Spatial Distribution-Based Pseudo Labeling for Pathological Image Segmentation
Spatial Distribution-Based Pseudo Labeling for Pathological Image Segmentation
复制标题
DOI：
10.1109/isbi53787.2023.10230407
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Yuki Shigeyasu;Kengo Araki;S. Harada;A. Yoshizawa;K. Terada;Ryoma Bise
中科院分区：
文献类型：
--
作者：
Yuki Shigeyasu;Kengo Araki;S. Harada;A. Yoshizawa;K. Terada;Ryoma Bise
本文提出了一种半监督的病理图像分割方法，可以改善分割使用大量的未标记的数据。典型的伪标记方法基于每个补丁的置信度从未标记的数据中选择伪标记以用于重新训练。然而，初始估计是不准确的，因此伪标签包含许多不准确的标签。这可能会影响分割性能。本研究的亮点是，我们避免选择不正确的伪标签，通过引入一个空间分布模型，在整个幻灯片图像。这是基于肿瘤区域在组织中形成簇的假设。这提高了伪标签选择和分割性能。实验结果证明了我们方法的有效性，相比之下我们的方法获得了最好的分割性能。
This paper proposes a semi-supervised pathological image segmentation method that can improve the segmentation using a large amount of unlabeled data. Typical pseudo labeling methods select pseudo labels from unlabeled data to be used for re-training based on the confidence of each patch. However, the initial estimation is not accurate, so the pseudo labels contain many inaccurate labels. This may affect the segmentation performance. The highlight of this study is that we avoid selecting incorrect pseudo labels by introducing a spatial distribution model in a whole slide image. This is based on the assumption that a tumor region forms a cluster in tissue. This improves pseudo label selection and segmentation performance. Experimental results demonstrate the effectiveness of our method, where our method achieved the best segmentation performance in comparison.