Related Experiment Videos
Artificial Second Harmonic Generation Image Feature Tuning with Generative Models and SeFa Semantic Analysis
Melissa Champer1, Vikas Singh2, Paul Campagnola1
1Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI.
Jphys Photonics
|July 17, 2026
Summary
This study adapted StyleGAN2-ADA-SHG for analyzing collagen fiber morphology in Second Harmonic Generation (SHG) microscopy images. The model generates realistic images, aiding in disease-related collagen structure analysis.
Area of Science:
- Biomedical Imaging
- Computational Biology
- Materials Science
Background:
- Collagen fiber morphology changes in diseases like cancer.
- Second Harmonic Generation (SHG) microscopy visualizes fibrillar collagen.
- Deep learning methods can analyze microscopy data.
Purpose of the Study:
- Adapt StyleGAN2-ADA-SHG for SHG data analysis.
- Extract information on collagen fiber morphology.
- Develop tools for SHG image analysis and editing.
Main Methods:
- Trained StyleGAN2-ADA-SHG on 1,319 SHG images.
- Utilized Semantic Factorization (SeFa) to identify morphological features.
- Quantified fiber morphology using CT-Fire and CurveAlign.
- Tested encoder-based and LPIPS methods for image editing.
Main Results:
- StyleGAN2-ADA-SHG generated novel SHG images perceptually similar to training data.
- Identified two key semantics correlating with fiber morphology.
- Encoder-based image editing outperformed LPIPS.
- Developed an extensible framework for SHG image analysis.
Conclusions:
- StyleGAN2-ADA-SHG is suitable for analyzing SHG microscopy data.
- The developed tools can aid in understanding disease-related collagen changes.
- Future refinements can enable creation of disease-specific collagen fiber images.