Related Experiment Video
Updated: Mar 18, 2026
04:25
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
4.0K
BIANCA (Brain Intensity AbNormality Classification Algorithm): A new tool for automated segmentation of white matter
Ludovica Griffanti1, Giovanna Zamboni2, Aamira Khan1
1Centre for the Functional MRI of the Brain (FMRIB), Nuffield Department of Clinical Neurosciences, University of Oxford, UK.
Neuroimage
|July 13, 2016
Summary
BIANCA is a new automated method for detecting white matter hyperintensities (WMHs) on MRI scans. This reliable tool offers a valid alternative to manual segmentation for large studies.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Neurology
Background:
- White matter hyperintensities (WMHs) of presumed vascular origin are common MRI findings in various neurological and vascular disorders, as well as in healthy aging.
- Accurate quantification of WMHs is crucial for understanding their role in disease and aging.
- Existing manual segmentation methods are time-consuming and prone to inter-rater variability.
Purpose of the Study:
- To introduce BIANCA (Brain Intensity AbNormality Classification Algorithm), a fully automated, supervised method for WMH detection and quantification.
- To evaluate the performance, flexibility, and reproducibility of BIANCA compared to manual segmentation and existing methods.
- To provide a reliable tool for large-scale neuroimaging studies.
Main Methods:
- BIANCA utilizes a k-nearest neighbour (k-NN) algorithm with customizable options for spatial information weighting and training point selection.
- The algorithm is multimodal and adaptable to different MRI protocols and user needs.
- Optimization and validation were performed on two distinct patient cohorts ('predominantly neurodegenerative' and 'predominantly vascular') using manual WMH segmentation as a reference.
Main Results:
- BIANCA demonstrated good overlap and volumetric agreement with manual WMH segmentations after optimization.
- WMH volume estimates from BIANCA showed strong correlations with visual ratings and participant age.
- Reproducibility tests confirmed the robustness of BIANCA, and performance comparisons indicated it is a reliable alternative to existing methods.
Conclusions:
- BIANCA is a reliable and automated method for segmenting white matter hyperintensities.
- Its flexibility and accuracy make it suitable for large cross-sectional cohort studies.
- BIANCA will be freely available as part of the FSL package, promoting wider adoption in research.
