Advanced Deep Networks for 3D Mitochondria Instance Segmentation

TL;DR

This paper introduces two advanced deep learning networks, Res-UNet-R and Res-UNet-H, that significantly improve 3D mitochondria segmentation accuracy in electron microscopy images, achieving top performance in a major challenge.

Contribution

The paper presents novel anisotropic convolution blocks and a multi-scale training strategy, enhancing segmentation performance and model generalizability for 3D mitochondria instance segmentation.

Findings

Achieved first place in ISBI 2021 challenge

Improved segmentation accuracy with anisotropic convolution and multi-scale training

Enhanced model robustness through denoising pre-processing

Abstract

Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods. In this paper, we propose two advanced deep networks, named Res-UNet-R and Res-UNet-H, for 3D mitochondria instance segmentation from Rat and Human samples. Specifically, we design a simple yet effective anisotropic convolution block and deploy a multi-scale training strategy, which together boost the segmentation performance. Moreover, we enhance the generalizability of the trained models on the test set by adding a denoising operation as pre-processing. In the Large-scale 3D Mitochondria Instance Segmentation Challenge at ISBI 2021, our method ranks the 1st place. Code is available at https://github.com/Limingxing00/MitoEM2021-Challenge.