Related Experiment Video
Updated: Jan 24, 2026

DIPLOMA Approach for Standardized Pathology Assessment of Distal Pancreatectomy Specimens
Published on: February 1, 2020
Pathology-preserving intensity standardization framework for multi-institutional FLAIR MRI datasets
Brittany Reiche1, A R Moody2, April Khademi3
1School of Engineering, University of Guelph, Guelph, Canada.
Abstract:
Fluid-Attenuated Inversion Recovery (FLAIR) MRI are used by physicians to analyze white matter lesions (WML) of the brain, which are related to neurodegenerative diseases such as dementia and vascular disease. To study the causes and progression of these diseases, multi-centre (MC) studies are conducted, with images acquired and analyzed from multiple institutions. Due to differences in acquisition software and hardware, there is variability in image properties, which creates challenges for automated algorithms. This work explores this variability, known as the MC effect, by analyzing nearly 5000 MC FLAIR volumes and proposes an intensity standardization framework to normalize intensity non-standardness in FLAIR MRI, while ensuring the appearance of WML. Results show that original image characteristics varied significantly between scanner vendors and centres, and that this variability was reduced with standardization. To further highlight the utility of intensity standardization, a threshold-based brain extraction algorithm is implemented and compared with a classifier-based approach. A competitive Dice Similarity Coefficient of 81% was achieved on 183 volumes, demonstrating that optimized pre-processing can effectively reduce the variability in MC studies, allowing for simplified algorithms to be applied on large datasets robustly.
Insights
Multi-centre studies analyzing brain white matter lesions (WML) using Fluid-Attenuated Inversion Recovery (FLAIR) MRI face image variability. This study introduces an intensity standardization framework to reduce this multi-centre effect, improving automated analysis.
Area of Science:
- Medical Imaging
- Neuroimaging
- Radiology
Background:
- Fluid-Attenuated Inversion Recovery (FLAIR) MRI is crucial for analyzing brain white matter lesions (WML) associated with neurodegenerative diseases.
- Multi-centre (MC) studies are essential for understanding disease progression but suffer from image variability due to diverse acquisition parameters.
- This variability, termed the MC effect, poses significant challenges for automated image analysis algorithms.
Purpose of the Study:
- To investigate the variability in FLAIR MRI image properties across different institutions and scanner vendors in multi-centre studies.
- To propose and evaluate an intensity standardization framework to mitigate the MC effect in FLAIR MRI.
- To demonstrate the impact of intensity standardization on the performance of automated algorithms, such as brain extraction.
Main Methods:
- Analysis of approximately 5000 multi-centre FLAIR MRI volumes to characterize image property variability.
- Development and application of an intensity standardization framework designed to normalize FLAIR MRI intensities while preserving white matter lesion appearance.
- Implementation and comparison of a threshold-based brain extraction algorithm against a classifier-based approach on standardized and original data.
Main Results:
- Significant variations in image characteristics were observed across different scanner vendors and centres in the original FLAIR MRI data.
- The proposed intensity standardization framework effectively reduced the observed variability between centres and vendors.
- The threshold-based brain extraction algorithm achieved a competitive Dice Similarity Coefficient of 81% on 183 volumes after intensity standardization.
Conclusions:
- Intensity non-standardness in multi-centre FLAIR MRI studies is a significant issue that impacts automated analysis.
- The developed intensity standardization framework successfully reduces multi-centre variability, enabling more robust and simplified automated algorithms.
- Optimized pre-processing through intensity standardization enhances the reliability of large-scale neuroimaging studies for analyzing white matter lesions.
Related Concept Videos
Sound Intensity
Measurement: Standard Units
Sound Intensity Level
The human ear can perceive an extensive range of sound intensity, necessitating the use of the logarithmic scale to define a physical quantity—the intensity level. It is a ratio of two intensities and...
Intensity Of Electromagnetic Waves
Standard Enthalpy of Formation
Standard Electrode Potentials

