Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 6, 2026Annals of Biomedical EngineeringOpen Access

Supervised Learning for Collagen Segmentation in Bright-Field Histology: A Comparative Evaluation of U-Net and MLP

View Full Paper
Ask AI
Bookmark
Share

Authors

ESEvelyn R. SilvaLSLívia B. SouzaFTFernanda S. Tenorio

Discussion

Loading...

Member takes

Overview

Comparative evaluation shows Supervised Learning models segment collagen in histology, suggesting a cost-effective method for analysis.

Key Points

  • Assess the effectiveness of machine learning algorithms for collagen segmentation in histological images.
  • Analyzed 140 histological images from mice and rats stained with PicroSirius Red
  • Employed Multilayer Perceptron and U-Net for segmentation
  • Fragmented images into smaller patches and conducted non-polarized analysis
  • Both models achieved high performance, particularly in rat tendon samples
  • MLP outperformed U-Net slightly with Dice and precision exceeding 80%
  • Performance varied with lower results in mouse kidney images due to staining issues

Cite This Study

Silva et al. (2026) studied this question.

synapsesocial.com/papers/69fa8eac04f884e66b530fc8https://doi.org/10.1007/s10439-026-04155-0
View Full Paper
Ask AI
Bookmark
Share