatic aortic stenosis in the elderly: a clinical review","volume":"310","author":"Manning","year":"2013","journal-title":"JAMA"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1016\/j.jacc.2019.08.004","article-title":"Poor long-term survival in patients with moderate aortic stenosis","volume":"74","author":"Strange","year":"2019","journal-title":"J Am Coll Cardiol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.echo.2017.02.009","article-title":"Recommendations on the echocardiographic assessment of aortic valve stenosis: a focused update from the European Association of Cardiovascular Imaging and the American Society of Echocardiography","volume":"30","author":"Baumgartner","year":"2017","journal-title":"J Am Soc Echocardiogr"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"e25","DOI":"10.1016\/j.jacc.2020.11.018","article-title":"2020 ACC\/AHA guideline for the management of patients with valvular heart disease","volume":"77","author":"Otto","year":"2021","journal-title":"J Am Coll Cardiol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.crad.2020.04.007","article-title":"Imaging aortic valve calcification: significance, approach and implications","volume":"76","author":"Fletcher","year":"2021","journal-title":"Clin Radiol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1038\/s41746-019-0216-8","article-title":"Deep learning interpretation of echocardiograms","volume":"3","author":"Ghorbani","year":"2020","journal-title":"npj Digit Med"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1038\/s41598-022-27211-w","article-title":"A deep learning framework assisted echocardiography with diagnosis, lesion localization, phenogrouping heterogeneous disease, and anomaly detection","volume":"13","author":"Liu","year":"2023","journal-title":"Sci Rep"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"63","DOI":"10.29304\/jqcm.2023.15.2.1233","article-title":"Different deep learning techniques in heart disease classification: survey","author":"Hassan","year":"2023","journal-title":"J Al-Qadisiyah Comput Sci Math"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"4592","DOI":"10.1093\/eurheartj\/ehad456","article-title":"Severe aortic stenosis detection by deep learning applied to echocardiography","volume":"44","author":"Holste","year":"2023","journal-title":"Eur Heart J"},{"key":"ref13","first-page":"275","article-title":"Deep learning based aortic valve detection and state classification on Echocardiographies","author":"Hatfaludi","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1109\/TMI.2023.3305384","article-title":"Transformer-based spatio-temporal analysis for classification of aortic stenosis severity from echocardiography cine series","volume":"43","author":"Ahmadi","year":"2024","journal-title":"IEEE Trans Med Imaging"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"108037","DOI":"10.1016\/j.cmpb.2024.108037","article-title":"MV-MS-FETE: multi-view multi-scale feature extractor and transformer encoder for stenosis recognition in echocardiograms","volume":"245","author":"Avola","year":"2024","journal-title":"Comput Methods Prog Biomed"},{"key":"ref16","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref17","first-page":"6153","article-title":"SCConv: spatial and channel reconstruction convolution for feature redundancy","author":"Li","year":"2023"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01261-8_1","article-title":"Group normalization","author":"Wu","year":"2018"},{"key":"ref19","first-page":"510","article-title":"Selective kernel networks","author":"Li","year":"2019"},{"key":"ref20","article-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"ref21","article-title":"Restormer: efficient transformer for high-resolution image restoration","author":"Zamir","year":"2023"},{"key":"ref22","article-title":"A new semi-supervised learning benchmark for classifying view and diagnosing aortic stenosis from echocardiograms","author":"Huang","year":"2021"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00277","article-title":"Do better ImageNet models transfer better?","author":"Kornblith","year":"2019"},{"key":"ref25","article-title":"EfficientNetV2: smaller models and faster training","author":"Tan","year":"2021"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"ref27","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size","author":"Iandola","year":"2016"},{"key":"ref28","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1587307\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T05:34:36Z","timestamp":1745818476000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1587307\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,28]]},"references-count":28,"alternative-id":["10.3389\/fmed.2025.1587307"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1587307","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,28]]},"article-number":"1587307"}}