General Roadmap and Core Steps for the Development of AI Tools in Digital Pathology

Yasmine Makhlouf; Manuel Salto-Tellez; Jacqueline James; Paul O’Reilly; Perry Maxwell

doi:10.3390/diagnostics12051272

General Roadmap and Core Steps for the Development of AI Tools in Digital Pathology

Yasmine Makhlouf, Manuel Salto-Tellez, Jacqueline James, Paul O’Reilly^*, Perry Maxwell

^*Corresponding author for this work

Patrick G Johnston Centre for Cancer Research

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

141 Downloads (Pure)

Abstract

Integrating Artificial Intelligence (AI) tools in the tissue diagnostic workflow will benefit the pathologist and, ultimately, the patient. The generation of such AI tools has two parallel yet interconnected processes, namely the definition of the pathologist’s task to be delivered in silico, and the software development requirements. In this review paper, we demystify this process, from a viewpoint that joins experienced pathologists and data scientists, by proposing a general pathway and describing the core steps to build an AI digital pathology tool. In doing so, we highlight the importance of the collaboration between AI scientists and pathologists, from the initial formulation of the hypothesis to the final, ready-to-use product.

Original language	English
Article number	e1272
Number of pages	8
Journal	Diagnostics
Volume	12
Issue number	5
Early online date	20 May 2022
DOIs	https://doi.org/10.3390/diagnostics12051272
Publication status	Early online date - 20 May 2022

Keywords

artificial intelligence
digital pathology
human-AI interaction
diagnostic
machine learning
deep learning

Access to Document

10.3390/diagnostics12051272Licence: CC BY

General Roadmap and Core Steps for the Development of AI Tools in Digital Pathology
© 2022 The Authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final published version, 643 KBLicence: CC BY

Cite this

@article{ea559d24382b4cbbb0411f85f1be2d87,

title = "General Roadmap and Core Steps for the Development of AI Tools in Digital Pathology",

abstract = "Integrating Artificial Intelligence (AI) tools in the tissue diagnostic workflow will benefit the pathologist and, ultimately, the patient. The generation of such AI tools has two parallel yet interconnected processes, namely the definition of the pathologist{\textquoteright}s task to be delivered in silico, and the software development requirements. In this review paper, we demystify this process, from a viewpoint that joins experienced pathologists and data scientists, by proposing a general pathway and describing the core steps to build an AI digital pathology tool. In doing so, we highlight the importance of the collaboration between AI scientists and pathologists, from the initial formulation of the hypothesis to the final, ready-to-use product.",

keywords = "artificial intelligence, digital pathology, human-AI interaction, diagnostic, machine learning, deep learning",

author = "Yasmine Makhlouf and Manuel Salto-Tellez and Jacqueline James and Paul O{\textquoteright}Reilly and Perry Maxwell",

year = "2022",

month = may,

day = "20",

doi = "10.3390/diagnostics12051272",

language = "English",

volume = "12",

journal = "Diagnostics",

publisher = "MDPI",

number = "5",

}

TY - JOUR

T1 - General Roadmap and Core Steps for the Development of AI Tools in Digital Pathology

AU - Makhlouf, Yasmine

AU - Salto-Tellez, Manuel

AU - James, Jacqueline

AU - O’Reilly, Paul

AU - Maxwell, Perry

PY - 2022/5/20

Y1 - 2022/5/20

N2 - Integrating Artificial Intelligence (AI) tools in the tissue diagnostic workflow will benefit the pathologist and, ultimately, the patient. The generation of such AI tools has two parallel yet interconnected processes, namely the definition of the pathologist’s task to be delivered in silico, and the software development requirements. In this review paper, we demystify this process, from a viewpoint that joins experienced pathologists and data scientists, by proposing a general pathway and describing the core steps to build an AI digital pathology tool. In doing so, we highlight the importance of the collaboration between AI scientists and pathologists, from the initial formulation of the hypothesis to the final, ready-to-use product.

AB - Integrating Artificial Intelligence (AI) tools in the tissue diagnostic workflow will benefit the pathologist and, ultimately, the patient. The generation of such AI tools has two parallel yet interconnected processes, namely the definition of the pathologist’s task to be delivered in silico, and the software development requirements. In this review paper, we demystify this process, from a viewpoint that joins experienced pathologists and data scientists, by proposing a general pathway and describing the core steps to build an AI digital pathology tool. In doing so, we highlight the importance of the collaboration between AI scientists and pathologists, from the initial formulation of the hypothesis to the final, ready-to-use product.

KW - artificial intelligence

KW - digital pathology

KW - human-AI interaction

KW - diagnostic

KW - machine learning

KW - deep learning

U2 - 10.3390/diagnostics12051272

DO - 10.3390/diagnostics12051272

M3 - Article

VL - 12

JO - Diagnostics

JF - Diagnostics

IS - 5

M1 - e1272

ER -

General Roadmap and Core Steps for the Development of AI Tools in Digital Pathology

Abstract

Keywords

Access to Document

Fingerprint

Cite this