{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:55:57Z","timestamp":1790916957411,"version":"4.1.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate preoperative risk stratification of cystic renal lesions (CRLs) remains a clinical challenge, primarily due to morphological overlap which often leads to the overtreatment of indolent cysts. To address this, we developed and validated an integrated deep learning framework that combines interactive segmentation with tri-phase CT feature integration to refine malignancy prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective multicenter study enrolled 434 patients with CRLs from four institutions, partitioned into training (n=195), validation (n=100), and external test (n=139) cohorts. The reference standard was histopathological diagnosis or \u22654 years of radiological stability. For volumetric segmentation, we implemented an interactive \u2018human-in-the-loop\u2019 Swin UNETR model. To integrate complementary information across the three CT phases, we then deployed a Tri-Phase-Channel (TPC) Perceiver architecture to integrate features extracted by parallel SEResNet50 backbones from unenhanced, corticomedullary, and nephrographic CT phases. Diagnostic performance was evaluated against the single-phase SEResNet50 models and the Bosniak classification version 2019 using the Area Under the Receiver Operating Characteristic Curve (AUC) and Decision Curve Analysis (DCA).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In the external test cohort, the interactive segmentation model yielded a Dice score of 0.890. For malignancy prediction, the TPC-Perceiver attained an AUC of 0.969 (95% CI: 0.911\u20131.000), significantly outperforming the Bosniak classification version 2019 (AUC 0.884;\n                      <jats:italic>p =0.016<\/jats:italic>\n                      ). At the fixed probability threshold of 0.5, the model achieved a sensitivity of 94.4% and a specificity of 96.7%, compared with 100.0% and 76.9%, respectively, for the clinical standard. Furthermore, decision curve analysis indicated that the deep learning framework conferred greater net benefit across a broad range of threshold probabilities.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The integrated framework showed favorable performance for cystic renal lesion risk stratification. Exploratory pairwise AUC comparisons favored the TPC Perceiver over the single-phase models and the clinical Bosniak v2019 assessment, while its AUC was comparable to that of the previous SETD model. The sensitivity-specificity profile observed at the fixed threshold suggests potential value in reducing false-positive risk stratification. Larger prospective multicenter studies are required before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1832969","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:36:35Z","timestamp":1790915795000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning with interactive segmentation for risk stratification of cystic renal lesions on tri-phase CT: a multicenter study"],"prefix":"10.3389","volume":"16","author":[{"given":"Wenlong","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Urology, The First Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pinglin","family":"He","sequence":"additional","affiliation":[{"name":"Department of Urology, The First Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]},{"name":"Department of Urology, Affiliated Hospital of Chengdu University","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanhao","family":"He","sequence":"additional","affiliation":[{"name":"Department of Urology, The First Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Urology, Yongchuan Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Urology, The Second Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwen","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Urology, Chongqing University Fuling Hospital","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fajin","family":"Lv","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence Medicine, Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyang","family":"He","sequence":"additional","affiliation":[{"name":"Department of Urology, The First Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhao","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Urology, The First Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s13244-019-0826-3","article-title":"CT and MR imaging of cystic renal lesions","volume":"11","author":"Agnello","year":"2020","journal-title":"Insights Imaging"},{"key":"B2","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1002\/jmri.27364","article-title":"Update on MRI of cystic renal masses including Bosniak version 2019","volume":"54","author":"Krishna","year":"2021","journal-title":"J Magn Reson Imaging"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.urolonc.2012.08.018","article-title":"Progression, interobserver agreement, and Malignancy rate in complex renal cysts (\u2265 Bosniak category IIF)","volume":"32","author":"El-Mokadem","year":"2014","journal-title":"Urol Oncol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1186\/s13244-024-01700-0","article-title":"Deep learning system for Malignancy risk prediction in cystic renal lesions: a multicenter study","volume":"15","author":"He","year":"2024","journal-title":"Insights Imaging"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-09082-x","article-title":"CT-based Bosniak classification of cystic renal lesions: is version 2019 an improvement on version 2005","volume":"33","author":"Dana","year":"2023","journal-title":"Eur Radiol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"192.e1","DOI":"10.1016\/j.urolonc.2024.10.011","article-title":"Interrater agreement and reliability of the Bosniak classification for cystic renal masses version 2019","volume":"43","author":"Abufaraj","year":"2025","journal-title":"Urol Oncol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1097\/ju.0000000000001438","article-title":"Prevalence of Malignancy and histopathological association of Bosniak classification, version 2019 class III and IV cystic renal masses","volume":"205","author":"Tse","year":"2021","journal-title":"J Urol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08006-5","article-title":"Bosniak classification version 2019: validation and comparison to original classification in pathologically confirmed cystic masses","volume":"31","author":"Yan","year":"2021","journal-title":"Eur Radiol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.euf.2019.03.006","article-title":"The harms of overdiagnosis and overtreatment in patients with small renal masses: a mini-review","volume":"5","author":"Sohlberg","year":"2019","journal-title":"Eur Urol Focus"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.18.20415","article-title":"Active surveillance versus nephron-sparing surgery for a Bosniak IIF or III renal cyst: a cost-effectiveness analysis","volume":"212","author":"Smith","year":"2019","journal-title":"AJR Am J Roentgenol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1097\/ju.0000000000003112","article-title":"Evolution of Bosniak IIF renal cysts and impact of the 2019 Bosniak classification","volume":"209","author":"Couture","year":"2023","journal-title":"J Urol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asjsur.2020.03.006","article-title":"Risk factors for intraoperative cyst rupture in partial nephrectomy for cystic renal masses","volume":"44","author":"Chen","year":"2021","journal-title":"Asian J Surg"},{"key":"B13","doi-asserted-by":"publisher","first-page":"12","DOI":"10.69888\/FTSHSL.2026.000592","article-title":"Domain-adaptive multi-stage hybrid segmentation with deep learning and watershed techniques for accurate medical image analysis","volume":"4","author":"Kanaujia","year":"2026","journal-title":"FMDB Trans Sustain Health Sci Lett"},{"key":"B14","doi-asserted-by":"publisher","first-page":"17","DOI":"10.64091\/ATIHL.2026.000262","article-title":"U-Net driven deep learning segmentation for retinal vasculature for early disease detection","volume":"3","author":"Sumathi","year":"2026","journal-title":"AVE Trends Intelligent Health Lett"},{"key":"B15","doi-asserted-by":"crossref","first-page":"46","DOI":"10.4018\/979-8-3693-5946-4.ch004","article-title":"Thorough analysis of deep learning methods for diagnosis of COVID-19 CT images","volume-title":"Advancements in Clinical Medicine","author":"Gnanaguru","year":"2024"},{"key":"B16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/979-8-3693-5946-4.ch001","article-title":"Revolutionizing biometrics with AI-enhanced X-ray and MRI analysis","volume-title":"Advancements in Clinical Medicine","author":"Komperla","year":"2024"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.kint.2021.05.031","article-title":"A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning","volume":"100","author":"Zheng","year":"2021","journal-title":"Kidney Int"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2743","DOI":"10.3390\/diagnostics13172743","article-title":"The use of radiomic tools in renal mass characterization","volume":"13","author":"Guti\u00e9rrez Hidalgo","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-020-02629-w","article-title":"Stratification of cystic renal masses into benign and potentially Malignant: applying machine learning to the Bosniak classification","volume":"46","author":"Miskin","year":"2021","journal-title":"Abdom Radiol (NY)"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.euf.2021.09.004","article-title":"A radiomic-based machine learning algorithm to reliably differentiate benign renal masses from renal cell carcinoma","volume":"8","author":"Nassiri","year":"2022","journal-title":"Eur Urol Focus"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08449-w","article-title":"Malignancy risk stratification of cystic renal lesions based on a contrast-enhanced CT-based machine learning model and a clinical decision algorithm","volume":"32","author":"Dana","year":"2022","journal-title":"Eur Radiol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.kint.2020.02.027","article-title":"Artificial intelligence and machine learning in nephropathology","volume":"98","author":"Becker","year":"2020","journal-title":"Kidney Int"},{"key":"B23","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s13244-023-01415-8","article-title":"CheckList for EvaluAtion of Radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII","volume":"14","author":"Kocak","year":"2023","journal-title":"Insights Imaging"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1148\/rg.285075744","article-title":"Pitfalls in renal mass evaluation and how to avoid them","volume":"28","author":"Israel","year":"2008","journal-title":"Radiographics"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-019-02271-1","article-title":"Association of tumor grade, enhancement on multiphasic CT and microvessel density in patients with clear cell renal cell carcinoma","volume":"45","author":"Coy","year":"2020","journal-title":"Abdom Radiol (NY)"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.22.28599","article-title":"Outcomes of Bosniak classification version 2019 class IIF cystic renal masses at imaging surveillance","volume":"220","author":"Shen","year":"2023","journal-title":"AJR Am J Roentgenol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.17.18142","article-title":"Malignancy rate, histologic grade, and progression of Bosniak category III and IV complex renal cystic lesions","volume":"209","author":"Mousessian","year":"2017","journal-title":"AJR Am J Roentgenol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.eururo.2022.03.006","article-title":"European association of urology guidelines on renal cell carcinoma: the 2022 update","volume":"82","author":"Ljungberg","year":"2022","journal-title":"Eur Urol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.juro.2017.09.078","article-title":"Natural history of complex renal cysts: clinical evidence supporting active surveillance","volume":"199","author":"Chandrasekar","year":"2018","journal-title":"J Urol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.14122908","article-title":"Follow-up for Bosniak category 2F cystic renal lesions","volume":"272","author":"Hindman","year":"2014","journal-title":"Radiology"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-09044-3","article-title":"Bosniak classification version 2019: a prospective comparison of CT and MRI","volume":"33","author":"Almalki","year":"2023","journal-title":"Eur Radiol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2022.110163","article-title":"Clinical utility of the Bosniak classification version 2019: diagnostic value of adding magnetic resonance imaging to computed tomography examination","volume":"148","author":"Arita","year":"2022","journal-title":"Eur J Radiol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2024.01.003","article-title":"Multiparametric MRI-based machine learning models for the characterization of cystic renal masses compared to the Bosniak classification, version 2019: a multicenter study","volume":"31","author":"Kang","year":"2024","journal-title":"Acad Radiol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.20.23656","article-title":"Bosniak classification of cystic renal masses version 2019: comparison of categorization using CT and MRI","volume":"216","author":"Tse","year":"2021","journal-title":"AJR Am J Roentgenol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1832969\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:36:44Z","timestamp":1790915804000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1832969\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":34,"alternative-id":["10.3389\/fonc.2026.1832969"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1832969","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]},"article-number":"1832969"}}