Assessment of Immunological Features in Muscle-Invasive Bladder Cancer Prognosis Using Ensemble Learning

Abstract

Simple Summary Muscle-invasive bladder cancer (MIBC) accounts for the majority of bladder cancer mortality worldwide. Clinical assessment of MIBC mainly relies on the TNM staging system to provide guidance for both prognosis and therapy planning. Based on standardized quantification of tumour-immune features across whole slide images, and in conjunction with clinical information, we construct an ensemble machine learning model that correctly classifies 71.4% of the patients who succumb to MIBC, significantly higher than the 28.6% of TNM staging system. Post-hoc analysis of our model reveals clinically relevant, immunological features for MIBC prognosis, thereby further supporting their adoption into the clinic. Abstract The clinical staging and prognosis of muscle-invasive bladder cancer (MIBC) routinely includes the assessment of patient tissue samples by a pathologist. Recent studies corroborate the importance of image analysis in identifying and quantifying immunological markers from tissue samples that can provide further insight into patient prognosis. In this paper, we apply multiplex immunofluorescence to MIBC tissue sections to capture whole-slide images and quantify potential prognostic markers related to lymphocytes, macrophages, tumour buds, and PD-L1. We propose a machine-learning-based approach for the prediction of 5 year prognosis with different combinations of image, clinical, and spatial features. An ensemble model comprising several functionally different models successfully stratifies MIBC patients into two risk groups with high statistical significance (p value < 1×10−5). Critical to improving MIBC survival rates, our method correctly classifies 71.4% of the patients who succumb to MIBC, which is significantly more than the 28.6% of the current clinical gold standard, the TNM staging system.