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.

Japan's largest platform for academic e-journals: J-STAGE is a full text database for reviewed academic papers published by Japanese societies

Background: Active surveillance (AS) is one of the treatment methods for patients with small renal masses (SRMs; < 4 cm), including renal cell carcinomas (RCCs). However, some small RCCs may exhibit aggressive neoplastic behaviors and metastasize. Little is known about imaging biomarkers capable of identifying potentially aggressive small RCCs. Contrast-enhanced computed tomography (CECT) often detects collateral vessels arising from neoplastic angiogenesis in RCCs. Therefore, this study aimed to evaluate the association between SRM differential diagnoses and prognoses, and the detection of collateral vessels using CECT. Methods: A total of 130 consecutive patients with pathologically confirmed non-metastatic SRMs (fat-poor angiomyolipomas [fpAMLs; n = 7] and RCCs [n = 123]) were retrospectively enrolled. Between 2011 and 2019, SRM diagnoses in these patients were confirmed after biopsy or surgical resection. All RCCs were surgically resected. Regardless of diameter, a collateral vessel (CV) was defined as any blood vessel connecting the tumor from around the kidney using CECT. First, we analyzed the role of CV-detection in differentiating between fpAML and RCC. Then, we evaluated the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of RCC diagnosis based on CV-detection using CECT. We also assessed the prognostic value of CV-detection using the Fisher exact test, and Kaplan-Meier method and the log-rank test. Results: The sensitivity, specificity, PPV, NPV, and accuracy of CV-detection for the diagnosis of small RCCs was 48.5, 45.5, 100, 100, and 9.5% respectively. Five of 123 (4.1%) patients with RCC experienced recurrence. CV-detection using CECT was the only significant factor associated with recurrence (p = 0.0177). Recurrence-free survival (RFS) was significantly lower in patients with CV compared with in those without CV (5-year RFS 92.4% versus 100%, respectively; p = 0.005). In addition, critical review of the CT images revealed the CVs to be continuous with the venous vessels around the kidney. Conclusions: The detection of CVs using CECT is useful for differentiating between small fpAMLs and RCCs. CV-detection may also be applied as a predictive parameter for small RCCs prone to recurrence after surgical resection. Moreover, AS could be suitable for small RCCs without CVs.

Background: While high body mass index (BMI) and visceral obesity are reportedly associated with a prolonged duration of laparoscopic radical nephrectomy (LRN) via the transperitoneal approach, factors that might prolong the retroperitoneal approach remain unknown. We therefore investigated factors associated with prolonged LRN using a retroperitoneal approach applied by non-expert surgeons. Methods: We defined surgeons who were not certified to perform laparoscopic surgery by the Japanese Society of Endourology as non-experts. We retrospectively reviewed the medical records of 59 consecutive patients with renal cell carcinoma treated with LRN using the retroperitoneal approach by non-experts at our hospital between 2014 and 2019. Relationships between surgical duration and age, sex, body mass index, visceral fat area (VFA) and subcutaneous fat area (SFA), laterality and location of the tumor, length of major tumor axis (tumor length), clinical T stage, ipsilateral adrenalectomy and specimen weight were analyzed using Spearman rank correlation coefficients. Results: The surgical duration positively correlated with ipsilateral adrenalectomy (rs = 0.3162, p = 0.0147) and specimen weight (rs = 0.3103, p = 0.0168), but not with BMI (rs = 0.2016, p = 0.1257) or VFA (rs = 0.0185, p = 0.8894). Conclusions: Factors associated with prolonged LRN via the retroperitoneal approach implemented by non-expert surgeons are ipsilateral adrenalectomy and specimen weight.

Background: One of the major concerns of patients with upper tract urothelial carcinoma (UTUC) treated with nephroureterectomy is intravesical recurrence (IVR). The purpose of the present study was to investigate the predictive risk factors for IVR after retroperitoneoscopic nephroureterectomy (RNU) for UTUC. Methods: Clinicopathological and surgical information were collected from the medical records of 73 patients treated with RNU for non-metastatic UTUC, without a history of or concomitant bladder cancer. The association between IVR after RNU and clinicopathological and surgery-related factors, including preoperative urine cytology and pneumoretroperitoneum time, was analyzed using the Fisher exact test. Results: During the median follow-up time of 39.1 months, 18 (24.7%) patients had subsequent IVR after RNU. The 1- and 3-year IVR-free survival rates were 85.9% and 76.5%, respectively. The Fisher exact test revealed that prolonged pneumoretroperitoneum time of ≥ 210 min was a risk factor for IVR in 1 year after RNU (p = 0.0358) and positive urine cytology was a risk factor for IVR in 3 years after RNU (p = 0.0352). Conclusions: In UTUC, the occurrences of IVR in 1 and 3 years after RNU are highly probable when the pneumoretroperitoneum time is prolonged (≥ 210 min) and in patients with positive urine cytology, respectively. Strict follow-up after RNU is more probable recommended for these patients.