Prostate Imaging Reporting and Data System (PI-RADS) score, a reporting system of prostate MRI cases, has become a standard prostate cancer (PCa) screening method due to exceptional diagnosis performance. However, PI-RADS 3 lesions are an unmet medical need because PI-RADS provides diagnosis accuracy of only 30-40% at most, accompanied by a high false-positive rate. Here, we propose an explainable artificial intelligence (XAI) based PCa screening system integrating a highly sensitive dual-gate field-effect transistor (DGFET) based multi-marker biosensor for ambiguous lesions identification. This system produces interpretable results by analyzing sensing patterns of three urinary exosomal biomarkers, providing a possibility of an evidence-based prediction from clinicians. In our results, XAI-based PCa screening system showed a high accuracy with an AUC of 0.93 using 102 blinded samples with the non-invasive method. Remarkably, the PCa diagnosis accuracy of patients with PI-RADS 3 was more than twice that of conventional PI-RADS scoring. Our system also provided a reasonable explanation of its decision that TMEM256 biomarker is the leading factor for screening those with PI-RADS 3. Our study implies that XAI can facilitate informed decisions, guided by insights into the significance of visualized multi-biomarkers and clinical factors. The XAI-based sensor system can assist healthcare professionals in providing practical and evidence-based PCa diagnoses.

The study was to compare the oncologic and functional outcomes of partial nephrectomy (PN) and radical nephrectomy (RN) for pathologically proven T1b renal cell carcinoma using pair-matched groups. We reviewed our prospectively maintained database for RN and PN in T1b renal tumors surgically treated between 1999 and 2011 at five institutions in Korea. Of 611 patients treated with PN or RN for a solitary and NX/N0 M0 renal mass (4-7 cm), 577 (PN, 100; RN, 477) patients with pathologically confirmed pT1b remained for analysis. Study subjects were grouped by PN or RN, then matched by age, sex, comorbidities, body mass index, tumor size and depth, histologic type, and preoperative estimated glomerular filtration rate (eGFR) using propensities score. To evaluate oncologic outcomes, overall survival (OS), cancer-specific survival (CSS), and progression-free survival (PFS) rates were analyzed. The functional outcomes were evaluated by postoperative eGFR. The median follow-up in the RN group was 48.1 and 42.6 months in the PN group. The estimated 10-year CSS rate (PN 85.7% vs. RN 84.4%, p=0.52) and 5- and estimated 10-year PFS rates (PN: 86.4% and 79.2% vs. RN: 86.0% and 66.1%, p=0.66) did not differ significantly between groups. The estimated 10-year OS rate was significantly higher in the PN group (85.7%) compared to the RN group (73.3%) (p=0.003). PN was less likely to induce new-onset chronic kidney disease (CKD) and end-stage CKD compared with RN. Our study suggests that patients treated with PN demonstrate a superior OS rate and postoperative renal function with analogous CSS and PFS rates compared with pair-matched patients treated with RN.

Purpose: To compare the perioperative outcomes, postoperative complications, and early oncologic outcomes of intracorporeal urinary diversion (ICUD) with those of extracorporeal urinary diversion (ECUD) following robot-assisted radical cystectomy (RARC) performed by a single surgeon at a tertiary referral hospital. Materials and Methods: We reviewed a prospectively maintained, institutional review board–approved database of 70 patients treated with RARC and pelvic lymph node (LN) dissection for bladder cancer performed from 2007 through 2014. Data were collected for 64 patients who underwent either ICUD or ECUD. Results: Thirty-eight patients underwent ECUD, and the remaining 26 underwent ICUD. Urinary diversion was performed extracorporeally in the first 37 cases and performed intracorporeally thereafter. There were no significant differences in patient characteristics between the ECUD and ICUD groups. Mean total operative time was 468 minutes for ECUD and 581 minutes for ICUD (P < .05). Mean estimated blood loss was 265 and 148 mL, respectively (P < .05). Minor and total complication rates for patients with the ECUD were higher than in patients with the ICUD (minor: 47.4% vs. 15.4%; total: 57.9% vs. 30.8%; P < .05). All patients showed negative surgical margin, while 21% in the ECUD group and 26.9% in the ICUD group had pathologic stage T3 or T4 (P > .05). The mean LN yield was 23.2 and 31.8, respectively (P < .05). Conclusions: From our experience, the results show that ICUD after RARC can be successful, with the benefits of decreased blood loss and lower transfusion and complication rates than ECUD. A larger series and long-term follow-up data will be necessary to support our results.

Kim SB, et al. Investig Clin Urol. 2018 Mar;59(2):98-105. https://doi.org/10.4111/icu.2018.59.2.98