Related Experiment Video
Updated: May 26, 2025
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Comparison of intensity normalization methods in prostate, brain, and breast cancer multi-parametric magnetic
Savannah R Duenweg1, Samuel A Bobholz2, Allison K Lowman2
1Department of Biophysics, Medical College of Wisconsin, Milwaukee, WI, United States.
Objectives:
Intensity variation in multi-parametric magnetic resonance imaging (MP-MRI) is a confounding factor in MRI analyses. Previous studies have employed several normalization methods, but there is a lack of consensus on which method results in the most comparable images across vendors and acquisitions. This study used MP-MRI collected from patients with confirmed prostate, brain, or breast cancer to examine common intensity normalization methods to identify which best harmonizes intensity values across cofounds.
Materials And Methods:
Multiple normalization methods were deployed for intensity comparison between three unique sites, MR vendors, and magnetic field strength. Additionally, we calculated radiomic features before and after intensity normalization to determine how downstream analyses may be affected. Specifically, in the prostate cancer cohort, we tested these methods on T2-weighted imaging (T2WI) and additionally looked at a subset of patients who were scanned with and without the use of an endorectal coil (ERC). In a cohort of glioblastoma (GBM) patients, we tested these methods in T1 pre- and post-contrast enhancement (T1, T1C), fluid attenuated inversion recovery (FLAIR), and apparent diffusion coefficient (ADC) maps. Finally, in the breast cancer cohort, we tested methods on T1-weighted nonfat-suppressed images. All methods were compared using a two one-sided test (TOST) to test for equivalence of mean and standard deviation of intensity distributions.
Results:
While each organ had unique results, across every tested comparison, using the Z-score of intensity within a mask of the organ consistently provided an equivalent distribution (all p < 0.001).
Conclusions:
Our results suggest that intensity normalization using the Z-score of intensity within prostate, breast, and brain MR images produces the most comparable intensities between sites, MR vendors, magnetic field strength, and prostate endorectal coil usage. Likewise, Z-score normalization provided the highest percentage of radiomic features that were statistically equal across the three organs.
Insights
Z-score intensity normalization harmonizes multi-parametric MRI data across various conditions. This method ensures comparable images for prostate, brain, and breast cancer analyses, improving radiomic feature consistency.
Area of Science:
- Radiology and Medical Imaging
- Oncology
- Biomedical Engineering
Background:
- Intensity variation in multi-parametric magnetic resonance imaging (MP-MRI) poses challenges for accurate image analysis.
- Existing normalization methods lack consensus, leading to inconsistencies across different MRI vendors and acquisition settings.
- Harmonizing MRI intensity values is crucial for reliable quantitative analysis and radiomics.
Purpose of the Study:
- To evaluate common intensity normalization techniques for MP-MRI data.
- To identify the most effective method for harmonizing intensity values across diverse imaging conditions and patient cohorts.
- To assess the impact of normalization on downstream radiomic feature analysis.
Main Methods:
- MP-MRI data from prostate, brain (glioblastoma), and breast cancer patients were utilized.
- Multiple intensity normalization methods were applied and compared across different sites, MR vendors, and magnetic field strengths.
- Radiomic features were extracted before and after normalization to evaluate method performance.
- Statistical equivalence testing (TOST) was used to compare intensity distributions.
Main Results:
- Z-score normalization of intensity within an organ mask consistently yielded equivalent intensity distributions across all tested comparisons (p < 0.001).
- This method proved effective regardless of organ, site, MR vendor, magnetic field strength, or endorectal coil usage.
- Z-score normalization preserved the highest percentage of statistically equivalent radiomic features.
Conclusions:
- Intensity normalization using Z-score within an organ mask is the most effective method for harmonizing MP-MRI data.
- This approach ensures comparable image intensities across various confounding factors, including different scanners and acquisition protocols.
- Z-score normalization enhances the reliability of radiomic feature analysis in multi-parametric MRI studies for cancer imaging.
