Automated machine learning for prostate cancer detection and Gleason score prediction using T2WI: a diagnostic multi-center study

• Published in: BMC cancer Vol. 25; no. 1; pp. 1483 - 14
• Main Authors: Jin, Liang, Ma, Zhuangxuan, Gao, Feng, Li, Ming, Li, Haiqing, Geng, Daoying
• Format: Journal Article
• Language: English
• Published: London BioMed Central 01.10.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Aged; Algorithms; Artificial intelligence; Automation; Biomedical and Life Sciences; Biomedicine; Biopsy; Cancer Research; Cancer therapies; Clinical significance; Computer-aided medical diagnosis; Datasets; Decision making; Diagnosis; Endocrine therapy; Energy; Feature selection; Gleason score; Health Promotion and Disease Prevention; Humans; Learning algorithms; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Malignancy; Medical diagnosis; Medicine/Public Health; Methods; Middle Aged; MLJAR; Neoplasm Grading; Oncology; Open source software; Pathology; Patients; Prostate cancer; Prostatic Neoplasms - diagnosis; Prostatic Neoplasms - diagnostic imaging; Prostatic Neoplasms - pathology; Radiation therapy; Radiomics; Review boards; ROC Curve; Surgery; Surgical Oncology; China; Gleason score; Magnetic resonance imaging; MLJAR; Prostate cancer; Machine learning
• ISSN: 1471-2407; 1471-2407
• DOI: 10.1186/s12885-025-14917-z

Background Prostate cancer (PCa) is one of the most common malignancies in men, and accurate assessment of tumor aggressiveness is crucial for treatment planning. The Gleason score (GS) remains the gold standard for risk stratification, yet it relies on invasive biopsy, which has inherent risks and sampling errors. The aim of this study was to detect PCa and non-invasively predict the GS for the early detection and stratification of clinically significant cases. Methods We used single-modality T2-weighted imaging (T2WI) with an automatic machine-learning (ML) approach, MLJAR. The internal dataset comprised PCa patients who underwent magnetic resonance imaging (MRI) examinations at our hospital from September 2015 to June 2022 prior to prostate biopsy, surgery, radiotherapy, and endocrine therapy and whose examinations resulted in pathological findings. An external dataset from another medical center and a public challenge dataset were used for external validation. The Kolmogorov–Smirnov curve was used to evaluate the risk-differentiation ability of the PCa detection model. The area under the receiver operating characteristic curve (AUC) was calculated with confidence intervals to compare the model performance. The internal MRI dataset included 198 non-PCa and 291 PCa patients with histopathological results obtained through biopsy or surgery. External and public challenge datasets included 45 and 68 PCa patients, respectively. Results AUC for PCa detection in the internal-testing cohort ( n  = 147, PCa = 78) was 0.99. For GS prediction, AUCs were GS = 3 + 3 (0.97), GS = 3 + 4 (0.97), GS = 3 + 5 (1.0), GS = 4 + 3 (0.87), GS = 4 + 4 (0.91), GS = 4 + 5 (0.95), GS = 5 + 4 (1.0), and GS = 5 + 5 (0.99) in the internal-testing cohort (PCa = 88); GS = 3 + 3 (0.95), GS = 3 + 4 (0.76); GS = 3 + 5 (0.77), GS = 4 + 3 (0.88), GS = 4 + 4 (0.82), GS = 4 + 5 (0.87), GS = 5 + 4 (0.95), and GS = 5 + 5 (0.85) in the external-testing cohort (PCa = 45); and GS = 3 + 4 (0.89), GS = 4 + 3 (0.75), GS = 4 + 4 (0.65), and GS = 4 + 5 (0.91) in the public challenge cohort (PCa = 68). Conclusions This multi-center study shows that an auto-ML model using only T2WI can accurately detect PCa and predict Gleason scores non-invasively, offering potential to reduce biopsy reliance and improve early risk stratification. These results warrant further validation and exploration for integration into clinical workflows.