Physical Color Calibration of Digital Pathology Scanners for Deep Learning Based Diagnosis of Prostate Cancer

Xiaoyi Ji, Richard Salmon, Nita Mulliqi, Henrik Olsson, Lars Egevad, Pekka Ruusuvuori, Martin Eklund, Kimmo Kartasalo

Keywords: Color Calibration, Cancer Detection, Artificial Intelligence

TL;DR: We apply a commercial color calibration slide for standardising WSIs of prostate biopsies, and the results show that this calibration improves the diagnostic performance of an AI system for detecting prostate cancer.

Abstract: Variation in whole slide image (WSI) across different scanners poses a problem for deep learning algorithms. We apply a color calibration slide to standardize WSIs from different sites and evaluate the effect of calibration on a deep learning model for prostate cancer diagnosis. We show that calibration can significantly improve the accuracy of the model.

Registration: I acknowledge that acceptance of this work at MIDL 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.

Paper Type: novel methodological ideas without extensive validation

Primary Subject Area: Detection and Diagnosis

Secondary Subject Area: Application: Histopathology

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.