Validating Whole Slide Imaging Systems for Diagnosis: Updated Guidelines

Whole slide imaging (WSI) entails the use of systems to scan entire glass slides to generate digital tissue images. Since the emergence of whole slide scanning systems approximately two decades ago, there have been significant advances in WSI technologies.1

The potentials of WSI in pathology and disease diagnosis are tremendous. Indeed, WSI is set to transform modern pathology and the way diseases are diagnosed based on tissue biopsies.2

Instead of observing stained tissue slides under microscopes used in traditional pathology, digital whole slide images can be reviewed using computerized systems. In addition to remote slide reviewing, WSI also facilitates easy sharing of pathology images among collaborators across the globe.1

The adoption of WSI in pathology laboratories has reached unprecedented levels in recent years, and despite its many advantages, guidelines are required to confirm the performance and diagnostic accuracy of WSI systems before they are used for diagnostic purposes.

First guidelines on WSI validation and the need for updated guidelines

The first guidelines on the clinical validation of WSI systems for diagnostic purposes were published in 2013 by the College of American Pathologists (CAP) and the Laboratory Quality Center. The original guidelines included 12 recommendations.3

Since the publication of the original CAP guidelines of 2013, the US Food and Drug Administration (FDA) has granted regulatory approval for the use of WSI in surgical pathology and primary diagnosis.4

To address the challenges posed by the rapid advances in WSI hardware and software, the CAP joined forces with the American Society for Clinical Pathology (ASCP) and the Association for Pathology Informatics (API) to update the WSI validation guidelines.

These organizations jointly assembled an expert panel of pathologists and histotechnologists to evaluate the findings of studies on the performance of WSI systems. The panel was led by Dr. Andrew J. Evans, Medical Director of Laboratory Medicine at Mackenzie Health and chair of the CAP Digital and Computational Pathology Committee.

The expert panel established updated recommendations for validating diagnostic WSI systems based on evidence from recent studies (2012 onwards) and following standards set by the National Academies of Medicine for developing trustworthy clinical practice guidelines.5

Providing evidence-based recommendations

To ensure that the guidelines are updated based on high-quality evidence, the expert panel conducted a systematic review of studies on how to best validate WSI systems. Studies published between 2012 and 2019 were included in this systematic review. During their comprehensive review of the literature, the experts screened over 1,800 titles and abstracts and reviewed 173 full-text manuscripts.5

The panel extracted data from 62 studies selected using the Grading of Recommendations Assessment Development and Evaluation (GRADE) approach,6 and updated the original guidelines of 2013 based on information gathered through a systematic review of evidence.

Updated guidelines: What needs to be done to validate WSI for diagnostic purposes?

All WSI systems intended for use in patient care should be validated for clinical purposes before their clinical implementation. The updated guidelines reassert most aspects of the original guidelines and provide three strong recommendations and nine good practice statements. The key aspect differentiating a recommendation from a good practice statement in the updated guidelines is the strength of evidence. In contrast to strong recommendations, good practice statements lack sufficient direct evidence from the literature.

According to the updated recommendations, validation of the diagnostic WSI should be performed in a validation set consisting of at least 60 samples to establish intraobserver concordance between WSI and glass slide diagnoses. This validation set should include samples that capture a broad spectrum of specimen types and diagnoses. A washout period of at least two weeks between the review of digital whole slide images and glass slides is recommended.5

This validation process allows the intraobserver diagnostic concordance between digital images and glass slides to be measured. If the discordance rate is over 5%, the WSI system should be extensively reviewed to identify and correct systematic problems before its application for diagnostic purposes. Interobserver variability is not believed to reflect differences arising from the use of different technologies; thus, assessing interobserver variability is not part of the WSI validation guidelines.5

According to the good practice statements, all pathology laboratories implementing WSI for diagnostic purposes should perform their own validation assessments. The validation of the WSI system should be carried out in a real-world setting by a pathologist trained to use the system. The WSI system should be validated as a whole, and the performance of the entire system should be reassessed whenever there are changes in any of its components. Detailed validation methods and measurements should be documented and recorded. Documentation of the final approval of the system should also be maintained.5

Review and publication of the updated guidelines

The new recommendations and good practice statements underwent extensive review by different stakeholders and bodies, including an external expert review panel, an internal advisory panel, and CAP legal representatives.

The updated guidelines were also subjected to a three-week public comment period. After being reviewed, the final guidelines were published in the journal Archives of Pathology & Laboratory Medicine on May 18, 2021.5

 Future perspectives

WSI and other advanced digital technologies have greatly benefited pathology and opened new avenues for accurate primary diagnosis, telepathology, automated microdissection, quality assurance review, and intraoperative consultation. When used for diagnostic purposes, validated WSI systems can improve diagnostic accuracy and workflow efficiency.

The establishment of guidelines for the validation of diagnostic WSI has played a fundamental role in the clinical adoption of WSI systems in clinical laboratories. As technologies continue to evolve and clinical applications of WSI expand, it is imperative that recommendations, good practice guidelines, and quality control protocols are regularly updated and refined.

It is also necessary that all institutions and hospitals considering the adoption of WSI in patient care validate the performance of the system in accordance with the latest recommendation and guidelines to ensure the diagnostic accuracy of the system and that pathologists can leverage the full potentials of WSI in clinical diagnosis.


References

  1. Hanna MG, Parwani A, Sirintrapun SJ. Whole Slide Imaging: Technology and Applications. Adv Anat Pathol. 2020;27(4):251-259. doi:10.1097/PAP.0000000000000273
  2. Kumar N, Gupta R, Gupta S. Whole Slide Imaging (WSI) in Pathology: Current Perspectives and Future Directions. J Digit Imaging. 2020;33(4):1034-1040. doi:10.1007/s10278-020-00351-z
  3. Pantanowitz L, Sinard JH, Henricks WH, et al. Validating whole slide imaging for diagnostic purposes in pathology: guideline from the College of American Pathologists Pathology and Laboratory Quality Center. Arch Pathol Lab Med. 2013;137(12):1710-1722. doi:10.5858/arpa.2013-0093-CP
  4. Hanna MG, Reuter VE, Ardon O, et al. Validation of a digital pathology system including remote review during the COVID-19 pandemic. Mod Pathol. 2020;33(11):2115-2127. doi:10.1038/s41379-020-0601-5
  5. Evans AJ, Brown RW, Bui MM, et al. Validating Whole Slide Imaging Systems for Diagnostic Purposes in Pathology: Guideline Update From the College of American Pathologists in Collaboration With the American Society for Clinical Pathology and the Association for Pathology Informatics. Arch Pathol Lab Med. May 2021. doi:10.5858/arpa.2020-0723-CP
  6. Guyatt GH, Oxman AD, Vist GE, et al. GRADE: an emerging consensus on rating quality of evidence and strength of recommendations. BMJ. 2008;336(7650):924-926. doi:10.1136/bmj.39489.470347.AD

 

 

 

Christos received his Masters in Cancer Biology from Heidelberg University and PhD from the University of Manchester.  After working as a scientist in cancer research for ten years, Christos decided to switch gears and start a career as a medical writer and editor. He is passionate about communicating science and translating complex science into clear messages for the scientific community and the wider public.

Share This Post

Leave a Reply