High-level Prior-based Loss Functions for Medical Image Segmentation: A Survey

TL;DR

This survey reviews high-level prior-based loss functions in CNNs for medical image segmentation, emphasizing shape, size, topology, and inter-region constraints to improve anatomical plausibility.

Contribution

It categorizes existing prior-based loss functions, analyzes their strengths and limitations, and discusses future research directions in integrating prior knowledge into CNN segmentation.

Findings

High-level prior losses improve anatomical plausibility.

Current methods face challenges in design and optimization.

Future research should focus on better integration strategies.

Abstract

Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To mitigate this effect, recent research works have focused on incorporating spatial information or prior knowledge to enforce anatomically plausible segmentation. If the integration of prior knowledge in image segmentation is not a new topic in classical optimization approaches, it is today an increasing trend in CNN based image segmentation, as shown by the growing literature on the topic. In this survey, we focus on high level prior, embedded at the loss function level. We categorize the articles according to the nature of the prior: the object shape, size, topology, and the inter-regions constraints. We highlight strengths and limitations of current approaches, discuss the challenge related to the design and the integration of prior-based losses, and the optimization strategies, and draw future research directions.