{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T14:25:49Z","timestamp":1775485549536,"version":"3.50.1"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:00:00Z","timestamp":1775433600000},"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:p>Predicting prostate cancer (PCa) recurrence after radical treatment is crucial for personalised adjuvant therapy. This study aimed to compare different algorithms in order to select the best model for predicting recurrence. Therefore, a retrospective cohort analysis was conducted on 72 patients with radical prostate cancer, including 39 patients with biochemical recurrence and 33 patients without recurrence. We extracted features from imaging data, construct and evaluate 10 machine learning models and 8 deep learning models. Model performance was assessed using the area under the curve (AUC), accuracy, sensitivity, specificity, precision, 10-fold cross-validation AUC, and F1-score. In addition, the feature importance was analysed. Among all models, the MLP-Mixed-Act model exhibited superior performance in all evaluation indicators (AUC\u00a0=\u00a00.910, accuracy =0.819, sensitivity =0.744, specificity =0.909, precision =0.912, F1\u00a0=\u00a00.817), thereby indicating its strong predictive ability and clinical application potential. This study provides a theoretical basis for the development of preventive and non-invasive recurrence prediction tools. Especially in the context of valuing the tumor microenvironment, accurate recurrence prediction can effectively help select immunotherapy strategies, improve treatment efficacy and prognosis, and support for personalized treatment of PCa.<\/jats:p>","DOI":"10.3389\/fonc.2026.1733046","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T13:37:37Z","timestamp":1775482657000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting recurrence of prostate cancer after radical treatment using AI models based on PET\/CT radiomics: a dual-center study"],"prefix":"10.3389","volume":"16","author":[{"given":"Zhanxiong","family":"Yi","sequence":"first","affiliation":[{"name":"Department of Nuclear Medicine, Dongyang People\u2019s Hospital","place":["Dongyang, Zhejiang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weichun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Dongyang People\u2019s Hospital","place":["Dongyang, Zhejiang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueyang","family":"Lou","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Dongyang People\u2019s Hospital","place":["Dongyang, Zhejiang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinbing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Quzhou People\u2019s Hospital","place":["Quzhou, Zhejiang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3892\/ijo.2019.4893","article-title":"Assessment of biochemical recurrence of prostate cancer (review)","volume":"55","author":"Lin","year":"2019","journal-title":"Int J Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2018.10.011","article-title":"Prognostic value of biochemical recurrence following treatment with curative intent for prostate cancer: A systematic review","volume":"75","author":"Van den Broeck","year":"2019","journal-title":"Eur Urol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"991","DOI":"10.2147\/OTT.S485869","article-title":"The application of prostate specific membrane antigen in the diagnosis and treatment of prostate cancer: Status and challenge","volume":"17","author":"Zeng","year":"2024","journal-title":"Onco Targets Ther"},{"key":"B5","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1038\/s41391-021-00394-5","article-title":"Advances in psma-targeted therapy for prostate cancer","volume":"25","author":"Wang","year":"2022","journal-title":"Prostate Cancer Prostatic Dis"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1097\/CCO.0000000000000439","article-title":"Advances in prostate-specific membrane antigen pet of prostate cancer","volume":"30","author":"Bouchelouche","year":"2018","journal-title":"Curr Opin Oncol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-020-05140-y","article-title":"Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [ (68)Ga]Ga-psma-11 pet\/mri","volume":"48","author":"Papp","year":"2021","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.redii.2022.100021","article-title":"((18)F)-psma-1007pet\/ct in patients with biochemical recurrence after radical prostatectomy: Diagnostic performance and impact on treatment management","volume":"5","author":"Jiang","year":"2023","journal-title":"Res Diagn Interv Imaging"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07624-9","article-title":"A pet\/ct nomogram incorporating suvmax and ct radiomics for preoperative nodal staging in non-small cell lung cancer","volume":"31","author":"Xie","year":"2021","journal-title":"Eur Radiol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16040810","article-title":"Emerging trends in ai and radiomics for bladder, kidney, and prostate cancer: A critical review","volume":"16","author":"Feretzakis","year":"2024","journal-title":"Cancers (Basel)"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.4111\/icu.20230435","article-title":"Applications of artificial intelligence in urologic oncology","volume":"65","author":"Pak","year":"2024","journal-title":"Investig Clin Urol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ad8201","article-title":"Prediction of prostate cancer recurrence after radiotherapy using a fused machine learning approach: Utilizing radiomics from pretreatment t2w mri images with clinical and pathological information","author":"Piran Nanekaran","year":"2024","journal-title":"BioMed Phys Eng Express"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1342104","article-title":"Deep learning-based radiomics model from pretreatment adc to predict biochemical recurrence in advanced prostate cancer","volume":"14","author":"Wang","year":"2024","journal-title":"Front Oncol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3390\/jpm14030287","article-title":"The application of radiomics and ai to molecular imaging for prostate cancer","volume":"14","author":"Tapper","year":"2024","journal-title":"J Pers Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1097\/CM9.0000000000003689","article-title":"Artificial intelligence in prostate cancer","volume":"138","author":"Li","year":"2025","journal-title":"Chin Med J (Engl)"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3332\/ecancer.2025.1953","article-title":"Unlocking artificial intelligence, machine learning and deep learning to combat therapeutic resistance in metastatic castration-resistant prostate cancer: a comprehensive review","volume":"19","author":"Ejaz","year":"2025","journal-title":"Ecancermedicalscience"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-025-02037-4","article-title":"Combining mri radiomics, hypoxia gene signature score and clinical variables for prediction of biochemical recurrence-free survival after radiotherapy in prostate cancer","volume":"130","author":"Zhong","year":"2025","journal-title":"Radiol Med"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ac8e6f","article-title":"Radiomics software comparison using digital phantom and patient data: IBSI-compliance does not guarantee concordance of feature values","volume":"8","author":"Paquier","year":"2022","journal-title":"BioMed Phys Eng Express"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000013820","article-title":"Pitx2 methylation: A novel and effective biomarker for monitoring biochemical recurrence risk of prostate cancer","volume":"98","author":"Jiang","year":"2019","journal-title":"Med (Baltimore)"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/bjc.2013.530","article-title":"A phase ii study evaluating the toxicity and efficacy of single-agent temsirolimus in chemotherapy-naive castration-resistant prostate cancer","volume":"109","author":"Kruczek","year":"2013","journal-title":"Br J Cancer"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1097\/JU.0000000000003825","article-title":"Risk of biochemical recurrence in patients with grade group 1 prostate cancer with extraprostatic extension treated with radical prostatectomy","volume":"211","author":"Rezaee","year":"2024","journal-title":"J Urol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.114.141887","article-title":"Gleason score at diagnosis predicts the rate of detection of 18f-choline pet\/ct performed when biochemical evidence indicates recurrence of prostate cancer: Experience with 1, 000 patients","volume":"56","author":"Cimitan","year":"2015","journal-title":"J Nucl Med"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/cancers17061049","article-title":"The role of 18f psma-1007 pet\/ct in the staging and detection of recurrence of prostate cancer, a scoping review","volume":"17","author":"Armany","year":"2025","journal-title":"Cancers (Basel)"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.29386","article-title":"Added value of [18f]psma-1007 pet\/ct and pet\/mri in patients with biochemically recurrent prostate cancer: Impact on detection rates and clinical management","volume":"61","author":"Abrahamsen","year":"2025","journal-title":"J Magn Reson Imaging"},{"key":"B25","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1038\/s41585-022-00670-6","article-title":"Using PSMA imaging for prognostication in localized and advanced prostate cancer","volume":"20","author":"Roberts","year":"2023","journal-title":"Nat Rev Urol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12040799","article-title":"Current value of biparametric prostate mri with machine-learning or deep-learning in the detection, grading, and characterization of prostate cancer: A systematic review","volume":"12","author":"Michaely","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.23.00180","article-title":"Deep learning features can improve radiomics-based prostate cancer aggressiveness prediction","volume":"8","author":"Rodrigues","year":"2024","journal-title":"JCO Clin Cancer Inform"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109339","article-title":"Integrating pet\/ct, radiomics and clinical data: An advanced multi-modal approach for lymph node metastasis prediction in prostate cancer","volume":"184","author":"Ogulmus","year":"2025","journal-title":"Comput Biol Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s13139-019-00571-4","article-title":"Radiomics in oncological PET\/CT: a methodological overview","volume":"53","author":"Ha","year":"2019","journal-title":"Nucl Med Mol Imaging"},{"key":"B30","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s13073-024-01315-6","article-title":"Deep learning in cancer genomics and histopathology","volume":"16","author":"Unger","year":"2024","journal-title":"Genome Med"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-025-11360-3","article-title":"Baseline PSMA PET\/CT parameters predict overall survival and treatment response in metastatic castration-resistant prostate cancer patients","volume":"35","author":"Kleiburg","year":"2025","journal-title":"Eur Radiol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1733046\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T13:37:38Z","timestamp":1775482658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1733046\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,6]]},"references-count":31,"alternative-id":["10.3389\/fonc.2026.1733046"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1733046","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,6]]},"article-number":"1733046"}}