{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T17:05:35Z","timestamp":1793207135049,"version":"4.5.0"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec026\">\n<jats:title>Background<\/jats:title>\n<jats:p>Prostate cancer is a common malignancy in men, and accurately distinguishing between benign and malignant nodules at an early stage is crucial for optimizing treatment. Multimodal imaging (such as ADC and T2) plays an important role in the diagnosis of prostate cancer, but effectively combining these imaging features for accurate classification remains a challenge.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec027\">\n<jats:title>Methods<\/jats:title>\n<jats:p>This retrospective study included MRI data from 199 prostate cancer patients. Radiomic features from both the tumor and peritumoral regions were extracted, and a random forest model was used to select the most contributive features for classification. Three machine learning models\u2014Random Forest, XGBoost, and Extra Trees\u2014were then constructed and trained on four different feature combinations (tumor ADC, tumor T2, tumor ADC+T2, and tumor\u2009+\u2009peritumoral ADC+T2).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec028\">\n<jats:title>Results<\/jats:title>\n<jats:p>The model incorporating multimodal imaging features and peritumoral characteristics showed superior classification performance. The Extra Trees model outperformed the others across all feature combinations, particularly in the tumor\u2009+\u2009peritumoral ADC+T2 group, where the AUC reached 0.729. The AUC values for the other combinations also exceeded 0.65. While the Random Forest and XGBoost models performed slightly lower, they still demonstrated strong classification abilities, with AUCs ranging from 0.63 to 0.72. SHAP analysis revealed that key features, such as tumor texture and peritumoral gray-level features, significantly contributed to the model\u2019s classification decisions.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec029\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>The combination of multimodal imaging data with peritumoral features moderately improved the accuracy of prostate cancer classification. This model provides a non-invasive and effective diagnostic tool for clinical use and supports future personalized treatment decisions.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0323752","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T17:37:46Z","timestamp":1747330666000},"page":"e0323752","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["Integrating multimodal imaging and peritumoral features for enhanced prostate cancer diagnosis: A machine learning approach"],"prefix":"10.1371","volume":"20","author":[{"given":"Huadi","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemiao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhan","family":"Shou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9910-3185","authenticated-orcid":true,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,5,15]]},"reference":[{"issue":"12","key":"pone.0323752.ref001","doi-asserted-by":"crossref","first-page":"3200","DOI":"10.3390\/biomedicines11123200","article-title":"Equilibrium optimization algorithm with deep learning enabled prostate cancer detection on MRI images","volume":"11","author":"E Yang","year":"2023","journal-title":"Biomedicines"},{"issue":"8","key":"pone.0323752.ref002","doi-asserted-by":"crossref","first-page":"1893","DOI":"10.1158\/1055-9965.EPI-10-0437","article-title":"Global patterns of cancer incidence and mortality rates and trends","volume":"19","author":"A Jemal","year":"2010","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"key":"pone.0323752.ref003","article-title":"Prostate cancer screening with prostate-specific antigen (PSA) test: a systematic review and meta-analysis","volume":"362","author":"D Ilic","year":"2018","journal-title":"BMJ"},{"issue":"18","key":"pone.0323752.ref004","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1056\/NEJM200105033441806","article-title":"Clinical practice. Prostate-specific-antigen testing for early diagnosis of prostate cancer","volume":"344","author":"MJ Barry","year":"2001","journal-title":"N Engl J Med"},{"issue":"3","key":"pone.0323752.ref005","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1016\/j.juro.2014.03.117","article-title":"Optimization of prostate biopsy: the role of magnetic resonance imaging targeted biopsy in detection, localization and risk assessment","volume":"192","author":"MA Bjurlin","year":"2014","journal-title":"J Urol"},{"key":"pone.0323752.ref006","doi-asserted-by":"crossref","unstructured":"Gutierrez Y, Arevalo J, Martinez F. Multimodal contrastive supervised learning to classify clinical significance MRI regions on prostate cancer. Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society Annual International Conference. 2022;2022:1682\u20135.doi: 10.1109\/embc48229.2022.9871243 360864647.","DOI":"10.1109\/EMBC48229.2022.9871243"},{"key":"pone.0323752.ref007","doi-asserted-by":"crossref","DOI":"10.5489\/cuaj.1248","article-title":"How reliable is 12-core prostate biopsy procedure in the detection of prostate cancer?","volume":"7","author":"EC Serefoglu","year":"2013","journal-title":"Can Urol Assoc J"},{"issue":"4","key":"pone.0323752.ref008","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1016\/j.eururo.2015.06.033","article-title":"Re: can clinically significant prostate cancer be detected with multiparametric magnetic resonance imaging? A systematic review of the literature","volume":"68","author":"A Sivaraman","year":"2015","journal-title":"Eur Urol"},{"issue":"2","key":"pone.0323752.ref009","doi-asserted-by":"crossref","first-page":"384","DOI":"10.2214\/AJR.18.20796","article-title":"The evolution of MRI of the prostate: the past, the present, and the future","volume":"213","author":"F Giganti","year":"2019","journal-title":"AJR Am J Roentgenol"},{"issue":"4","key":"pone.0323752.ref010","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1007\/s00330-011-2377-y","article-title":"ESUR prostate MR guidelines 2012","volume":"22","author":"JO Barentsz","year":"2012","journal-title":"Eur Radiol"},{"issue":"1","key":"pone.0323752.ref011","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1148\/radiol.2461070057","article-title":"Assessment of biologic aggressiveness of prostate cancer: correlation of MR signal intensity with Gleason grade after radical prostatectomy","volume":"246","author":"L Wang","year":"2008","journal-title":"Radiology"},{"issue":"1","key":"pone.0323752.ref012","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.eururo.2015.08.052","article-title":"PI-RADS prostate imaging - Reporting and data system: 2015, Version 2","volume":"69","author":"JC Weinreb","year":"2016","journal-title":"Eur Urol"},{"issue":"1","key":"pone.0323752.ref013","doi-asserted-by":"crossref","first-page":"109","DOI":"10.2214\/AJR.13.10699","article-title":"Radiologist, be aware: ten pitfalls that confound the interpretation of multiparametric prostate MRI","volume":"202","author":"AB Rosenkrantz","year":"2014","journal-title":"AJR Am J Roentgenol"},{"issue":"2","key":"pone.0323752.ref014","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1148\/radiol.11091409","article-title":"Relationship between apparent diffusion coefficients at 3.0-T MR imaging and Gleason grade in peripheral zone prostate cancer","volume":"259","author":"T Hambrock","year":"2011","journal-title":"Radiology"},{"issue":"2","key":"pone.0323752.ref015","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1002\/pros.20124","article-title":"Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a useful modality for the precise detection and staging of early prostate cancer","volume":"62","author":"N Hara","year":"2005","journal-title":"Prostate"},{"issue":"6","key":"pone.0323752.ref016","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.2214\/AJR.12.8510","article-title":"Overview of dynamic contrast-enhanced MRI in prostate cancer diagnosis and management","volume":"198","author":"S Verma","year":"2012","journal-title":"AJR Am J Roentgenol"},{"issue":"1","key":"pone.0323752.ref017","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s00292-015-0136-6","article-title":"The 2014 consensus conference of the ISUP on Gleason grading of prostatic carcinoma","volume":"37","author":"G Kristiansen","year":"2016","journal-title":"Pathologe"},{"issue":"4","key":"pone.0323752.ref018","doi-asserted-by":"crossref","first-page":"799","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":"HJ Michaely","year":"2022","journal-title":"Diagnostics (Basel)"},{"issue":"2","key":"pone.0323752.ref019","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1148\/radiol.13130029","article-title":"Transition zone prostate cancer: incremental value of diffusion-weighted endorectal MR imaging in tumor detection and assessment of aggressiveness","volume":"269","author":"SI Jung","year":"2013","journal-title":"Radiology"},{"issue":"2","key":"pone.0323752.ref020","doi-asserted-by":"crossref","first-page":"343","DOI":"10.2214\/AJR.13.11046","article-title":"Accuracy of multiparametric MRI for prostate cancer detection: a meta-analysis","volume":"202","author":"M de Rooij","year":"2014","journal-title":"AJR Am J Roentgenol"},{"issue":"1","key":"pone.0323752.ref021","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41585-019-0212-4","article-title":"Multiparametric MRI for prostate cancer diagnosis: current status and future directions","volume":"17","author":"A Stabile","year":"2020","journal-title":"Nat Rev Urol"},{"issue":"2","key":"pone.0323752.ref022","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1177\/1460458219855884","article-title":"Combination possibility and deep learning model as clinical decision-aided approach for prostate cancer","volume":"26","author":"O Eminaga","year":"2020","journal-title":"Health Informatics J"},{"issue":"9","key":"pone.0323752.ref023","doi-asserted-by":"crossref","first-page":"6526","DOI":"10.1007\/s00330-022-08712-8","article-title":"A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics","volume":"32","author":"J Bleker","year":"2022","journal-title":"Eur Radiol"},{"key":"pone.0323752.ref024","doi-asserted-by":"crossref","first-page":"1225490","DOI":"10.3389\/fonc.2023.1225490","article-title":"A classifier model for prostate cancer diagnosis using CNNs and transfer learning with multi-parametric MRI","volume":"13","author":"M Mehmood","year":"2023","journal-title":"Front Oncol"},{"issue":"6","key":"pone.0323752.ref025","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.1016\/j.acra.2023.12.042","article-title":"Deep learning based on ResNet-18 for classification of prostate imaging-reporting and data system category 3 Lesions","volume":"31","author":"Z Kang","year":"2024","journal-title":"Acad Radiol"},{"key":"pone.0323752.ref026","doi-asserted-by":"crossref","first-page":"1533033819858363","DOI":"10.1177\/1533033819858363","article-title":"A transfer learning approach for malignant prostate lesion detection on multiparametric MRI","volume":"18","author":"Q Chen","year":"2019","journal-title":"Technol Cancer Res Treat"},{"key":"pone.0323752.ref027","doi-asserted-by":"crossref","first-page":"1032115","DOI":"10.3389\/fonc.2022.1032115","article-title":"Use of radiomics containing an effective peritumoral area to predict early recurrence of solitary hepatocellular carcinoma \u22645\u2009cm in diameter","volume":"12","author":"F Wang","year":"2022","journal-title":"Front Oncol"},{"issue":"16","key":"pone.0323752.ref028","doi-asserted-by":"crossref","first-page":"6497","DOI":"10.1088\/1361-6560\/aa7731","article-title":"Automated diagnosis of prostate cancer in multi-parametric MRI based on multimodal convolutional neural networks","volume":"62","author":"MH Le","year":"2017","journal-title":"Phys Med Biol"},{"issue":"1","key":"pone.0323752.ref029","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s00292-015-0136-6","article-title":"The 2014 consensus conference of the ISUP on Gleason grading of prostatic carcinoma","volume":"37","author":"G Kristiansen","year":"2016","journal-title":"Pathologe"},{"key":"pone.0323752.ref030","doi-asserted-by":"crossref","first-page":"9266889","DOI":"10.1155\/2023\/9266889","article-title":"Machine learning hybrid model for the prediction of chronic kidney disease","volume":"2023","author":"H Khalid","year":"2023","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"pone.0323752.ref031","doi-asserted-by":"crossref","first-page":"13511","DOI":"10.1038\/s41598-024-63159-9","article-title":"Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine","volume":"14","author":"A Mahmoudzadeh","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0323752.ref032","doi-asserted-by":"crossref","first-page":"114335","DOI":"10.1016\/j.ab.2021.114335","article-title":"iPromoter-ET: identifying promoters and their strength by extremely randomized trees-based feature selection","volume":"630","author":"Y Liang","year":"2021","journal-title":"Anal Biochem"},{"issue":"12","key":"pone.0323752.ref033","doi-asserted-by":"crossref","first-page":"1612","DOI":"10.1038\/modpathol.2011.113","article-title":"Tumor-infiltrating neutrophils in pancreatic neoplasia","volume":"24","author":"MD Reid","year":"2011","journal-title":"Mod Pathol"},{"issue":"1","key":"pone.0323752.ref034","doi-asserted-by":"crossref","first-page":"74","DOI":"10.37349\/etat.2024.00205","article-title":"Quantitative peritumoral magnetic resonance imaging fingerprinting improves machine learning-based prediction of overall survival in colorectal cancer","volume":"5","author":"A Tabari","year":"2024","journal-title":"Explor Target Antitumor Ther"},{"issue":"1","key":"pone.0323752.ref035","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1186\/s13244-024-01760-2","article-title":"Preoperative prediction of microvascular invasion risk in hepatocellular carcinoma with MRI: peritumoral versus tumor region","volume":"15","author":"G Wei","year":"2024","journal-title":"Insights Imaging"},{"issue":"5","key":"pone.0323752.ref036","doi-asserted-by":"crossref","first-page":"2386","DOI":"10.1002\/mp.14787","article-title":"Repeatability of CBCT radiomic features and their correlation with CT radiomic features for prostate cancer","volume":"48","author":"R Delgadillo","year":"2021","journal-title":"Med Phys"},{"issue":"11","key":"pone.0323752.ref037","doi-asserted-by":"crossref","first-page":"5075","DOI":"10.1002\/mp.13808","article-title":"Stability and reproducibility of computed tomography radiomic features extracted from peritumoral regions of lung cancer lesions","volume":"46","author":"I Tunali","year":"2019","journal-title":"Med Phys"},{"issue":"1","key":"pone.0323752.ref038","doi-asserted-by":"crossref","first-page":"11","DOI":"10.4103\/ijmr.IJMR_555_20","article-title":"Extent of use of artificial intelligence & machine learning protocols in cancer diagnosis: a scoping review","volume":"157","author":"A Dang","year":"2023","journal-title":"Indian J Med Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0323752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T17:37:55Z","timestamp":1747330675000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0323752"}},"subtitle":[],"editor":[{"given":"Yuki","family":"Arita","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"references-count":38,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0323752","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,15]]}}}