组织病理学图像的半监督分割：噪声感知的拓扑一致性
Semi-supervised Segmentation of Histopathology Images with Noise-Aware Topological Consistency
AI总结：
针对半监督组织病理学图像分割中的拓扑错误问题，提出TopoSemiSeg方法，通过噪声感知的拓扑一致性损失对齐教师-学生模型，学习真实拓扑信号，提升分割性能。
摘要：
在数字病理学中，对腺体和细胞核等密集分布的对象进行分割对于下游分析至关重要。由于详细的像素级标注非常耗时，我们需要能够从未标注图像中学习的半监督分割方法。现有的半监督方法常常容易产生拓扑错误，例如，遗漏或错误合并/分离的腺体或细胞核。为了解决这一问题，我们提出了TopoSemiSeg，这是第一个从未标注的组织病理学图像中学习拓扑表示的半监督方法。主要挑战在于未标注图像；我们只有携带噪声拓扑的预测。为此，我们引入了一种噪声感知的拓扑一致性损失，以对齐教师和学生模型的表示。通过将预测的拓扑分解为信号拓扑和噪声拓扑，我们确保模型学习真实的拓扑信号并对噪声具有鲁棒性。在公开的组织病理学图像数据集上进行的大量实验表明，我们的方法具有优越性，尤其是在拓扑感知的评估指标上。代码可在https://github.com/Melon-Xu/TopoSemiSeg获取。
英文摘要：
In digital pathology, segmenting densely distributed objects like glands and nuclei is crucial for downstream analysis. Since detailed pixel-wise annotations are very time-consuming, we need semi-supervised segmentation methods that can learn from unlabeled images. Existing semi-supervised methods are often prone to topological errors, e.g., missing or incorrectly merged/separated glands or nuclei. To address this issue, we propose TopoSemiSeg, the first semi-supervised method that learns the topological representation from unlabeled histopathology images. The major challenge is for unlabeled images; we only have predictions carrying noisy topology. To this end, we introduce a noise-aware topological consistency loss to align the representations of a teacher and a student model. By decomposing the topology of the prediction into signal topology and noisy topology, we ensure that the models learn the true topological signals and become robust to noise. Extensive experiments on public histopathology image datasets show the superiority of our method, especially on topology-aware evaluation metrics. Code is available at https://github.com/Melon-Xu/TopoSemiSeg.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
