Deep learning algorithms have achieved great success in cancer image classification. However, it is imperative to understand the differences between the deep learning and human approaches. Using an explainable model, we aimed to compare the deep learning-focused regions of magnetic resonance (MR) images with cancerous locations identified by radiologists and pathologists. First, 307 prostate MR images were classified using a well-established deep neural network without locational information of cancers. Subsequently, we assessed whether the deep learning-focused regions overlapped the radiologist-identified targets. Furthermore, pathologists provided histopathological diagnoses on 896 pathological images, and we compared the deep learning-focused regions with the genuine cancer locations through 3D reconstruction of pathological images. The area under the curve (AUC) for MR images classification was sufficiently high (AUC = 0.90, 95% confidence interval 0.87–0.94). Deep learning-focused regions overlapped radiologist-identified targets by 70.5% and pathologist-identified cancer locations by 72.1%. Lymphocyte aggregation and dilated prostatic ducts were observed in non-cancerous regions focused by deep learning. Deep learning algorithms can achieve highly accurate image classification without necessarily identifying radiological targets or cancer locations. Deep learning may find clues that can help a clinical diagnosis even if the cancer is not visible.

This study presents the enfortumab vedotin (EV) treatment analysis at our institution. We retrospectively analyzed patients with metastatic urothelial cancer (mUC) treated with EV between January 2021 and October 2023. EV was administered at 1.25 mg/kg on days 1, 8, and 15 in a 28-day cycle. Whole-body computed tomography scans were performed to assess the treatment response. Patient characteristics, treatment histories, response rates, progression-free survival, and adverse events were evaluated. Response rates were determined, and adverse events were recorded. Among the 20 patients, 70% were male and 65% had bladder tumors. Most patients had lung (65%) or lymph node (65%) metastases. The median follow-up was 11.2 months, with 45% of the patients succumbing to the disease. The overall response rate was 55%. The median progression-free and median overall survivals were 10.5 and 12.9 months, respectively. Severe adverse events occurred in 35% of patients. In this real-world study, EV demonstrated promising efficacy and manageable safety profiles in Japanese patients with mUC. The study’s results were consistent with previous clinical trials, although a longer follow-up was required. Our findings support EV use as a treatment option for patients with mUC who exhibit disease progression after platinum-based chemotherapy and immune-checkpoint inhibitor therapy.

Prostate cancer (PCa) is a clinically heterogeneous disease. Predicting clinically significant PCa with low–intermediate prostate-specific antigen (PSA), which often includes aggressive cancers, is imperative. This study evaluated the predictive accuracy of deep learning analysis using multimodal medical data focused on clinically significant PCa in patients with PSA ≤ 20 ng/mL. Our cohort study included 178 consecutive patients who underwent ultrasound-guided prostate biopsy. Deep learning analyses were applied to predict clinically significant PCa. We generated receiver operating characteristic curves and calculated the corresponding area under the curve (AUC) to assess the prediction. The AUC of the integrated medical data using our multimodal deep learning approach was 0.878 (95% confidence interval [CI]: 0.772–0.984) in all patients without PSA restriction. Despite the reduced predictive ability of PSA when restricted to PSA ≤ 20 ng/mL (n = 122), the AUC was 0.862 (95% CI: 0.723–1.000), complemented by imaging data. In addition, we assessed clinical presentations and images belonging to representative false-negative and false-positive cases. Our multimodal deep learning approach assists physicians in determining treatment strategies by predicting clinically significant PCa in patients with PSA ≤ 20 ng/mL before biopsy, contributing to personalized medical workflows for PCa management.

In patients with high-risk prostate cancer (HRPC) after radical prostatectomy (RP), biochemical recurrence (BCR) increases the risk of distant metastasis. Accordingly, additional prognostic biomarkers are required to identify the subpopulation of patients with HRPC who develop clinical recurrence (CR) after BCR. The objective of this study was to identify biomarkers in formalin-fixed paraffin-embedded (FFPE) RP samples that are prognostic for CR in patients with HRPC who experience BCR after RP (post-RP BCR). First, we performed a preliminary RNA sequencing analysis to comprehensively profile RNA expression in FFPE RP samples obtained from patients with HRPC who developed CR after post-RP BCR and found that many snRNAs were very abundant in preserved FFPE samples. Subsequently, we used quantitative polymerase chain reaction (qPCR) to compare the expression levels of highly abundant snRNAs in FFPE RP samples from patients with HRPC with and without CR after post-RP BCR (21 CR patients and 46 non-CR patients who had more than 5 years of follow-up after BCR). The qPCR analysis revealed that the expression levels of snRNA RNU1-1/1-2 and RNU4-1 were significantly higher in patients with CR than in patients without CR. These snRNAs were significantly correlated with clinical recurrence-free survival (RFS) in patients with HRPC who experienced post-RP BCR. Furthermore, snRNA RNU1-1/1-2 could serve as an independent prognostic factor for clinical RFS in post-RP BCR of HRPC cases where known prognostic factors (e.g., Gleason score) cannot distinguish between CR and non-CR patients. Our findings provide new insights into the involvement of snRNAs in prostate cancer progression.

Objective: This study aimed to evaluate the clinical relevance of early relative dose intensity (eRDI) during enfortumab vedotin (EV) monotherapy in patients with metastatic urothelial carcinoma (mUC) based on a Japanese real‐world multicenter cohort. Methods: We retrospectively analyzed 119 patients with mUC who received EV. The temporal trend of total relative dose intensity (tRDI), defined as the cumulative relative dose intensity during treatment, was assessed over the first 5 months. eRDI, calculated as the mean RDI over the initial 3 months, was also evaluated. Survival analyses were performed in 84 patients evaluable beyond the first radiographic assessment, excluding those with early progressive disease (PD). Patients were stratified by eRDI (≥ 80% vs. < 80%), and progression‐free survival (PFS) and overall survival (OS) were compared. Subgroup analyses were conducted according to the presence or absence of adverse event–related dose modification (AE‐related DM). Results: Dose intensity gradually declined during the early treatment phase. The eRDI was not significantly associated with PFS or OS in the PD‐excluded cohort ( n = 84). However, among patients without AE‐related DM ( n = 44), high eRDI was associated with significantly longer PFS (median 11.7 vs. 4.2 months; p = 0.001) and OS (not reached vs. 13.8 months; p = 0.021). No significant association was observed between eRDI and survival in patients with AE‐related DM. Conclusions: Although eRDI was not an overall significant prognostic factor, it showed clinical relevance in patients without AE‐related DM. These findings underscore the importance of preserving eRDI in patients with sufficient tolerability and support individualized dosing strategies for EV therapy.

Background: We evaluated whether the efficacy and safety of transurethral enucleation with bipolar energy (TUEB) is affected by prostate volume (PV) in the treatment of benign prostatic hyperplasia (BPH). Methods: We retrospectively evaluated 180 patients with symptomatic BPH who underwent TUEB between 2008 and 2015. Efficacy was assessed by perioperative changes in the international prostate symptom score (IPSS), Quality of Life Score (QOLS), maximum flow rate on uroflowmetry (Qmax), and serum prostate-specific antigen level (PSA), which were recorded at 3 months postoperative. Safety was assessed by perioperative incidence of adverse events (AEs). AEs were recorded up to 2 years after surgery. Patients were divided into two groups based on PV: standard group (SG), PV < 80 mL, and large group (LG), PV ≥ 80 mL. Results: A total of 132 (73%) patients were grouped in the SG, whereas 48 (27%) were grouped in the LG. No significant differences were observed in the preoperative parameters of age, IPSS, and QOLS between the two groups. However, the LG had a significantly larger PV and higher serum PSA levels. Regarding surgical outcomes, postoperative changes in IPSS, QOLS, Qmax, serum PSA, serum sodium, and hemoglobin levels did not differ significantly between the groups. However, the LG demonstrated a significantly longer operative time and heavier specimen weight. The rates of early complications, including hyponatremia, and blood transfusion, and late complications after surgery did not differ between the groups. Conclusion: This study demonstrated the safety and efficacy of TUEB for BPH therapy regardless of PV.