Synergistic Bleeding Region and Point Detection in Surgical Videos

• URL: http://arxiv.org/abs/2503.22174v1
• Date: Fri, 28 Mar 2025 06:27:55 GMT
• Title: Synergistic Bleeding Region and Point Detection in Surgical Videos
• Authors: Jialun Pei, Zhangjun Zhou, Diandian Guo, Zhixi Li, Jing Qin, Bo Du, Pheng-Ann Heng,
• Abstract summary: Intraoperative bleeding in laparoscopic surgery causes rapid obscuration of the operative field to hinder the surgical process.<n>In this study, we first construct a real-world surgical bleeding detection dataset, named SurgBlood, comprising 5,330 frames from 95 surgical video clips with bleeding region and point annotations.<n>We develop a dual-task synergistic online detector called BlooDet, designed to perform simultaneous detection of bleeding regions and points in surgical videos.
• Score: 58.52416525595543
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Intraoperative bleeding in laparoscopic surgery causes rapid obscuration of the operative field to hinder the surgical process. Intelligent detection of bleeding regions can quantify the blood loss to assist decision-making, while locating the bleeding point helps surgeons quickly identify the source of bleeding and achieve hemostasis in time. In this study, we first construct a real-world surgical bleeding detection dataset, named SurgBlood, comprising 5,330 frames from 95 surgical video clips with bleeding region and point annotations. Accordingly, we develop a dual-task synergistic online detector called BlooDet, designed to perform simultaneous detection of bleeding regions and points in surgical videos. Our framework embraces a dual-branch bidirectional guidance design based on Segment Anything Model 2 (SAM 2). The mask branch detects bleeding regions through adaptive edge and point prompt embeddings, while the point branch leverages mask memory to induce bleeding point memory modeling and captures the direction of bleed point movement through inter-frame optical flow. By interactive guidance and prompts, the two branches explore potential spatial-temporal relationships while leveraging memory modeling from previous frames to infer the current bleeding condition. Extensive experiments demonstrate that our approach outperforms other counterparts on SurgBlood in both bleeding region and point detection tasks, e.g., achieving 64.88% IoU for bleeding region detection and 83.69% PCK-10% for bleeding point detection.

Related papers

• ClassifyViStA:WCE Classification with Visual understanding through Segmentation and Attention [3.887356044145916]
  We propose ClassifyViStA, an AI-based framework designed for the automated detection and classification of bleeding and non-bleeding frames from WCE videos.<n>The model is built upon an ensemble of ResNet18 and VGG16 architectures to enhance classification performance.<n>Our approach not only automates the detection of GI bleeding but also provides an interpretable solution that can ease the burden on healthcare professionals.
  arXiv  Detail & Related papers  (2024-12-24T18:45:14Z)
• 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)
• A dual-task mutual learning framework for predicting post-thrombectomy cerebral hemorrhage [42.24368372333753]
  We propose a novel prediction framework for measuring postoperative cerebral hemorrhage using only the patient's initial CT scan. Our method can generate follow-up CT scans better than state-of-the-art methods, and achieves an accuracy of 86.37% in predicting follow-up prognostic labels.
  arXiv  Detail & Related papers  (2024-08-01T22:08:52Z)
• Real-time guidewire tracking and segmentation in intraoperative x-ray [52.51797358201872]
  We propose a two-stage deep learning framework for real-time guidewire segmentation and tracking. In the first stage, a Yolov5 detector is trained, using the original X-ray images as well as synthetic ones, to output the bounding boxes of possible target guidewires. In the second stage, a novel and efficient network is proposed to segment the guidewire in each detected bounding box.
  arXiv  Detail & Related papers  (2024-04-12T20:39:19Z)
• HemoSet: The First Blood Segmentation Dataset for Automation of Hemostasis Management [26.312321557596224]
  HemoSet is the first blood segmentation dataset based on bleeding during a live animal robotic surgery. We benchmark several state-of-the-art segmentation models and provide insight into the difficulties specific to blood detection.
  arXiv  Detail & Related papers  (2024-03-24T20:31:42Z)
• 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)
• An Algorithm for the Labeling and Interactive Visualization of the Cerebrovascular System of Ischemic Strokes [59.116811751334225]
  VirtualDSA++ is an algorithm designed to segment and label the cerebrovascular tree on CTA scans. We extend the labeling mechanism for the cerebral arteries to identify occluded vessels. We present the generic concept of iterative systematic search for pathways on all nodes of said model, which enables new interactive features.
  arXiv  Detail & Related papers  (2022-04-26T14:20:26Z)
• A Deep Learning Approach to Predicting Collateral Flow in Stroke Patients Using Radiomic Features from Perfusion Images [58.17507437526425]
  Collateral circulation results from specialized anastomotic channels which provide oxygenated blood to regions with compromised blood flow. The actual grading is mostly done through manual inspection of the acquired images. We present a deep learning approach to predicting collateral flow grading in stroke patients based on radiomic features extracted from MR perfusion data.
  arXiv  Detail & Related papers  (2021-10-24T18:58:40Z)
• Multiple Sclerosis Lesion Activity Segmentation with Attention-Guided Two-Path CNNs [49.32653090178743]
  convolutional neural networks (CNNs) are studied for lesion activity segmentation from two time points. CNNs are designed and evaluated that combine the information from two points in different ways. It is demonstrated that deep learning-based methods outperform classic approaches.
  arXiv  Detail & Related papers  (2020-08-05T08:49:20Z)

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.