OccluNet: Spatio-Temporal Deep Learning for Occlusion Detection on DSA
This work addresses a critical problem for clinicians in acute ischemic stroke by improving occlusion detection accuracy, though it appears incremental as it builds on existing object detection and attention mechanisms.
The paper tackled automated occlusion detection in digital subtraction angiography sequences for acute ischemic stroke, achieving precision of 89.02% and recall of 74.87% with a spatio-temporal deep learning model that outperformed baseline methods.
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