Related Experiment Video
Updated: Aug 19, 2025
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
Segmentation and differentiation of periventricular and deep white matter hyperintensities in 2D T2-FLAIR MRI based
Tan Gong1, Hualu Han2, Zheng Tan1
1Department of Biomedical Engineering, Beijing Institute of Technology School of Life Science, Beijing, China.
Background:
White matter hyperintensities (WMHs) are a subtype of cerebral small vessel disease and can be divided into periventricular WMHs (pvWMHs) and deep WMHs (dWMHs). pvWMHs and dWMHs were proved to be determined by different etiologies. This study aimed to develop a 2D Cascade U-net (Cascade U) for the segmentation and differentiation of pvWMHs and dWMHs on 2D T2-FLAIR images.
Methods:
A total of 253 subjects were recruited in the present study. All subjects underwent 2D T2-FLAIR scan on a 3.0 Tesla MR scanner. Both contours of pvWMHs and dWMHs were manually delineated by the observers and considered as the gold standard. Fazekas scale was used to evaluate the burdens of pvWMHs and dWMHs, respectively. Cascade U consisted of a segmentation U-net and a differentiation U-net and was trained with a combined loss function. The performance of Cascade U was compared with two other U-net models (Pipeline U and Separate U). Dice similarity coefficient (DSC), Matthews correlation coefficient (MCC), precision, and recall were used to evaluate the performances of all models. The linear correlations between WMHs volume (WMHV) measured by all models and the gold standard were also conducted.
Results:
Compared with other models, Cascade U exhibited a better performance on WMHs segmentation and pvWMHs identification. Cascade U achieved DSC values of 0.605 ± 0.135, 0.517 ± 0.263, and 0.510 ± 0.241 and MCC values of 0.617 ± 0.122, 0.526 ± 0.263, and 0.522 ± 0.243 on the segmentation of total WMHs, pvWMHs, and dWMHs, respectively. Cascade U exhibited strong correlations with the gold standard on measuring WMHV (R2 = 0.954, p < 0.001), pvWMHV (R2 = 0.933, p < 0.001), and dWMHV (R2 = 0.918, p < 0.001). A significant correlation was found on lesion volume between Cascade U and gold standard (r > 0.510, p < 0.001).
Conclusion:
Cascade U showed competitive results in segmentation and differentiation of pvWMHs and dWMHs on 2D T2-FLAIR images, indicating potential feasibility in precisely evaluating the burdens of WMHs.
Insights
A novel 2D Cascade U-net model accurately segments and differentiates periventricular (pvWMHs) and deep (dWMHs) white matter hyperintensities. This AI approach shows promise for precisely evaluating white matter hyperintensities burdens in patients.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Neurology
Background:
- White matter hyperintensities (WMHs) are a key indicator of cerebral small vessel disease.
- Periventricular WMHs (pvWMHs) and deep WMHs (dWMHs) have distinct etiologies.
- Accurate differentiation of WMH subtypes is crucial for understanding disease progression.
Purpose of the Study:
- To develop and evaluate a 2D Cascade U-net (Cascade U) model.
- To segment and differentiate pvWMHs and dWMHs from 2D T2-FLAIR images.
- To compare Cascade U's performance against other U-net models.
Main Methods:
- A total of 253 subjects underwent 2D T2-FLAIR MRI scans.
- Manual delineation by observers served as the gold standard for WMH segmentation.
- Cascade U, comprising segmentation and differentiation U-nets, was trained and validated.
Main Results:
- Cascade U demonstrated superior performance in WMH segmentation and pvWMH identification compared to other models.
- Achieved Dice Similarity Coefficients (DSC) of 0.605 for total WMHs, 0.517 for pvWMHs, and 0.510 for dWMHs.
- Showed strong correlations with the gold standard for WMH volume measurements (R² > 0.918).
Conclusions:
- The 2D Cascade U-net model offers competitive results for segmenting and differentiating WMH subtypes.
- This AI-driven approach shows potential for precise evaluation of WMH burdens.
- Further validation may support its clinical application in assessing cerebral small vessel disease.
