{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T18:35:09Z","timestamp":1793212509671,"version":"4.5.0"},"reference-count":40,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T00:00:00Z","timestamp":1791590400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019266","name":"Korea Medical Device Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Trade, Industry and Resources","id":[{"id":"https:\/\/ror.org\/02jfryy43","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003625","name":"Ministry of Health and Welfare","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003625","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety","doi-asserted-by":"publisher","award":["2410018818"],"award-info":[{"award-number":["2410018818"]}],"id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety","doi-asserted-by":"publisher","award":["RS-2026-25540191"],"award-info":[{"award-number":["RS-2026-25540191"]}],"id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Breast ultrasonography (US) is cost-effective for detecting breast implant\u2013related complications, but its reliability remains highly operator-dependent.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study developed and validated a deep learning model for the automated multi-class identification and quantitative evaluation of breast implant complications (rupture, capsular contracture, and hematoma).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The authors retrospectively analyzed 14,679 breast US images across 1022 breast implant sequences from 908 patients. The proposed architecture integrates multiscale visual encoding, automated probe position mapping, and a pathology-informed mask-graph layer with a gradient reversal layer for lumen adversarial debiasing. Four convolutional backbones were benchmarked using an independent patient-level test dataset (n = 197 implants).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The optimized DenseNet-based framework achieved 96.97% balanced accuracy with expert-guided spatial priors and 88.67% under autonomous baseline conditions. The model yielded 100% sensitivity for normal, rupture, and hematoma cohorts, and 87.88% sensitivity for capsular contracture; minor false negatives were traced to morphological heterogeneity and coexisting pathologies. Furthermore, the system extracted quantitative morphometric profiles, yielding a mean relative capsule thickness of 2.4 \u00b1 0.4% for capsular contractures and a mean relative fluid area of 13.9 \u00b1 6.4% for hematomas.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed multiscale model delivers a comprehensive, clinical-grade output, comprising accurate complication classification, 5-zone spatial localization, and objective morphometric metrics, while mitigating operator dependency. This system holds strong potential as an accessible, high-performance decision support tool for long-term safety screening of patients with breast implants.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence: 3 (Diagnostic)<\/jats:title>\n                    <jats:p\/>\n                  <\/jats:sec>","DOI":"10.1093\/asj\/sjag221","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T11:51:10Z","timestamp":1791546670000},"source":"Crossref","is-referenced-by-count":0,"title":["Multi-Class Identification and Quantification of Breast Implant\u2013Related Complications in Ultrasonography Using a Pathology-Informed Lesion Graph: A Deep Learning Development and Validation Study"],"prefix":"10.1093","author":[{"given":"Hyokyung","family":"Yoo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byeong Soo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Jin","family":"Ock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ki Yong","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hak","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-849X","authenticated-orcid":false,"given":"Sungwan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,10]]},"reference":[{"key":"2026102813565939100_sjag221-B1","doi-asserted-by":"publisher","DOI":"10.3390\/medicina57111214","article-title":"Current challenges in breast implantation","volume":"57","author":"Pelc","year":"2021","journal-title":"Medicina (B Aires)"},{"key":"2026102813565939100_sjag221-B2","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1007\/s00266-021-02701-w","article-title":"The role of high resolution ultrasonography in elucidating features of the breast implants in asymptomatic patients after implant-based augmentation mammaplasty","volume":"46","author":"Nam","year":"2022","journal-title":"Aesthetic Plast Surg"},{"key":"2026102813565939100_sjag221-B3","doi-asserted-by":"publisher","first-page":"256","DOI":"10.11152\/mu.2013.2066.163.ac1","article-title":"The role of ultrasound in the imaging assessment of the augmented breast. A pictorial review","volume":"16","author":"Ciurea","year":"2014","journal-title":"Med Ultrason"},{"key":"2026102813565939100_sjag221-B4","doi-asserted-by":"publisher","DOI":"10.3390\/medicina59061092","article-title":"Use of high-resolution ultrasound in characterizing the surface topography of a breast implant","volume":"59","author":"Kim","year":"2023","journal-title":"Medicina (B Aires)"},{"key":"2026102813565939100_sjag221-B5","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1093\/asj\/sjaf220","article-title":"Deep learning-based model for breast implant classification in ultrasonography: a multi-institutional model development and validation study","volume":"46","author":"Yoo","year":"2026","journal-title":"Aesthet Surg J"},{"key":"2026102813565939100_sjag221-B6","doi-asserted-by":"publisher","first-page":"446e","DOI":"10.1097\/PRS.0000000000006506","article-title":"Current risk estimate of breast implant-associated anaplastic large cell lymphoma in textured breast implants","volume":"145","author":"Sheena","year":"2020","journal-title":"Plast Reconstr Surg"},{"key":"2026102813565939100_sjag221-B7","doi-asserted-by":"publisher","first-page":"58S","DOI":"10.1097\/PRS.0000000000008047","article-title":"Management of symptomatic patients with textured implants","volume":"147","author":"Asaad","year":"2021","journal-title":"Plast Reconstr Surg"},{"key":"2026102813565939100_sjag221-B8","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1093\/asj\/sjy091","article-title":"A different perspective on breast implant surface texturization and anaplastic large cell lymphoma (ALCL)","volume":"39","author":"Brown","year":"2019","journal-title":"Aesthet Surg J"},{"key":"2026102813565939100_sjag221-B9","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1093\/asj\/sjw259","article-title":"NCCN consensus guidelines for the diagnosis and management of breast implant-associated anaplastic large cell lymphoma","volume":"37","author":"Clemens","year":"2017","journal-title":"Aesthet Surg J"},{"key":"2026102813565939100_sjag221-B10","doi-asserted-by":"publisher","DOI":"10.1093\/asjof\/ojab046","article-title":"High-resolution ultrasound-assisted assessment of preliminary short-term safety outcomes of an implant-based augmentation mammaplasty using a bioengineered, cell-friendly, smooth-surface device in Korean females","volume":"4","author":"Lee","year":"2022","journal-title":"Aesthet Surg J Open Forum"},{"key":"2026102813565939100_sjag221-B11","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1007\/s13244-011-0122-3","article-title":"Imaging of breast implants\u2014a pictorial review","volume":"2","author":"Juanpere","year":"2011","journal-title":"Insights Imaging"},{"key":"2026102813565939100_sjag221-B12","doi-asserted-by":"publisher","first-page":"216","DOI":"10.4103\/0971-3026.184409","article-title":"Imaging of common breast implants and implant-related complications: a pictorial essay","volume":"26","author":"Shah","year":"2016","journal-title":"Indian J Radiol Imaging"},{"key":"2026102813565939100_sjag221-B13","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1148\/rg.2017160086","article-title":"Multimodality imaging-based evaluation of single-lumen silicone breast implants for rupture","volume":"37","author":"Seiler","year":"2017","journal-title":"Radiographics"},{"key":"2026102813565939100_sjag221-B14","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s00266-014-0300-z","article-title":"Ultrasonography: a useful tool for plastic surgeons","volume":"38","author":"Benito-Ruiz","year":"2014","journal-title":"Aesthetic Plast Surg"},{"key":"2026102813565939100_sjag221-B15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.cps.2020.08.001","article-title":"Fundamentals of high-resolution ultrasound in breast implant screening for plastic surgeons","volume":"48","author":"Schafer","year":"2021","journal-title":"Clin Plast Surg"},{"key":"2026102813565939100_sjag221-B16","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1097\/00013644-200412000-00006","article-title":"Sonography of mammary implants","volume":"20","author":"Stavros","year":"2004","journal-title":"Ultrasound Q"},{"key":"2026102813565939100_sjag221-B17","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1053\/j.ro.2021.12.005","article-title":"Updates in artificial intelligence for breast imaging","volume":"57","author":"Bahl","year":"2022","journal-title":"Semin Roentgenol"},{"key":"2026102813565939100_sjag221-B18","doi-asserted-by":"publisher","DOI":"10.1259\/bjro.20210060","article-title":"Deep learning in breast imaging","volume":"4","author":"Bhowmik","year":"2022","journal-title":"BJR Open"},{"key":"2026102813565939100_sjag221-B19","doi-asserted-by":"publisher","first-page":"183","DOI":"10.14366\/usg.20117","article-title":"Artificial intelligence in breast ultrasonography","volume":"40","author":"Kim","year":"2021","journal-title":"Ultrasonography"},{"key":"2026102813565939100_sjag221-B20","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10121055","article-title":"The utility of deep learning in breast ultrasonic imaging: a review","volume":"10","author":"Fujioka","year":"2020","journal-title":"Diagnostics"},{"key":"2026102813565939100_sjag221-B21","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1002\/jum.15684","article-title":"Diagnostic performance of an artificial intelligence system in breast ultrasound","volume":"41","author":"O'Connell","year":"2022","journal-title":"J Ultrasound Med"},{"key":"2026102813565939100_sjag221-B22","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00438-z","article-title":"Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis","volume":"4","author":"Aggarwal","year":"2021","journal-title":"NPJ Digit Med"},{"key":"2026102813565939100_sjag221-B23","doi-asserted-by":"publisher","author":"Briechle","DOI":"10.1117\/12.421129"},{"key":"2026102813565939100_sjag221-B24","author":"Vaswani"},{"key":"2026102813565939100_sjag221-B25","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0069-y","article-title":"Graph convolutional networks: a comprehensive review","volume":"6","author":"Zhang","year":"2019","journal-title":"Comput Soc Netw"},{"key":"2026102813565939100_sjag221-B26","doi-asserted-by":"publisher","author":"Zhu","DOI":"10.1107\/12.421130"},{"key":"2026102813565939100_sjag221-B27","author":"Ganin"},{"key":"2026102813565939100_sjag221-B28","doi-asserted-by":"publisher","author":"Zhang","DOI":"10.24963\/ijcai.2018\/547"},{"key":"2026102813565939100_sjag221-B29","doi-asserted-by":"publisher","author":"ParsaPour","DOI":"10.2139\/ssrn.5982714"},{"key":"2026102813565939100_sjag221-B30","doi-asserted-by":"publisher","first-page":"38","DOI":"10.34218\/IJEET.12.5.2021.005","article-title":"Multiple plant leaf disease classification using densenet-121 architecture","volume":"12","author":"Vellaichamy","year":"2021","journal-title":"Int J Electr Eng Technol"},{"key":"2026102813565939100_sjag221-B31","author":"Tan"},{"key":"2026102813565939100_sjag221-B32","doi-asserted-by":"publisher","author":"Liu","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2026102813565939100_sjag221-B33","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41416-021-01333-w","article-title":"Adoption of artificial intelligence in breast imaging: evaluation, ethical constraints and limitations","volume":"125","author":"Hickman","year":"2021","journal-title":"Br J Cancer"},{"key":"2026102813565939100_sjag221-B34","doi-asserted-by":"publisher","first-page":"19","DOI":"10.4329\/wjr.v11.i2.19","article-title":"Artificial intelligence in breast ultrasound","volume":"11","author":"Wu","year":"2019","journal-title":"World J Radiol"},{"key":"2026102813565939100_sjag221-B35","first-page":"5396","article-title":"Normal ultrasound findings and complications of breast implants in Colombia","volume":"31","author":"Orozco","year":"2020","journal-title":"Rev Colomb Radiol"},{"key":"2026102813565939100_sjag221-B36","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.jmbbm.2018.08.035","article-title":"Breast implant surface texture impacts host tissue response","volume":"88","author":"Atlan","year":"2018","journal-title":"J Mech Behav Biomed Mater"},{"key":"2026102813565939100_sjag221-B37","doi-asserted-by":"publisher","author":"Selvaraju","DOI":"10.1109\/ICCV.2017.74"},{"key":"2026102813565939100_sjag221-B38","doi-asserted-by":"publisher","first-page":"405","DOI":"10.4048\/jbc.2023.26.e45","article-title":"Artificial intelligence in breast cancer diagnosis and personalized medicine","volume":"26","author":"Ahn","year":"2023","journal-title":"J Breast Cancer"},{"key":"2026102813565939100_sjag221-B39","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.crad.2019.02.006","article-title":"Artificial intelligence in breast imaging","volume":"74","author":"Le","year":"2019","journal-title":"Clin Radiol"},{"key":"2026102813565939100_sjag221-B40","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12123111","article-title":"Artificial intelligence (AI) in breast imaging: a scientometric umbrella review","volume":"12","author":"Tan","year":"2022","journal-title":"Diagnostics"}],"container-title":["Aesthetic Surgery Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/asj\/advance-article-pdf\/doi\/10.1093\/asj\/sjag221\/71820494\/sjag221.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/asj\/advance-article-pdf\/doi\/10.1093\/asj\/sjag221\/71820494\/sjag221.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T17:57:07Z","timestamp":1793210227000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/asj\/advance-article\/doi\/10.1093\/asj\/sjag221\/8904706"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1093\/asj\/sjag221","relation":{},"ISSN":["1090-820X","1527-330X"],"issn-type":[{"value":"1090-820X","type":"print"},{"value":"1527-330X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,10]]},"article-number":"sjag221"}}