Seeded iterative clustering for histology region identification
This addresses the time-consuming and resource-intensive process of creating dense annotations for histopathology, which is a bottleneck for developing computer vision algorithms in medical imaging.
The paper tackles the problem of generating dense annotations for whole slide histopathology images by developing seeded iterative clustering, which uses sparse interactive annotations as seeds to classify image patches. This approach provides a fast and effective method for coarse segmentation at the whole slide level.
Annotations are necessary to develop computer vision algorithms for histopathology, but dense annotations at a high resolution are often time-consuming to make. Deep learning models for segmentation are a way to alleviate the process, but require large amounts of training data, training times and computing power. To address these issues, we present seeded iterative clustering to produce a coarse segmentation densely and at the whole slide level. The algorithm uses precomputed representations as the clustering space and a limited amount of sparse interactive annotations as seeds to iteratively classify image patches. We obtain a fast and effective way of generating dense annotations for whole slide images and a framework that allows the comparison of neural network latent representations in the context of transfer learning.