Multiple artifacts are present in virtually all histological slides digitized by modern scanning systems. These artifacts are related to tissue processing and sectioning, staining, and digitization itself.
Every artifact type can lead to significant and often critical (from the clinical point of view) misclassifications, such as false positive or false negative tumor tissue detection.
Here we develop the GrandQC tool for tissue and multi-class artifact segmentation. Slides from 19 international pathology departments digitized with themost common scanning systems and from The Cancer Genome Atlas dataset were used to establish a QC benchmark, analyzing inter-institutional, intra-institutional, temporal, and inter-scanner slide quality variations.
GrandQC allows for high precision tissue segmentation (Dice score 0.957) and segmentation of tissue without artifacts (Dice score 0.919–0.938 dependent on magnification).
GrandQC is an effective benchmark for pathology departments and scanning systems, allowing pathology departments to select the optimal scanning system for their particular slide quality while considering digitization.
【MORE】