Bladder segmentation based on deep learning approaches: current limitations and lessons

TL;DR

This paper reviews the current state, challenges, and lessons learned from applying deep learning to bladder segmentation for cancer staging, emphasizing the need for tailored approaches due to unique clinical challenges.

Contribution

It provides an in-depth analysis of deep learning methods for bladder segmentation, highlighting limitations and lessons specific to this application.

Findings

Deep learning models show promise but face unique challenges in bladder segmentation.

Most existing approaches borrow methods from other medical imaging tasks without validation.

Current models are still in early development stages with limited multi-region segmentation success.

Abstract

Precise determination and assessment of bladder cancer (BC) extent of muscle invasion involvement guides proper risk stratification and personalized therapy selection. In this context, segmentation of both bladder walls and cancer are of pivotal importance, as it provides invaluable information to stage the primary tumour. Hence, multi region segmentation on patients presenting with symptoms of bladder tumours using deep learning heralds a new level of staging accuracy and prediction of the biologic behaviour of the tumour. Nevertheless, despite the success of these models in other medical problems, progress in multi region bladder segmentation is still at a nascent stage, with just a handful of works tackling a multi region scenario. Furthermore, most existing approaches systematically follow prior literature in other clinical problems, without casting a doubt on the validity of these methods on bladder segmentation, which may present different challenges. Inspired by this, we provide an in-depth look at bladder cancer segmentation using deep learning models. The critical determinants for accurate differentiation of muscle invasive disease, current status of deep learning based bladder segmentation, lessons and limitations of prior work are highlighted.