DBT-Bleed: Dual-Branch Temporal Modeling with Key-Frame Selection for Surgical Bleeding Detection

• URL: http://arxiv.org/abs/2606.22829v1
• Date: Mon, 22 Jun 2026 04:12:38 GMT
• Title: DBT-Bleed: Dual-Branch Temporal Modeling with Key-Frame Selection for Surgical Bleeding Detection
• Abstract summary: Intraoperative Adverse Events (IAEs) are among the most frequent events across many surgery types.<n>We propose a dual-branch multi-scale temporal modeling framework disentangling bleeding and normal representations using layer-wise temporal adapters.<n>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.<n>We introduce EndoPit-IAE, an Endonasal Pituitary Surgery dataset annotated for IAEs, representing the first IAE-annotated dataset in neurosurgery.
• Score: 11.479806559754365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal Confirmation [28.876740706448345]
  We propose a two-stage framework for MM lesion segmentation on WB-DWI.<n>In the first stage, we train a bone ROI generation model from ADC images without dedicated bone labels.<n>In the second stage, we propose Anatomy-guided Multimodal U-Net.
  arXiv  Detail & Related papers  (2026-09-05T16:08:29Z)
• TimeLesSeg: Unified Contrast-Agnostic Cross-Sectional and Longitudinal MS Lesion Segmentation via a Stochastic Generative Model [0.338424069286569]
  TimeLesSeg is a unified contrast-agnostic framework designed to segment MS lesions regardless of the presence of a temporal dimension in its inputs.<n>Our approach models pathological priors through lesion masks, which are processed together with the current scan.<n>Cross-sectional processing is enabled by exposing the model to training cases where no prior information is available.
  arXiv  Detail & Related papers  (2026-05-08T16:19:34Z)
• ODySSeI: An Open-Source End-to-End Framework for Automated Detection, Segmentation, and Severity Estimation of Lesions in Invasive Coronary Angiography Images [23.05175906366438]
  Invasive Coronary Angiography (ICA) is the clinical gold standard for the assessment of coronary artery disease.<n>In this work, we introduce ODySSeI: an Open-source framework for automated Detection, lesions, and Severity estimation in ICA images.<n> ODySSeI integrates deep learning-based lesion detection and lesion segmentation models trained using a novel Pyramidal Augmentation Scheme (PAS)<n>Our LSE technique achieves high accuracy, with predicted MLD values differing by only $pm$ 2-3 pixels from the corresponding ground truths.
  arXiv  Detail & Related papers  (2026-03-20T15:07:15Z)
• Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction [45.67071315035565]
  Intraoperative hypotension poses significant surgical risks, but accurate prediction remains challenging due to patient-specific variability.<n>We propose CSA-TTA, a novel Cross-Sample Augmented Test-Time Adaptation framework that enhances training by incorporating hypotension events from other individuals.<n>We evaluate the proposed CSA-TTA on both the VitalDB dataset and a real-world in-hospital dataset by integrating it with state-of-the-art time series forecasting models.
  arXiv  Detail & Related papers  (2025-12-12T08:02:37Z)
• Cancer-Net PCa-MultiSeg: Multimodal Enhancement of Prostate Cancer Lesion Segmentation Using Synthetic Correlated Diffusion Imaging [55.62977326180104]
  Current deep learning approaches for prostate cancer lesion segmentation achieve limited performance.<n>We investigate synthetic correlated diffusion imaging (CDI$s$) as an enhancement to standard diffusion-based protocols.<n>Our results establish validated integration pathways for CDI$s$ as a practical drop-in enhancement for PCa lesion segmentation tasks.
  arXiv  Detail & Related papers  (2025-11-11T04:16:12Z)
• A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler [49.03919553747297]
  We propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries.<n>No prior studies have explored AI-driven cerebrovascular segmentation using Transcranial Color-coded Doppler (TCCD)<n>The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels.
  arXiv  Detail & Related papers  (2025-08-19T14:41:22Z)
• Synergistic Bleeding Region and Point Detection in Laparoscopic Surgical Videos [58.52416525595543]
  BlooDet is designed to perform simultaneous detection of bleeding regions and points in laparoscopic surgery.<n>Our framework embraces a dual-branch bidirectional guidance design based on Segment Anything Model 2.<n>In experiments, our baseline outperforms 12 counterparts on SurgBlood in both bleeding region and point detection.
  arXiv  Detail & Related papers  (2025-03-28T06:27:55Z)
• Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2 [1.0536099636804035]
  We investigate how inconsistencies in annotation density and frame rate sampling influence the evaluation of zero-shot segmentation models.<n>We find that lower frame rates can appear to outperform higher ones due to a smoothing effect that conceals temporal inconsistencies.<n>When assessed under real-time streaming conditions, higher frame rates yield superior segmentation stability.
  arXiv  Detail & Related papers  (2025-02-28T10:42:09Z)
• Enhancing Diagnostic Precision in Gastric Bleeding through Automated Lesion Segmentation: A Deep DuS-KFCM Approach [20.416923956241497]
  We introduce a novel deep learning model, the Dual Spatial Kernelized Constrained Fuzzy C-Means (Deep DuS-KFCM) clustering algorithm. This system synergizes Neural Networks with Fuzzy Logic to offer a highly precise and efficient identification of bleeding regions. Our model demonstrated unprecedented accuracy rates of 87.95%, coupled with a specificity of 96.33%, outperforming contemporary segmentation methods.
  arXiv  Detail & Related papers  (2024-11-21T18:21:42Z)
• LoViT: Long Video Transformer for Surgical Phase Recognition [59.06812739441785]
  We present a two-stage method, called Long Video Transformer (LoViT) for fusing short- and long-term temporal information. Our approach outperforms state-of-the-art methods on the Cholec80 and AutoLaparo datasets consistently.
  arXiv  Detail & Related papers  (2023-05-15T20:06:14Z)
• Learning-Based Keypoint Registration for Fetoscopic Mosaicking [65.02392513942533]
  In Twin-to-Twin Transfusion Syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the two fetuses. We propose a learning-based framework for in-vivo fetoscopy frame registration for field-of-view expansion.
  arXiv  Detail & Related papers  (2022-07-26T21:21:12Z)
• TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks [43.95869213955351]
  We propose a Multi-Stage Temporal Convolutional Network (MS-TCN) that performs hierarchical prediction refinement for surgical phase recognition. Our method is thoroughly evaluated on two datasets of laparoscopic cholecystectomy videos with and without the use of additional surgical tool information.
  arXiv  Detail & Related papers  (2020-03-24T10:12:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.