arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.19983cs.CV
收藏

TSdetector：用于结肠镜视频检测的时空自校正协同学习

TSdetector: Temporal-Spatial Self-correction Collaborative Learning for Colonoscopy Video Detection

School of Biological Science and Medical Engineering, Southeast University（东南大学生物科学与医学工程学院）；Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University（东南大学江苏省生物材料与器件重点实验室）；TUGE Healthcare（图格医疗）；Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医学技术研究院）；Laboratory of Image Science and Technology, Southeast University（东南大学图像科学与技术实验室）；Key Laboratory of Computer Network and Information Integration, Southeast University（东南大学计算机网络和信息集成重点实验室）；Department of Computer and Data Science and Department of Biomedical Engineering, Case Western Reserve University（凯斯西储大学计算机与数据科学系及生物医学工程系）

Kaini Wang, Haolin Wang, Guang-Quan Zhou, Yangang Wang, Ling Yang, Yang Chen, Shuo Li

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出时空自校正检测器TSdetector，通过时间级一致性学习和空间级可靠性学习解决结肠镜视频中息肉检测的序列分布异质性与精度-置信度不一致问题，在三个公开数据集上取得最优检测率。

摘要：

基于CNN的、在性能与速度之间取得平衡的目标检测模型已逐渐应用于息肉检测任务。然而，在复杂的结肠镜视频场景中准确定位息肉仍然具有挑战性，因为现有方法忽略了两个关键问题：序列内分布异质性和精度-置信度不一致。为解决这些挑战，我们提出了一种新颖的时空自校正检测器（TSdetector），它首先整合时间级一致性学习和空间级可靠性学习以连续检测目标。在技术层面，我们首先提出了一种全局时间感知卷积，汇集先前信息以动态引导当前卷积核关注序列间的全局特征。此外，我们设计了一种分层队列整合机制，通过渐进累积方式组合多时间特征，充分利用上下文一致性信息并保留长序列依赖特征。同时，在空间层面，我们提出了一种位置感知聚类方法，探索候选框之间的空间关系以自适应地重新校准预测置信度，从而高效地消除冗余边界框。在三个公开可用的息肉视频数据集上的实验结果表明，TSdetector实现了最高的息肉检测率，并优于其他最先进的方法。代码可在https://github.com/soleilssss/TSdetector获取。

英文摘要：

CNN-based object detection models that strike a balance between performance and speed have been gradually used in polyp detection tasks. Nevertheless, accurately locating polyps within complex colonoscopy video scenes remains challenging since existing methods ignore two key issues: intra-sequence distribution heterogeneity and precision-confidence discrepancy. To address these challenges, we propose a novel Temporal-Spatial self-correction detector (TSdetector), which first integrates temporal-level consistency learning and spatial-level reliability learning to detect objects continuously. Technically, we first propose a global temporal-aware convolution, assembling the preceding information to dynamically guide the current convolution kernel to focus on global features between sequences. In addition, we designed a hierarchical queue integration mechanism to combine multi-temporal features through a progressive accumulation manner, fully leveraging contextual consistency information together with retaining long-sequence-dependency features. Meanwhile, at the spatial level, we advance a position-aware clustering to explore the spatial relationships among candidate boxes for recalibrating prediction confidence adaptively, thus eliminating redundant bounding boxes efficiently. The experimental results on three publicly available polyp video dataset show that TSdetector achieves the highest polyp detection rate and outperforms other state-of-the-art methods. The code can be available at https://github.com/soleilssss/TSdetector.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑