Detection of Vascular Leukoencephalopathy in CT Images

TL;DR

This study demonstrates that convolutional neural networks, especially ConvNext, can accurately diagnose vascular leukoencephalopathy from CT scans, achieving up to 98.5% accuracy, thus advancing AI-based medical diagnostics.

Contribution

The paper introduces the application of ConvNext architecture for leukoencephalopathy detection in CT images, outperforming other models and providing interpretability via Grad-CAM.

Findings

ConvNext achieved 98.5% accuracy without preprocessing.

AI models focus on relevant scan regions as shown by Grad-CAM.

CNNs significantly improve diagnostic accuracy for brain vascular diseases.

Abstract

Artificial intelligence (AI) has seen a significant surge in popularity, particularly in its application to medicine. This study explores AI's role in diagnosing leukoencephalopathy, a small vessel disease of the brain, and a leading cause of vascular dementia and hemorrhagic strokes. We utilized a dataset of approximately 1200 patients with axial brain CT scans to train convolutional neural networks (CNNs) for binary disease classification. Addressing the challenge of varying scan dimensions due to different patient physiologies, we processed the data to a uniform size and applied three preprocessing methods to improve model accuracy. We compared four neural network architectures: ResNet50, ResNet50 3D, ConvNext, and Densenet. The ConvNext model achieved the highest accuracy of 98.5% without any preprocessing, outperforming models with 3D convolutions. To gain insights into model decision-making, we implemented Grad-CAM heatmaps, which highlighted the focus areas of the models on the scans. Our results demonstrate that AI, particularly the ConvNext architecture, can significantly enhance diagnostic accuracy for leukoencephalopathy. This study underscores AI's potential in advancing diagnostic methodologies for brain diseases and highlights the effectiveness of CNNs in medical imaging applications.