EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Ultrastructural Morphometry of Mitochondria: Comparison Between Conventional Operator‐Dependent and Artificial Intelligence ( AI )‐Operated Machine Learning Methods

Daniele Nosi, Daniele Guasti, Alessia Tani, Sara Germano, Daniele Bani iD

Microscopy Research and Technique · 2025-09 · 88 (9) · 2375-2380

DOI: 10.1002/jemt.24866 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Microscopy Research and Technique, online erschienen am 29.03.2025. Verfasst von Daniele Nosi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Imaging Platform, Dept. Experimental & Clinical Medicine, University of Florence, Florence, Italy. Hauptthemen laut MEDLINE: Mitochondria, Microscopy, Electron, Transmission, Machine Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Università degli Studi di Firenze.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Morphometric analysis of digital images is fundamental to substantiate the visual observations with objective quantitative data suitable for statistical analysis. The recent advances in artificial intelligence (AI) have allowed the development of machine learning (ML) protocols for automated morphometry. Transmission electron microscopy (TEM) morphometry requires that the ultrastructural details be recognized and interpreted by a trained observer; this makes adapting AI‐operated protocols to TEM particularly challenging. In this study, we have checked the accuracy of the results of mitochondrial morphometry yielded by a ML method by comparison with those obtained manually by a trained observer on the same TEM micrographs (magnification ×50,000) of cultured cells with different energy metabolism (overall n = 26). The measured parameter was the ratio between the total length of the mitochondrial cristae and the corresponding mitochondrial surface area (C/A ratio), directly related to mitochondrial function. No statistically significant correlation (Pearson's test) was found between the two methods in any of the experiments. Only in a few micrographs were the values similar ( n = 3) or very close ( n = 2) to be comprised within the s.e.m. of their experimental group. Moreover, as judged by the s.d. comparison, the scatter of values was more prominent with the ML‐operated than with the manual method. Conceivably, this outcome is because many ultrastructural details of the cell organelles are similar, for example, the membrane section profiles, and can only be properly recognized and distinguished by an experienced observer, while the current ML protocols still cannot.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MitochondriaMicroscopy, Electron, TransmissionMachine LearningImage Processing, Computer-AssistedArtificial IntelligenceHumansAnimals

Stichwörter der Autor:innen

machine learningmitochondriamorphometryultrastructure

Autor:innen und Institutionen

  • Imaging Platform, Dept. Experimental & Clinical Medicine, University of Florence, Florence, Italy.

ORCID-Profile: Daniele Bani

Förderung

  • Università degli Studi di Firenze

Zitieren

APA

Nosi, D., Guasti, D., Tani, A., Germano, S., & Bani, D. (2025). Ultrastructural Morphometry of Mitochondria: Comparison Between Conventional Operator‐Dependent and Artificial Intelligence ( AI )‐Operated Machine Learning Methods. Microscopy Research and Technique, 88(9), 2375-2380. https://doi.org/10.1002/jemt.24866

Vancouver

Nosi D, Guasti D, Tani A, Germano S, Bani D. Ultrastructural Morphometry of Mitochondria: Comparison Between Conventional Operator‐Dependent and Artificial Intelligence ( AI )‐Operated Machine Learning Methods. Microscopy Research and Technique. 2025;88(9):2375-2380. doi:10.1002/jemt.24866

BibTeX
@article{Nosi2025,
  author = {Nosi, Daniele and Guasti, Daniele and Tani, Alessia and Germano, Sara and Bani, Daniele},
  title = {Ultrastructural Morphometry of Mitochondria: Comparison Between Conventional Operator‐Dependent and Artificial Intelligence ( AI )‐Operated Machine Learning Methods},
  journal = {Microscopy Research and Technique},
  year = {2025},
  volume = {88},
  number = {9},
  pages = {2375--2380},
  doi = {10.1002/jemt.24866}
}
Kostenlos starten →