Reclassifying stroke lesion anatomy. (December 2021)

• Record Type: Journal Article
• Authors: Bonkhoff, Anna K.; Xu, Tianbo; Nelson, Amy; Gray, Robert; Jha, Ashwani; Cardoso, Jorge; Ourselin, Sebastien; Rees, Geraint; Jäger, Hans Rolf; Nachev, Parashkev
• Is Part Of: Cortex. Volume 145(2021)
• Page Start: 1
• Page End: 12
• Publication Date: 2021-12
• Subjects: Stroke -- Lesion anatomy -- Lesion–deficit prediction -- Dimensionality reduction -- Brain imaging; DWI diffusion-weighted imaging -- t-SNE t-stochastic neighbour embedding -- NMF non-negative matrix factorization -- BA Brodmann Area; Neuropsychology -- Periodicals; Nervous system -- Periodicals; Neurology -- Periodicals; Psychophysiology -- Periodicals; Behavior -- Periodicals; Neurology -- Periodicals; 612.825
• DOI: 10.1016/j.cortex.2021.09.007
• Languages: English
• ISSNs: 0010-9452

Abstract

Abstract: Cognitive and behavioural outcomes in stroke reflect the interaction between two complex anatomically-distributed patterns: the functional organization of the brain and the structural distribution of ischaemic injury. Conventional outcome models—for individual prediction or population-level inference—commonly ignore this complexity, discarding anatomical variation beyond simple characteristics such as lesion volume. This sets a hard limit on the maximum fidelity such models can achieve. High-dimensional methods can overcome this problem, but only at prohibitively large data scales. Drawing on one of the largest published collections of anatomically-registered imaging of acute stroke—N = 1333—here we use non-linear dimensionality reduction to derive a succinct latent representation of the anatomical patterns of ischaemic injury, agglomerated into 21 distinct intuitive categories. We compare the maximal predictive performance it enables against both simpler low-dimensional and more complex high-dimensional representations, employing multiple empirically-informed ground truth models of distributed structure–outcome relationships. We show our representation sets a substantially higher ceiling on predictive fidelity than conventional low-dimensional approaches, but lower than that achievable within a high-dimensional framework. Where descriptive simplicity is a necessity, such as within clinical care or research trials of modest size, the representation we propose arguably offers a favourable compromise of compactness and fidelity.