Asymmetric Loss Functions and Deep Densely Connected Networks for Highly Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection

Abstract

Fully convolutional deep neural networks have been asserted to be fast and precise frameworks with great potential in image segmentation. One of the major challenges in training such networks raises when data is unbalanced, which is common in many medical imaging applications such as lesion segmentation where lesion class voxels are often much lower in numbers than non-lesion voxels. A trained network with unbalanced data may make predictions with high precision and low recall, being severely biased towards the non-lesion class which is particularly undesired in most medical applications where FNs are more important than FPs. Various methods have been proposed to address this problem, more recently similarity loss functions and focal loss. In this work we trained fully convolutional deep neural networks using an asymmetric similarity loss function to mitigate the issue of data imbalance and achieve much better tradeoff between precision and recall. To this end, we developed a 3D FC-DenseNet with large overlapping image patches as input and an asymmetric similarity loss layer based on Tversky index (using Fbeta scores). We used large overlapping image patches as inputs for intrinsic and extrinsic data augmentation, a patch selection algorithm, and a patch prediction fusion strategy using B-spline weighted soft voting to account for the uncertainty of prediction in patch borders. We applied this method to MS lesion segmentation based on two different datasets of MSSEG and ISBI longitudinal MS lesion segmentation challenge, where we achieved top performance in both challenges. Our network trained with focal loss ranked first according to the ISBI challenge overall score and resulted in the lowest reported lesion false positive rate among all submitted methods. Our network trained with the asymmetric similarity loss led to the lowest surface distance and the best lesion true positive rate.

arXiv commentIEEE Access

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Focal Loss for Dense Object Detection
• Fully Convolutional Networks for Semantic Segmentation
• Automatic segmentation of MR brain images with a convolutional neural network
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
• DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy
• Deep Learning for Medical Image Segmentation
• Real-Time Automatic Fetal Brain Extraction in Fetal MRI by Deep Learning
• Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging
• Auto-context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging
• Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach

Cited by in corpus (14)

• A survey of loss functions for semantic segmentation
• Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation
• Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review
• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation
• Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging
• Segmentation Loss Odyssey
• PixelGame: Infrared small target segmentation as a Nash equilibrium
• Geometric Loss for Deep Multiple Sclerosis lesion Segmentation
• Point detection through multi-instance deep heatmap regression for sutures in endoscopy
• Simultaneous lesion and neuroanatomy segmentation in Multiple Sclerosis using deep neural networks
• SemSegLoss: A python package of loss functions for semantic segmentation
• Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods
• Deep Cerebellar Nuclei Segmentation via Semi-Supervised Deep Context-Aware Learning from 7T Diffusion MRI