paper-with-me

홈 › Papers

Real-Time Polyp Segmentation Using U-Net with IoU Loss

2020-12-15 · MediaEval Benchmarking Initiative for Multimedia Evaluation 2020 12 · George Batchkala, Sharib Ali

Colonoscopy is the third leading cause of cancer deaths worldwide. While automated segmentation methods can help detect polyps and consequently improve their surgical removal, the clinical usability of these methods requires a trade-off between accuracy and speed. In this work, we exploit the traditional U-Net methods and compare different segmentation-loss functions. Our results demonstrate that IoU loss results in an improved segmentation performance (nearly 3% improvement on Dice) for real-time polyp segmentation.

📄 PDF Abstract BibTeX

Code (1)

georgebatch/kvasir-seg pytorch

Tasks

Segmentation

Similar Papers 제목 키워드 기반

LGPS: A Lightweight GAN-Based Approach for Polyp Segmentation in Colonoscopy Images

2025-03-24 · Fiseha B. Tesema, Alejandro Guerra Manzanares, Tianxiang Cui, Qian Zhang 외

Colorectal cancer (CRC) is a major global cause of cancer-related deaths, with early polyp detection and removal during colonoscopy being crucial for prevention. While deep learning methods have shown promise in polyp se…

Automatic Polyp Segmentation via Multi-scale Subtraction Network

2021-08-11 · Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

More than 90\% of colorectal cancer is gradually transformed from colorectal polyps. In clinical practice, precise polyp segmentation provides important information in the early detection of colorectal cancer. Therefore,…

Segmentation

NeoUNet: Towards accurate colon polyp segmentation and neoplasm detection

2021-07-11 · Phan Ngoc Lan, Nguyen Sy An, Dao Viet Hang, Dao Van Long 외

Automatic polyp segmentation has proven to be immensely helpful for endoscopy procedures, reducing the missing rate of adenoma detection for endoscopists while increasing efficiency. However, classifying a polyp as being…

Medical Image SegmentationSegmentation

MixPolyp: Integrating Mask, Box and Scribble Supervision for Enhanced Polyp Segmentation

2024-09-25 · Yiwen Hu, Jun Wei, Yuncheng Jiang, Haoyang Li 외

Limited by the expensive labeling, polyp segmentation models are plagued by data shortages. To tackle this, we propose the mixed supervised polyp segmentation paradigm (MixPolyp). Unlike traditional models relying on a s…

SSTFB: Leveraging self-supervised pretext learning and temporal self-attention with feature branching for real-time video polyp segmentation

2024-06-14 · Ziang Xu, Jens Rittscher, Sharib Ali

Polyps are early cancer indicators, so assessing occurrences of polyps and their removal is critical. They are observed through a colonoscopy screening procedure that generates a stream of video frames. Segmenting polyps…

Representation LearningSelf-Supervised LearningVideo Polyp Segmentation