[Identifying Molecular Subtypes of Whole-Slide Image in Colorectal Cancer via Deep Learning].

OBJECTIVE: To establish an artificial intelligence-assisted diagnosis system for molecular subtyping of colorectal cancer (CRC). METHODS: 812 whole-slide images (WSIs) of 422 patients were selected from the database of The Cancer Genome Atlas (TCGA) and were put into the training set (75%) and the test set (25%). The slides were stored in the www.paiwsit.com database. We preprocessed and segmented the slides based on the labelling results of experienced pathologists to generate a training set of more than 4 million labeled samples. Finally, deep learning models were adopted for training. RESULTS: After training with several convolutional neural network models, we tested the performance of the trained deep learning model on the test set of 203 WSIs from 110 patients, and our model achieved an accuracy of 53.04% at patch-level and 51.72% at slide-level, while the accuracy of CMS2 (one of a consensus of four subtypes for CRC) at slide-level was as high as 75.00%. CONCLUSION: This study is of great significance to the promotion of colorectal cancer screening and precision treatment.

Modulatory effect of aquaporin 5 on estrogen-induced epithelial-mesenchymal transition in prostate epithelial cells.

BACKGROUND: Estrogen is involved in the pathophysiological process of benign prostatic hyperplasia (BPH), in which epithelial-mesenchymal transition (EMT) plays an important role. Upregulation of aquaporin (AQP) 5, which is directly activated by estrogen, has been reported to promote EMT in multiple cells. This study aimed to examine the effects of AQP5 on estrogen-induced EMT in the prostate. METHODS: Normal prostate (NP) tissue samples without any histopathological changes and BPH tissue samples with pathologically confirmed hyperplasia were obtained. An EMT cell model was subsequently established by adding estradiol (E2) to RWPE-1 cells, after which AQP5 knockdown was performed. Tissue morphological and immunohistochemical features were examined using hematoxylin-eosin and immunohistochemical staining. Western blot analysis was performed to determine the expression of AQPs, estrogen receptors, and EMT-related proteins. Cell proliferation was assessed and supernatants were collected for enzyme-linked immunosorbent assay to determine transforming growth factor-ß1 (TGF-ß1) concentrations. Immunofluorescence staining was performed to assess protein expressions in RWPE-1 cells. RESULTS: BPH tissues exhibited greater EMT (TGF-ß1: 1.362 ±â€Š0.196 vs. 0.107 ±â€Š0.067, P = 0.003; vimentin: 1.581 ±â€Š0.508 vs. 0.221 ±â€Š0.047, P < 0.001; E-cadherin: 0.197 ±â€Š0.188 vs. 1.344 ±â€Š0.088, P < 0.001), higher AQP5 (1.268 ±â€Š0.136 vs. 0.227 ±â€Š0.055, P < 0.001) and estrogen receptor (ER) α (1.250 ±â€Š0.117 vs. 0.329 ±â€Š0.134, P < 0.001) expression but lower ERß (0.271 ±â€Š0.184 vs. 1.564 ±â€Š0.130, P < 0.001) expression than NP tissues. E2-stimulated cells had higher AQP5 expression (1.298 ±â€Š0.058 vs. 1.085 ±â€Š0.104, P = 0.049), increased cell proliferation (1.510 ±â€Š0.089 vs.1.000 ±â€Š0.038, P < 0.001), and EMT (TGF-ß1 concentration: 0.352 ±â€Š0.021 ng/mL vs. 0.125 ±â€Š0.014 ng/mL, P < 0.001; vimentin: 1.641 ±â€Š0.120 vs. 0.188 ±â€Š0.020, P = 0.002; E-cadherin: 0.075 ±â€Š0.030 vs. 0.843 ±â€Š0.046, P < 0.001) than controls. E2-stimulated cells with AQP5 knockdown exhibited decreased EMT (TGF-ß1 concentration: 0.223 ±â€Š0.041 ng/mL vs. 0.352 ±â€Š0.021 ng/mL, P = 0.016; vimentin: 0.675 ±â€Š0.056 vs. 1.641 ±â€Š0.120, P = 0.001; E-cadherin: 0.159 ±â€Š0.037 vs. 0.075 ±â€Š0.030, P = 0.040) than E2-stimulated cells with non-related small interfering RNA (siRNA). CONCLUSION: Our findings suggest that estrogen induces BPH possibly by promoting AQP5 expression. Hence, AQP5 might be a novel target for modulating EMT in prostate epithelial cells.

[Predictive Value of Obesity Indicators for Metabolic Syndrome in Adults of Han and Yi Nationalities in Sichuan].

OBJECTIVE: To compare the predictive value of different measures of obesity for metabolic syndrome (MetS) in adult Yi and Han nationality population. METHODS: A total of 3 492 urban and rural residents in Chengdu and Liangshan Yi Autonomous Prefecture participated in this study. Demographic and laboratory data were collected. Spearman correlation analysis was used to investigate the relationship between different obesity measurement indexes and MetS. Receiver operating characteristic (ROC) curve was used to compare the predictive value between different obesity measurement indexes. RESULTS: Spearman correlation analysis showed that MetS was related to body mass index (BMI), waist circumference (WC), waist-to-hip ratio (WHR), waist-to-height ratio (WHtR), lipid accumulation index (LAP) and visceral adiposity index (VAI). The ROC curve showed that the LAP had the highest predictive value for MetS in both Yi and Han male adults, area under the curves (AUCs) >0.90; whereas WHR had the lowest predictive value. WHtR had high predictive value for MetS in both Yi and Han female adults (AUCs >0.88), VAI had the worst predictive value. CONCLUSION: Among different measures of obesity, LAP may have the optimal predictive value for MetS in male adults as do WHtR in female adults either in Yi or Han nationality. These findings should be confirmed through the measure of visceral fat volume and prospective study.

[Clinical Characteristics of Patients with Type 2 Diabetes Mellitus and Obstructive Sleep Apnea Syndrome].

OBJECTIVES: To compare the clinical characteristics and prevalence of chronic complications in type 2 diabetes mellitus (T2DM) patients with various degrees of obstructive sleep apnea syndrome (OSAS). METHODS: A total of 170 patients with T2DM and OSAS were enrolled in this study. These participants were divided into three groups with low, medium and high apnea-hypopnea index (AHI), respectively. The demographic characteristics, biochemical indicators and chronic complications of the patients in the three groups were compared. Multivariate Logistic regression analysis was performed to determine the associations between chronic complications and OSAS. RESULTS: The patients with severe OSAS had higher waist circumference (P=0.045), higher BMI (P=0.069), higher prevalence of diabetic peripheral neuropathy (DPN), and higher prevalence of diabetic retinopathy (DR) than the patients with mild-moderate OSAS. Similar levels of macrovascular complications were found in the three groups (P>0.05). The logistic regression analyses showed that DPN (OR=1.024, 95%CI 1.002-1.046) and chronic kidney disease (OR=1.026, 95%CI 1.004-1.049) were independent predictors of AHI, adjusting for the lowest oxygen saturation, gender, age, diabetic duration, family history of diabetes, BMI, and HbA1c. Other microvascular and macrovascular complications were not predictors of AHI. CONCLUSIONS: Patients with T2DM and severe OSAS have a higher risk of DPN and DR. Particular attention should be paid to T2DM patients with severe OSAS to prevent complications.

Clinical study on long-term overall survival of advanced non-small-cell lung cancer patients treated with Chinese medicine and Western medicine.

OBJECTIVE: To investigate the prognostic influence on long-term overall survival (OS) from treatment with Chinese medicine (CM) and chemotherapy or targeted therapy in advanced non-small-cell lung cancer (NSCLC) patients. METHODS: The clinical data of 206 advanced NSCLC patients who were treated with CM and Western medicine in Beijing Cancer Hospital from April 1999 to July 2013 were retrospectively analyzed. Long-term survivors were defined as OS ≥ 3 years after treatment with CM and chemotherapy. Twenty-eight patients had OS ≥ 3 years, 178 had OS < 3 years, and all clinical data were statistically analyzed with the Cox model. Variables were gender, age, smoking status, performance status (PS) score, pathological type, clinical stage, first-line chemotherapy, targeted therapy, and use of CM. Univariate survival analysis was performed using the Kaplan-Meier method and log-rank sequential inspection. Multivariate survival analysis was used to analyze the meaningful factors of univariate survival analysis with the Cox model. RESULTS: The survival rate of patients with OS ≥ 3 years was 13.6% (28/206). Cox multivariate regression analysis showed that PS score, clinical stage, disease control rate to first-line chemotherapy, and use of CM were independent factors of longterm OS (all <0.05). However, gender, age, smoking, and use of epidermal growth factor receptor tyrosine-kinase inhibitor were not significant (P>0.05). CONCLUSION: PS score, clinical stage, disease control rate to first-line chemotherapy, and use of CM are probably independent prognostic factors for long-term OS in patients with advanced NSCLC.