Scalable Neural Architecture Search for 3D Medical Image Segmentation
This work addresses the challenge of efficient architecture design for 3D medical image segmentation, which is important for medical imaging applications, but it is incremental as it builds on existing NAS methods by adapting them to 3D data.
The paper tackles the problem of designing neural architectures for 3D medical image segmentation by proposing a scalable neural architecture search (NAS) framework that automatically optimizes architectures from a large design space, resulting in an automatically designed architecture that outperforms the human-designed 3D U-Net on benchmark tasks and shows good transferability.
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.