Cluster Entropy: Active Domain Adaptation in Pathological Image Segmentation
Cluster Entropy: Active Domain Adaptation in Pathological Image Segmentation
复制标题
DOI：
10.1109/isbi53787.2023.10230359
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Xiaoqing Liu;Kengo Araki;S. Harada;A. Yoshizawa;K. Terada;M. Kurata;N. Nakajima;Hiroyuki Abe
中科院分区：
文献类型：
--
作者：
Xiaoqing Liu;Kengo Araki;S. Harada;A. Yoshizawa;K. Terada;M. Kurata;N. Nakajima;Hiroyuki Abe
病理分割中的域偏移是一个重要问题，其中由源域（在特定医院收集）训练的网络由于不同的图像特征而在目标域（来自不同医院）中不能很好地工作。由于病理学的类别不平衡和不同类别先验的问题，典型的无监督域自适应方法不能很好地通过对齐源域和目标域的分布来工作。在本文中，我们提出了一个聚类熵选择一个有效的整个幻灯片图像（WSI），用于半监督域适应。该方法通过计算每个簇的熵来衡量WSI图像特征对目标域的覆盖程度，可以显著提高域自适应性能。我们的方法在从两家医院收集的数据集上取得了与现有技术相比具有竞争力的结果。
The domain shift in pathological segmentation is an important problem, where a network trained by a source domain (collected at a specific hospital) does not work well in the target domain (from different hospitals) due to the different image features. Due to the problems of class imbalance and different class prior of pathology, typical unsupervised domain adaptation methods do not work well by aligning the distribution of source domain and target domain. In this paper, we propose a cluster entropy for selecting an effective whole slide image (WSI) that is used for semi-supervised domain adaptation. This approach can measure how the image features of the WSI cover the entire distribution of the target domain by calculating the entropy of each cluster and can significantly improve the performance of domain adaptation. Our approach achieved competitive results against the prior arts on datasets collected from two hospitals.