loading page

Current Progress and Challenges in Large-scale3D Mitochondria Instance Segmentation
  • +24
  • Daniel Franco-Barranco ,
  • Zudi Lin ,
  • Won-Dong Jang ,
  • Xueying Wang ,
  • Qijia Shen ,
  • Wenjie Yin ,
  • Yutian Fan ,
  • Mingxing Li ,
  • Chang Chen ,
  • Zhiwei Xiong ,
  • Rui Xin ,
  • Hao Liu ,
  • Huai Chen ,
  • Zhili Li ,
  • Jie Zhao ,
  • Xuejin Chen ,
  • Constantin Pape ,
  • Ryan Conrad ,
  • Jozefus De Folter ,
  • Luke Nightingale ,
  • Martin Jones ,
  • Yanling Liu ,
  • Dorsa Ziaei ,
  • Stephan Huschauer ,
  • Ignacio Arganda-Carreras ,
  • Hanspeter Pfister ,
  • Donglai Wei
Daniel Franco-Barranco
Donostia International Physics Center, Donostia International Physics Center

Corresponding Author:[email protected]

Author Profile
Won-Dong Jang
Author Profile
Xueying Wang
Author Profile
Qijia Shen
Author Profile
Wenjie Yin
Author Profile
Yutian Fan
Author Profile
Mingxing Li
Author Profile
Chang Chen
Author Profile
Zhiwei Xiong
Author Profile
Huai Chen
Author Profile
Xuejin Chen
Author Profile
Constantin Pape
Author Profile
Ryan Conrad
Author Profile
Jozefus De Folter
Author Profile
Luke Nightingale
Author Profile
Martin Jones
Author Profile
Yanling Liu
Author Profile
Dorsa Ziaei
Author Profile
Stephan Huschauer
Author Profile
Ignacio Arganda-Carreras
Author Profile
Hanspeter Pfister
Author Profile
Donglai Wei
Author Profile

Abstract

In this paper, we present the results of the MitoEM challenge on mitochondria 3D instance segmentation from electron microscopy images, organized in conjunction with the IEEE-ISBI 2021 conference. Our benchmark dataset consists of two large-scale 3D volumes, one from human and one from rat cortex tissue, which are 3,600 times larger than previously used datasets. At the time of paper submission, 257 participants had registered for the challenge, 14 teams had submitted their results, and six teams participated in the challenge workshop. Here, we present eight top-performing approaches from the challenge participants, along with our own baseline strategies. Posterior to the challenge, annotation errors in the ground truth were corrected without altering the final ranking. Although several of the top methods are compared favorably to our own baselines, substantial errors remain unsolved for mitochondria with challenging morphologies. Thus, the challenge remains open for submission and automatic evaluation, with all volumes available for download. Additionally, we present a retrospective evaluation of the scoring system performed using TIMISE, our novel open-source evaluation toolbox, which revealed that (1) the challenge metric was permissive with the false positive predictions and (2) the size-based grouping of instances did not correctly categorize mitochondria of interest. Thus, we propose a new scoring system that better reflects the correctness of the segmentation results.
2023Published in IEEE Transactions on Medical Imaging on pages 1-1. 10.1109/TMI.2023.3320497