Keywords: Multi-class artifact segmentation, quality control, digital pathology
TL;DR: A multi-class deep learning model is proposed for the segmentation of six artifacts commonly-seen in whole-slide histopathology images and it is extended into a quality control system for use-case demonstration in clinical practice.
Abstract: Quality control is an integral part in the digitization process of whole-slide histopathology images due to artifacts that arise during various stages of slide preparation. Manual control and supervision of these gigapixel images are labor-intensive. Therefore, we report the first multi-class deep learning model trained on whole-slide images covering multiple tissue and stain types for semantic segmentation of artifacts. Our approach reaches a Dice score of 0.91, on average, across six artifact types, and outperforms the competition on external test set. Finally, we extend the artifact segmentation network to a multi-decision quality control system that can be deployed in routine clinical practice.
Paper Type: validation/application paper
Primary Subject Area: Segmentation
Secondary Subject Area: Application: Histopathology
Paper Status: original work, not submitted yet
Source Code Url: Online tool: https://grand-challenge.org/algorithms/quality-assessment-of-whole-slide-images-through-a/ Code repo: https://github.com/DIAGNijmegen/pathology-artifact-detection
Data Set Url: Our data set contains digitized pathology images from multiple study groups collected from different centers. Unfortunately, we cannot make our data set public based on the data transfer agreements at this time.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.