🤖 AI Summary
This study addresses the diagnostic challenge posed by the similar imaging appearances of white matter hyperintensities (WMHs) in vascular and demyelinating diseases. To improve differential diagnosis, the authors propose an integrated segmentation-and-classification framework. First, they achieve precise WMH segmentation using an Attention U-Net enhanced with BAM/CBAM attention mechanisms, 2.5D input representation, and a patch-based training strategy. Subsequently, morphological features derived from the segmentation masks are employed to drive lesion-type classification. This work is the first to synergistically combine these attention modules with a 2.5D patch approach for WMH segmentation. The method demonstrates significantly improved generalization and etiological discrimination performance across five multi-protocol public MRI datasets.
📝 Abstract
White Matter Hyperintensities (WMHs) are commonly observed in brain Magnetic Resonance Imaging (MRI) scans. They are associated with various neurological conditions, including vascular and inflammatory demyelinating diseases. Despite differing in etiology, WMHs from these conditions often appear similar on Fluid Attenuated Inversion Recovery (FLAIR) images. This similarity makes differential diagnosis challenging. In this work, we highlight the potential of combining attention-based segmentation with feature-driven classification. This approach supports more accurate and efficient classification between vascular and demyelinating white matter pathologies. For segmentation, we evaluate the effectiveness of attention mechanisms, specifically the Bottleneck Attention Module (BAM) and the Convolutional Block Attention Module (CBAM). We also test different architectures, particularly Attention U-Net. In addition, we explore advanced training strategies, such as patch-based learning and a 2.5D approach, to enhance lesion detection. After segmentation, we extract morphological features from the lesion masks. We then use them to classify WMHs based on their underlying cause. Our experiments utilize five publicly available datasets with diverse imaging protocols to promote model generalizability, despite limited sample sizes. The results suggest that attention-based segmentation and feature-driven classification offer a promising direction for discriminating vascular and demyelinating white matter lesions. Further validation in larger clinical cohorts is still needed.