Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation

By Woong Bae, Seungho Lee, Yeha Lee, Beomhee Park, Minki Chung, Kyu-Hwan Jung. 2019

47 citations recorded by the source corpus.

Neural Architecture Search (NAS), a framework which automates the task of designing neural networks, has recently been actively studied in the field of deep learning. However, there are only a few NAS methods suitable for 3D medical image segmentation. Medical 3D images are generally very large; thus it is difficult to apply previous NAS methods due to their GPU computational burden and long training time. We propose the resource-optimized neural architecture search method which can be applied to 3D medical segmentation tasks in a short training time (1.39 days for 1GB dataset) using a small amount of computation power (one RTX 2080Ti, 10.8GB GPU memory). Excellent performance can also be achieved without retraining(fine-tuning) which is essential in most NAS methods. These advantages can be achieved by using a reinforcement learning-based controller with parameter sharing and focusing on the optimal search space configuration of macro search rather than micro search. Our experiments demonstrate that the proposed NAS method outperforms manually designed networks with state-of-the-art performance in 3D medical image segmentation.

Subfields: Computer Vision and Pattern Recognition, Medical Imaging, Neural Architecture Search & AutoML

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. Chuang Gan

In Neural Architecture Search & AutoML

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

Citations in the corpus

• Deep learning based brain tumor segmentation: a survey (2020, methodology): “In the future, we anticipate the application of network architecture search for searching effective brain tumor segmentation architectures [118], [119], [120], [121].”
• Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution (2020, background): “Lately, researchers have applied neural architecture search to 3D medical image segmentation [78, 22, 72, 2, 65, 74] and 3D shape classification [34, 26].”