2000 character limit reached
Consisaug: A Consistency-based Augmentation for Polyp Detection in Endoscopy Image Analysis (2404.11355v1)
Published 17 Apr 2024 in cs.CV
Abstract: Colorectal cancer (CRC), which frequently originates from initially benign polyps, remains a significant contributor to global cancer-related mortality. Early and accurate detection of these polyps via colonoscopy is crucial for CRC prevention. However, traditional colonoscopy methods depend heavily on the operator's experience, leading to suboptimal polyp detection rates. Besides, the public database are limited in polyp size and shape diversity. To enhance the available data for polyp detection, we introduce Consisaug, an innovative and effective methodology to augment data that leverages deep learning. We utilize the constraint that when the image is flipped the class label should be equal and the bonding boxes should be consistent. We implement our Consisaug on five public polyp datasets and at three backbones, and the results show the effectiveness of our method.
- Magnitude, risk factors, and factors associated with adenoma miss rate of tandem colonoscopy: a systematic review and meta-analysis. Gastroenterology, 156(6):1661–1674, 2019.
- Physician sentiment toward artificial intelligence (ai) in colonoscopic practice: a survey of us gastroenterologists. Endoscopy international open, 8(10):E1379–E1384, 2020.
- Asge technology committee systematic review and meta-analysis assessing the asge pivi thresholds for adopting real-time endoscopic assessment of the histology of diminutive colorectal polyps. Gastrointestinal endoscopy, 81(3):502–e1, 2015.
- Best of both worlds: human-machine collaboration for object annotation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2121–2131, 2015.
- Transresu-net: Transformer based resu-net for real-time colonoscopy polyp segmentation. arXiv preprint arXiv:2206.08985, 2022.
- Pranet: Parallel reverse attention network for polyp segmentation. In International conference on medical image computing and computer-assisted intervention, pages 263–273. Springer, 2020.
- Maf-net: Multi-branch anchor-free detector for polyp localization and classification in colonoscopy. In International Conference on Medical Imaging with Deep Learning, pages 1162–1172. PMLR, 2022.
- Yona: You only need one adjacent reference-frame for accurate and fast video polyp detection. arXiv preprint arXiv:2306.03686, 2023.
- Wm-dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized medical imaging and graphics, 43:99–111, 2015.
- Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. International journal of computer assisted radiology and surgery, 9:283–293, 2014.
- Towards automatic polyp detection with a polyp appearance model. Pattern Recognition, 45(9):3166–3182, 2012.
- Hyperkvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Scientific data, 7(1):283, 2020.
- Ldpolypvideo benchmark: a large-scale colonoscopy video dataset of diverse polyps. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part V 24, pages 387–396. Springer, 2021.
- Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242, 2016.
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
- Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence, 41(8):1979–1993, 2018.
- Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
- Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10687–10698, 2020.
- ultralytics/yolov5: v7. 0-yolov5 sota realtime instance segmentation. Zenodo, 2022.
- Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pages 21–37. Springer, 2016.
- End-to-end object detection with transformers. In European conference on computer vision, pages 213–229. Springer, 2020.
- Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.