OccluNet: Spatio-Temporal Deep Learning for Occlusion Detection on DSA

TL;DR

OccluNet is a novel spatio-temporal deep learning model that automates vascular occlusion detection in DSA sequences, improving accuracy over existing methods by integrating YOLOX with transformer-based temporal attention.

Contribution

This work introduces OccluNet, combining YOLOX with transformer-based attention for the first time to detect occlusions in DSA sequences, capturing temporal consistency effectively.

Findings

Achieved 89.02% precision and 74.87% recall in occlusion detection.

Outperformed baseline YOLOv11 models on DSA sequences.

Both attention variants showed similar high performance.

Abstract

Accurate detection of vascular occlusions during endovascular thrombectomy (EVT) is critical in acute ischemic stroke (AIS). Interpretation of digital subtraction angiography (DSA) sequences poses challenges due to anatomical complexity and time constraints. This work proposes OccluNet, a spatio-temporal deep learning model that integrates YOLOX, a single-stage object detector, with transformer-based temporal attention mechanisms to automate occlusion detection in DSA sequences. We compared OccluNet with a YOLOv11 baseline trained on either individual DSA frames or minimum intensity projections. Two spatio-temporal variants were explored for OccluNet: pure temporal attention and divided space-time attention. Evaluation on DSA images from the MR CLEAN Registry revealed the model's capability to capture temporally consistent features, achieving precision and recall of 89.02% and 74.87%, respectively. OccluNet significantly outperformed the baseline models, and both attention variants attained similar performance. Source code is available at https://github.com/anushka-kore/OccluNet.git