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

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Automatic segmentation of fibrosis in histological images of tissues stained with Picrosirius red using supervised and unsupervised machine learning algorithms2024
  2. 2Machine learning for automated classification of lung collagen in a urethane-induced lung injury mouse model2024 · 2 citations
  3. 3Detection of collagen band–associated regions in H&E-stained colonic biopsies of collagenous colitis patients using superpixel-based feature extraction and neural network classification2026
  4. 4Automated Segmentation of Hepatic Vessels and Lobules in Whole-Slide Images Using U-Net Models2025
  5. 5Improved Segmentation of Cellular Nuclei Using UNET Architectures for Enhanced Pathology Imaging2024 · 6 citations