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

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 l...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryanne Offenberg, Alberto De Luca, Geert Jan Biessels, Frederik Barkhof, Wiesje M. van der Flier, Argonde C. van Harten, Ewoud van der Lelij, Josien Pluim, Hugo Kuijf
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:NeuroImage: Clinical
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2213158225000609
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849694868801060864
author Ryanne Offenberg
Alberto De Luca
Geert Jan Biessels
Frederik Barkhof
Wiesje M. van der Flier
Argonde C. van Harten
Ewoud van der Lelij
Josien Pluim
Hugo Kuijf
author_facet Ryanne Offenberg
Alberto De Luca
Geert Jan Biessels
Frederik Barkhof
Wiesje M. van der Flier
Argonde C. van Harten
Ewoud van der Lelij
Josien Pluim
Hugo Kuijf
author_sort Ryanne Offenberg
collection DOAJ
description 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.
format Article
id doaj-art-d3c66d2f12ed4c77985da1c06b544643
institution DOAJ
issn 2213-1582
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series NeuroImage: Clinical
spelling doaj-art-d3c66d2f12ed4c77985da1c06b5446432025-08-20T03:19:56ZengElsevierNeuroImage: Clinical2213-15822025-01-014610379010.1016/j.nicl.2025.103790Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensitiesRyanne Offenberg0Alberto De Luca1Geert Jan Biessels2Frederik Barkhof3Wiesje M. van der Flier4Argonde C. van Harten5Ewoud van der Lelij6Josien Pluim7Hugo Kuijf8Image Sciences Institute, UMC Utrecht, Utrecht, the Netherlands; Corresponding author at: Image Sciences Institute, UMC Utrecht, Heidelberglaan 100, 3584 CX Utrecht, the Netherlands.Image Sciences Institute, UMC Utrecht, Utrecht, the NetherlandsDepartment of Neurology, UMC Utrecht, Utrecht, the NetherlandsDepartment of Radiology & Nuclear Medicine, Amsterdam UMC, Vrije Universiteit, the Netherlands; Queen Square Institute of Neurology and Centre for Medical Image Computing, University College London, UKAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC Location VUmc, Amsterdam, the Netherlands; Amsterdam Neuroscience, Neurodegeneration, Amsterdam, the Netherlands; Epidemiology & Data Science, Vrije Universiteit Amsterdam, Amsterdam UMC Location VUmc, Amsterdam, the NetherlandsAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC Location VUmc, Amsterdam, the Netherlands; Amsterdam Neuroscience, Neurodegeneration, Amsterdam, the NetherlandsDepartment of Neurology, UMC Utrecht, Utrecht, the NetherlandsImage Sciences Institute, UMC Utrecht, Utrecht, the Netherlands; Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the NetherlandsImage Sciences Institute, UMC Utrecht, Utrecht, the NetherlandsLesion-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.http://www.sciencedirect.com/science/article/pii/S2213158225000609Lesion-symptom mappingNeural networkExplainable artificial intelligenceVascular cognitive impairmentMachine learning
spellingShingle Ryanne Offenberg
Alberto De Luca
Geert Jan Biessels
Frederik Barkhof
Wiesje M. van der Flier
Argonde C. van Harten
Ewoud van der Lelij
Josien Pluim
Hugo Kuijf
Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities
NeuroImage: Clinical
Lesion-symptom mapping
Neural network
Explainable artificial intelligence
Vascular cognitive impairment
Machine learning
title Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities
title_full Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities
title_fullStr Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities
title_full_unstemmed Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities
title_short Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities
title_sort individualized lesion symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities
topic Lesion-symptom mapping
Neural network
Explainable artificial intelligence
Vascular cognitive impairment
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2213158225000609
work_keys_str_mv AT ryanneoffenberg individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT albertodeluca individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT geertjanbiessels individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT frederikbarkhof individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT wiesjemvanderflier individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT argondecvanharten individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT ewoudvanderlelij individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT josienpluim individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities
AT hugokuijf individualizedlesionsymptommappingusingexplainableartificialintelligenceforthecognitiveimpactofwhitematterhyperintensities