(1) Background: Recent studies report high accuracies when using machine learning (ML) algorithms to classify prostate cancer lesions on publicly available datasets. However, it is unknown if these trained models generalize well to data from different institutions. (2) Methods: This was a retrospective study using multi-parametric Magnetic Resonance Imaging (mpMRI) data from our institution (63 mpMRI lesions) and the ProstateX-2 challenge, a publicly available annotated image set (112 mpMRI lesions). Residual Neural Network (ResNet) algorithms were trained to classify lesions as high-risk (hrPCA) or low-risk/benign. Models were trained on (a) ProstateX-2 data, (b) local institutional data, and (c) combined ProstateX-2 and local data. The models were then tested on (a) ProstateX-2, (b) local and (c) combined ProstateX-2 and local data. (3) Results: Models trained on either local or ProstateX-2 image data had high Area Under the ROC Curve (AUC)s (0.82–0.98) in the classification of hrPCA when tested on their own respective populations. AUCs decreased significantly (0.23–0.50, p < 0.01) when models were tested on image data from the other institution. Models trained on image data from both institutions re-achieved high AUCs (0.83–0.99). (4) Conclusions: Accurate prostate cancer classification models trained on single-institutional image data performed poorly when tested on outside-institutional image data. Heterogeneous multi-institutional training image data will likely be required to achieve broadly applicable mpMRI models.
Prostate cancer is the most common non-cutaneous malignancy in men, with the majority of newly diagnosed patients eligible for active surveillance. Despite definitive treatment, a considerable percentage of men will experience biochemical recurrence and even regional and distant metastatic recurrence after radiation therapy or radical prostatectomy. Salvage prostatectomy, while oncologically effective, poses significant morbidity with poor functional outcomes. Salvage cryotherapy has emerged as a promising alternative for localized recurrence, demonstrating safety and efficacy. This review examines the oncologic and functional outcomes of whole-gland and focal salvage cryotherapy, including disease-free survival, cancer-specific survival, and overall survival. The crucial role of multiparametric prostate MRI and evolving role of next-generation PSMA-targeted PET imaging are also examined. The comparison of outcomes of cryotherapy to other salvage ablation modalities, such as high-intensity focused ultrasound (HIFU), is also explored.
Background:Nutritional status (NS) is an independent predictor of overall survival (OS) after radical cystectomy (RC). Various biomarkers of NS are proposed to predict postoperative outcome...
The genetic landscape of urologic cancers has evolved with the identification of actionable mutations that impact diagnosis, prognosis, and therapeutic strategies. This narrative review consolidates existing literature on genetic mutations across key urologic cancers, including bladder, renal, prostate, upper tract urothelial, testicular, and penile. The review highlights mutations in DNA damage repair genes, such as BRCA1/2 and PTEN, as well as pathway alterations like FGFR and PD-L1 overexpression. These mutations influence tumor behavior and therapeutic outcomes, emphasizing the need for precision oncology approaches. Molecular profiling, through tools like next-generation sequencing, has revolutionized patient care by enabling targeted treatment strategies, especially in cancers with distinct molecular subtypes such as luminal or basal bladder cancer and clear cell renal carcinoma. Emerging therapies, including FGFR inhibitors and immune checkpoint blockade, offer new treatment avenues, although resistance mechanisms remain a challenge. We also emphasize the importance of biomarker identification for personalized management, especially in metastatic settings where treatment intensification is often required. Future research is needed to further elucidate our understanding of the genetics affecting urologic cancers, which will help develop novel, individualized therapies to enhance oncologic outcomes.