Search

Androgen deprivation therapy is a cornerstone of treatment for advanced prostate cancer, and the development of castrate-resistant prostate cancer (CRPC) is the primary cause of prostate cancer-related mortality. While CRPC typically develops through a gain in androgen receptor (AR) signaling, a subset of CRPC will lose reliance on the AR. This process involves genetic, epigenetic, and hormonal changes that promote cellular plasticity, leading to AR-indifferent disease, with neuroendocrine prostate cancer (NEPC) being the quintessential example. NEPC is enriched following treatment with second-generation anti-androgens and exhibits resistance to endocrine therapy. Loss of RB1, TP53, and PTEN expression and MYCN and AURKA amplification appear to be key drivers for NEPC differentiation. Epigenetic modifications also play an important role in the transition to a neuroendocrine phenotype. DNA methylation of specific gene promoters can regulate lineage commitment and differentiation. Histone methylation can suppress AR expression and promote neuroendocrine-specific gene expression. Emerging data suggest that EZH2 is a key regulator of this epigenetic rewiring. Several mechanisms drive AR-dependent castration resistance, notably AR splice variant expression, expression of the adrenal-permissive 3βHSD1 allele, and glucocorticoid receptor expression. Aberrant epigenetic regulation also promotes radioresistance by altering the expression of DNA repair- and cell cycle-related genes. Novel therapies are currently being developed to target these diverse genetic, epigenetic, and hormonal mechanisms promoting lineage plasticity-driven NEPC.

Purpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve such issues. However, developing reliable algorithms is usually time-consuming and costly. We created an international community-driven competition (KiTS19) to develop and identify the best system for automatic segmentation of kidneys and kidney tumors in contrast CT and report the results.Methods: A training and test set of CT scans that was manually annotated by trained individuals were generated from consecutive patients undergoing renal surgery for whom demographic, clinical and outcome data were available. The KiTS19 Challenge was a machine learning competition hosted on grand-challenge.org in conjunction with an international conference. Teams were given 3 months to develop their algorithm using a full-annotated training set of images and an unannotated test set was released for 2 weeks from which average Sørensen-Dice coefficient between kidney and tumor regions were calculated across all 90 test cases.Results: There were 100 valid submissions that were based on deep neural networks but there were differences in pre-processing strategies, architectural details, and training procedures. The winning team scored a 0.974 kidney Dice and a 0.851 tumor Dice resulting in 0.912 composite score. Automatic segmentation of the kidney by the participating teams performed comparably to expert manual segmentation but was less reliable when segmenting the tumor.Conclusion: Rapid advancement in automated semantic segmentation of kidney lesions is possible with relatively high accuracy when the data is released publicly, and participation is incentivized. We hope that our findings will encourage further research that would enable the potential of adopting AI into the medical field.