Comparison of Different Methods for Tissue Segmentation in Histopathological Whole-Slide Images
This work addresses the problem of inaccurate tissue detection in digital pathology for pathologists and researchers, but it is incremental as it compares new methods to existing ones without a major breakthrough.
The paper tackled tissue segmentation in histopathological whole-slide images by introducing two convolutional neural network architectures and comparing them to a traditional method, achieving Jaccard indices of 0.937 and 0.929 versus 0.870 with statistical significance.
Tissue segmentation is an important pre-requisite for efficient and accurate diagnostics in digital pathology. However, it is well known that whole-slide scanners can fail in detecting all tissue regions, for example due to the tissue type, or due to weak staining because their tissue detection algorithms are not robust enough. In this paper, we introduce two different convolutional neural network architectures for whole slide image segmentation to accurately identify the tissue sections. We also compare the algorithms to a published traditional method. We collected 54 whole slide images with differing stains and tissue types from three laboratories to validate our algorithms. We show that while the two methods do not differ significantly they outperform their traditional counterpart (Jaccard index of 0.937 and 0.929 vs. 0.870, p < 0.01).