Improving Quality Control of Whole Slide Images by Explicit Artifact Augmentation

TL;DR

This paper introduces an artifact augmentation method for whole slide images to improve artifact detection, significantly enhancing classification performance and supporting open science in histopathology quality control.

Contribution

It presents a novel artifact augmentation tool that generates and blends artifacts into histopathology images, aiding the training of artifact classification models.

Findings

Artifact augmentation improves classification AUROC from 0.10 to 0.01.

The framework and annotations are freely available for research.

Enhanced artifact detection supports better quality control in histopathology.

Abstract

The problem of artifacts in whole slide image acquisition, prevalent in both clinical workflows and research-oriented settings, necessitates human intervention and re-scanning. Overcoming this challenge requires developing quality control algorithms, that are hindered by the limited availability of relevant annotated data in histopathology. The manual annotation of ground-truth for artifact detection methods is expensive and time-consuming. This work addresses the issue by proposing a method dedicated to augmenting whole slide images with artifacts. The tool seamlessly generates and blends artifacts from an external library to a given histopathology dataset. The augmented datasets are then utilized to train artifact classification methods. The evaluation shows their usefulness in classification of the artifacts, where they show an improvement from 0.10 to 0.01 AUROC depending on the artifact type. The framework, model, weights, and ground-truth annotations are freely released to facilitate open science and reproducible research.