Deep Learning for Medical Image Segmentation

Abstract

This report provides an overview of the current state of the art deep learning architectures and optimisation techniques, and uses the ADNI hippocampus MRI dataset as an example to compare the effectiveness and efficiency of different convolutional architectures on the task of patch-based 3-dimensional hippocampal segmentation, which is important in the diagnosis of Alzheimer's Disease. We found that a slightly unconventional "stacked 2D" approach provides much better classification performance than simple 2D patches without requiring significantly more computational power. We also examined the popular "tri-planar" approach used in some recently published studies, and found that it provides much better results than the 2D approaches, but also with a moderate increase in computational power requirement. Finally, we evaluated a full 3D convolutional architecture, and found that it provides marginally better results than the tri-planar approach, but at the cost of a very significant increase in computational power requirement.

References in corpus (4)

• Improving neural networks by preventing co-adaptation of feature detectors
• ADADELTA: An Adaptive Learning Rate Method
• Do Deep Nets Really Need to be Deep?
• Encoding Source Language with Convolutional Neural Network for Machine Translation

Cited by in corpus (14)

• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
• Asymmetric Loss Functions and Deep Densely Connected Networks for Highly Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection
• Predictive modeling of brain tumor: A Deep learning approach
• Pancreas segmentation with probabilistic map guided bi-directional recurrent UNet
• Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
• Thickened 2D Networks for Efficient 3D Medical Image Segmentation
• Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation
• Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation
• Elastic Boundary Projection for 3D Medical Image Segmentation
• A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans
• A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images
• 3D Dense Separated Convolution Module for Volumetric Image Analysis
• Adaptive Class Weight based Dual Focal Loss for Improved Semantic Segmentation