Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
This work addresses the challenge of efficiently training neural networks for medical image segmentation, offering an automated solution that reduces manual tuning efforts, though it is incremental as it builds on existing baseline models.
The authors tackled the problem of optimizing training strategies for 3D medical image segmentation by proposing an automated approach using reinforcement learning to search for hyper-parameters and data augmentation, which boosted baseline model performance to achieve comparable accuracy to manually-tuned state-of-the-art methods.
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.