Predicting muscle invasion in bladder cancer by deep learning analysis of MRI: comparison with vesical imaging-reporting and data system.

OBJECTIVES: To compare the diagnostic performance of a novel deep learning (DL) method based on T2-weighted imaging with the vesical imaging-reporting and data system (VI-RADS) in predicting muscle invasion in bladder cancer (MIBC). METHODS: A total of 215 tumours (129 for training and 31 for internal validation, centre 1; 55 for external validation, centre 2) were included. MIBC was confirmed by pathological examination. VI-RADS scores were provided by two groups of radiologists (readers 1 and readers 2) independently. A deep convolutional neural network was constructed in the training set, and validation was conducted on the internal and external validation sets. ROC analysis was performed to evaluate the performance for MIBC diagnosis. RESULTS: The AUCs of the DL model, readers 1, and readers 2 were as follows: in the internal validation set, 0.963, 0.843, and 0.852, respectively; in the external validation set, 0.861, 0.808, and 0.876, respectively. The accuracy of the DL model in the tumours scored VI-RADS 2 or 3 was higher than that of radiologists in the external validation set: for readers 1, 0.886 vs. 0.600, p = 0.006; for readers 2, 0.879 vs. 0.636, p = 0.021. The average processing time (38 s and 43 s in two validation sets) of the DL method was much shorter than the readers, with a reduction of over 100 s in both validation sets. CONCLUSIONS: Compared to radiologists using VI-RADS, the DL method had a better diagnostic performance, shorter processing time, and robust generalisability, indicating good potential for diagnosing MIBC. KEY POINTS: • The DL model shows robust performance for MIBC diagnosis in both internal and external validation. • The diagnostic performance of the DL model in the tumours scored VI-RADS 2 or 3 is better than that obtained by radiologists using VI-RADS. • The DL method shows potential in the preoperative assessment of MIBC.

Claspin Overexpression Promotes Tumor Progression and Predicts Poor Clinical Outcome in Prostate Cancer.

Background: Claspin (CLSPN) expression is acknowledged as a poor clinical prognostic factor in various tumors. However, the clinical characteristics and biological functions of CLSPN in prostate cancer (PCa) are still to be clarified. The aim of our study was to evaluate the association of CLSPN expression during PCa progression and its potential role in prognosis. Methods: We analyzed mRNA expression of the CLSPN gene with various clinicopathological features using the Cancer Genome Atlas and GSE21032 dataset. Immunohistochemical assays were used to detect the protein expression levels of CLSPN in human PCa tissue microarrays. Furthermore, we characterized the role of CLSPN in PCa progression through in vitro experiments using a CLSPN knockout. Results: Immunohistochemistry and public datasets revealed that CLSPN expression was increased in PCa with: a high Gleason score; advanced pathological stage; and positive surgical margins. In addition, upregulation of CLSPN was correlated with shorter biochemical recurrence (BCR)-free survival and overall survival. After we knocked-out CLSPN in DU145 and LNCaP cells, the in vitro phenotypic results showed that the ability of the knockouts to proliferate, migrate, and invade was attenuated; but that apoptosis was promoted. Conclusions: Our data support an oncogenic role for CLSPN in PCa progression. Moreover, increased CLSPN expression was identified as an independent factor in predicting bCR-free survival and disease-free survival in PCa patients.

A case report of primary upper urinary tract signet-ring cell carcinoma and literature review.

BACKGROUND: Upper tract urothelial carcinoma with pure non-urothelial histology is an exception but variants are present in ~ 25% of cases. Primary upper urinary tract signet -ring cell carcinoma is extremely rare. CASE PRESENTATION: We report the case of a 65-year-old male diagnosed primary upper urinary tract signet-ring cell carcinoma while underwent percutaneous nephrolithotomy. Radical nephroureterectomy and adjuvant chemotherapy were performed sequentially. The patient is now recovering well with a regular follow-up for more than 1 year. CONCLUSIONS: The upper urinary tract malignancy often appears as a high grade, high stage tumor and has a uniformly poor prognosis, but a timely multimodal management can bring a good outcome.

[Ten significantly differentially expressed genes in prostate cancer: Screening and verification].

OBJECTIVE: To screen and verify differentially expressed genes in prostate cancer. METHODS: Using DNA microarray, we screened differentially expressed genes in prostate cancer tissue and its adjacent tissue followed by verification by PCR. RESULTS: A total of 1 444 genes were found to be differentially expressed (differentiation ≥ 1.5-fold; P≤ 0.05) in the prostate cancer tissue, of which 769 (53%) were up-regulated and 675 (47%) down-regulated. Fifty percent of the differentially expressed genes showed a 1.5- to 2-fold differentiation, including 396 up-regulated and 182 down-regulated ones. Additionally, 308 up-regulated and 334 down-regulated genes exhibited a >2- to 5-fold, 46 up-regulated and 78 down-regulated genes a > 5- to 10-fold, and 19 up-regulated and 81 down-regulated genes a > 10-fold differentiation. Verification by subjecting 15 most significantly up-regulated and another 15 most markedly down-regulated genes to quantitative real-time PCR (qRT-PCR) showed that most of the genes had a transcriptional profile similar to that in the microarray data, with a Pearson correction coefficient of 0.83 between the microarray data and qRT-PCR results. Totally, 10 significantly differentially expressed genes were identified. CONCLUSION: DNA microarray analysis provides reliable information on differentially expressed genes in prostate cancer and benign tissues. The 10 significantly differentially expressed genes verified by qRT-PCR could possibly become new bio-markers and specific molecules for tumor identification.