Multimodal data integration for predicting progression risk in castration-resistant prostate cancer using deep learning: a multicenter retrospective study.

Purpose: Patients with advanced prostate cancer (PCa) often develop castration-resistant PCa (CRPC) with poor prognosis. Prognostic information obtained from multiparametric magnetic resonance imaging (mpMRI) and histopathology specimens can be effectively utilized through artificial intelligence (AI) techniques. The objective of this study is to construct an AI-based CRPC progress prediction model by integrating multimodal data. Methods and materials: Data from 399 patients diagnosed with PCa at three medical centers between January 2018 and January 2021 were collected retrospectively. We delineated regions of interest (ROIs) from 3 MRI sequences viz, T2WI, DWI, and ADC and utilized a cropping tool to extract the largest section of each ROI. We selected representative pathological hematoxylin and eosin (H&E) slides for deep-learning model training. A joint combined model nomogram was constructed. ROC curves and calibration curves were plotted to assess the predictive performance and goodness of fit of the model. We generated decision curve analysis (DCA) curves and Kaplan-Meier (KM) survival curves to evaluate the clinical net benefit of the model and its association with progression-free survival (PFS). Results: The AUC of the machine learning (ML) model was 0.755. The best deep learning (DL) model for radiomics and pathomics was the ResNet-50 model, with an AUC of 0.768 and 0.752, respectively. The nomogram graph showed that DL model contributed the most, and the AUC for the combined model was 0.86. The calibration curves and DCA indicate that the combined model had a good calibration ability and net clinical benefit. The KM curve indicated that the model integrating multimodal data can guide patient prognosis and management strategies. Conclusion: The integration of multimodal data effectively improves the prediction of risk for the progression of PCa to CRPC.

Multiparametric MRI radiomics in prostate cancer for predicting Ki-67 expression and Gleason score: a multicenter retrospective study.

PURPOSE: Prostate cancer (PCa) with high Ki-67 expression and high Gleason Scores (GS) tends to have aggressive clinicopathological characteristics and a dismal prognosis. In order to predict the Ki-67 expression status and the GS in PCa, we sought to construct and verify MRI-based radiomics signatures. METHODS AND MATERIALS: We collected T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) images from 170 PCa patients at three institutions and extracted 321 original radiomic features from each image modality. We used support vector machine (SVM) and least absolute shrinkage and selection operator (LASSO) logistic regression to select the most informative radiomic features and built predictive models using up sampling and feature selection techniques. Using receiver operating characteristic (ROC) analysis, the discriminating power of this feature was determined. Subsequent decision curve analysis (DCA) assessed the clinical utility of the radiomic features. The Kaplan-Meier (KM) test revealed that the radiomics-predicted Ki-67 expression status and GS were prognostic factors for PCa survival. RESULT: The hypothesized radiomics signature, which included 15 and 9 selected radiomics features, respectively, was significantly correlated with pathological Ki-67 and GS outcomes in both the training and validation datasets. Areas under the curve (AUC) for the developed model were 0.813 (95% CI 0.681,0.930) and 0.793 (95% CI 0.621, 0.929) for the training and validation datasets, respectively, demonstrating discrimination and calibration performance. The model's clinical usefulness was verified using DCA. In both the training and validation sets, high Ki-67 expression and high GS predicted by radiomics using SVM models were substantially linked with poor overall survival (OS). CONCLUSIONS: Both Ki-67 expression status and high GS correlate with PCa patient survival outcomes; therefore, the ability of the SVM classifier-based model to estimate Ki-67 expression status and the Lasso classifier-based model to assess high GS may enhance clinical decision-making.

[Research on the anti-tumor effects of CRYAB in prostate cancer].

OBJECTIVE: To explore the relationship between CRYAB and the prognosis of prostate cancer (PCa) as well as the potential mechanism. METHODS: Bioinformatics analysis was performed using R software, including differential gene expression and clinical correlation analysis, receiver operating characteristic (ROC) curve and Kaplan-Meier (KM) curve generation. Gene expression was detected using RT-qPCR, and protein expression was validated using Western Blot. The proliferation, apoptosis, and metastatic ability of PCa cells were detected using CCK8, TUNEL, Transwell migration, and invasion assays. RESULTS: According to the TCGA and GEO databases, CRYAB mRNA expression was down-regulated in PCa tissue compared with normal tissue (P< 0.05), and CRYAB mRNA and protein were down-regulated in PCa cells compared with RWPE1 cells (P< 0.05). Cell function experiments showed that up-regulated CRYAB could inhibit the proliferation, invasion, and migration of prostate cancer cells, promote apoptosis (P< 0.05), and up-regulate CDH1 expression while down-regulating CDH2 expression in the CRYAB-upregulated cell line. In addition, CRYAB mRNA expression was correlated with Gleason score (P< 0.01). The area under the ROC curve was 0.914, the KM curve showed that CRYAB had prognostic value for progression-free survival (P = 0.008) and disease-specific survival (P = 0.032). CONCLUSION: CRYAB is down-regulated in PCa tissue and is associated with the anti- tumor function of PCa cells. It may affect the metastatic ability of prostate cancer cells by regulating epithelial-mesenchymal transition molecules. CRYAB mRNA has important diagnostic and prognostic value in PCa.

[Establishment of a model of reproductive system injury in male Wistar rats in high-altitude hypoxia environment].

OBJECTIVE: To establish a model of reproductive system injury in male rats at high altitude using the low-pressure hypoxic animal laboratory and study the changes in the testicular tissue, semen parameters, blood gas and oxidative stress in male rats at different altitudes. METHODS: Sixty male Wistar rats were randomly assigned to be raised on the plains (the plains group, n = 20), at an altitude of 4 000 m (the plateau model group Ⅰ, n = 20), or at an altitude of 6 000 m (the plateau model group Ⅱ, n = 20) for a spermatogenic cycle of 14 days. After establishment of the model of high-altitude reproductive system injury, the testis tissues of the rats were harvested for HE staining and observed for histopathological changes under the light microscope, and their epididymedes collected for preparation of sperm suspension and detection of sperm motility, sperm count and the percentage of morphologically abnormal sperm (MAS). The blood gas level and oxidative stress-related indexes in different groups were also measured using the serological test. RESULTS: With the elevation of altitude, the levels of pH and PO2 were decreased, those of PCO2, Hct, K+, Cl－ and Hb increased markedly, while that of Na+ exhibited no significant change. The model rats also showed folded spermatogenic tubule walls, thinned spermatogenic epithelia, disorderly arranged and reduced number of spermatogenic cells, and increased vascuolization in the spermatogenic epithelia, with decreased sperm motility and count, increased percentage of MAS, elevated concentration of malondialdehyde (MDA) and reduced activity of superoxide dismutase (SOD). CONCLUSIONS: A model of reproductive system injury was successfully established in male rats at a simulated altitude of 4 000 m. With increasing of the altitude to 6000 m, oxidative damage to the testicular tissue was aggravated, sperm motility decreased, and the percentage of MAS increased, indicating that an altitude of 6 000 m may cause serious damage to the rat reproductive system.

VHL gene mutation analysis of a Chinese family with non- syndromic pheochromocytomas and patients with apparently sporadic pheochromocytoma.

OBJECTIVE: The Von Hippel-Lindau syndrome (VHLD), an inherited neoplastic syndrome predisposing to central nervous system hemangioblastoma (CNS), pheochromocytoma (PCC), renal cell carcinoma(RCC), retinal hemangioma (RA) and renal cysts, is caused by mutations or deletions of the VHL tumor-suppressor gene. To assess VHL genotype-phenotype correlations with function of pVHL a gene mutation analysis of members in a Chinese family with non-syndromic PCCs and individuals with apparently sporadic pheochromocytoma (ASP) was performed. MATERIALS AND METHODS: DNA samples of 20 members from the Chinese family with non-syndromic PCCs and 41 patients with ASP were analyzed by polymerase chain reaction and direct sequencing, confirmed by Taqman probe. RESULTS: Three novel mutations (H125P, 623(?TTTGTtG) and R120T) were identified in the Chinese family and in 3 among 41 ASP patients. The mutations were all located in exon 2 of VHL gene encoding ß-domain of pVHL. The tumor type in H125P carriers and R120T carriers was VHL type 2C. And 623(?TTTGTtG) carriers presented VHL type 2B or type 2C. CONCLUSIONS: VHL gene abnormalities were identified in the Chinese family with non-syndromic PCCs and patients with APS, resulting in dysfunction of pVHL. H125P and R120T could be associated with VHL type 2C, while 623(?TTTGTtG) might be linked with VHL type 2B or type 2C. Not only is the genetic analysis helpful for early diagnosis and treatment of patients with VHLD, it is also benefitial for research into VHLD pathogenesis.

[Mutation screening of VHL gene in a Chinese family with nonsyndromic pheochromocytoma].

OBJECTIVE: To detect the VHL gene mutations in a Chinese family with nonsyndromic pheochromocytoma. METHODS: Mutations of VHL gene were detected in a Chinese family with nonsyndromic pheochromocytoma. Five patients and fifteen relatives were involved in this study. Peripheral blood was collected and total genomic DNA was prepared for polymerase chain reaction (PCR). PCR products of all the three exons of VHL gene were purified and a direct gene sequence analysis was performed. RESULTS: All the five patients presented a codon 125 from Histidine (H) to Proline (P) change at nucleotide 587 (A --> C) in exon 2. Seven members of fifteen relatives were carriers with the same VHL gene mutation. Two carriers were detected with bilateral adrenal tumors and right renal cyst respectively by ultrasonic inspection. CONCLUSION: The novel VHL gene mutation detected in this kindred may be the causative gene. Genetic test can detect the carriers in an early period. It is recommended as a routine method of genetic test in nonsyndromic pheochromocytoma patients.

[Effects of polychlorinated biphenyl on bcl-2 and TGFbeta1 expression in rat testes].

OBJECTIVE: To study the effects of polychlorinated biphenyl (PCB) on bcl-2 and TGFbeta1 expression in rat testes. METHODS: Forty male Wistar rats were divided into 4 groups at random: Group A (normal control), Group B (fed on 10(-8) mol/L PBC), Group C (feb on 10(-7) mol/L) and Group D (feb on 10(-6) mol/L). After three months, all the rats were killed, the animal model established, and observations made on the expression of bcl2 and TGFbeta1 in the rat testis using the optical microscope and immunohistochemical techniques. RESULTS: The damage to the structure of the testis was related to the dosage of PCB: the higher the dodage, the more serious the damage. PCB induced the expression of bcl-2 and TGFbeta1. The TGFbeta1 expression was significantly higher in the highest dosage group than in others (P < 0.01 ), and the bcl-2 expression was dramatically higher in Group C than in other groups (P < 0.01). CONCLUSION: PCB can cause injury in rat testes.