Multimodal radiomics based on lesion connectome predicts stroke prognosis

Stroke significantly contributes to global mortality and disability, emphasizing the critical need for effective prognostic evaluations. Connectome-based lesion-symptom mapping (CLSM) identifies structural and functional connectivity disruptions related to the lesion, while radiomics extracts high-dimensional quantitative data from multimodal medical images. Despite the potential of these methodologies, no study has yet integrated CLSM and multimodal radiomics for acute ischemic stroke (AIS).

This retrospective study analyzed lesion, structural disconnection (SDC), and functional disconnection (FDC) maps of 148 patients with AIS and assessed their association with the National Institutes of Health Stroke Scale (NIHSS) score at admission and prognostic outcomes, measured by the modified Rankin Scale at six months. Additionally, an innovative approach was proposed by utilizing the SDC map as mask, and radiomic features were extracted and selected from T1-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient, susceptibility-weighted imaging, and fluid-attenuated inversion recovery images. Five machine learning classifiers were then used to predict the prognosis of AIS.

This study constructed lesion, SDC and FDC maps to correlate with NIHSS scores and prognostic outcomes, thereby revealing the neuroanatomical mechanisms underlying neural damage and prognosis. Poor prognosis was associated with distal cortical dysfunction and fiber disconnection. Fifteen radiomic features within SDC maps from multimodal imaging were selected as inputs for machine learning models. Among the five classifiers tested, Categorical Boosting achieved the highest performance (AUC = 0.930, accuracy = 0.836).

A novel model integrating CLSM and multimodal radiomics was proposed to predict long-term prognosis in AIS, which would be a promising tool for early prognostic evaluation and therapeutic planning. Further investigation is needed to assess its robustness in clinical application.