Convolutional neural networks for medical image segmentation

TL;DR

This paper reviews convolutional neural networks (CNNs) for medical image segmentation, focusing on architecture, data sampling, and historical evolution, highlighting key models like FCN, U-Net, and DeepMedic.

Contribution

It provides a comprehensive overview of CNN architectures and their development for medical image segmentation, emphasizing the relationship between different models.

Findings

Analysis of CNN architecture components

Insights into sampling strategies for segmentation

Historical comparison of key CNN models

Abstract

In this article, we look into some essential aspects of convolutional neural networks (CNNs) with the focus on medical image segmentation. First, we discuss the CNN architecture, thereby highlighting the spatial origin of the data, voxel-wise classification and the receptive field. Second, we discuss the sampling of input-output pairs, thereby highlighting the interaction between voxel-wise classification, patch size and the receptive field. Finally, we give a historical overview of crucial changes to CNN architectures for classification and segmentation, giving insights in the relation between three pivotal CNN architectures: FCN, U-Net and DeepMedic.