Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation

TL;DR

Med-DANet introduces a dynamic architecture that adaptively selects models for each slice in 3D MRI segmentation, improving efficiency while maintaining or enhancing accuracy compared to existing methods.

Contribution

The paper proposes Med-DANet, a novel adaptive model selection framework for 3D MRI segmentation that reduces complexity and improves efficiency without compromising accuracy.

Findings

Achieves comparable or better segmentation accuracy than state-of-the-art methods.

Reduces model complexity and improves efficiency by up to 3.5 times.

Demonstrates effectiveness on BraTS 2019 and 2020 datasets.

Abstract

For 3D medical image (e.g. CT and MRI) segmentation, the difficulty of segmenting each slice in a clinical case varies greatly. Previous research on volumetric medical image segmentation in a slice-by-slice manner conventionally use the identical 2D deep neural network to segment all the slices of the same case, ignoring the data heterogeneity among image slices. In this paper, we focus on multi-modal 3D MRI brain tumor segmentation and propose a dynamic architecture network named Med-DANet based on adaptive model selection to achieve effective accuracy and efficiency trade-off. For each slice of the input 3D MRI volume, our proposed method learns a slice-specific decision by the Decision Network to dynamically select a suitable model from the predefined Model Bank for the subsequent 2D segmentation task. Extensive experimental results on both BraTS 2019 and 2020 datasets show that our proposed method achieves comparable or better results than previous state-of-the-art methods for 3D MRI brain tumor segmentation with much less model complexity. Compared with the state-of-the-art 3D method TransBTS, the proposed framework improves the model efficiency by up to 3.5x without sacrificing the accuracy. Our code will be publicly available soon.