{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:04:20Z","timestamp":1789535060049,"version":"build-2803163510"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24SF1904202"],"award-info":[{"award-number":["24SF1904202"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop an explainable hybrid deep learning features framework using low-dose chest CT (LDCT)-derived pectoralis features for opportunistic type 2 diabetes mellitus (T2DM) opportunistic screening, evaluating its incremental value over conventional biomarkers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This multi-center study analyzed LDCT images from 1,209 individuals. Following automated MedSAM segmentation, conventional metrics (e.g., Mean_HU, SMI) and deep learning (DL) features (ResNet152) were extracted. To prevent data leakage, PCA, LASSO selection, and ExtraTrees model optimization were strictly confined to the training set. A hybrid (COM) model integrating both feature types was compared against a baseline Muscle model. SHapley Additive exPlanations (SHAP) provided clinical interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The COM model achieved an area under the curve (AUC) of 0.830 (training), 0.759 (internal validation), and 0.746 (external validation). While performing comparably to the DL model without significant difference across validation cohorts (DeLong p &amp;gt; 0.05), it significantly outperformed the baseline Muscle model (external AUC: 0.515; DeLong test, p &amp;lt; 0.001). SHAP analysis confirmed that lower Mean_HU correlated with higher T2DM risk, while DL signatures provided robust, independent diagnostic value.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This explainable hybrid model and DL model capture sub-visual pectoralis alterations, offering significant incremental diagnostic value over simple clinical and imaging metrics. They serves as an efficient, non-invasive tool for opportunistic T2DM screening during routine LDCT.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1926903","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:30:53Z","timestamp":1789533053000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable hybrid deep learning features of pectoralis on low-dose chest CT for detecting type 2 diabetes"],"prefix":"10.3389","volume":"17","author":[{"given":"Yuning","family":"Guo","sequence":"first","affiliation":[{"name":"Department of Radiology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxun","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Radiology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunyi","family":"Lyu","sequence":"additional","affiliation":[{"name":"Department of Rehabilitation Medicine, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huimei","family":"Chao","sequence":"additional","affiliation":[{"name":"Department of Radiology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dewei","family":"Kong","sequence":"additional","affiliation":[{"name":"Department of Radiology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xifu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Shanghai General Hospital","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiufeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Radiology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2021.109119","article-title":"IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045","volume":"183","author":"Sun","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.7326\/AITC202406180","article-title":"Type 2 diabetes","volume":"177","author":"Crawford","year":"2024","journal-title":"Ann Intern Med"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s00592-024-02440-9","article-title":"Unraveling the role of muscle mass and strength in predicting type 2 diabetes risk: a systematic review","volume":"62","author":"Putranata","year":"2025","journal-title":"Acta Diabetol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1186\/s12902-022-01107-2","article-title":"The sonographic quantitative assessment of the deltoid muscle to detect type 2 diabetes mellitus: a potential noninvasive and sensitive screening method","volume":"22","author":"Rosen","year":"2022","journal-title":"BMC Endocr Disord"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/nu13010183","article-title":"A narrative review on sarcopenia in type 2 diabetes mellitus: prevalence and associated factors","volume":"13","author":"Izzo","year":"2021","journal-title":"Nutrients"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1002\/jum.15110","article-title":"The hyperechoic appearance of the deltoid muscle on shoulder ultrasound imaging as a predictor of diabetes and prediabetes","volume":"39","author":"Soliman","year":"2020","journal-title":"J Ultrasound Med Off J Am Inst Ultrasound Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s13244-024-01661-4","article-title":"Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study","volume":"15","author":"Yashar","year":"2024","journal-title":"Insights Imaging"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtcvs.2020.12.014","article-title":"Commentary: Identifying sarcopenia-can the pectoralis do the heavy lifting","volume":"163","author":"Sudarshan","year":"2022","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21338","article-title":"Cancer statistics in China, 2015","volume":"66","author":"Chen","year":"2016","journal-title":"CA Cancer J Clin"},{"key":"B10","doi-asserted-by":"publisher","first-page":"769","DOI":"10.3760\/cma.j.cn112152-20250511-00215","article-title":"Chinese Medical Association guideline for clinical diagnosis and treatment of lung cancer (2025 edition)","volume":"47","year":"2025","journal-title":"Zhonghua Zhong Liu Za Zhi"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.2337\/dc24-S002","article-title":"2. Diagnosis and classification of diabetes: Standards of care in diabetes-2024","volume":"47","year":"2024","journal-title":"Diabetes Care"},{"key":"B12","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s12931-018-0771-6","article-title":"Pectoralis muscle area and mortality in smokers without airflow obstruction","volume":"19","author":"Diaz","year":"2018","journal-title":"Respir Res"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.nut.2020.110752","article-title":"Low-attenuation muscle is a predictor of diabetes mellitus: A population-based cohort study","volume":"74","author":"Tanaka","year":"2020","journal-title":"Nutrition"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3390\/ijms26020752","article-title":"Type 2 diabetes induces mitochondrial dysfunction in zebrafish skeletal muscle leading to diabetic myopathy via the miR-139-5p\/NAMPT pathway","volume":"26","author":"Chen","year":"2025","journal-title":"Int J Mol Sci"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.clnu.2021.06.025","article-title":"Deep neural network for automatic volumetric segmentation of whole-body CT images for body composition assessment","volume":"40","author":"Lee","year":"2021","journal-title":"Clin Nutr Edinb Scotl"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1148\/ryct.230146","article-title":"Predictive value of deep learning-derived CT pectoralis muscle and adipose measurements for incident heart failure: Multi-ethnic study of atherosclerosis","volume":"5","author":"Hathaway","year":"2023","journal-title":"Radiol Cardiothorac Imaging"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1183\/23120541.00485-2023","article-title":"A fully automated pipeline for the extraction of pectoralis muscle area from chest computed tomography scans","volume":"10","author":"Genkin","year":"2024","journal-title":"ERJ Open Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat Commun"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.243412","article-title":"MRI-based ovarian lesion classification via a foundation segmentation model and multimodal analysis: A multicenter study","volume":"316","author":"Hsu","year":"2025","journal-title":"Radiology"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2018.10.031","article-title":"Exudate detection in fundus images using deeply-learnable features","volume":"104","author":"Khojasteh","year":"2019","journal-title":"Comput Biol Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"101701","DOI":"10.1016\/j.artmed.2019.07.009","article-title":"Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey","volume":"99","author":"Asiri","year":"2019","journal-title":"Artif Intell Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.13527","article-title":"Association between myosteatosis and impaired glucose metabolism: A deep learning whole-body magnetic resonance imaging population phenotyping approach","volume":"15","author":"Jung","year":"2024","journal-title":"J Cachexia Sarcopenia Muscle"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.maturitas.2025.108710","article-title":"Diabetes is associated with impaired skeletal muscle quality, not quantity, in older adults, based on CT-derived chest muscle metrics","volume":"202","author":"Zhang","year":"2025","journal-title":"Maturitas"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1249\/MSS.0000000000002030","article-title":"One-year lifestyle intervention, muscle lipids, and cardiometabolic risk","volume":"51","author":"Maltais","year":"2019","journal-title":"Med Sci Sports Exerc"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1926903\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:30:58Z","timestamp":1789533058000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1926903\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":24,"alternative-id":["10.3389\/fendo.2026.1926903"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1926903","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1926903"}}