Related Experiment Video
Updated: Mar 29, 2026
07:13
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
Published on: October 27, 2023
1.8K
Design and Development of an Automated Pipeline for Medical Hyperspectral Image Acquisition, Processing, and Fusion
Felix Wühler1, Tim Markus Häußermann1, Alessa Rache1
1CeMOS-Research and Transfer Center, Technical University of Applied Sciences Mannheim, Paul-Wittsack-Straße 10, 68163 Mannheim, Germany.
Journal of Imaging
|March 27, 2026
Summary
This study introduces an automated pipeline for processing hyperspectral imaging data from biological tissues. Multimodal data fusion enhances anatomical structure identification, improving spectral interpretability for medical imaging research.
Area of Science:
- Medical Imaging
- Computational Biology
- Spectroscopy
Background:
- Automated processing of hyperspectral image data is crucial for research and medical technology.
- Current methods may lack comprehensive integration for biological tissue analysis.
Purpose of the Study:
- To develop and evaluate an automated pipeline for hyperspectral image processing, multimodal fusion, and data management.
- To enhance the interpretability of spectral information for biological tissue analysis.
Main Methods:
- Developed a modular Python-based pipeline for hyperspectral data acquisition, analysis, and multimodal fusion.
- Applied clustering and spectral correlation metrics to evaluate fusion performance on mouse brain tissue data.
Main Results:
- Multimodal fusion identified structures not visible in single modalities, despite a slight decrease in clustering compactness (silhouette coefficient 0.5420).
- High spectral correlation ( > 0.98) confirmed preserved spectral fidelity during fusion.
- Individual modalities showed silhouette coefficients of 0.5879 (NIR), 0.6020 (MIR), and 0.6715 (RGB).
Conclusions:
- Automated multimodal hyperspectral data fusion improves biological tissue interpretability for medical imaging.
- The pipeline offers a structured framework for preclinical hyperspectral imaging and exploratory biological analysis.
