{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:58:58Z","timestamp":1761227938524,"version":"build-2065373602"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"vor","delay-in-days":35,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA249422","P41EB032840"],"award-info":[{"award-number":["R01CA249422","P41EB032840"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"In Vivo Translational Imaging Shared Resources"},{"name":"National Cancer Institute","award":["P30CA093373"],"award-info":[{"award-number":["P30CA093373"]}]},{"name":"University of California, Davis Comprehensive Cancer Center"},{"name":"NCI\u2019s Paul Calabresi K12","award":["5K12CA138464-14"],"award-info":[{"award-number":["5K12CA138464-14"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Atypical lipomatous tumors (ALTs) are aggressive fat cell tumors that are distinguished from benign lipomas (SL) mainly through histopathology. Biopsy is needed for suspicious cases but can miss malignancy, so complete surgical removal and examination are essential. MRI is used but often can't differentiate ALT from SL. We introduce a machine learning method for tumor classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To characterize the classification performance of a Bayesian additive regression trees (BART) model, built from MR radiomic features, and compare it to the readings of a musculoskeletal radiologist in classifying atypical lipomatous tumors (ALTs) from simple lipomas.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>Retrospective data were collected from 5 medical institutions in North America, for a total of 437 patients; the mean age was 58\u2009years \u00b112 years, with 248 men and 287 women. At each institution, at least T1-MRI images without contrast were collected from patients with suspected ALT prior to surgery. Histopathology was used as the reference standard. Radiomic features extracted from the MRI images were used to train the BART model and a random forest model for comparison of classification performance using a 10-fold cross-validation. Both models were compared with the classifications of an experienced (&amp;gt;10\u2009years) musculoskeletal radiologist who scored the images on a 5-point scale.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A cohort of 423 patients was included, and 1132 radiomic features were extracted from each MR study. The BART model had an accuracy, sensitivity, and specificity of 77.07% (72.76%-80.99%), 77.67% (71.36%-83.16%), and 76.50% (70.28%-81.97%), respectively, when utilizing all predictors and aggregating training and testing data from all the cohorts, approximating the human reader at 78.72% (74.51%-82.53%), 76.21% (69.80%-81.85%), and 81.11% (75.25%-86.09%), respectively. In the external validation, the average area under the curve (AUC) value across cohorts between the BART model and the human reader differed by 0.04 AUC points. From the receiver operating characteristic curve, the AUC was calculated to be 84.72% (81.00%-88.50%) and 84.74% (81.00%-88.50%) for the BART and human reader, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrated that the BART model can distinguish ALT from lipoma with diagnostic performance comparable to an experienced human observer.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/radadv\/umaf036","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:18:04Z","timestamp":1759234684000},"source":"Crossref","is-referenced-by-count":0,"title":["Bayesian additive regression trees for machine learning to classify benign vs atypical lipomatous tumors on MRI"],"prefix":"10.1093","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0951-8370","authenticated-orcid":false,"given":"Felipe","family":"Godinez","sequence":"first","affiliation":[{"name":"Department of Radiology, University of California, Davis , Sacramento, CA 95817,","place":["United States"]},{"name":"University of California Davis Comprehensive Cancer Center , Sacramento, CA 95817,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8434-2015","authenticated-orcid":false,"given":"Nimu","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of California, Davis , Davis, CA 95616,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rijul","family":"Garg","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley , Berkeley, CA 94720,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasser G","family":"Abdelhafez","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of California, Davis , Sacramento, CA 95817,","place":["United States"]},{"name":"Department of Radiotherapy and Nuclear Medicine, South Egypt Cancer Institute, Assiut University , Assiut, 71515,","place":["Egypt"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anik","family":"Roy","sequence":"additional","affiliation":[{"name":"Indian Statistical Institute Statistics, , Kolkata, 700108,","place":["India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hande","family":"Nalbant","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of California, Davis , Sacramento, CA 95817,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cyrus P","family":"Bateni","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of California, Davis , Sacramento, CA 95817,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyi","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of California, Davis , Davis, CA 95616,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology, McGill University Health Center , Montreal, QC H3A0G4,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonia","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiological Sciences, University of California, Irvine , Irvine, CA 92697,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6860-1513","authenticated-orcid":false,"given":"Ahmed W","family":"Moawad","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology, Mercy Catholic Medical Center , Darby, PA 19023,","place":["United States"]},{"name":"Department of Diagnostic Imaging, University of Texas MD Anderson Cancer Center , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0184-0717","authenticated-orcid":false,"given":"Khaled M","family":"Elsayes","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, University of Texas MD Anderson Cancer Center , Houston, TX 77030,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Guindani","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of California, Los Angeles , Los Angeles, CA 90095,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Nardo","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of California, Davis , Sacramento, CA 95817,","place":["United States"]},{"name":"University of California Davis Comprehensive Cancer Center , Sacramento, CA 95817,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"key":"2025102309412058000_umaf036-B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-28845-1_5352-1","volume-title":"Encyclopedia of Pathology","author":"Sbaraglia","year":"2020"},{"key":"2025102309412058000_umaf036-B2","volume-title":"Enzinger & Weiss\u2019s Soft Tissue Tumors","author":"Goldblum","year":"2020","edition":"7th ed"},{"issue":"5","key":"2025102309412058000_umaf036-B3","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1002\/jso.21600","article-title":"The role of core needle biopsy in the diagnosis of suspected soft tissue tumours","volume":"102","author":"Strauss","year":"2010","journal-title":"J Surg Oncol"},{"issue":"6","key":"2025102309412058000_umaf036-B4","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1007\/s00256-020-03372-5","article-title":"Qualitative evaluation of MRI features of lipoma and atypical lipomatous tumor: results from a multicenter study","volume":"49","author":"Nardo","year":"2020","journal-title":"Skeletal Radiol"},{"issue":"12","key":"2025102309412058000_umaf036-B5","doi-asserted-by":"crossref","first-page":"8605","DOI":"10.1007\/s00330-023-09916-2","article-title":"Diagnostic accuracy of CT and MR features for detecting atypical lipomatous tumors and malignant liposarcomas: a systematic review and meta-analysis","volume":"33","author":"Wilson","year":"2023","journal-title":"Eur Radiol"},{"issue":"1","key":"2025102309412058000_umaf036-B6","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1038\/s43856-022-00199-0","article-title":"Artificial intelligence and machine learning in cancer imaging","volume":"2","author":"Koh","year":"2022","journal-title":"Commun Med (Lond)"},{"issue":"2","key":"2025102309412058000_umaf036-B7","doi-asserted-by":"crossref","first-page":"173","DOI":"10.3390\/bioengineering10020173","article-title":"Machine learning methods for cancer classification using gene expression data: a review","volume":"10","author":"Alharbi","year":"2023","journal-title":"Bioengineering (Basel)"},{"issue":"2","key":"2025102309412058000_umaf036-B8","doi-asserted-by":"crossref","first-page":"114161","DOI":"10.1016\/j.eswa.2020.114161","article-title":"Deep and machine learning techniques for medical imaging-based breast cancer: a comprehensive review","volume":"167","author":"Houssein","year":"2021","journal-title":"Expert Syst Appl"},{"key":"2025102309412058000_umaf036-B9","first-page":"429","volume-title":"Handbook of Medical Image Computing and Computer Assisted Intervention","author":"Starmans","year":"2019"},{"issue":"1","key":"2025102309412058000_umaf036-B10","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s41747-022-00295-9","article-title":"Prediction of lipomatous soft tissue malignancy on MRI: comparison between machine learning applied to radiomics and deep learning","volume":"6","author":"Fradet","year":"2022","journal-title":"Eur Radiol Exp"},{"issue":"6","key":"2025102309412058000_umaf036-B11","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1007\/s00256-022-04232-0","article-title":"Radiomics-based approaches outperform visual analysis for differentiating lipoma from atypical lipomatous tumors: a review","volume":"52","author":"Haidey","year":"2023","journal-title":"Skeletal Radiol"},{"issue":"7","key":"2025102309412058000_umaf036-B12","doi-asserted-by":"crossref","first-page":"2150","DOI":"10.3390\/cancers15072150","article-title":"Development and evaluation of MR-based radiogenomic models to differentiate atypical lipomatous tumors from lipomas","volume":"15","author":"Foreman","year":"2023","journal-title":"Cancers (Basel)"},{"issue":"9","key":"2025102309412058000_umaf036-B13","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1007\/s11604-022-01278-x","article-title":"Discrimination of lipoma from atypical lipomatous tumor\/well-differentiated liposarcoma using magnetic resonance imaging radiomics combined with machine learning","volume":"40","author":"Cay","year":"2022","journal-title":"Jpn J Radiol"},{"key":"2025102309412058000_umaf036-B14","doi-asserted-by":"crossref","first-page":"102802","DOI":"10.1016\/j.eclinm.2024.102802","article-title":"Multi-center external validation of an automated method segmenting and differentiating atypical lipomatous tumors from lipomas using radiomics and deep-learning on MRI","volume":"76","author":"Spaanderman","year":"2024","journal-title":"EClinicalMedicine"},{"issue":"1","key":"2025102309412058000_umaf036-B15","first-page":"266","article-title":"BART: Bayesian additive regression trees","volume":"6","author":"Chipman","year":"2012","journal-title":"Ann Appl Stat"},{"issue":"25","key":"2025102309412058000_umaf036-B16","doi-asserted-by":"crossref","first-page":"5048","DOI":"10.1002\/sim.8347","article-title":"Bayesian additive regression trees and the general BART model","volume":"38","author":"Tan","year":"2019","journal-title":"Stat Med"},{"issue":"2","key":"2025102309412058000_umaf036-B17","doi-asserted-by":"crossref","first-page":"103","DOI":"10.5336\/biostatic.2022-89894","article-title":"Bayesian additive regression trees for predicting colon cancer: methodological study (validity study)","volume":"14","author":"Olaniran","year":"2022","journal-title":"Turkiye Klinikleri J Biostat"},{"issue":"3","key":"2025102309412058000_umaf036-B18","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1007\/s10278-023-00785-1","article-title":"AI-based automated lipomatous tumor segmentation in MR images: ensemble solution to heterogeneous data","volume":"36","author":"Liu","year":"2023","journal-title":"J Digit Imaging"},{"issue":"6","key":"2025102309412058000_umaf036-B19","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"issue":"2","key":"2025102309412058000_umaf036-B20","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"},{"issue":"21","key":"2025102309412058000_umaf036-B21","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"issue":"2","key":"2025102309412058000_umaf036-B22","doi-asserted-by":"crossref","first-page":"172","DOI":"10.2967\/jnumed.121.262464","article-title":"A guide to ComBat harmonization of imaging biomarkers in multicenter studies","volume":"63","author":"Orlhac","year":"2022","journal-title":"J Nucl Med"},{"issue":"4","key":"2025102309412058000_umaf036-B23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v070.i04","article-title":"bartMachine: machine learning with Bayesian additive regression trees","volume":"70","author":"Kapelner","year":"2016","journal-title":"J Stat Soft"},{"issue":"3","key":"2025102309412058000_umaf036-B24","doi-asserted-by":"crossref","first-page":"1750","DOI":"10.1214\/14-AOAS755","article-title":"Variable selection for Bart: an application to gene regulation","volume":"8","author":"Bleich","year":"2014","journal-title":"Ann Appl Stat"},{"issue":"22","key":"2025102309412058000_umaf036-B25","doi-asserted-by":"crossref","first-page":"2635","DOI":"10.1002\/(SICI)1097-0258(19981130)17:22<2635::AID-SIM954>3.0.CO;2-C","article-title":"Improved confidence intervals for the difference between binomial proportions based on paired data","volume":"17","author":"Newcombe","year":"1998","journal-title":"Statist Med"},{"issue":"10","key":"2025102309412058000_umaf036-B26","doi-asserted-by":"crossref","first-page":"2170","DOI":"10.1002\/sim.2677","article-title":"Confidence intervals for predictive values with an emphasis to case-control studies","volume":"26","author":"Mercaldo","year":"2007","journal-title":"Stat Med"}],"container-title":["Radiology Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/radadv\/advance-article-pdf\/doi\/10.1093\/radadv\/umaf036\/64519070\/umaf036.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/5\/umaf036\/64519070\/umaf036.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/5\/umaf036\/64519070\/umaf036.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:41:33Z","timestamp":1761226893000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/radadv\/article\/doi\/10.1093\/radadv\/umaf036\/8275783"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":26,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9,4]]}},"URL":"https:\/\/doi.org\/10.1093\/radadv\/umaf036","relation":{},"ISSN":["2976-9337"],"issn-type":[{"type":"electronic","value":"2976-9337"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,9]]},"article-number":"umaf036"}}