Learning to be EXACT, Cell Detection for Asthma on Partially Annotated Whole Slide Images

TL;DR

This paper introduces a novel deep learning training pipeline for cell detection in whole slide images of asthma, capable of learning from partially annotated data and outperforming traditional methods.

Contribution

The authors develop a training pipeline that enables effective deep learning-based cell detection from partially annotated WSIs, addressing annotation labor constraints.

Findings

Outperforms classical sub-image training by up to 15% mAP

Achieves human-like performance compared to trained pathologists

Works effectively with partially annotated WSIs

Abstract

Asthma is a chronic inflammatory disorder of the lower respiratory tract and naturally occurs in humans and animals including horses. The annotation of an asthma microscopy whole slide image (WSI) is an extremely labour-intensive task due to the hundreds of thousands of cells per WSI. To overcome the limitation of annotating WSI incompletely, we developed a training pipeline which can train a deep learning-based object detection model with partially annotated WSIs and compensate class imbalances on the fly. With this approach we can freely sample from annotated WSIs areas and are not restricted to fully annotated extracted sub-images of the WSI as with classical approaches. We evaluated our pipeline in a cross-validation setup with a fixed training set using a dataset of six equine WSIs of which four are partially annotated and used for training, and two fully annotated WSI are used for validation and testing. Our WSI-based training approach outperformed classical sub-image-based training methods by up to 15\% $mAP$ and yielded human-like performance when compared to the annotations of ten trained pathologists.