Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities

Abstract

Lesion-symptom mapping methods assess the relationship between lesions caused by cerebral small vessel disease and cognition, but current technology like support vector regression (SVR)) primarily provide group-level results. We propose a novel lesion-symptom mapping approach that can indicate how lesion patterns contribute to cognitive impairment on an individual level. A convolutional neural network (CNN) predicts cognitive scores and is combined with explainable artificial intelligence (XAI) to map the relation between cognition and vascular lesions. This method was evaluated primarily using real white matter hyperintensity maps of 821 memory clinic patients and simulated cognitive data, with weighted lesions and noise levels. Simulated data provided ground truth locations to assess predictive performance of the CNN and accuracy of strategic lesion identification by XAI, using an established lesion-symptom mapping method, SVR, and a simple fully connected neural network (FNN) as benchmarks. Real cognitive scores were used in a final proof-of-principle analysis. Predictive performance in simulation experiments was high for the CNN (R2 = 0.964), SVR (R2 = 0.875), and FNN (R2 = 0.863). CNN with XAI provided patient-specific attribution maps that highlighted the ground truth locations. All methods showed similar sensitivity to noise. Using real cognitive scores, SVR (R2 = 0.291) obtained a somewhat higher predictive performance than the CNN (R2 = 0.216), although both methods substantially exceeded the predictive performance of total WMH volume alone (R2 = 0.013). The FNN performed worse on real data (R2 = 0.020). To conclude, results show that CNNs combined with XAI can perform lesion-symptom mapping and generate individual attribution maps, which could be a valuable feature with further method development.