Automatic segmentation and reconstruction of intracellular compartments in volumetric electron microscopy data.

Deep learning Electron microscopy Fusiform vesicles Golgi apparatus Instance segmentation Intracellular compartments Mitochondria Reconstruction Urothelium

Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
Aug 2022
Historique:
received: 08 03 2021
revised: 02 02 2022
accepted: 14 06 2022
pubmed: 29 6 2022
medline: 10 8 2022
entrez: 28 6 2022
Statut: ppublish

Résumé

In recent years, electron microscopy is enabling the acquisition of volumetric data with resolving power to directly observe the ultrastructure of intracellular compartments. New insights and knowledge about cell processes that are offered by such data require a comprehensive analysis which is limited by the time-consuming manual segmentation and reconstruction methods. We present methods for automatic segmentation, reconstruction, and analysis of intracellular compartments from volumetric data obtained by the dual-beam electron microscopy. We specifically address segmentation of fusiform vesicles and the Golgi apparatus, reconstruction of mitochondria and fusiform vesicles, and morphological analysis of the reconstructed mitochondria. Evaluation on the public UroCell dataset demonstrated high accuracy of the proposed methods for segmentation of fusiform vesicles and the Golgi apparatus, as well as for reconstruction of mitochondria and analysis of their shapes, while reconstruction of fusiform vesicles proved to be more challenging. We published an extension of the UroCell dataset with all of the data used in this work, to further contribute to research on automatic analysis of the ultrastructure of intracellular compartments.

Sections du résumé

BACKGROUND AND OBJECTIVES OBJECTIVE
In recent years, electron microscopy is enabling the acquisition of volumetric data with resolving power to directly observe the ultrastructure of intracellular compartments. New insights and knowledge about cell processes that are offered by such data require a comprehensive analysis which is limited by the time-consuming manual segmentation and reconstruction methods.
METHOD METHODS
We present methods for automatic segmentation, reconstruction, and analysis of intracellular compartments from volumetric data obtained by the dual-beam electron microscopy. We specifically address segmentation of fusiform vesicles and the Golgi apparatus, reconstruction of mitochondria and fusiform vesicles, and morphological analysis of the reconstructed mitochondria.
RESULTS AND CONCLUSION CONCLUSIONS
Evaluation on the public UroCell dataset demonstrated high accuracy of the proposed methods for segmentation of fusiform vesicles and the Golgi apparatus, as well as for reconstruction of mitochondria and analysis of their shapes, while reconstruction of fusiform vesicles proved to be more challenging. We published an extension of the UroCell dataset with all of the data used in this work, to further contribute to research on automatic analysis of the ultrastructure of intracellular compartments.

Identifiants

pubmed: 35763876
pii: S0169-2607(22)00341-8
doi: 10.1016/j.cmpb.2022.106959
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

106959

Informations de copyright

Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of Competing Interest Authors declare that they have no conflict of interest.

Auteurs

Manca Žerovnik Mekuč (M)

Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, Ljubljana 1000, Slovenia. Electronic address: manca.zerovnik-mekuc@fri.uni-lj.si.

Ciril Bohak (C)

Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, Ljubljana 1000, Slovenia; Visual Computing Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia. Electronic address: ciril.bohak@fri.uni-lj.si.

Eva Boneš (E)

Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, Ljubljana 1000, Slovenia. Electronic address: eb1690@student.uni-lj.si.

Samo Hudoklin (S)

Institute of Cell Biology, Faculty of Medicine, University of Ljubljana, Vrazov trg 2, Ljubljana 1000, Slovenia. Electronic address: samo.hudoklin@mf.uni-lj.si.

Rok Romih (R)

Institute of Cell Biology, Faculty of Medicine, University of Ljubljana, Vrazov trg 2, Ljubljana 1000, Slovenia. Electronic address: rok.romih@mf.uni-lj.si.

Matija Marolt (M)

Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, Ljubljana 1000, Slovenia; Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, Ljubljana 1000, Slovenia. Electronic address: matija.marolt@fri.uni-lj.si.

Articles similaires

1.00
Humans Magnetic Resonance Imaging Brain Infant, Newborn Infant, Premature
Cephalometry Humans Anatomic Landmarks Software Internet
Humans Artificial Intelligence Neoplasms Prognosis Image Processing, Computer-Assisted
Humans Breast Neoplasms Female Deep Learning Ultrasonography, Mammary

Classifications MeSH