Deep learning approach for accurate prostate cancer identification and stratification using combined immunostaining of cytokeratin, p63, and racemase

Background: Prostate cancer (PCa) is the most frequently diagnosed cancer in men worldwide, affecting around 1.4 million individuals. Current PCa diagnosis relies on histological analysis of prostate biopsy samples, an activity that is both time-consuming and prone to observer bias. Previous studies have demonstrated that immunostaining of cytokeratin, p63, and racemase can significantly improve the sensitivity and the specificity of PCa detection compared to traditional H & E staining. Methods: This study introduces a novel approach that combines diagnosis-specific immunohistochemical (IHC) staining and deep learning techniques to provide reliable stratification of prostate glands. Our approach leverages a customized segmentation network, called K-PPM, that incorporates adaptive kernels and multiscale feature integration to enhance the functional information of IHC. To address the high class-imbalance problem in the dataset, we propose a weighted adaptive patch-extraction and specific-class kernel update. Results: Our system achieved noteworthy results, with a mean Dice Score Coefficient of 90.36% and a mean absolute error of 1.64 % in specific-class gland quantification on whole slides. These findings demonstrate the potential of our system as a valuable support tool for pathologists, reducing workload and decreasing diagnostic inter-observer variability. Conclusions: Our study presents innovative approaches that have broad applicability to other digital pathology areas beyond PCa diagnosis. As a fully automated system, this model can serve as a framework for improving the histological and IHC diagnosis of other types of cancer.

Automated summary

This study introduces a novel approach that combines diagnosis-specific immunohistochemical (IHC) staining and deep learning techniques to provide reliable stratification of prostate glands. The system achieved noteworthy results in specific-class gland quantification on whole slides, with a mean Dice Score Coefficient of 90.36% and a mean absolute error of 1.64%. The findings demonstrate the potential of this system as a valuable support tool for pathologists, reducing workload and decreasing diagnostic inter-observer variability.