DSA-NRP: No-Reflow Prediction from Angiographic Perfusion Dynamics in Stroke EVT

2025-06-20

AI Summary

Approximately 20–30% of acute ischemic stroke patients successfully recanalized via endovascular thrombectomy (EVT) develop “no-reflow”—persistent microvascular hypoperfusion leading to neurological deterioration. Current diagnosis relies on 24-hour post-procedural perfusion MRI, causing critical therapeutic delay. Method: We propose the first intraoperative, real-time prediction paradigm using dual-angle dynamic subtraction angiography (DSA) perfusion sequences. Quantitative perfusion kinetics—including time-to-peak (TTP), mean transit time (MTT), and temporal slope—along with clinical variables, are extracted and integrated into XGBoost and random forest ensemble models. Contribution/Results: The model enables immediate no-reflow risk assessment at recanalization, achieving an AUC of 0.770±0.12 and accuracy of 81.3%±10%, significantly outperforming a clinical-only baseline (AUC 0.573±0.12). This study is the first to demonstrate that DSA-derived dynamic perfusion metrics sensitively reflect microcirculatory integrity, overcoming the diagnostic latency inherent to MRI.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Metareasoning and Metaheuristics
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Following successful large-vessel recanalization via endovascular thrombectomy (EVT) for acute ischemic stroke (AIS), some patients experience a complication known as no-reflow, defined by persistent microvascular hypoperfusion that undermines tissue recovery and worsens clinical outcomes. Although prompt identification is crucial, standard clinical practice relies on perfusion magnetic resonance imaging (MRI) within 24 hours post-procedure, delaying intervention. In this work, we introduce the first-ever machine learning (ML) framework to predict no-reflow immediately after EVT by leveraging previously unexplored intra-procedural digital subtraction angiography (DSA) sequences and clinical variables. Our retrospective analysis included AIS patients treated at UCLA Medical Center (2011-2024) who achieved favorable mTICI scores (2b-3) and underwent pre- and post-procedure MRI. No-reflow was defined as persistent hypoperfusion (Tmax > 6 s) on post-procedural imaging. From DSA sequences (AP and lateral views), we extracted statistical and temporal perfusion features from the target downstream territory to train ML classifiers for predicting no-reflow. Our novel method significantly outperformed a clinical-features baseline(AUC: 0.7703 $pm$ 0.12 vs. 0.5728 $pm$ 0.12; accuracy: 0.8125 $pm$ 0.10 vs. 0.6331 $pm$ 0.09), demonstrating that real-time DSA perfusion dynamics encode critical insights into microvascular integrity. This approach establishes a foundation for immediate, accurate no-reflow prediction, enabling clinicians to proactively manage high-risk patients without reliance on delayed imaging.

Problem

• Predict no-reflow post-EVT using DSA sequences
• Overcome delayed diagnosis from standard MRI methods
• Improve clinical outcomes via real-time ML prediction

Innovation

• Machine learning predicts no-reflow post-EVT
• Uses intra-procedural DSA sequences and clinical variables
• Extracts statistical and temporal perfusion features