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/Viewpoint-Aware-Network.

中文翻译：

---

了解你的方向：息肉分割的视点感知框架


内窥镜图像中的自动息肉分割对于结直肠癌的早期诊断至关重要。尽管存在强大的分割模型，但仍有两个挑战阻碍了息肉分割算法的准确性。首先，在结肠镜检查过程中，医生经常调整结肠镜尖端的方向以捕获潜在病变，导致结肠镜检查图像的视点发生变化。这些变化增加了息肉视觉外观的多样性，对学习稳健的息肉特征提出了挑战。其次，息肉通常表现出与周围组织相似的特性，导致息肉边界模糊。为了解决这些问题，我们提出了一种名为 VANet 的视点感知框架，用于精确的息肉分割。在 VANet 中，息肉被强调为一种判别特征，因此可以在视点分类过程中通过类激活图进行定位。利用这些息肉位置，我们设计了一个视点感知变压器（VAFormer）来减轻周围组织对注意力的侵蚀，从而诱导更好的息肉表示。此外，为了增强网络的息肉边界感知，我们开发了一个边界感知变压器（BAFormer）来鼓励对不确定区域的自我关注。因此，两个模块的组合能够校准预测并显着提高息肉分割性能。对七个公共数据集、六个指标的广泛实验证明了我们方法的最先进结果，并且 VANet 可以有效地处理现实场景中的结肠镜检查图像。源代码可在 https://github.com/1024803482/Viewpoint-Aware-Network 获取。