We aimed to evaluate the detection rates of prostate cancer (PCa) and clinically significant PCa (csPCa) using magnetic resonance imaging-targeted biopsy (MRI-TBx) in men with low prostate-specific antigen (PSA) levels (2.5–4.0 ng/mL). Clinicopathologic data of 5502 men with PSA levels of 2.5–10.0 ng/mL who underwent transrectal ultrasound-guided biopsy (TRUS-Bx) or MRI-TBx were reviewed. Participants were divided into four groups: LP-T [low PSA (2.5–4.0 ng/mL) and TRUS-Bx, n = 2018], LP-M (low PSA and MRI-TBx, n = 186), HP-T [high PSA (4.0–10.0 ng/mL) and TRUS-Bx, n = 2953], and HP-M (high PSA and MRI-TBx, n = 345). The detection rates of PCa and csPCa between groups were compared, and association of biopsy modality with detection of PCa and csPCa in men with low PSA levels were analyzed. The detection rates of PCa (20.0% vs. 38.2%; P < 0.001) and csPCa (11.5% vs. 32.3%; P < 0.001) were higher in the LP-M group than in the LP-T group. Conversely, there were no significant differences in the detection rates of PCa (38.2% vs. 43.2%; P = 0.263) and csPCa (32.3% vs. 39.4%; P = 0.103) between the LP-M and HP-M groups. Multivariate analyses revealed that using MRI-TBx could predict the detection of csPCa (odds ratio 2.872; 95% confidence interval 1.996‒4.132; P < 0.001) in men with low PSA levels. In summary, performing MRI-TBx in men with low PSA levels significantly improved the detection rates of PCa and csPCa as much as that in men with high PSA levels.

Purpose: The aim of this study was to investigate the rate and pattern of recurrence for patients with Hunner lesion (HL) type interstitial cystitis/bladder pain syndrome (IC/BPS) after transurethral ablation.Methods: This prospective study included 210 patients with HL type IC/BPS. The primary outcomes were the recurrence rate according to 3 patterns of recurrence: pattern A (according to the relationship with the previous surgical site), pattern B (according to the bladder zone), and pattern C (according to the number of lesions). The secondary outcomes were recurrencefree time after treatment according to pattern A and pattern C.Results: The pattern A recurrence rate was 50.8% in the same site (A1), 6.7% at a new site (A2), and 42.5% at mixed sites (A3). The pattern B recurrence rate was 10.5% for the anterior wall, 59.0% for the posterior wall, 69.5% for the lateral wall, and 69.0% for the dome area. Multiple lesions recurred as multiple lesions in 75.8% of cases. The pattern C recurrence rate was 10.8% for C1 (single → single), 6.7% for C2 (single → multiple), 6.7% for C3 (multiple → single), and 75.8% for C4 (multiple → multiple). The recurrence-free time in pattern A was 13 months for A1, 12.5 months for A2, and 8 months for A3, with a significant difference between A1 and A3 (P=0.008). There was no significant difference in recurrence-free time in pattern C, either with single or multiple HLs.Conclusions: The distinct recurrence characteristics of HLs was not predictable despite repeated ablations. Complete remission should not be expected because the whole bladder was to have the potential to develop the HLs even after repeated transurethral ablation.

Purpose To diagnose lower urinary tract symptoms (LUTS) in a noninvasive manner, we created a prediction model for bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using simple uroflowmetry. In this study, we used deep learning to analyze simple uroflowmetry. Materials and Methods We performed a retrospective review of 4,835 male patients aged ≥40 years who underwent a urodynamic study at a single center. We excluded patients with a disease or a history of surgery that could affect LUTS. A total of 1,792 patients were included in the study. We extracted a simple uroflowmetry graph automatically using the ABBYY Flexicapture ® image capture program (ABBYY, Moscow, Russia). We applied a convolutional neural network (CNN), a deep learning method to predict DUA and BOO. A 5-fold cross-validation average value of the area under the receiver operating characteristic (AUROC) curve was chosen as an evaluation metric. When it comes to binary classification, this metric provides a richer measure of classification performance. Additionally, we provided the corresponding average precision-recall (PR) curves. Results Among the 1,792 patients, 482 (26.90%) had BOO, and 893 (49.83%) had DUA. The average AUROC scores of DUA and BOO, which were measured using 5-fold cross-validation, were 73.30% (mean average precision [mAP]=0.70) and 72.23% (mAP=0.45), respectively. Conclusions Our study suggests that it is possible to differentiate DUA from non-DUA and BOO from non-BOO using a simple uroflowmetry graph with a fine-tuned VGG16, which is a well-known CNN model.