Comparing Baseline and Day-1 Diffusion MRI Using Multimodal Deep Embeddings for Stroke Outcome Prediction

2025-12-01

AI Summary

This study investigates the comparative predictive performance of baseline (J0) versus 24-hour (J1) diffusion MRI for 3-month functional outcomes in acute ischemic stroke patients. We propose a multimodal prediction model that extracts deep MRI features using a 3D ResNet-50 architecture, integrates clinical variables, applies PCA for dimensionality reduction, and employs linear SVM for binary outcome classification. A key innovation is the incorporation of lesion volume as an interpretable, structured imaging biomarker. Results demonstrate that the J1-based multimodal model achieves superior discriminative ability (AUC = 0.923 ± 0.085), significantly outperforming the J0 model (AUC ≤ 0.86). The J1 model maintains high accuracy while enhancing robustness and clinical interpretability. These findings establish J1 diffusion MRI—combined with lesion volume and clinical data—as a reliable tool for early, individualized prognostic assessment in acute ischemic stroke.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This study compares baseline (J0) and 24-hour (J1) diffusion magnetic resonance imaging (MRI) for predicting three-month functional outcomes after acute ischemic stroke (AIS). Seventy-four AIS patients with paired apparent diffusion coefficient (ADC) scans and clinical data were analyzed. Three-dimensional ResNet-50 embeddings were fused with structured clinical variables, reduced via principal component analysis (<=12 components), and classified using linear support vector machines with eight-fold stratified group cross-validation. J1 multimodal models achieved the highest predictive performance (AUC = 0.923 +/- 0.085), outperforming J0-based configurations (AUC<= 0.86). Incorporating lesion-volume features further improved model stability and interpretability. These findings demonstrate that early post-treatment diffusion MRI provides superior prognostic value to pre-treatment imaging and that combining MRI, clinical, and lesion-volume features produces a robust and interpretable framework for predicting three-month functional outcomes in AIS patients.

Problem

• Predicts three-month functional outcomes after acute ischemic stroke
• Compares baseline and 24-hour diffusion MRI for stroke prognosis
• Combines MRI, clinical, and lesion-volume features for robust prediction

Innovation

• Multimodal deep embeddings fusion for stroke prediction
• Day-1 diffusion MRI outperforms baseline imaging
• Combined MRI, clinical, and lesion-volume features enhance interpretability