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

2020/11/16 by Rosana El Jurdi, Jurdi, Rosana El, Caroline Petitjean +8 · 5 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Medical Image Segmentation Techniques #Medical Imaging and Analysis #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.2011.08018

openalex publication_date 2020/11/16 · arxiv created 2020/11/22 · arxiv updated 2020/11/24 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

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.

Citations

• Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?
• nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation

Cited by

• Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation
• XBusNet: Text-Guided Breast Ultrasound Segmentation via Multimodal Vision-Language Learning
• Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models
• Adaptive Confidence-Wise Loss for Improved Lens Structure Segmentation in AS-OCT
• CALF: A Conditionally Adaptive Loss Function to Mitigate Class-Imbalanced Segmentation
• Task-based Loss Functions in Computer Vision: A Comprehensive Review

Related

• Effect of Prior-based Losses on Segmentation Performance: A Benchmark
• Learning with Explicit Shape Priors for Medical Image Segmentation
• A survey on shape-constraint deep learning for medical image segmentation
• Incorporating prior knowledge in medical image segmentation: a survey
• Trustworthy Deep Learning for Medical Image Segmentation