blob loss: instance imbalance aware loss functions for semantic segmentation

Abstract

Deep convolutional neural networks (CNN) have proven to be remarkably effective in semantic segmentation tasks. Most popular loss functions were introduced targeting improved volumetric scores, such as the Dice coefficient (DSC). By design, DSC can tackle class imbalance, however, it does not recognize instance imbalance within a class. As a result, a large foreground instance can dominate minor instances and still produce a satisfactory DSC. Nevertheless, detecting tiny instances is crucial for many applications, such as disease monitoring. For example, it is imperative to locate and surveil small-scale lesions in the follow-up of multiple sclerosis patients. We propose a novel family of loss functions, \emph{blob loss}, primarily aimed at maximizing instance-level detection metrics, such as F1 score and sensitivity. \emph{Blob loss} is designed for semantic segmentation problems where detecting multiple instances matters. We extensively evaluate a DSC-based \emph{blob loss} in five complex 3D semantic segmentation tasks featuring pronounced instance heterogeneity in terms of texture and morphology. Compared to soft Dice loss, we achieve 5% improvement for MS lesions, 3% improvement for liver tumor, and an average 2% improvement for microscopy segmentation tasks considering F1 score.

arXiv comment23 pages, 7 figures // corrected one mistake where it said beta instead of alpha in the text

References in corpus (6)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy
• Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index
• Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks
• pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis

Cited by in corpus (2)

• Metrics reloaded: Recommendations for image analysis validation
• Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses