Digital pathology and computational image analysis in nephropathology

• Published in: Nature reviews. Nephrology Vol. 16; no. 11; pp. 669 - 685
• Main Authors: Barisoni, Laura, Lafata, Kyle J., Hewitt, Stephen M., Madabhushi, Anant, Balis, Ulysses G. J.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01-11-2020; Nature Publishing Group
• Subjects: 631/553; 692/4022/1585; Care and treatment; Diagnosis; Diagnostic imaging; Disease; Humans; Image Interpretation, Computer-Assisted; Image Processing, Computer-Assisted - trends; Kidney diseases; Kidney Diseases - diagnostic imaging; Kidney Diseases - pathology; Machine Learning; Medical research; Medicine; Medicine & Public Health; Medicine, Experimental; Nephrology; Nephrology - trends; Pathology; Precision Medicine; Review; Review Article; Technology application; Vision systems; United States
• ISSN: 1759-5061; 1759-507X
• DOI: 10.1038/s41581-020-0321-6

The emergence of digital pathology — an image-based environment for the acquisition, management and interpretation of pathology information supported by computational techniques for data extraction and analysis — is changing the pathology ecosystem. In particular, by virtue of our new-found ability to generate and curate digital libraries, the field of machine vision can now be effectively applied to histopathological subject matter by individuals who do not have deep expertise in machine vision techniques. Although these novel approaches have already advanced the detection, classification, and prognostication of diseases in the fields of radiology and oncology, renal pathology is just entering the digital era, with the establishment of consortia and digital pathology repositories for the collection, analysis and integration of pathology data with other domains. The development of machine-learning approaches for the extraction of information from image data, allows for tissue interrogation in a way that was not previously possible. The application of these novel tools are placing pathology centre stage in the process of defining new, integrated, biologically and clinically homogeneous disease categories, to identify patients at risk of progression, and shifting current paradigms for the treatment and prevention of kidney diseases.
Developments in digital pathology and computational image analysis have the potential to identify new disease mechanisms, improve disease classification and prognostication, and ultimately aid the identification of targeted therapies. In this Review, the authors provide an outline of the digital ecosystem in nephropathology and describe potential applications and challenges associated with the emerging armamentarium of technologies for image analysis.
Key points
The introduction of digital pathology in clinical research, trials and practice has catalysed the development of novel machine-learning models for tissue interrogation with the potential to improve our ability to discover disease mechanisms, identify comprehensive, patient-specific phenotypes, classify kidney patients into clinically relevant categories, predict disease outcome and, ultimately, identify more targeted therapies.
The development of computational image analysis tools for tissue interrogation has brought pathology to the forefront in this process of re-defining kidney diseases.
The new nephropathology ecosystem offers several advantages over conventional pathology but also brings some challenges that need to be addressed collectively by all the stake holders, including pathologists, nephrologists, computer scientists, regulatory agencies and patient’s representatives; overcoming these challenges is a pre-requisite for these new machine-learning and computational pathology models to be fully deployed for patient care.
The development of novel powerful computational tools for image analysis and data integration in kidney diseases has exposed the need to revise the curriculum for medical professionals to prepare the next generation to fully operate within the new digital pathology ecosystem.
Ultimately, our ability to treat kidney diseases (actionable intelligence) will be largely based on the application of artificial (augmenting) intelligence tools and the establishment of synergistic human–machine protocols that integrate digital pathology data with clinical and molecular data for personalized nephrology.