loading page

Automated Segmentation of Cell Organelles in volume electron microscopy using Deep Learning
  • +10
  • Nebojša Nešić,
  • Xavier Heiligenstein,
  • Lydia Zopf,
  • Valentin Blüml,
  • Katharina S. Keuenhof,
  • Michael Wagner,
  • Johanna L. Höög,
  • Heng Qi,
  • Zhiyang Li,
  • Georgios Tsaramirsis,
  • Christopher J. Peddie,
  • Miloš Stojmenović,
  • Andreas Walter
Nebojša Nešić
Univerzitet Singidunum
Author Profile
Xavier Heiligenstein
CryoCapCell
Author Profile
Lydia Zopf
BioImaging Austria
Author Profile
Valentin Blüml
BioImaging Austria
Author Profile
Katharina S. Keuenhof
Goteborgs universitet Institutionen for kemi och molekylarbiologi
Author Profile
Michael Wagner
Aalen University of Applied Sciences
Author Profile
Johanna L. Höög
Goteborgs universitet Institutionen for kemi och molekylarbiologi
Author Profile
Heng Qi
Dalian University of Technology
Author Profile
Zhiyang Li
Dalian Maritime University
Author Profile
Georgios Tsaramirsis
Higher Colleges of Technology
Author Profile
Christopher J. Peddie
The Francis Crick Institute
Author Profile
Miloš Stojmenović
Univerzitet Singidunum
Author Profile
Andreas Walter
Aalen University of Applied Sciences

Corresponding Author:andreas.walter@hs-aalen.de

Author Profile

Abstract

Recent advances in computing power triggered the use of Artificial Intelligence in image analysis in life sciences. To train these algorithms, a large enough set of certified labelled data is required. The trained neural network is then capable of producing accurate instance segmentation results, that will then need to be re-assembled into the original dataset: the entire process requires substantial expertise and time to achieve quantifiable results. To speed-up the process, from cell organelle detection to quantification across modalities, we propose a deep learning based approach for Fast AutoMatic Outline Segmentation (FAMOUS), that involves organelle detection combined with image morphology, and 3D meshing to automatically segment, visualize and quantify cell organelles within volume electron microscopy datasets. From start to finish, FAMOUS provides full segmentation results within a week on previously unseen datasets. FAMOUS was showcased on a dataset acquired using a focused ion beam scanning electron microscope (FIBSEM), and on yeast cells acquired by transmission electron microscopy.
24 Oct 2023Submitted to Microscopy Research and Technique
15 Nov 2023Submission Checks Completed
15 Nov 2023Assigned to Editor
19 Nov 2023Review(s) Completed, Editorial Evaluation Pending
19 Nov 2023Reviewer(s) Assigned
05 Feb 20241st Revision Received
06 Feb 2024Submission Checks Completed
06 Feb 2024Assigned to Editor
06 Feb 2024Review(s) Completed, Editorial Evaluation Pending
26 Feb 2024Editorial Decision: Accept