An end-to-end tracking method for polyp detectors in colonoscopy videos

Yu, Tao; Lin, Na; Zhang, Xu; Pan, Yanqi; Hu, Huiyi; Zheng, Wenfang; Liu, Jiquan; Duan, Huilong; Si, Jianmin

doi:10.1016/j.artmed.2022.102363

Cited by 11 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The integration of advanced technologies not only improves the identification and tracking of objects in image sequences, but also facilitates the automatic and continuous annotation of these objects. An example of this evolution is the work of Tao Yu et al [46] who developed the "Instance Tracking Head" (ITH), integrated into the Scaled-YOLOv4 detector. This innovation offers improvements in the detection and tracking of objects in medical videos, such as colonoscopies.…”

Section: Discussionmentioning

confidence: 99%

“…Tao Yu et al [46] present a revolutionary method that integrates the "Instance Tracking Head" (ITH) module into object detection frameworks to detect and track polyps in colonoscopy videos. This method, aligned with the Scaled-YOLOv4 detector, allows sharing of low-level feature extraction and progressive specialization in detection and tracking.…”

Section: Single Object Trackingmentioning

confidence: 99%

“…The field of object tracking has been marked by significant innovations, especially with the application of advanced neural networks and deep learning techniques. The introduction of the Instance Tracking Head (ITH) by Tao Yu et al [46] exemplifies this evolution, offering a notable improvement in tracking accuracy in medical contexts, such as colonoscopy videos. This innovation underlines the ability of these new technologies to adapt to specialized applications where precision is crucial.…”

Section: A Object Trackingmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Image Annotation With Object Tracking and Image Retrieval: A Systematic Review

Fernandes,

Pessoa,

Salgado

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Effective image and video annotation is a fundamental pillar in computer vision and artificial intelligence, crucial for the development of accurate machine learning models. Object tracking and image retrieval techniques are essential in this process, significantly improving the efficiency and accuracy of automatic annotation. This paper systematically investigates object tracking and image acquisition techniques. It explores how these technologies can collectively enhance the efficiency and accuracy of the annotation processes for image and video datasets. Object tracking is examined for its role in automating annotations by tracking objects across video sequences, while image retrieval is evaluated for its ability to suggest annotations for new images based on existing data. The review encompasses diverse methodologies, including advanced neural networks and machine learning techniques, highlighting their effectiveness in various contexts like medical analyses and urban monitoring. Despite notable advancements, challenges such as algorithm robustness and effective human-AI collaboration are identified. This review provides valuable insights into these technologies' current state and future potential in improving image annotation processes, even showing existing applications of these techniques and their full potential when combined.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Single Object Trackingmentioning

confidence: 99%

Section: A Object Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Image Annotation With Object Tracking and Image Retrieval: A Systematic Review

Fernandes,

Pessoa,

Salgado

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Finally, 91.6% was achieved in terms of accuracy (Cao et al, 2021). Yu et al (2022) designed the ITH module based on Scaled-YOLOv4, which shares weights with the YOLO detection head for fast feature extraction. In addition, a learning method based on similarity metrics is designed to improve the performance of model evaluation.…”

Section: Related Workmentioning

confidence: 99%

“…In addition, a learning method based on similarity metrics is designed to improve the performance of model evaluation. The introduction of the ITH module enables the model to improve the recognition speed by 30% compared to the original model (Yu et al, 2022). Dash et al (2023) proposed an expert system designed to address the problems of time-consuming polyp detection and high misdiagnosis rates.…”

Section: Related Workmentioning

confidence: 99%

Colorectal image analysis for polyp diagnosis

Zhu,

Wan,

Shao

et al. 2024

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Colorectal polyp is an important early manifestation of colorectal cancer, which is significant for the prevention of colorectal cancer. Despite timely detection and manual intervention of colorectal polyps can reduce their chances of becoming cancerous, most existing methods ignore the uncertainties and location problems of polyps, causing a degradation in detection performance. To address these problems, in this paper, we propose a novel colorectal image analysis method for polyp diagnosis via PAM-Net. Specifically, a parallel attention module is designed to enhance the analysis of colorectal polyp images for improving the certainties of polyps. In addition, our method introduces the GWD loss to enhance the accuracy of polyp diagnosis from the perspective of polyp location. Extensive experimental results demonstrate the effectiveness of the proposed method compared with the SOTA baselines. This study enhances the performance of polyp detection accuracy and contributes to polyp detection in clinical medicine.

show abstract