3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes

Abstract

With the introduction of fully convolutional neural networks, deep learning has raised the benchmark for medical image segmentation on both speed and accuracy, and different networks have been proposed for 2D and 3D segmentation with promising results. Nevertheless, most networks only handle relatively small numbers of labels (<10), and there are very limited works on handling highly unbalanced object sizes especially in 3D segmentation. In this paper, we propose a network architecture and the corresponding loss function which improve segmentation of very small structures. By combining skip connections and deep supervision with respect to the computational feasibility of 3D segmentation, we propose a fast converging and computationally efficient network architecture for accurate segmentation. Furthermore, inspired by the concept of focal loss, we propose an exponential logarithmic loss which balances the labels not only by their relative sizes but also by their segmentation difficulties. We achieve an average Dice coefficient of 82% on brain segmentation with 20 labels, with the ratio of the smallest to largest object sizes as 0.14%. Less than 100 epochs are required to reach such accuracy, and segmenting a 128x128x128 volume only takes around 0.4 s.

arXiv commentAccepted by the International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2018 (oral presentation, acceptance rate 4%)

References in corpus (2)

• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Deeply-Supervised Nets

Cited by in corpus (27)

• A survey of loss functions for semantic segmentation
• Medical Image Segmentation Using Deep Learning: A Survey
• Boundary loss for highly unbalanced segmentation
• Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation
• Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation
• Evaluation of Multi-Slice Inputs to Convolutional Neural Networks for Medical Image Segmentation
• Deep convolutional neural networks for multi-planar lung nodule detection: improvement in small nodule identification
• Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses
• Segmentation Loss Odyssey
• Distribution-aware Margin Calibration for Semantic Segmentation in Images
• Saliency-Guided Deep Learning Network for Automatic Tumor Bed Volume Delineation in Post-operative Breast Irradiation
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors
• Lesion-aware network for diabetic retinopathy diagnosis
• SemSegLoss: A python package of loss functions for semantic segmentation
• Image-Based Soil Organic Carbon Remote Sensing from Satellite Images with Fourier Neural Operator and Structural Similarity
• 3D Segmentation with Fully Trainable Gabor Kernels and Pearson's Correlation Coefficient
• Pairwise Relation Learning for Semi-supervised Gland Segmentation
• Deep Distance Map Regression Network with Shape-aware Loss for Imbalanced Medical Image Segmentation
• FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator
• A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images
• Multi Scale Supervised 3D U-Net for Kidney and Tumor Segmentation
• HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
• Deep Learning for Automated Medical Image Analysis
• Distribution-aware Margin Calibration for Medical Image Segmentation
• MPG-Net: Multi-Prediction Guided Network for Segmentation of Retinal Layers in OCT Images
• Automatic Image Co-Segmentation: A Survey