{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T20:32:06Z","timestamp":1786393926700,"version":"build-2736575974"},"reference-count":28,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":6,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Prostate cancer (PCa) patients frequently experience biochemical recurrence (BCR) following definitive primary treatment. Although fluorine\u201018\u2013labeled prostate\u2010specific membrane antigen positron emission tomography\/computed tomography (\n                      <jats:sup>1<\/jats:sup>\n                      <jats:sup>8<\/jats:sup>\n                      F\u2010PSMA PET\/CT) is an imaging modality that is highly sensitive for BCR, false\u2010positive findings owing to benign nonspecific uptake complicate diagnosis. Existing artificial intelligence (AI) tools have attempted to address this challenge but are often limited by their reliance on ground\u2010truth labels derived from expert visual interpretation; thus, these tools reproduce expert opinion rather than confirming disease status.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>\n                      The purpose of this study was to develop a computer\u2010aided diagnosis (CAD) system for classifying benign and malignant findings on\n                      <jats:sup>1<\/jats:sup>\n                      <jats:sup>8<\/jats:sup>\n                      F\u2010PSMA PET\/CT imaging in patients with PCa and BCR. Post\u2010therapy imaging follow\u2010up was used as an objective reference standard for malignancy.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A dataset of 69 patients with PCa and BCR who underwent\n                      <jats:sup>1<\/jats:sup>\n                      <jats:sup>8<\/jats:sup>\n                      F\u2010PSMA PET\/CT imaging was used to develop a CAD. The system was evaluated under two classification schemes based on different ground truths: Task 1 used post\u2010therapy imaging follow\u2010up as the objective reference standard for malignant findings (in a subset of 45 patients), whereas task 2 relied on expert visual interpretation at baseline. In total, after data augmentation and filtering, 334 findings were analyzed for task 1, and 467 findings were analyzed for task 2. Suspicious findings were manually segmented using LifeX software (version 25.06.1). One\u2010dimensional intensity profiles were extracted along the\n                      <jats:italic>x<\/jats:italic>\n                      \u2010,\n                      <jats:italic>y<\/jats:italic>\n                      \u2010, and\n                      <jats:italic>z<\/jats:italic>\n                      \u2010axes at the maximum intensity voxel of each finding, from which profile\u2010based and Gaussian\u2010fit features were derived. The intensity profiles were used directly as inputs to a multilayer perceptron (MLP) classifier and were also used to extract profile\u2010 and Gaussian\u2010fit\u2013based features to train a random forest (RF) classifier using feature\u2010importance analysis. The final model incorporated a stacking ensemble architecture combining the MLP and RF base models; logistic regression was the meta\u2010classifier. The model was trained and evaluated using stratified 10\u2010fold cross\u2010validation. In each fold, 90% of the findings were assigned to the training set for model development, including feature selection, and the remaining 10% were held out as an independent test set for performance evaluation. Within each training set, five\u2010fold internal cross\u2010validation was used as the validation procedure for feature selection and stacking.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      For task 1, the stacking ensemble model achieved an accuracy of 92.5% (SD, 3.5%), sensitivity of 92.3% (SD, 4.6%), specificity of 93.0% (SD, 9.2%), and an area under the receiver operating characteristic curve (AUROC) of 0.97. For task 2, performance was similar: accuracy, 91.7% (SD, 5.2%); sensitivity, 93.8% (SD, 4.5%); specificity, 85.8% (SD, 8.6%); and AUROC, 0.97. Feature\u2010importance analysis revealed that raw intensity magnitude and spatial gradients along the\n                      <jats:italic>x<\/jats:italic>\n                      \u2010axis were the most discriminative features for classification.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      The proposed CAD system achieved highly accurate classification of\n                      <jats:sup>1<\/jats:sup>\n                      <jats:sup>8<\/jats:sup>\n                      F\u2010PSMA PET\/CT findings, leveraging post\u2010therapy imaging follow\u2010up as a more objective reference standard for identifying malignancy than expert\u2010based visual interpretation alone. The system achieved high and consistent performance across both the follow\u2010up\u2013based and expert\u2010based labeling tasks. The integration of this tool into clinical workflow could improve diagnostic confidence and support the personalized management of PCa patients with BCR.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70572","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:24:26Z","timestamp":1783488266000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A computer\u2010aided diagnosis tool in prostate cancer patients with biochemical recurrence using 18F\u2010PSMA PET\/CT imaging"],"prefix":"10.1002","volume":"53","author":[{"given":"Ioanna","family":"Stamouli","sequence":"first","affiliation":[{"name":"3DMI Research Group, Department of Medical Physics, School of Medicine University of Patras  Rion Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilias","family":"Gatos","sequence":"additional","affiliation":[{"name":"3DMI Research Group, Department of Medical Physics, School of Medicine University of Patras  Rion Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodoros","family":"Kalathas","sequence":"additional","affiliation":[{"name":"Nuclear Medicine Department Cancer Hospital of Thessaloniki Theagenio  Thessaloniki Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stavros","family":"Tsantis","sequence":"additional","affiliation":[{"name":"3DMI Research Group, Department of Medical Physics, School of Medicine University of Patras  Rion Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lydia\u2010Aggeliki","family":"Zoglopitou","sequence":"additional","affiliation":[{"name":"Nuclear Medicine Department Cancer Hospital of Thessaloniki Theagenio  Thessaloniki Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paraskevi F.","family":"Katsakiori","sequence":"additional","affiliation":[{"name":"3DMI Research Group, Department of Medical Physics, School of Medicine University of Patras  Rion Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Papathanasiou","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine School of Medicine University of Patras  Rion Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Makridou","sequence":"additional","affiliation":[{"name":"Nuclear Medicine Department Cancer Hospital of Thessaloniki Theagenio  Thessaloniki Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vassiliki","family":"Chatzipavlidou","sequence":"additional","affiliation":[{"name":"Nuclear Medicine Department Cancer Hospital of Thessaloniki Theagenio  Thessaloniki Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John D.","family":"Hazle","sequence":"additional","affiliation":[{"name":"Department of Imaging Physics The University of Texas MD Anderson Cancer Center  Houston Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George C.","family":"Kagadis","sequence":"additional","affiliation":[{"name":"3DMI Research Group, Department of Medical Physics, School of Medicine University of Patras  Rion Greece"},{"name":"Department of Imaging Physics The University of Texas MD Anderson Cancer Center  Houston Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21871"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2020.09.046"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.urology.2006.03.075"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.juro.2015.12.075"},{"issue":"1","key":"e_1_2_8_6_1","first-page":"1","article-title":"18F\u2010PSMA\u20101007 PET\/CT versus 18F\u2010choline PET\/CT in patients with recurrent prostate cancer: comparison by image processing and analysis on PET\/CT images","volume":"36","author":"Katsikakis M","year":"2024","journal-title":"Hellenic Urol"},{"issue":"1","key":"e_1_2_8_7_1","first-page":"6","article-title":"More advantages in detecting bone and soft tissue metastases from prostate cancer using (18)F\u2010PSMA PET\/CT","volume":"22","author":"Pianou NK","year":"2019","journal-title":"Hell J Nucl Med"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLU.0000000000004430"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.118.212233"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.119.234187"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.118.215434"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11934-025-01268-2"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.3389\/fsurg.2022.943760"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-021-05456-3"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2023.08.044"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/tomography7030027"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-024-01104-y"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10090622"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2025.111265"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-022-06089-w"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-18-0125"},{"key":"e_1_2_8_22_1","unstructured":"Jorge CardosoM LiWenqi BrownRichard et\u00a0al.MONAI: an open\u2010source framework for deep learning in healthcare.arXiv. Preprint posted online November 4 2022."},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1177\/875647939000600106"},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"LizaF SamsuzzamanM AzimR et\u00a0al.An ensemble approach of supervised learning algorithms and artificial neural network for early prediction of diabetes.2021 3rd International Conference on Sustainable Technologies for Industry 4.0 (STI);2021.","DOI":"10.1109\/STI53101.2021.9732413"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"YadavS KadamV JadhavS Comparative analysis of ensemble classifier and single base classifier in medical disease diagnosis.2020.","DOI":"10.1007\/978-981-15-3325-9_37"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12553-024-00835-w"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0239414"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-022-05927-1"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-022-00948-1"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70572","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70572","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:54:54Z","timestamp":1786391694000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":28,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1002\/mp.70572"],"URL":"https:\/\/doi.org\/10.1002\/mp.70572","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"2026-05-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70572"}}