{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T06:07:45Z","timestamp":1788847665736,"version":"build-2803163510"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate an interpretable machine learning (ML) framework that differentiates adrenal lipid-poor adenomas (LPAs) from pheochromocytomas (PHEOs) using radiomic features derived from multi-phase contrast-enhanced computed tomography (CECT).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included 229 patients with pathologically confirmed adrenal tumours (132 LPAs, 97 PHEOs). Lesions were stratified into washout (absolute percentage washout [APW]\u202f&amp;gt;\u202f60%) and non-washout (APW\u202f\u2264\u202f60%) cohorts according to established criteria. We trained decision tree (DT), support vector machine (SVM), and logistic regression (LR) models using a predefined set of clinically relevant CT features. The inherently interpretable DT model was further dissected to revealr key discriminative features and its underlying decision logic. Model performance was evaluated using the area under the curve (AUC) with 95% confidence intervals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The DT model achieved excellent diagnostic performance, with an AUC of 0.977 (95% CI: 0.934\u20131.000) in the washout group and 0.983 (95% CI: 0.962\u20131.000) in the non-washout group. Feature importance analysis identified cystic degeneration as the most influential discriminator, followed by enhancement potential (EP) and baseline attenuation (CTu). The DT\u2019s hierarchical decision rules provided clear and clinically transparent pathways.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This interpretable ML framework accurately distinguishes LPAs from PHEOs. The DT model strikes an optimal balance between high diagnostic accuracy and inherent interpretability, offering a practical tool that may enhance clinical confidence when managing indeterminate adrenal lesions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1915569","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:35:15Z","timestamp":1788845715000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An interpretable machine learning framework using multi-phase computed tomography for differentiation of adrenal lipid-poor adenomas and pheochromocytomas"],"prefix":"10.3389","volume":"9","author":[{"given":"Panliang","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Radiology, Tongde Hospital of Zhejiang Province Affiliated to Zhejiang Chinese Medical University","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangmei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hangzhou First People's Hospital, Westlake University School of Medicine","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Radiology, Tongde Hospital of Zhejiang Province Affiliated to Zhejiang Chinese Medical University","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongfeng","family":"Niu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linyang","family":"He","sequence":"additional","affiliation":[{"name":"Jianpei Technology","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyu","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Affiliated Hospital of Bengbu Medical University","place":["Bengbu, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Tongde Hospital of Zhejiang Province Affiliated to Zhejiang Chinese Medical University","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"234","DOI":"10.5152\/dir.2022.21266","article-title":"Machine learning analysis of adrenal lesions: preliminary study evaluating texture analysis in the differentiation of adrenal lesions","volume":"29","author":"Altay","year":"2023","journal-title":"Diagn. Interv. Radiol."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e2183","DOI":"10.1210\/clinem\/dgae781","article-title":"Clinical and radiological features of atypical adrenal masses-a multicenter retrospective study","volume":"110","author":"Balderrama-Brondani","year":"2025","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"201","DOI":"10.2214\/ajr.171.1.9648789","article-title":"Characterization of adrenal masses using unenhanced CT: an analysis of the CT literature","volume":"171","author":"Boland","year":"1998","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1530\/EJE-18-0006","article-title":"Unenhanced CT imaging is highly sensitive to exclude pheochromocytoma: a multicenter study","volume":"178","author":"Buitenwerf","year":"2018","journal-title":"Eur. J. Endocrinol."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1210\/jc.2018-01532","article-title":"CT characteristics of pheochromocytoma: relevance for the evaluation of adrenal incidentaloma","volume":"104","author":"Canu","year":"2019","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"G1","DOI":"10.1093\/ejendo\/lvad066","article-title":"European Society of Endocrinology clinical practice guidelines on the management of adrenal incidentalomas, in collaboration with the European network for the study of adrenal tumors","volume":"189","author":"Fassnacht","year":"2023","journal-title":"Eur. J. Endocrinol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"4722","DOI":"10.1007\/s00261-025-04893-0","article-title":"Using interpretable rule-learning artificial intelligence to optimally differentiate adrenal pheochromocytomas from adenomas with CT radiomics","volume":"50","author":"Glazer","year":"2025","journal-title":"Abdom Radiol (NY)."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"362","DOI":"10.21037\/gs.2020.03.04","article-title":"Not all adrenal incidentalomas require biochemical testing to exclude pheochromocytoma: Mayo clinic experience and a meta-analysis","volume":"9","author":"Gruber","year":"2020","journal-title":"Gland Surg."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"424","DOI":"10.7326\/0003-4819-138-5-200303040-00013","article-title":"Management of the clinically inapparent adrenal mass (\"incidentaloma\")","volume":"138","author":"Grumbach","year":"2003","journal-title":"Ann. Intern. Med."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1210\/edrv-16-4-460","article-title":"Incidentally discovered adrenal masses","volume":"16","author":"Kloos","year":"1995","journal-title":"Endocr. Rev."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1530\/EC-23-0466","article-title":"Bilateral pheochromocytomas: clinical presentation and morbidity rate related to surgery technique and genetic status","volume":"13","author":"Lider Burciulescu","year":"2024","journal-title":"Endocr. Connect."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"833413","DOI":"10.3389\/fendo.2022.833413","article-title":"Computed tomography-based machine learning differentiates adrenal Pheochromocytoma from lipid-poor adenoma","volume":"13","author":"Liu","year":"2022","journal-title":"Front. Endocrinol. (Lausanne)"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1339671","DOI":"10.3389\/fonc.2024.1339671","article-title":"Differentiation of pheochromocytoma and adrenal lipoid adenoma by radiomics: are enhanced CT scanning images necessary?","volume":"14","author":"Liu","year":"2024","journal-title":"Front. Oncol."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.2174\/1573405619666221115124352","article-title":"A CT Radiomics analysis of the adrenal masses: can we discriminate lipid-poor adenomas from the Pheochromocytoma and malignant masses?","volume":"19","author":"Mendi","year":"2023","journal-title":"Curr Med Imaging."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"4853","DOI":"10.1007\/s00261-021-03136-2","article-title":"Machine learning-based texture analysis for differentiation of radiologically indeterminate small adrenal tumors on adrenal protocol CT scans","volume":"46","author":"Moawad","year":"2021","journal-title":"Abdom Radiol (NY)."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"684","DOI":"10.2214\/ajr.185.3.01850684","article-title":"Comparison of CT findings in symptomatic and incidentally discovered pheochromocytomas","volume":"185","author":"Motta-Ramirez","year":"2005","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"925577","DOI":"10.3389\/fendo.2022.925577","article-title":"Risk prediction model establishment with tri-phasic CT image features for differential diagnosis of adrenal pheochromocytomas and lipid-poor adenomas: grouping method","volume":"13","author":"Niu","year":"2022","journal-title":"Front. Endocrinol. (Lausanne)"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"122","DOI":"10.2214\/AJR.12.9620","article-title":"Can established CT attenuation and washout criteria for adrenal adenoma accurately exclude pheochromocytoma?","volume":"201","author":"Patel","year":"2013","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1210\/jendso\/bvae199","article-title":"High diagnostic accuracy of arterial phase CT in differentiating Pheochromocytoma in good\/poor washout adrenal masses","volume":"9","author":"Phadte","year":"2024","journal-title":"J Endocr Soc."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1097\/JU.0000000000003644","article-title":"Diagnosis, management, and follow-up of the incidentally discovered adrenal mass: CUA guideline endorsed by the AUA","volume":"210","author":"Rowe","year":"2023","journal-title":"J. Urol."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/s00104-023-01988-6","article-title":"Personalized treatment of pheochromocytoma","volume":"95","author":"Schlegel","year":"2024","journal-title":"Chirurgie (Heidelb)."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1186\/s12880-025-01835-6","article-title":"Combined nomogram for differentiating adrenal pheochromocytoma from large-diameter lipid-poor adenoma using multiphase CT radiomics and clinico-radiological features","volume":"25","author":"Shan","year":"2025","journal-title":"BMC Med. Imaging"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1007\/s00330-017-5076-5","article-title":"Pheochromocytoma as a frequent false-positive in adrenal washout CT: a systematic review and meta-analysis","volume":"28","author":"Woo","year":"2018","journal-title":"Eur. Radiol."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1186\/s12880-023-01106-2","article-title":"Machine learning for differentiation of lipid-poor adrenal adenoma and subclinical pheochromocytoma based on multiphase CT imaging radiomics","volume":"23","author":"Xiao","year":"2023","journal-title":"BMC Med. Imaging"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2540596","DOI":"10.1080\/07853890.2025.2540596","article-title":"Automatic recognition of adrenal incidentalomas using a two-stage cascade network: a multicenter study","volume":"57","author":"Xie","year":"2025","journal-title":"Ann. Med."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"3577","DOI":"10.7150\/jca.26356","article-title":"Adrenal incidentaloma: machine learning-based quantitative texture analysis of unenhanced CT can effectively differentiate sPHEO from lipid-poor adrenal adenoma","volume":"9","author":"Yi","year":"2018","journal-title":"J. Cancer"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/s0889-8529(05)70122-5","article-title":"Management approaches to adrenal incidentalomas. A view from Rochester, Minnesota","volume":"29","author":"Young","year":"2000","journal-title":"Endocrinol. Metab. Clin. N. Am."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4158\/EP.15.S1.1","article-title":"The American Association of Clinical Endocrinologists and American Association of endocrine surgeons medical guidelines for the management of adrenal incidentalomas","volume":"15","author":"Zeiger","year":"2009","journal-title":"Endocr. Pract."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1007\/s00261-024-04279-8","article-title":"CT-based radiomics research for discriminating the risk stratification of pheochromocytoma using different machine learning models: a multi-center study","volume":"49","author":"Zhao","year":"2024","journal-title":"Abdom Radiol (NY)."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s13244-025-01952-4","article-title":"CT-based radiomics deep learning signatures for non-invasive prediction of metastatic potential in pheochromocytoma and paraganglioma: a multicohort study","volume":"16","author":"Zhou","year":"2025","journal-title":"Insights Imaging"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1915569\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:35:16Z","timestamp":1788845716000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1915569\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":30,"alternative-id":["10.3389\/frai.2026.1915569"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1915569","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"article-number":"1915569"}}