Computational pathology in cancer diagnosis, prognosis, and prediction – present day and prospects

Gregory Verghese; Jochen K. Lennerz; Danny Ruta; Wen Ng; Selvam Thavaraj; Kalliopi P. Siziopikou; Threnesan Naidoo; Swapnil Rane; Roberto Salgado; Sarah E. Pinder; Anita Grigoriadis

doi:10.1002/path.6163

Computational pathology in cancer diagnosis, prognosis, and prediction – present day and prospects

Gregory Verghese, Jochen K. Lennerz, Danny Ruta, Wen Ng, Selvam Thavaraj, Kalliopi P. Siziopikou, Threnesan Naidoo, Swapnil Rane, Roberto Salgado, Sarah E. Pinder, Anita Grigoriadis^*

^*Corresponding author for this work

Research output: Contribution to journal › Review article › peer-review

31 Citations (Scopus)

Abstract

Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists’ perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques.

Original language	English
Pages (from-to)	551-563
Number of pages	13
Journal	Journal of pathology
Volume	260
Issue number	5
DOIs	https://doi.org/10.1002/path.6163
Publication status	Published - Aug 2023

Keywords

biomarkers
computational pathology
deep learning
digital pathology
histopathology

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1002/path.6163

Cite this

@article{d1e5a91d0cad417f8ea2ff9ee520a222,

title = "Computational pathology in cancer diagnosis, prognosis, and prediction – present day and prospects",

abstract = "Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists{\textquoteright} perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques.",

keywords = "biomarkers, computational pathology, deep learning, digital pathology, histopathology",

author = "Gregory Verghese and Lennerz, {Jochen K.} and Danny Ruta and Wen Ng and Selvam Thavaraj and Siziopikou, {Kalliopi P.} and Threnesan Naidoo and Swapnil Rane and Roberto Salgado and Pinder, {Sarah E.} and Anita Grigoriadis",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.",

year = "2023",

month = aug,

doi = "10.1002/path.6163",

language = "English",

volume = "260",

pages = "551--563",

journal = "Journal of pathology",

issn = "0022-3417",

publisher = "Pathological Society of Great Britain and Ireland",

number = "5",

}

TY - JOUR

T1 - Computational pathology in cancer diagnosis, prognosis, and prediction – present day and prospects

AU - Verghese, Gregory

AU - Lennerz, Jochen K.

AU - Ruta, Danny

AU - Ng, Wen

AU - Thavaraj, Selvam

AU - Siziopikou, Kalliopi P.

AU - Naidoo, Threnesan

AU - Rane, Swapnil

AU - Salgado, Roberto

AU - Pinder, Sarah E.

AU - Grigoriadis, Anita

PY - 2023/8

Y1 - 2023/8

N2 - Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists’ perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques.

AB - Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists’ perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques.

KW - biomarkers

KW - computational pathology

KW - deep learning

KW - digital pathology

KW - histopathology

UR - http://www.scopus.com/inward/record.url?scp=85167983936&partnerID=8YFLogxK

U2 - 10.1002/path.6163

DO - 10.1002/path.6163

M3 - Review article

C2 - 37580849

AN - SCOPUS:85167983936

SN - 0022-3417

VL - 260

SP - 551

EP - 563

JO - Journal of pathology

JF - Journal of pathology

IS - 5

ER -

Computational pathology in cancer diagnosis, prognosis, and prediction – present day and prospects

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this