Related Experiment Video
Updated: Oct 18, 2025
11:05
Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery
Published on: September 19, 2014
12.4K
VNIR-NIR hyperspectral imaging fusion targeting intraoperative brain cancer detection
Raquel Leon1, Himar Fabelo2, Samuel Ortega3,4
1Institute for Applied Microelectronics, University of Las Palmas de Gran Canaria, 35017, Las Palmas de Gran Canaria, Spain. slmartin@iuma.ulpgc.es.
Scientific Reports
|October 5, 2021
Summary
Hyperspectral (HS) imaging fusion enhances brain tumor resection by combining visual and near-infrared data. This novel technique improves tumor tissue classification accuracy during surgery.
Area of Science:
- Medical imaging
- Neurosurgery
- Optical engineering
Background:
- Current intraoperative guidance tools for brain tumor resection have limitations.
- Hyperspectral (HS) imaging offers potential for real-time tumor delineation.
- Existing HS acquisition systems face challenges with spatial and spectral resolution.
Purpose of the Study:
- To develop and evaluate an intraoperative HS image fusion system for brain tumor resection.
- To improve spatial and spectral resolution of HS data for better tumor delineation.
- To assess the impact of fused HS data on tumor classification accuracy.
Main Methods:
- Integrated two push-broom HS cameras (VNIR [400-1000 nm] and NIR [900-1700 nm]) into an intraoperative system.
- Employed intensity-based and feature-based registration with geometric transformations for HS image fusion.
- Acquired four HS datasets to validate registration and fusion processes.
- Evaluated segmentation and classification methods using VNIR, NIR, and fused data.
Main Results:
- Successfully fused VNIR and NIR HS data into a wide spectral range cube [435-1638 nm].
- Image fusion significantly improved classification accuracy compared to individual modalities.
- Classification accuracy improved by up to 21% using fused VNIR-NIR data.
Conclusions:
- The proposed HS image fusion methodology enhances intraoperative brain tumor delineation.
- Fused HS data provides superior performance for tumor classification in neurosurgery.
- This technique represents a significant advancement in surgical guidance systems.
