Objective Deep learning algorithms were used to develop a model for predicting the staging and grading of renal clear cell carcinoma to inform clinicians’ treatment plans. Methods Clinical and pathological information was collected from 878 patients diagnosed with renal clear cell carcinoma in the Department of Urology, Peking University First Hospital. The patients were randomly assigned to the test set (n = 702) or the verification set (n = 176). Pathological staging and grading of renal clear cell carcinoma were predicted by preoperative clinical variables using deep learning algorithms. Receiver operating characteristic curves were used to evaluate the predictive accuracy as measured by the area under the receiver operating characteristic curve (AUC). Results For tumor pathological staging, AUC values of 0.933, 0.947, and 0.948 were obtained using the BiLSTM, CNN-BiLSTM, and CNN-BiGRU models, respectively. For tumor pathological grading, the AUC values were 0.754, 0.720, and 0.770, respectively. Conclusions The proposed model for predicting renal clear cell carcinoma allows for accurate projection of the staging and grading of renal clear cell carcinoma and helps clinicians optimize individual treatment plans.

No abstract

Background To compare the efficacy of secondary pyeloplasty and balloon dilation and to analyze the risk factors for secondary surgical failure in patients with recurrent uretero-pelvic junction obstruction (UPJO). Methods We retrospectively analyzed 65 patients with recurrent UPJO who underwent secondary surgery between September 2011 and March 2019, of whom 33 had complete baseline data and follow-up data. General clinical information, perioperative data, and follow-up results were collected from patients. Risk factors for surgical failure in patients with recurrent UPJO were analyzed using logistic regression. Results The failure rates of secondary pyeloplasty and balloon dilation in secondary surgery were 16.7% and 33.3%, respectively. Univariate analysis showed that ureteral stenosis length and operative time were associated with secondary pyeloplasty and balloon dilatation failure (p < 0.05), and ureteral stenosis length was an independent risk factor for secondary pyeloplasty failure (OR = 0.074, 95% CI: 0.006–0.864, p = 0.038). In the balloon dilation group, treatment failure rates were significantly lower in patients with stenotic segment lengths less than 1 ± 0.32 cm than in patients with stenotic segment lengths greater than 1 ± 0.32 cm (p = 0.019). Conclusions The secondary pyeloplasty may provide better benefit. Ureteral stricture length is an independent risk factor for failure of secondary pyeloplasty and a potential risk factor for balloon dilatation. Operation time is a potential risk factor for pyeloplasty and balloon dilatation.

Fruit softening is a complex, genetically programmed and environmentally regulated process, which undergoes biochemical and physiological changes during fruit development. The molecular mechanisms that determine these changes in Chinese cherry [Cerasus peseudocerasus (Lindl.) G.Don] fruits are still unknown. In the present study, fruits of hard-fleshed ‘Hongfei’ and soft-fleshed ‘Pengzhoubai’ varieties of Chinese cherry were selected to illustrate the fruit softening at different developmental stages. We analyzed physiological characteristics and transcriptome profiles to identify key cell wall components and candidate genes related to fruit softening and construct the co-expression networks. The dynamic changes of cell wall components (cellulose, hemicellulose, pectin, and lignin), the degrading enzyme activities, and the microstructure were closely related to the fruit firmness during fruit softening. A total of 6,757 and 3,998 differentially expressed genes (DEGs) were screened between stages and varieties, respectively. Comprehensive functional enrichment analysis supported that cell wall metabolism and plant hormone signal transduction pathways were involved in fruit softening. The majority of structural genes were significantly increased with fruit ripening in both varieties, but mainly down-regulated in Hongfei fruits compared with Pengzhoubai, especially DEGs related to cellulose and hemicellulose metabolism. The expression levels of genes involving lignin biosynthesis were decreased with fruit ripening, while mainly up-regulated in Hongfei fruits at red stage. These obvious differences might delay the cell all degrading and loosening, and enhance the cell wall stiffing in Hongfei fruits, which maintained a higher level of fruit firmness than Pengzhoubai. Co-expressed network analysis showed that the key structural genes were correlated with plant hormone signal genes (such as abscisic acid, auxin, and jasmonic acid) and transcription factors (MADS, bHLH, MYB, ERF, NAC, and WRKY). The RNA-seq results were supported using RT-qPCR by 25 selected DEGs that involved in cell wall metabolism, hormone signal pathways and TF genes. These results provide important basis for the molecular mechanism of fruit softening in Chinese cherry.