CLAIRE-DSA: Fluoroscopic Image Classification for Quality Assurance of Computer Vision Pipelines in Acute Ischemic Stroke

2025-08-18

AI Summary

Poor digital subtraction angiography (DSA) image quality in mechanical thrombectomy for acute ischemic stroke undermines the robustness of computer vision models. To address this, we propose CLAIRE-DSA—the first multi-attribute joint classification framework for fluoroscopic minimum intensity projection (MinIP) images. Leveraging transfer learning with a pretrained ResNet backbone, it performs multi-label classification of nine critical quality attributes—including contrast agent usage, projection angle, and motion artifacts—on a dataset of 1,758 annotated MinIP images. The model achieves ROC-AUC scores of 0.91–0.98 and precision of 0.70–1.00 across attributes. When integrated into downstream vascular segmentation, quality-aware image filtering increases success rates from 42% to 69% (p < 0.001). CLAIRE-DSA thus enables real-time intraoperative quality control and workflow optimization in neurointerventional procedures.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Web data integration and cleaning
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Computer vision models can be used to assist during mechanical thrombectomy (MT) for acute ischemic stroke (AIS), but poor image quality often degrades performance. This work presents CLAIRE-DSA, a deep learning--based framework designed to categorize key image properties in minimum intensity projections (MinIPs) acquired during MT for AIS, supporting downstream quality control and workflow optimization. CLAIRE-DSA uses pre-trained ResNet backbone models, fine-tuned to predict nine image properties (e.g., presence of contrast, projection angle, motion artefact severity). Separate classifiers were trained on an annotated dataset containing $1,758$ fluoroscopic MinIPs. The model achieved excellent performance on all labels, with ROC-AUC ranging from $0.91$ to $0.98$, and precision ranging from $0.70$ to $1.00$. The ability of CLAIRE-DSA to identify suitable images was evaluated on a segmentation task by filtering poor quality images and comparing segmentation performance on filtered and unfiltered datasets. Segmentation success rate increased from $42%$ to $69%$, $p < 0.001$. CLAIRE-DSA demonstrates strong potential as an automated tool for accurately classifying image properties in DSA series of acute ischemic stroke patients, supporting image annotation and quality control in clinical and research applications. Source code is available at https://gitlab.com/icai-stroke-lab/wp3_neurointerventional_ai/claire-dsa.

Problem

• Classify fluoroscopic image quality for stroke treatment
• Improve computer vision model performance in thrombectomy
• Automate quality control in acute ischemic stroke imaging

Innovation

• Deep learning framework for fluoroscopic image classification
• Pre-trained ResNet models fine-tuned for nine properties
• Improves segmentation success rate by filtering poor images