EUVIMEDEUVIMED entdecken
Crossref

Leveraging deep learning semantic segmentation for imaging coral skeletons

Alejandra Coronel-Zegarra, Jamie L Knaub, Vivian Merk, Abhijit Pandya

Journal of Structural Biology · 2026

DOI: 10.1016/j.jsb.2026.108313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Structural Biology, 2026. Verfasst von Alejandra Coronel-Zegarra und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry and Biochemistry, Department of Ocean and Mechanical Engineering, Florida Atlantic University, Boca Raton, FL 33431, the Unit…. Hauptthemen laut MEDLINE: Deep Learning, Anthozoa, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Friedrich-Alexander-Universität Erlangen-Nürnberg, Harbor Branch Oceanographic Institute Foundation, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Micro-computed tomography and semantic segmentation provide insights into the structural hierarchy of biomineralized tissues, as exemplified by stony coral skeletons. Non-destructive imaging reveals mechanistic aspects of skeletal growth, including variations in porosity, density, and skeletal thickness across species and in the context of disease. Recent developments in semantic segmentation based on convolutional neural network models are poised to transform the streamlined analysis of large 3D tomography datasets, surpassing the performance of traditional segmentation methods. In this work, a series of U-Net deep learning models were trained and applied on exemplary micro-CT datasets from stony corals pertaining to Montastraea cavernosa and Porites astreoides species for the segmentation of pores and skeleton. The models were statistically evaluated, revealing that Attention U-Net was the top performer with respect to computational efficiency, accuracy, and generalizability, followed by U-Net++ and standard U-Net. Our analysis highlights accuracy limitations of U-Net-based deep learning segmentations that can result in false-positive or false-negative classifications. The segmented 3D models were utilized to perform porosity, bulk density, and thickness analyses of each dataset, revealing quantitative differences between the two species, as well as between healthy and stony coral tissue loss disease afflicted M. cavernosa coral skeletons. This work provides a framework for streamlined training and deployment of deep learning models for semantic segmentation of calcified tissues that inform our understanding of skeletogenesis and growth patterns across species and pathogenesis contexts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAnthozoaImage Processing, Computer-AssistedAnimalsX-Ray MicrotomographyImaging, Three-DimensionalConvolutional Neural Networks

Stichwörter der Autor:innen

BiomineralConvolutional neural networksDeep learningImage segmentationMorphogenesisX-ray tomography

Autor:innen und Institutionen

  • Department of Chemistry and Biochemistry, Department of Ocean and Mechanical Engineering, Florida Atlantic University, Boca Raton, FL 33431, the United States of America.
  • FAU Lab Schools, Florida Atlantic University, Boca Raton, FL 33431, the United States of America.
  • Department of Chemistry and Biochemistry, Department of Ocean and Mechanical Engineering, Florida Atlantic University, Boca Raton, FL 33431, the United States of America. Electronic address: vmerk@fau.edu.
  • Department of Electrical Engineering and Computer Science, Department of Biomedical Engineering, Florida Atlantic University, Boca Raton, FL 33431, the United States of America.

Förderung

  • Friedrich-Alexander-Universität Erlangen-Nürnberg
  • Harbor Branch Oceanographic Institute Foundation
  • National Science Foundation
  • Florida Atlantic University
  • Florida Fish and Wildlife Conservation Commission
  • Biology Department, Gannon University
  • Division of Materials Research

Zitieren

APA

Coronel-Zegarra, A., Knaub, J. L., Merk, V., & Pandya, A. (2026). Leveraging deep learning semantic segmentation for imaging coral skeletons. Journal of Structural Biology. https://doi.org/10.1016/j.jsb.2026.108313

Vancouver

Coronel-Zegarra A, Knaub JL, Merk V, Pandya A. Leveraging deep learning semantic segmentation for imaging coral skeletons. Journal of Structural Biology. 2026. doi:10.1016/j.jsb.2026.108313

BibTeX
@article{CoronelZegarra2026,
  author = {Coronel-Zegarra, Alejandra and Knaub, Jamie L and Merk, Vivian and Pandya, Abhijit},
  title = {Leveraging deep learning semantic segmentation for imaging coral skeletons},
  journal = {Journal of Structural Biology},
  year = {2026},
  doi = {10.1016/j.jsb.2026.108313}
}
Kostenlos starten →