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

By Dong Yang, Holger R. Roth, Ziyue Xu, Fausto Milletarì, Ling Zhang, Daguang Xu. 2019

50 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Reinforcement Learning, Medical Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Song Han
2. Ji Lin
3. Zhijian Liu
4. Yujun Lin
5. Hanrui Wang
6. Haotian Tang
7. Shengyu Zhao
8. Daguang Xu

In Reinforcement Learning

1. Song Han
2. Hanrui Wang
3. Ji Lin
4. Zhijian Liu

In Medical Imaging

1. Xiaosong Wang
2. Andriy Myronenko

Citations in the corpus

• Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution (2020, methodology): “st of these methods are tailored for 2D visual recognition, which has many well-dened search spaces [44]. Lately, researchers have applied neural architecture search to 3D medical image segmentation [78,22,72,2,65,74] and 3D shape classication [34,26]. However, they are not directly applicable to 3D”
• Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation (2020, methodology): “Recently, we proposed a reinforcement learning-based searching approach for selecting necessary data augmentations in 3D medical image segmentation tasks [28].”