Open-source tool ensures quality of digital pathology images

Researchers have devised an approach for coping with the lack of reliable standards for the preparation and digitization of tissue slides used to diagnose patients.

Poor quality slides can result because of air bubbles and smears or during the digitization process, when blurriness and brightness issues can arise. However, manual review of these slides can be time-consuming and labor-intensive, as well as subject to intra- and inter-reader variability.

To ensure the quality of digital images for diagnostic and research purposes, researchers have developed an open-source tool that leverages different measurements and classifiers, which automatically flag corrupted images—while keeping those that are valuable for making diagnoses.



“The idea is simple—assess digital images and determine which slides are worthy for analysis by a computer and which are not,” says Anant Madabhushi, the F. Alex Nason Professor II of biomedical engineering at Case Western Reserve University’s School of Engineering. “This is important right now, as digital pathology is taking off worldwide and laying the groundwork for more use of (artificial intelligence) for interrogating tissue images.”

Also See: New tech could change how pathologists view tissue samples

Madabhushi and Andrew Janowczyk, a senior research fellow in Madabhushi's Center for Computational Imaging and Personal Diagnostics at CWRU, developed the quality-control tool—called HistoQC. They describe the tool in an article in the Journal of Clinical Oncology Clinical Informatics, along with researchers from Cleveland’s University Hospitals, the Perelman School of Medicine at the University of Pennsylvania and the Louis Stokes Cleveland VA Medical Center.

“The output of HistoQC on 450 slides from The Cancer Genome Atlas was reviewed by two pathologists and found to be suitable for computational analysis more than 95 percent of the time,” the authors contend. “These results suggest that HistoQC could provide an automated, quantifiable, quality control process for identifying artefacts and measuring slide quality, in turn helping to improve both the repeatability and robustness of (digital pathology) workflows.”