Adversarial training and dilated convolutions for brain MRI segmentation

Abstract

Convolutional neural networks (CNNs) have been applied to various automatic image segmentation tasks in medical image analysis, including brain MRI segmentation. Generative adversarial networks have recently gained popularity because of their power in generating images that are difficult to distinguish from real images. In this study we use an adversarial training approach to improve CNN-based brain MRI segmentation. To this end, we include an additional loss function that motivates the network to generate segmentations that are difficult to distinguish from manual segmentations. During training, this loss function is optimised together with the conventional average per-voxel cross entropy loss. The results show improved segmentation performance using this adversarial training procedure for segmentation of two different sets of images and using two different network architectures, both visually and in terms of Dice coefficients.

MICCAI 2017 Workshop on Deep Learning in Medical Image Analysis

References in corpus (4)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Adversarial Networks for the Detection of Aggressive Prostate Cancer
• SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays

Cited by in corpus (8)

• Generative Adversarial Network in Medical Imaging: A Review
• Leveraging Uncertainty Estimates for Predicting Segmentation Quality
• Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging
• A Survey on Deep Learning of Small Sample in Biomedical Image Analysis
• MRI Banding Removal via Adversarial Training
• Deep Learning in Multi-organ Segmentation
• Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
• Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration