A Guided Spatial Transformer Network for Histology Cell Differentiation

TL;DR

This paper introduces a deep learning model with a spatial transformer for histology cell classification, achieving over 91% accuracy on a large dataset, aiding pathologists in more accurate cell counting.

Contribution

The novel integration of a spatial transformer network into a deep convolutional model for histology cell classification on a large dataset.

Findings

Achieved 91.45% mean accuracy in cross-validation.

Trained on a dataset with ten times more mitotic figures than previous datasets.

Demonstrated potential for semi-automated, objective cell counting in pathology.

Abstract

Identification and counting of cells and mitotic figures is a standard task in diagnostic histopathology. Due to the large overall cell count on histological slides and the potential sparse prevalence of some relevant cell types or mitotic figures, retrieving annotation data for sufficient statistics is a tedious task and prone to a significant error in assessment. Automatic classification and segmentation is a classic task in digital pathology, yet it is not solved to a sufficient degree. We present a novel approach for cell and mitotic figure classification, based on a deep convolutional network with an incorporated Spatial Transformer Network. The network was trained on a novel data set with ten thousand mitotic figures, about ten times more than previous data sets. The algorithm is able to derive the cell class (mitotic tumor cells, non-mitotic tumor cells and granulocytes) and their position within an image. The mean accuracy of the algorithm in a five-fold cross-validation is 91.45%. In our view, the approach is a promising step into the direction of a more objective and accurate, semi-automatized mitosis counting supporting the pathologist.