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

TL;DR

TSdetector introduces a novel temporal-spatial self-correction framework for improved polyp detection in colonoscopy videos, leveraging global temporal features and spatial relationship modeling to enhance accuracy and reliability.

Contribution

The paper presents a new detection model combining temporal consistency and spatial relationship learning, addressing intra-sequence heterogeneity and confidence discrepancies in colonoscopy videos.

Findings

Achieves highest polyp detection rate on three datasets.

Outperforms existing state-of-the-art methods.

Effectively reduces redundant bounding boxes.

Abstract

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.