DBT-Bleed: Dual-Branch Temporal Modeling with Key-Frame Selection for Surgical Bleeding Detection
2026-06-22 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors address the challenge of detecting bleeding during surgery from video, which can be hard to tell apart from leftover blood. They developed DBT-Bleed, a system that looks at both short- and long-term changes in the video to better identify bleeding. To handle long surgery videos efficiently, they also created HiRED, a method that selects the most important video parts to analyze. Their approach improved bleeding detection accuracy on existing and new datasets, including a novel neurosurgical video collection. This work helps improve automated monitoring of surgical safety without needing manual review of entire videos.
Intraoperative Adverse Events (IAE)Bleeding detectionTemporal modelingSurgical video analysisMultiBypass datasetZero-shot transferHierarchical Entropy-Driven frame selectionEndonasal Pituitary SurgeryDBT-Bleed
Authors
Sudhanshu Mishra, Jialang Xu, Jensen Ang, Evangelos B. Mazomenos, Beng Ti Ang, Yueming Jin
Abstract
Intraoperative Adverse Events (IAEs) detection is critical for improving surgical safety, with bleeding being among the most frequent events across many surgery types. Existing methods struggle to distinguish bleeding IAE from visually similar residual blood due to limited temporal reasoning. Moreover, modeling long surgical videos while preserving fine-grained temporal dynamics remains computationally challenging. We propose DBT-Bleed, a dual-branch multi-scale temporal modeling framework disentangling bleeding and normal representations using layer-wise temporal adapters for short- and long-term bleeding progression. To efficiently process long surgical videos without sacrificing fine-grained temporal information, we introduce HiRED, a Hierarchical Entropy-Driven frame selection strategy that retains temporally informative segments while removing redundancy. Experiments on the MultiBypass dataset demonstrate gains of 6.53% in F1, 5.62% in Recall and 9% in MCC values for bleeding IAE detection, consistently outperforming video-level baselines. Additionally, we evaluate cross-procedure generalization on a newly curated dataset from a different surgical procedure type, where DBT-Bleed demonstrates robust transferability by achieving gain of 6% in F1 and 8% in MCC under zero-shot setting. To support this evaluation, we introduce EndoPit-IAE, an Endonasal Pituitary Surgery dataset annotated for IAEs, representing the first IAE-annotated dataset in neurosurgery. Code will be made publicly available upon acceptance.