.png){kind=icon}
返回
Know your orientation: A viewpoint-aware framework for polyp segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.media.2024.103288.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automatic polyp segmentation in endoscopic images is critical for the early diagnosis of colorectal cancer. Despite the availability of powerful segmentation models, two challenges still impede the accuracy of polyp segmentation algorithms. Firstly, during a colonoscopy, physicians frequently adjust the orientation of the colonoscope tip to capture underlying lesions, resulting in viewpoint changes in the colonoscopy images. These variations increase the diversity of polyp visual appearance, posing a challenge for learning robust polyp features. Secondly, polyps often exhibit properties similar to the surrounding tissues, leading to indistinct polyp boundaries. To address these problems, we propose a viewpoint-aware framework named VANet for precise polyp segmentation. In VANet, polyps are emphasized as a discriminative feature and thus can be localized by class activation maps in a viewpoint classification process. With these polyp locations, we design a viewpoint-aware Transformer (VAFormer) to alleviate the erosion of attention by the surrounding tissues, thereby inducing better polyp representations. Additionally, to enhance the polyp boundary perception of the network, we develop a boundary-aware Transformer (BAFormer) to encourage self-attention towards uncertain regions. As a consequence, the combination of the two modules is capable of calibrating predictions and significantly improving polyp segmentation performance. Extensive experiments on seven public datasets across six metrics demonstrate the state-of-the-art results of our method, and VANet can handle colonoscopy images in real-world scenarios effectively. The source code is available at https://github.com/1024803482/ViewpointAware-Network.
Keyword:
Colonoscopy image
Polyp segmentation
Viewpoint classification
Viewpoint-aware transformer
Boundary-aware transformer
期刊
IF:
11.8
论文数:
3.9K
被引数:
2.4W
机构
引用论文
WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians在结肠镜检查中准确突出显示息肉的wm-dova地图: 医生的验证与显著性地图
PREAI
分享收藏Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps卷积神经网络用于结直肠息肉语义分割的不确定性和可解释性.png)
MEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏Cross-level Feature Aggregation Network for Polyp Segmentation用于息肉分割的跨层次特征聚合网络PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning基于深度学习的结肠镜实时息肉检测、定位和分割IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
PREAI
分享收藏分享收藏
查看更多内容