Three-Dimensional (3D) deep learning model complements existing models for preoperative disease-free survival prediction (DFS) in localized clear cell renal cell carcinoma (ccRCC): A multicenter retrospective cohort study.

BACKGROUND: Current prognostic models have limited predictive abilities for the growing number of localized (stage I-III) ccRCCs. It is therefore crucial to explore novel preoperative recurrence prediction models to accurately stratify patients and optimize clinical decisions. This purpose of this study was to develop and externally validate a CT-based deep learning (DL) model for pre-surgical disease-free survival (DFS) prediction. METHODS: Patients with localized ccRCC were retrospectively enrolled from six independent medical centers. Three-dimensional (3D) tumor regions from CT images were utilized as input to architect a ResNet 50 model, which outputted DL computed risk score (DLCR) of each patient for DFS prediction later. The predictive performance of DLCR was assessed and compared to the radiomics model (Rad-Score), clinical model we built and two existing prognostic models (UISS and Leibovich). The complementary value of DLCR to the UISS, Leibovich, as well as Rad-Score were evaluated by stratified analysis. RESULTS: 707 patients with localized ccRCC were finally enrolled for models' training and validating. The DLCR we established can perfectly stratify patients into low-, intermediate- and high-risks, and outperformed the Rad-Score, clinical model, UISS and Leibovich score in DFS prediction, with a C-index of 0.754 (0.689-0.821) in the external testing set. Furthermore, the DLCR presented excellent risk stratification capacity in subgroups defined by almost all clinic-pathological features. Moreover, patients in the UISS/Leibovich score/Rad-Score stratified low-risk but DLCR-defined intermediate- and high-risk groups were significantly more likely to experience ccRCC recurrences than those of intermediate- and high-risk in DLCR determined low-risk (all Log-rank P values＜0.05). CONCLUSIONS: Our deep learning model, derived from preoperative CT, is superior to radiomics and current models in precisely DFS predicting of localized ccRCC, and can provide complementary values to them, which may assist more informed clinical decisions and adjuvant therapies adoptions.

A CT-based deep learning model predicts overall survival in patients with muscle invasive bladder cancer after radical cystectomy: a multicenter retrospective cohort study.

BACKGROUND: Muscle invasive bladder cancer (MIBC) has a poor prognosis even after radical cystectomy (RC). Postoperative survival stratification based on radiomics and deep learning (DL) algorithms may be useful for treatment decision-making and follow-up management. This study was aimed to develop and validate a DL model based on preoperative computed tomography (CT) for predicting postcystectomy overall survival (OS) in patients with MIBC. METHODS: MIBC patients who underwent RC were retrospectively included from four centers, and divided into the training, internal validation, and external validation sets. A DL model incorporated the convolutional block attention module (CBAM) was built for predicting OS using preoperative CT images. The authors assessed the prognostic accuracy of the DL model and compared it with classic handcrafted radiomics model and clinical model. Then, a deep learning radiomics nomogram (DLRN) was developed by combining clinicopathological factors, radiomics score (Rad-score) and deep learning score (DL-score). Model performance was assessed by C-index, KM curve, and time-dependent ROC curve. RESULTS: A total of 405 patients with MIBC were included in this study. The DL-score achieved a much higher C-index than Rad-score and clinical model (0.690 vs. 0.652 vs. 0.618 in the internal validation set, and 0.658 vs. 0.601 vs. 0.610 in the external validation set). After adjusting for clinicopathologic variables, the DL-score was identified as a significantly independent risk factor for OS by the multivariate Cox regression analysis in all sets (all P <0.01). The DLRN further improved the performance, with a C-index of 0.713 (95% CI: 0.627-0.798) in the internal validation set and 0.685 (95% CI: 0.586-0.765) in external validation set, respectively. CONCLUSIONS: A DL model based on preoperative CT can predict survival outcome of patients with MIBC, which may help in risk stratification and guide treatment decision-making and follow-up management.

Development and validation of a CT-based deep learning radiomics nomogram to predict muscle invasion in bladder cancer.

Objective: This study aimed to develop a nomogram combining CT-based handcrafted radiomics and deep learning (DL) features to preoperatively predict muscle invasion in bladder cancer (BCa) with multi-center validation. Methods: In this retrospective study, 323 patients underwent radical cystectomy with pathologically confirmed BCa were enrolled and randomly divided into the training cohort (n = 226) and internal validation cohort (n = 97). And fifty-two patients from another independent medical center were enrolled as an independent external validation cohort. Handcrafted radiomics and DL features were constructed from preoperative nephrographic phase CT images. Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in train cohort. Multivariate logistic regression was used to develop the predictive model and a deep learning radiomics nomogram (DLRN) was constructed. The predictive performance of models was evaluated by area under the curves (AUC) in the three cohorts. The calibration and clinical usefulness of DLRN were estimated by calibration curve and decision curve analysis. Results: The nomogram that incorporated radiomics signature and DL signature demonstrated satisfactory predictive performance for differentiating non-muscle invasive bladder cancer (NMIBC) from muscle invasive bladder cancer (MIBC), with an AUC of 0.884 (95 % CI: 0.813-0.953) in internal validation cohort and 0.862 (95 % CI: 0.756-0.968) in external validation cohort, respectively. Decision curve analysis confirmed the clinical usefulness of the nomogram. Conclusions: A CT-based deep learning radiomics nomogram exhibited a promising performance for preoperative prediction of muscle invasion in bladder cancer, and may be helpful in the clinical decision-making process.

Validity of a multiphase CT-based radiomics model in predicting the Leibovich risk groups for localized clear cell renal cell carcinoma: an exploratory study.

OBJECTIVE: To develop and validate a multiphase CT-based radiomics model for preoperative risk stratification of patients with localized clear cell renal cell carcinoma (ccRCC). METHODS: A total of 425 patients with localized ccRCC were enrolled and divided into training, validation, and external testing cohorts. Radiomics features were extracted from three-phase CT images (unenhanced, arterial, and venous), and radiomics signatures were constructed by the least absolute shrinkage and selection operator (LASSO) regression algorithm. The radiomics score (Rad-score) for each patient was calculated. The radiomics model was established and visualized as a nomogram by incorporating significant clinical factors and Rad-score. The predictive performance of the radiomics model was evaluated by the receiver operating characteristic curve, calibration curve, and decision curve analysis (DCA). RESULTS: The AUC of the triphasic radiomics signature reached 0.862 (95% CI: 0.809-0.914), 0.853 (95% CI: 0.785-0.921), and 0.837 (95% CI: 0.714-0.959) in three cohorts, respectively, which were higher than arterial, venous, and unenhanced radiomics signatures. Multivariate logistic regression analysis showed that Rad-score (OR: 4.066, 95% CI: 3.495-8.790) and renal vein invasion (OR: 12.914, 95% CI: 1.118-149.112) were independent predictors and used to develop the radiomics model. The radiomics model showed good calibration and discrimination and yielded an AUC of 0.872 (95% CI: 0.821-0.923), 0.865 (95% CI: 0.800-0.930), and 0.848 (95% CI: 0.728-0.967) in three cohorts, respectively. DCA showed the clinical usefulness of the radiomics model in predicting the Leibovich risk groups. CONCLUSIONS: The radiomics model can be used as a non-invasive and useful tool to predict the Leibovich risk groups for localized ccRCC patients. CRITICAL RELEVANCE STATEMENT: The triphasic CT-based radiomics model achieved favorable performance in preoperatively predicting the Leibovich risk groups in patients with localized ccRCC. Therefore, it can be used as a non-invasive and effective tool for preoperative risk stratification of patients with localized ccRCC. KEY POINTS: • The triphasic CT-based radiomics signature achieves better performance than the single-phase radiomics signature. • Radiomics holds prospects in preoperatively predicting the Leibovich risk groups for ccRCC. • This study provides a non-invasive method to stratify patients with localized ccRCC.

Prognostic significance of HER2 status evaluation using immunohistochemistry in patients with urothelial carcinoma of the bladder: A retrospective single­center experience.

In recent years, antibody-drug conjugate (ADC) therapy targeting human epidermal growth factor receptor 2 (HER2) has been proven to be beneficial in patients with advanced urothelial carcinoma of the bladder (UCB); however, the role of HER2 in UCB remains obscure. Thus, the present retrospective single-center study was performed to evaluate the expression of HER2 in UCB and its prognostic significance. The HER2 status of 108 patients with UCB who underwent radical cystectomy was assessed using immunohistochemistry, and its association with the recurrence and survival rates of patients was analyzed. HER2 overexpression was observed in 57.4% of the patients; this was significantly associated with higher tumor grades (P=0.006) and stages (P<0.001). Kaplan-Meier analysis suggested that patients with HER2 overexpression had a shorter 5-year overall survival rate (P=0.005) and recurrence-free survival rate (P=0.003). Multivariate Cox regression analysis indicated that HER2 overexpression was a high-risk independent predictor of UCB recurrence (hazard ratio, 3.61; 95% confidence interval, 1.07-12.18; P=0.039). On the whole, these findings demonstrate that evaluating the HER2 status may improve the prediction of cancer recurrence and may thus guide the selection of patients that will benefit the most from HER2-ADC therapies.

Preoperative red blood cell distribution width as an independent prognostic factor in metastatic renal cell carcinoma.

OBJECTIVE: This study aimed to explore the prognostic value of preoperative red blood cell distribution width (RDW) in patients with metastatic renal cell carcinoma (mRCC). METHODS: Clinicopathological data of 230 patients with mRCC treated at the First Affiliated Hospital of Chongqing Medical University and the Chinese PLA General Hospital from January 2008 to December 2018 were retrospectively analyzed. Patients were stratified according to the optimal cut-off value of RDW calculated using X-tile software. The prognostic value of RDW was analyzed using the Kaplan-Meier curve with log-rank test and univariate and multivariate Cox proportional hazards models. RESULTS: A total of 230 patients were included. The optimal cut-off value of RDW obtained using X-tile software was 13.1%. The median Progression-free survival (PFS) and Overall survival (OS) of all populations were 12.06 months (IQR: 4.73-36.9) and 32.20 months (IQR: 13.73-69.46), respectively. Kaplan-Meier curves showed that patients with high RDW had worse PFS and OS than those with low RDW (median PFS of 9.7 months vs. 17.9 months, P = 0.002, and median OS of 27.8 months vs. 45.1 months, P = 0.012, respectively). Multivariate analysis showed that RDW was an independent risk factor for PFS (HR: 1.505; 95% CI: 1.111-2.037; P = 0.008) and OS (HR: 1.626; 95% CI: 1.164-2.272; P = 0.004) in mRCC after cytoreductive nephrectomy. CONCLUSION: Preoperative RDW was independently associated with PFS and OS in patients with mRCC and may be a potential predictor of survival outcomes in mRCC.

EGF-induced nuclear translocation of SHCBP1 promotes bladder cancer progression through inhibiting RACGAP1-mediated RAC1 inactivation.

Bladder cancer is a highly heterogeneous and aggressive malignancy with a poor prognosis. EGF/EGFR activation causes the detachment of SHC-binding protein 1 (SHCBP1) from SHC adapter protein 1 (SHC1), which subsequently translocates into the nucleus and promotes cancer development via multiple signaling pathways. However, the role of the EGF-SHCBP1 axis in bladder cancer progression remains unexplored. Herein, we report that SHCBP1 is upregulated in bladder cancer tissues and cells, with cytoplasmic or nuclear localization. Released SHCBP1 responds to EGF stimulation by translocating into the nucleus following Ser273 phosphorylation. Depletion of SHCBP1 reduces EGF-induced cell migration and invasiveness of bladder cancer cells. Mechanistically, SHCBP1 binds to RACGAP1 via its N-terminal domain of amino acids 1 ~ 428, and this interaction is enhanced following EGF treatment. Furthermore, SHCBP1 facilitates cell migration by inhibiting RACGAP-mediated GTP-RAC1 inactivation, whose activity is indispensable for cell movement. Collectively, we demonstrate that the EGF-SHCBP1-RACGAP1-RAC1 axis acts as a novel regulatory mechanism of bladder cancer progression, which offers a new clinical therapeutic strategy to combat bladder cancer.

Secretory autophagy-induced bladder tumour-derived extracellular vesicle secretion promotes angiogenesis by activating the TPX2-mediated phosphorylation of the AURKA-PI3K-AKT axis.

Tumour angiogenesis is an independent risk factor for bladder cancer (BCa) progression, but viable and promising antiangiogenic targets are understudied. Secretory autophagy has received increasing interest recently, while the roles and executing mechanisms in the tumour microenvironment (TME) remain unclear. Herein, we found that active cathepsin B (CTSB) was upregulated in tumour tissues and serum EVs of 241 BCa patients from four cohorts and was significantly associated with poor prognosis. Starving TME (STME)-induced conventional autophagy in BCa cells elevated active CTSB levels by facilitating the expression and nuclear translocation of NFATC2. In addition, STME-induced secretory autophagy simultaneously led to markedly increased secretion of LC3-conjugated EVs loaded with active CTSB (EV-CTSB) into the TME. The increased exogenous active CTSB in endothelial cells by directly ingesting EV-CTSB prominently activated the TPX2-mediated phosphorylation of the AURKA-PI3K-AKT axis, increased VEGFA expression, and promoted angiogenesis. Our findings not only verify that EV-CTSB can be a promising target for antiangiogenic strategies in bladder cancer, but also reveal a novel action pattern based on secretory autophagy-induced EV secretion which is enlightening to explore crosstalk in the TME from various perspectives.

A Novel Prognostic Model Based on Autophagy-Related Long Non-Coding RNAs for Clear Cell Renal Cell Carcinoma.

BACKGROUND: Renal cell carcinoma (RCC) is one of the most common malignant tumors of the urinary system, of which the clear cell renal cell carcinoma (ccRCC) accounts for the most subtypes. The increasing discoveries of abundant autophagy-related long non-coding RNAs (ARLNRs) lead to a resurgent interest in evaluating their potential on prognosis prediction. Based on a large number of ccRCC gene samples from TCGA and clinics, ARLNRs analysis will provide a novel perspective into this field. METHODS: We calculated the autophagy scores of each sample according to the expression levels of autophagy-related genes (ARGs) and screened the survival-related ARLNRs (sARLNRs) of ccRCC patients by Cox regression analysis. The high-risk group and the low-risk group were distinguished by the median score of the autophagy-related risk score (ARRS) model. The functional annotations were detected by gene set enrichment analysis (GSEA) and principal component analysis (PCA). The expression levels of two kinds of sARLNRs in the renal tumor and adjacent normal tissues and cell lines were verified. RESULTS: There were 146 ARLNRs selected by Pearson analysis. A total of 30 sARLNRs were remarkably correlated with the clinical outcomes of ccRCC patients. Eleven sARLNRs (AC002553.1, AC092611.2, AL360181.2, AP002807.1, AC098484.1, AL513218.1, AC008735.2, MHENCR, AC020907.4, AC011462.4, and AC008870.2) with the highest prognosis value were recruited to establish the ARRS in which the overall survival (OS) in the high-risk group was shorter than that in the low-risk group. ARRS could be treated as an independent prognostic factor and has significant correlations with OS. The distributions of autophagy genes were different between the high-risk group and the low-risk group. In addition, we also found that the expression levels of AC098484.1 in ccRCC cell lines and tumor tissues were lower than those in HK-2 and adjacent normal tissues, but AL513218.1 showed the inverse level. Furthermore, the AC098484.1 expressed decreasingly with the more advanced T-stages, but AL513218.1 gradually increased. CONCLUSION: Our study identified and verified some sARLNRs with clinical significances and revealed their potential values on predicting prognoses of ccRCC patients, which may provide a novel perspective for autophagy-related research and clinical decisions.

Severe hematuria due to vesical varices in a patient with portal hypertension: A case report.

BACKGROUND: Hematuria is one of the most common clinical symptoms for urologists and is typically observed in urinary system tumors, prostate hyperplasia, and urinary stone disease. Hematuria due to vesical varices is very rare, and only a few cases have been reported since 1989. We report the first case of vesical varices due to portal hypertension with aberrant development and functioning of the genitourinary system along with the complete diagnosis and treatment process. CASE SUMMARY: This patient was a 53-year-old man with a history of aberrant development of the genitourinary system and hepatitis B-associated cirrhosis. He was admitted to the emergency department with severe hematuria and bladder clot tamponade. Many abnormally dilated blood vessels were found surrounding the bladder in the pelvis by color Doppler ultrasound, contrast-enhanced computed tomography, and three-dimensional visualization technology. It was difficult to perform transurethral cystoscopy and hemostasis in this patient, so we performed open surgical bladder exploration for hemostasis and surgical devascularization around the bladder. CONCLUSION: Urologists should improve the understanding of the pathophysiology, clinical manifestations, diagnosis, and treatment of vesical varices. This case may be presented as a reference for the diagnosis and management of severe hematuria due to vesical varices.

Bioinformatics profiling integrating a four immune-related long non-coding RNAs signature as a prognostic model for papillary renal cell carcinoma.

BACKGROUND: Papillary renal cell carcinoma (pRCC) was the 2nd most common subtype, accounting for approximately 15% incidence of renal cell carcinoma (RCC). Immune related long non-coding RNAs (IR-lncRs) plentiful in immune cells and immune microenvironment (IME) are potential in evaluating prognosis and assessing the effects of immunotherapy. A completed and meaningful IR-lncRs analysis based on abundant pRCC gene samples from The Cancer Genome Atlas (TCGA) will provide insight in this field. RESULTS: 17 IR-lncRs were selected by Pearson correlation analysis of immune score and the lncRNA expression level, and 5 sIRlncRs were significantly correlated with the OS of pRCC patients. 4 sIRlncRs (AP001267.3, AC026471.3, SNHG16 and ADAMTS9-AS1) with the most remarkable prognostic values were identified to establish the IRRS model and the OS of the low-risk group was longer than that in the high-risk group. The IRRS was certified as an independent prognosis factor and correlated with the OS. The high-risk group and low-risk group showed significantly different distributions and immune status through PCA and GSEA. In addition, we further found the expression levels of SNHG16 was remarkably enhanced in female patients with more advanced T-stages, but ADAMTS9-AS1 showed the opposite results. CONCLUSION: The IRRS model based on the identified 4 sIRlncRs showed the significant values on forecasting prognoses of pRCC patients, with the longer OS in the low-risk group. METHODS: We integrated the expression profiles of LncRNA and overall survival (OS) in the 322 pRCC patients based on the TCGA dataset. The immune scores calculated on account of the expression level of immune-related genes were used to verify the most relevant IR-lncRs. Survival-related IR-lncRs (sIRlncRs) were estimated by COX regression analysis in pRCC patients. The high-risk group and low-risk group were identified by the median immune-related risk score (IRRS) model established by the screened sIRlncRs. Functional annotation was displayed by gene set enrichment analysis (GSEA) and principal component analysis (PCA), and the immune composition and purity of the tumor were evaluated through microenvironment cell count records. The expression levels of sIRlncRs of pRCC samples were verified by real-time quantitative PCR.

Bioinformatics profiling integrating a three immune-related long non-coding RNA signature as a prognostic model for clear cell renal cell carcinoma.

BACKGROUND: Renal cell carcinoma (RCC) is one of the most common aggressive malignant tumors in urogenital system, and the clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal carcinoma. Immune related long non-coding RNAs (IRlncRs) plentiful in immune cells and immune microenvironment (IME) are potential in evaluating prognosis and assessing the effects of immunotherapy. A completed and meaningful IRlncRs analysis based on abundant ccRCC gene samples from The Cancer Genome Atlas (TCGA) will provide insight in this field. METHODS: Based on the TCGA dataset, we integrated the expression profiles of IRlncRs and overall survival (OS) in the 611 ccRCC patients. The immune score of each sample was calculated based on the expression level of immune-related genes and used to identify the most meaningful IRlncRs. Survival-related IRlncRs (sIRlncRs) was estimated by calculating the algorithm of difference and COX regression analysis in ccRCC patients. Based on the median immune-related risk score (IRRS) developed from the screened sIRlncRs, the high-risk and low-risk components were distinguished. Functional annotation was detected by gene set enrichment analysis (GSEA) and principal component analysis (PCA), and the immune composition and purity of the tumor was evaluated by microenvironment cell population records. The expression levels of three sIRlncRs were verified in various tissues and cell lines. RESULTS: A total of 39 IRlncRs were collected by Pearson correlation analyses among immune score and the lncRNA expression. A total of 7 sIRlncRs were significantly associated with the clinical outcomes of ccRCC patients. Three sIRlncRs (ATP1A1-AS1, IL10RB-DT and MELTF-AS1) with the most significant prognostic values were enrolled to build the IRRS model in which the OS of in the high-risk group was shorter than that in the low-risk group. The IRRS was identified as an independent prognosis factor and correlated with the OS. The high-risk group and low-risk group illustrated different distributions in PCA and different immune status in GSEA. Besides, we found the more significant expression in certain ccRCC cell lines and tumor tissues of ccRCC patients compared with the HK-2 and adjacent tissues respectively. Additionally, the expression levels of lncR-MELTF-AS1 and IL10RB-DT were remarkably enhanced along the more advanced T-stages, but the lncR-ATP1A1-AS1 showed the inverse gradient. CONCLUSION: Our results demonstrate some sIRlncRs with remark clinical relevance show the latent monitoring and prognosis values for ccRCC patients and may provide new insight in immunological researches and treatment strategies of ccRCC patients.