# Scalable Neural Architecture Search for 3D Medical Image Segmentation

## TL;DR

This paper introduces a scalable neural architecture search framework tailored for 3D medical image segmentation, enabling automatic design of efficient neural networks that outperform human-designed models and transfer well across tasks.

## Contribution

The paper presents a novel NAS framework with a stochastic sampling algorithm for high-resolution 3D images, optimizing both layer structure and connectivity.

## Key findings

- Automatically designed architecture outperforms 3D U-Net
- Optimized architecture transfers effectively across tasks
- Scalable gradient-based optimization for large search spaces

## Abstract

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.