CVApr 16, 2021

Advanced Deep Networks for 3D Mitochondria Instance Segmentation

arXiv:2104.07961v423 citationsHas Code
Originality Synthesis-oriented
AI Analysis

This work addresses a domain-specific problem in biomedical imaging for researchers studying mitochondria, but it is incremental as it builds on existing deep learning methods.

The paper tackles 3D mitochondria instance segmentation from electron microscopy images by proposing two advanced deep networks, Res-UNet-R and Res-UNet-H, which achieved first place in the ISBI 2021 challenge.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes