Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation

TL;DR

This paper introduces an automated reinforcement learning-based method to optimize training strategies for 3D medical image segmentation, improving baseline models and achieving competitive accuracy with manual tuning.

Contribution

It presents a novel reinforcement learning approach for automatic hyper-parameter tuning and data augmentation selection in 3D medical image segmentation.

Findings

Performance of baseline models improved after searching.

Achieved accuracy comparable to manual state-of-the-art methods.

Validated on multiple 3D segmentation tasks.

Abstract

Deep neural network (DNN) based approaches have been widely investigated and deployed in medical image analysis. For example, fully convolutional neural networks (FCN) achieve the state-of-the-art performance in several applications of 2D/3D medical image segmentation. Even the baseline neural network models (U-Net, V-Net, etc.) have been proven to be very effective and efficient when the training process is set up properly. Nevertheless, to fully exploit the potentials of neural networks, we propose an automated searching approach for the optimal training strategy with reinforcement learning. The proposed approach can be utilized for tuning hyper-parameters, and selecting necessary data augmentation with certain probabilities. The proposed approach is validated on several tasks of 3D medical image segmentation. The performance of the baseline model is boosted after searching, and it can achieve comparable accuracy to other manually-tuned state-of-the-art segmentation approaches.