Physical Color Calibration of Digital Pathology Scanners for Robust Artificial Intelligence Assisted Cancer Diagnosis

• Main Authors: Ji, Xiaoyi, Salmon, Richard, Mulliqi, Nita, Khan, Umair, Wang, Yinxi, Blilie, Anders, Olsson, Henrik, Pedersen, Bodil Ginnerup, Sørensen, Karina Dalsgaard, Ulhøi, Benedicte Parm, Kjosavik, Svein R, Janssen, Emilius AM, Rantalainen, Mattias, Egevad, Lars, Ruusuvuori, Pekka, Eklund, Martin, Kartasalo, Kimmo
• Format: Journal Article
• Language: English
• Published: 07-07-2023
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computer Vision and Pattern Recognition; Quantitative Biology - Quantitative Methods
• DOI: 10.48550/arxiv.2307.05519

The potential of artificial intelligence (AI) in digital pathology is limited
by technical inconsistencies in the production of whole slide images (WSIs),
leading to degraded AI performance and posing a challenge for widespread
clinical application as fine-tuning algorithms for each new site is
impractical. Changes in the imaging workflow can also lead to compromised
diagnoses and patient safety risks. We evaluated whether physical color
calibration of scanners can standardize WSI appearance and enable robust AI
performance. We employed a color calibration slide in four different
laboratories and evaluated its impact on the performance of an AI system for
prostate cancer diagnosis on 1,161 WSIs. Color standardization resulted in
consistently improved AI model calibration and significant improvements in
Gleason grading performance. The study demonstrates that physical color
calibration provides a potential solution to the variation introduced by
different scanners, making AI-based cancer diagnostics more reliable and
applicable in clinical settings.