No abstract

This study aimed to investigate the role of AR-V7 in development of castration-resistant prostate cancer (CRPC) and to determine whether the AR-V7 expression in CRPC tissues can predict cancer-specific survival. We enrolled 100 localized prostate cancer (PCa) (cohort 1), 104 newly diagnosed metastatic PCa (cohort 2), and 46 CRPC (cohort 3) patients treated at our institution. The expression of AR-V7 in PCa was assessed by immunohistochemistry. Cox regression models were used to evaluate the predictive role of all covariates for the development of CRPC in cohort 2 and for cancer-specific survival in cohort 3. Time to CRPC and cancer-specific survival curves were estimated using the Kaplan-Meier method. AR-V7 expression rate in cohort 3 was significantly elevated compared with other two cohorts (p < 0.001). Multivariate analysis revealed that AR-V7 was an independent predictive factor for CRPC development (HR = 2.627, p = 0.001) and for cancer specific survival (HR = 2.247, p = 0.033). Furthermore, the AR-V7 expression was associated with shorter survival in CRPC patients. Our results demonstrated protein AR-V7 levels in primary tumors can be used as a predictive marker for the development of CRPC and as a prognostic factor in CRPC patients. Therapy targeting AR-V7 may help prevent PCa progression and improve the prognosis of CRPC patients.

Signet ring cell carcinoma is a type of rare adenocarcinoma with poor prognosis. Early detection leads to huge improvement of patients' survival rate. However, pathologists can only visually detect signet ring cells under the microscope. This procedure is not only laborious but also prone to omission. An automatic and accurate signet ring cell detection solution is thus important but has not been investigated before. In this paper, we take the first step to present a semi-supervised learning framework for the signet ring cell detection problem. Self-training is proposed to deal with the challenge of incomplete annotations, and cooperative-training is adapted to explore the unlabeled regions. Combining the two techniques, our semi-supervised learning framework can make better use of both labeled and unlabeled data. Experiments on large real clinical data demonstrate the effectiveness of our design. Our framework achieves accurate signet ring cell detection and can be readily applied in the clinical trails. The dataset will be released soon to facilitate the development of the area.