VRXU-net: A Deep Learning Approach for Brain Ischemic Stroke Lesion Detection and Segmentation in T1W MRI

TL;DR

This paper presents VRXU-net, a novel deep learning architecture combining residual U-shaped networks and multi-plane 2D slice analysis for improved detection and segmentation of ischemic stroke lesions in T1W MRI scans.

Contribution

The study introduces VRXU-net, integrating residual connections and multi-plane analysis, achieving superior accuracy in stroke lesion segmentation over existing models.

Findings

Outperforms state-of-the-art models in accuracy and Dice coefficient.

Combining multi-plane segmentation improves lesion localization.

Sequential classification reduces false positives.

Abstract

When the blood supply to the brain is obstructed by a clot, oxygen delivery to brain tissues becomes insufficient, leading to cellular necrosis. In healthcare settings, accurately identifying and delineating ischemic lesion boundaries is essential for treatment and surgical planning. However, ischemic stroke lesions vary widely in shape, size, and location, and in grayscale MRI modalities such as T1W they may resemble surrounding brain structures. This makes lesion detection and segmentation a challenging task for clinicians. This study introduces a novel VRU-Net architecture, derived from visual features, residual connections, and a U-shaped network, for detecting and segmenting ischemic stroke lesions in 3D magnetic resonance imaging scans. The proposed method first uses a modified VGG model to identify ischemic stroke in separate 2D slices. Then, a U-shaped segmentation model with residual blocks segments the lesion in each slice. This procedure is applied independently to the axial, sagittal, and coronal planes, and the final output is generated by aggregating the three segmentation results. To improve both performance and processing speed, a high-performance classifier is applied before the segmentation model in a sequential framework. This strategy reduces unnecessary segmentation of non-lesion slices and improves overall accuracy. In addition, decomposing 3D images into 2D slices reduces model complexity while allowing information from three anatomical planes to support more accurate lesion localization. The proposed model is trained on the Anatomical Tracings of Lesions After Stroke dataset and outperforms state-of-the-art models in terms of accuracy and Dice coefficient. Moreover, the segmentation output provides feedback that helps the classification model reduce false-positive predictions.