Scalable Neural Architecture Search for 3D Medical Image Segmentation

By Sungwoong Kim, Ildoo Kim, Sungbin Lim, Woonhyuk Baek, Chiheon Kim, Hyungjoon Cho, Boogeon Yoon, Taesup Kim. 2019

84 citations recorded by the source corpus.

In this paper, a neural architecture search (NAS) framework is proposed for 3D medical image segmentation, to automatically optimize a neural architecture from a large design space. Our NAS framework searches the structure of each layer including neural connectivities and operation types in both of the encoder and decoder. Since optimizing over a large discrete architecture space is difficult due to high-resolution 3D medical images, a novel stochastic sampling algorithm based on a continuous relaxation is also proposed for scalable gradient based optimization. On the 3D medical image segmentation tasks with a benchmark dataset, an automatically designed architecture by the proposed NAS framework outperforms the human-designed 3D U-Net, and moreover this optimized architecture is well suited to be transferred for different tasks.

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. Luc Van Gool
8. Shengyu Zhao

In Neural Architecture Search & AutoML

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

Citations in the corpus

• Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation (2019, methodology): “3D U-ResNet[10] SCNAS[10] SCNAS ( transfer ) nnUnet[5] RONASMIS ( non fine-tunning )”
• Fast AutoAugment (2019, background): “Due to the remarkable successes of NAS algorithms on various computer vision tasks [19, 28, 42], several current studies also deal with automated search algorithms to obtain augmentation policies for given datasets and models.”
• 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].”
• Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis (2021, unknown): “Dice1 NSD1 Dice1 NSD1 Kim et al [25] 80.”