by: Cleopatra Kozlowski, PhD, Scientist; Genentech Inc.

 

Recently the term ‘computational pathology’ has been used a great deal among the digital pathology community, yet it sometimes leads to confusion due to its use in different contexts. In order to help advance this exciting new field, in our new white paper experts from the Digital Pathology Association (DPA) define terminology and concepts in computational pathology, with a focus on its application to histology images analyzed together with their associated patient data to extract information. We offer a historical perspective on whole slide imaging, and discuss the dramatic changes brought to digital pathology by the advent of deep learning.  We then describe the potential clinical benefits from research and applications in this field, but also place considerable emphasis on the significant obstacles to adoption, and suggest solutions. Best practices for implementing computational pathology workflows are presented. These include infrastructure considerations, acquisition of training data, quality assessments, as well as regulatory, ethical and cyber-security concerns. Recommendations are provided for regulators, vendors, and computational pathology practitioners in order to facilitate progress in the field, which has enormous potential to revolutionize personalized healthcare.

 

To access the full white paper, please click here.

 

Please also click here for an editorial from the The Journal of Pathology highlighting this paper and announcing a call for papers.

 

Disclaimer: In seeking to foster discourse on a wide array of ideas, the Digital Pathology Association believes that it is important to share a range of prominent industry viewpoints. This article does not necessarily express the viewpoints of the DPA, however we view this as a valuable point with which to facilitate discussion.