Automated reporting of cervical biopsies using artificial intelligence

Mahnaz Mohammadi; Christina Fell; David Morrison; Sheeba Syed; Prakash Konanahalli; Sarah Bell; Gareth Bryson; Ognjen Arandjelović; David J. Harrison; David Harris-Birtill

doi:10.1371/journal.pdig.0000381

Automated reporting of cervical biopsies using artificial intelligence

Mahnaz Mohammadi^*, Christina Fell, David Morrison, Sheeba Syed, Prakash Konanahalli, Sarah Bell, Gareth Bryson, Ognjen Arandjelović, David J. Harrison, David Harris-Birtill

^*Corresponding author for this work

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

8 Downloads (Pure)

Abstract

When detected at an early stage, the 5-year survival rate for people with invasive cervical cancer is 92%. Being aware of signs and symptoms of cervical cancer and early detection greatly improve the chances of successful treatment. We have developed an Artificial Intelligence (AI) algorithm, trained and evaluated on cervical biopsies for automated reporting of digital diagnostics. The aim is to increase overall efficiency of pathological diagnosis and to have the performance tuned to high sensitivity for malignant cases. Having a tool for triage/identifying cancer and high grade lesions may potentially reduce reporting time by identifying areas of interest in a slide for the pathologist and therefore improving efficiency. We trained and validated our algorithm on 1738 cervical WSIs with one WSI per patient. On the independent test set of 811 WSIs, we achieved 93.4% malignant sensitivity for classifying slides. Recognising a WSI, with our algorithm, takes approximately 1.5 minutes on the NVIDIA Tesla V100 GPU. Whole slide images of different formats (TIFF, iSyntax, and CZI) can be processed using this code, and it is easily extendable to other formats.

Original language	English
Article number	e0000381
Journal	PLOS Digital Health
Volume	3
Issue number	4
DOIs	https://doi.org/10.1371/journal.pdig.0000381
Publication status	Published - 22 Apr 2024

UN SDGs

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

Access to Document

10.1371/journal.pdig.0000381Licence: CC BY

Mohammadi_2024_P-DH_Automated-reporting_CC
Copyright: © 2024 Mohammadi et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Final published version, 2.5 MBLicence: CC BY

ICAIRD: I-CAIRD: Industrial Centre for AI Research in Digital Diagnostics
Harris-Birtill, D. C. C. (PI) & Arandelovic, O. (CoI)
Technology Strategy Board
1/02/19 → 31/01/23
Project: Standard

Cervical whole slide images and annotations for automated reporting of cervical biopsies using artificial intelligence
Mohammadi, M. (Creator), Fell, C. (Creator), Morrison, D. (Creator), Syed, S. (Creator), Konanahalli, P. (Creator), Bell, S. (Creator), Bryson, G. (Creator), Harrison, D. (Creator), Harris-Birtill, D. (Creator) & Orange, C. (Creator), Zenodo, 6 Dec 2023
DOI: 10.5281/zenodo.10276838
Dataset

Cite this

@article{2864314ec0c04990ba3f1a23efa15f6e,

title = "Automated reporting of cervical biopsies using artificial intelligence",

abstract = "When detected at an early stage, the 5-year survival rate for people with invasive cervical cancer is 92%. Being aware of signs and symptoms of cervical cancer and early detection greatly improve the chances of successful treatment. We have developed an Artificial Intelligence (AI) algorithm, trained and evaluated on cervical biopsies for automated reporting of digital diagnostics. The aim is to increase overall efficiency of pathological diagnosis and to have the performance tuned to high sensitivity for malignant cases. Having a tool for triage/identifying cancer and high grade lesions may potentially reduce reporting time by identifying areas of interest in a slide for the pathologist and therefore improving efficiency. We trained and validated our algorithm on 1738 cervical WSIs with one WSI per patient. On the independent test set of 811 WSIs, we achieved 93.4% malignant sensitivity for classifying slides. Recognising a WSI, with our algorithm, takes approximately 1.5 minutes on the NVIDIA Tesla V100 GPU. Whole slide images of different formats (TIFF, iSyntax, and CZI) can be processed using this code, and it is easily extendable to other formats.",

author = "Mahnaz Mohammadi and Christina Fell and David Morrison and Sheeba Syed and Prakash Konanahalli and Sarah Bell and Gareth Bryson and Ognjen Arandjelovi{\'c} and Harrison, {David J.} and David Harris-Birtill",

note = "Funding: For all authors this work is supported by the Industrial Centre for AI Research in digital Diagnostics (iCAIRD) which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) [project number: 104690], and in part by Chief Scientist Office, Scotland. DJH, DHB, OA and GB received funding from UKRI (funder project reference: TS/S013121/1). MM, DM and CF received salaries from UKRI for this project. ",

year = "2024",

month = apr,

day = "22",

doi = "10.1371/journal.pdig.0000381",

language = "English",

volume = "3",

journal = "PLOS Digital Health",

issn = "2767-3170",

publisher = "Public Library of Science",

number = "4",

}

TY - JOUR

T1 - Automated reporting of cervical biopsies using artificial intelligence

AU - Mohammadi, Mahnaz

AU - Fell, Christina

AU - Morrison, David

AU - Syed, Sheeba

AU - Konanahalli, Prakash

AU - Bell, Sarah

AU - Bryson, Gareth

AU - Arandjelović, Ognjen

AU - Harrison, David J.

AU - Harris-Birtill, David

N1 - Funding: For all authors this work is supported by the Industrial Centre for AI Research in digital Diagnostics (iCAIRD) which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) [project number: 104690], and in part by Chief Scientist Office, Scotland. DJH, DHB, OA and GB received funding from UKRI (funder project reference: TS/S013121/1). MM, DM and CF received salaries from UKRI for this project.

PY - 2024/4/22

Y1 - 2024/4/22

N2 - When detected at an early stage, the 5-year survival rate for people with invasive cervical cancer is 92%. Being aware of signs and symptoms of cervical cancer and early detection greatly improve the chances of successful treatment. We have developed an Artificial Intelligence (AI) algorithm, trained and evaluated on cervical biopsies for automated reporting of digital diagnostics. The aim is to increase overall efficiency of pathological diagnosis and to have the performance tuned to high sensitivity for malignant cases. Having a tool for triage/identifying cancer and high grade lesions may potentially reduce reporting time by identifying areas of interest in a slide for the pathologist and therefore improving efficiency. We trained and validated our algorithm on 1738 cervical WSIs with one WSI per patient. On the independent test set of 811 WSIs, we achieved 93.4% malignant sensitivity for classifying slides. Recognising a WSI, with our algorithm, takes approximately 1.5 minutes on the NVIDIA Tesla V100 GPU. Whole slide images of different formats (TIFF, iSyntax, and CZI) can be processed using this code, and it is easily extendable to other formats.

AB - When detected at an early stage, the 5-year survival rate for people with invasive cervical cancer is 92%. Being aware of signs and symptoms of cervical cancer and early detection greatly improve the chances of successful treatment. We have developed an Artificial Intelligence (AI) algorithm, trained and evaluated on cervical biopsies for automated reporting of digital diagnostics. The aim is to increase overall efficiency of pathological diagnosis and to have the performance tuned to high sensitivity for malignant cases. Having a tool for triage/identifying cancer and high grade lesions may potentially reduce reporting time by identifying areas of interest in a slide for the pathologist and therefore improving efficiency. We trained and validated our algorithm on 1738 cervical WSIs with one WSI per patient. On the independent test set of 811 WSIs, we achieved 93.4% malignant sensitivity for classifying slides. Recognising a WSI, with our algorithm, takes approximately 1.5 minutes on the NVIDIA Tesla V100 GPU. Whole slide images of different formats (TIFF, iSyntax, and CZI) can be processed using this code, and it is easily extendable to other formats.

U2 - 10.1371/journal.pdig.0000381

DO - 10.1371/journal.pdig.0000381

M3 - Article

SN - 2767-3170

VL - 3

JO - PLOS Digital Health

JF - PLOS Digital Health

IS - 4

M1 - e0000381

ER -

Automated reporting of cervical biopsies using artificial intelligence

Abstract

UN SDGs

Access to Document

Fingerprint

Projects

ICAIRD: I-CAIRD: Industrial Centre for AI Research in Digital Diagnostics

Datasets

Cervical whole slide images and annotations for automated reporting of cervical biopsies using artificial intelligence

Cite this