AI-enabled routine H E image based prognostic marker for early-stage luminal breast cancer

Abstract Breast cancer (BC) grade is a well-established subjective prognostic indicator of tumour aggressiveness. Tumour heterogeneity and subjective assessment result in high degree of variability among observers in BC grading. Here we propose an objective Haematoxylin & Eosin (H&E) image-b...

Full description

Saved in:
Bibliographic Details
Published in:NPJ precision oncology 2023-11, Vol.7 (1), p.1-13
Main Authors: Noorul Wahab, Michael Toss, Islam M. Miligy, Mostafa Jahanifar, Nehal M. Atallah, Wenqi Lu, Simon Graham, Mohsin Bilal, Abhir Bhalerao, Ayat G. Lashen, Shorouk Makhlouf, Asmaa Y. Ibrahim, David Snead, Fayyaz Minhas, Shan E. Ahmed Raza, Emad Rakha, Nasir Rajpoot
Format: Article
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 13
container_issue 1
container_start_page 1
container_title NPJ precision oncology
container_volume 7
creator Noorul Wahab
Michael Toss
Islam M. Miligy
Mostafa Jahanifar
Nehal M. Atallah
Wenqi Lu
Simon Graham
Mohsin Bilal
Abhir Bhalerao
Ayat G. Lashen
Shorouk Makhlouf
Asmaa Y. Ibrahim
David Snead
Fayyaz Minhas
Shan E. Ahmed Raza
Emad Rakha
Nasir Rajpoot
description Abstract Breast cancer (BC) grade is a well-established subjective prognostic indicator of tumour aggressiveness. Tumour heterogeneity and subjective assessment result in high degree of variability among observers in BC grading. Here we propose an objective Haematoxylin & Eosin (H&E) image-based prognostic marker for early-stage luminal/Her2-negative BReAst CancEr that we term as the BRACE marker. The proposed BRACE marker is derived from AI based assessment of heterogeneity in BC at a detailed level using the power of deep learning. The prognostic ability of the marker is validated in two well-annotated cohorts (Cohort-A/Nottingham: n = 2122 and Cohort-B/Coventry: n = 311) on early-stage luminal/HER2-negative BC patients treated with endocrine therapy and with long-term follow-up. The BRACE marker is able to stratify patients for both distant metastasis free survival (p = 0.001, C-index: 0.73) and BC specific survival (p 
doi_str_mv 10.1038/s41698-023-00472-y
format article
fullrecord <record><control><sourceid>doaj</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_a9e6a8e5c93b4edab4db8a7980977476</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_a9e6a8e5c93b4edab4db8a7980977476</doaj_id><sourcerecordid>oai_doaj_org_article_a9e6a8e5c93b4edab4db8a7980977476</sourcerecordid><originalsourceid>FETCH-doaj_primary_oai_doaj_org_article_a9e6a8e5c93b4edab4db8a79809774763</originalsourceid><addsrcrecordid>eNqtjU1OwzAQRi0kJCroBVjNBQxOnPpniVBRu2eB2FjjZBqlOHE1The5PQFxBFaf9PTpPSEeK_VUKe2eS1MZ76SqtVSqsbVcbsSm1t5Ka9zHndiWclZKVW5X1cZsxOfLUdKEMVEHnK_zMBEcYA_DiD1BxLLyC-d-ymUeWhiRv4jhlBkIOS2yzD-_dB2HCRNEJiwztDi1xA_i9oSp0PZv78Xxbf_-epBdxnO48JrgJWQcwi_I3AfkNZIooCeDjnat17GhDmPTRYfWO-WtbazR_-n6BiuSYrU</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>AI-enabled routine H E image based prognostic marker for early-stage luminal breast cancer</title><source>PubMed Central Free</source><source>Publicly Available Content Database</source><source>Alma/SFX Local Collection</source><source>Springer Nature - nature.com Journals - Fully Open Access</source><creator>Noorul Wahab ; Michael Toss ; Islam M. Miligy ; Mostafa Jahanifar ; Nehal M. Atallah ; Wenqi Lu ; Simon Graham ; Mohsin Bilal ; Abhir Bhalerao ; Ayat G. Lashen ; Shorouk Makhlouf ; Asmaa Y. Ibrahim ; David Snead ; Fayyaz Minhas ; Shan E. Ahmed Raza ; Emad Rakha ; Nasir Rajpoot</creator><creatorcontrib>Noorul Wahab ; Michael Toss ; Islam M. Miligy ; Mostafa Jahanifar ; Nehal M. Atallah ; Wenqi Lu ; Simon Graham ; Mohsin Bilal ; Abhir Bhalerao ; Ayat G. Lashen ; Shorouk Makhlouf ; Asmaa Y. Ibrahim ; David Snead ; Fayyaz Minhas ; Shan E. Ahmed Raza ; Emad Rakha ; Nasir Rajpoot</creatorcontrib><description>Abstract Breast cancer (BC) grade is a well-established subjective prognostic indicator of tumour aggressiveness. Tumour heterogeneity and subjective assessment result in high degree of variability among observers in BC grading. Here we propose an objective Haematoxylin &amp; Eosin (H&amp;E) image-based prognostic marker for early-stage luminal/Her2-negative BReAst CancEr that we term as the BRACE marker. The proposed BRACE marker is derived from AI based assessment of heterogeneity in BC at a detailed level using the power of deep learning. The prognostic ability of the marker is validated in two well-annotated cohorts (Cohort-A/Nottingham: n = 2122 and Cohort-B/Coventry: n = 311) on early-stage luminal/HER2-negative BC patients treated with endocrine therapy and with long-term follow-up. The BRACE marker is able to stratify patients for both distant metastasis free survival (p = 0.001, C-index: 0.73) and BC specific survival (p &lt; 0.0001, C-index: 0.84) showing comparable prediction accuracy to Nottingham Prognostic Index and Magee scores, which are both derived from manual histopathological assessment, to identify luminal BC patients that may be likely to benefit from adjuvant chemotherapy.</description><identifier>EISSN: 2397-768X</identifier><identifier>DOI: 10.1038/s41698-023-00472-y</identifier><language>eng</language><publisher>Nature Portfolio</publisher><ispartof>NPJ precision oncology, 2023-11, Vol.7 (1), p.1-13</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Noorul Wahab</creatorcontrib><creatorcontrib>Michael Toss</creatorcontrib><creatorcontrib>Islam M. Miligy</creatorcontrib><creatorcontrib>Mostafa Jahanifar</creatorcontrib><creatorcontrib>Nehal M. Atallah</creatorcontrib><creatorcontrib>Wenqi Lu</creatorcontrib><creatorcontrib>Simon Graham</creatorcontrib><creatorcontrib>Mohsin Bilal</creatorcontrib><creatorcontrib>Abhir Bhalerao</creatorcontrib><creatorcontrib>Ayat G. Lashen</creatorcontrib><creatorcontrib>Shorouk Makhlouf</creatorcontrib><creatorcontrib>Asmaa Y. Ibrahim</creatorcontrib><creatorcontrib>David Snead</creatorcontrib><creatorcontrib>Fayyaz Minhas</creatorcontrib><creatorcontrib>Shan E. Ahmed Raza</creatorcontrib><creatorcontrib>Emad Rakha</creatorcontrib><creatorcontrib>Nasir Rajpoot</creatorcontrib><title>AI-enabled routine H E image based prognostic marker for early-stage luminal breast cancer</title><title>NPJ precision oncology</title><description>Abstract Breast cancer (BC) grade is a well-established subjective prognostic indicator of tumour aggressiveness. Tumour heterogeneity and subjective assessment result in high degree of variability among observers in BC grading. Here we propose an objective Haematoxylin &amp; Eosin (H&amp;E) image-based prognostic marker for early-stage luminal/Her2-negative BReAst CancEr that we term as the BRACE marker. The proposed BRACE marker is derived from AI based assessment of heterogeneity in BC at a detailed level using the power of deep learning. The prognostic ability of the marker is validated in two well-annotated cohorts (Cohort-A/Nottingham: n = 2122 and Cohort-B/Coventry: n = 311) on early-stage luminal/HER2-negative BC patients treated with endocrine therapy and with long-term follow-up. The BRACE marker is able to stratify patients for both distant metastasis free survival (p = 0.001, C-index: 0.73) and BC specific survival (p &lt; 0.0001, C-index: 0.84) showing comparable prediction accuracy to Nottingham Prognostic Index and Magee scores, which are both derived from manual histopathological assessment, to identify luminal BC patients that may be likely to benefit from adjuvant chemotherapy.</description><issn>2397-768X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNqtjU1OwzAQRi0kJCroBVjNBQxOnPpniVBRu2eB2FjjZBqlOHE1The5PQFxBFaf9PTpPSEeK_VUKe2eS1MZ76SqtVSqsbVcbsSm1t5Ka9zHndiWclZKVW5X1cZsxOfLUdKEMVEHnK_zMBEcYA_DiD1BxLLyC-d-ymUeWhiRv4jhlBkIOS2yzD-_dB2HCRNEJiwztDi1xA_i9oSp0PZv78Xxbf_-epBdxnO48JrgJWQcwi_I3AfkNZIooCeDjnat17GhDmPTRYfWO-WtbazR_-n6BiuSYrU</recordid><startdate>20231101</startdate><enddate>20231101</enddate><creator>Noorul Wahab</creator><creator>Michael Toss</creator><creator>Islam M. Miligy</creator><creator>Mostafa Jahanifar</creator><creator>Nehal M. Atallah</creator><creator>Wenqi Lu</creator><creator>Simon Graham</creator><creator>Mohsin Bilal</creator><creator>Abhir Bhalerao</creator><creator>Ayat G. Lashen</creator><creator>Shorouk Makhlouf</creator><creator>Asmaa Y. Ibrahim</creator><creator>David Snead</creator><creator>Fayyaz Minhas</creator><creator>Shan E. Ahmed Raza</creator><creator>Emad Rakha</creator><creator>Nasir Rajpoot</creator><general>Nature Portfolio</general><scope>DOA</scope></search><sort><creationdate>20231101</creationdate><title>AI-enabled routine H E image based prognostic marker for early-stage luminal breast cancer</title><author>Noorul Wahab ; Michael Toss ; Islam M. Miligy ; Mostafa Jahanifar ; Nehal M. Atallah ; Wenqi Lu ; Simon Graham ; Mohsin Bilal ; Abhir Bhalerao ; Ayat G. Lashen ; Shorouk Makhlouf ; Asmaa Y. Ibrahim ; David Snead ; Fayyaz Minhas ; Shan E. Ahmed Raza ; Emad Rakha ; Nasir Rajpoot</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-doaj_primary_oai_doaj_org_article_a9e6a8e5c93b4edab4db8a79809774763</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Noorul Wahab</creatorcontrib><creatorcontrib>Michael Toss</creatorcontrib><creatorcontrib>Islam M. Miligy</creatorcontrib><creatorcontrib>Mostafa Jahanifar</creatorcontrib><creatorcontrib>Nehal M. Atallah</creatorcontrib><creatorcontrib>Wenqi Lu</creatorcontrib><creatorcontrib>Simon Graham</creatorcontrib><creatorcontrib>Mohsin Bilal</creatorcontrib><creatorcontrib>Abhir Bhalerao</creatorcontrib><creatorcontrib>Ayat G. Lashen</creatorcontrib><creatorcontrib>Shorouk Makhlouf</creatorcontrib><creatorcontrib>Asmaa Y. Ibrahim</creatorcontrib><creatorcontrib>David Snead</creatorcontrib><creatorcontrib>Fayyaz Minhas</creatorcontrib><creatorcontrib>Shan E. Ahmed Raza</creatorcontrib><creatorcontrib>Emad Rakha</creatorcontrib><creatorcontrib>Nasir Rajpoot</creatorcontrib><collection>DOAJ Directory of Open Access Journals</collection><jtitle>NPJ precision oncology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Noorul Wahab</au><au>Michael Toss</au><au>Islam M. Miligy</au><au>Mostafa Jahanifar</au><au>Nehal M. Atallah</au><au>Wenqi Lu</au><au>Simon Graham</au><au>Mohsin Bilal</au><au>Abhir Bhalerao</au><au>Ayat G. Lashen</au><au>Shorouk Makhlouf</au><au>Asmaa Y. Ibrahim</au><au>David Snead</au><au>Fayyaz Minhas</au><au>Shan E. Ahmed Raza</au><au>Emad Rakha</au><au>Nasir Rajpoot</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AI-enabled routine H E image based prognostic marker for early-stage luminal breast cancer</atitle><jtitle>NPJ precision oncology</jtitle><date>2023-11-01</date><risdate>2023</risdate><volume>7</volume><issue>1</issue><spage>1</spage><epage>13</epage><pages>1-13</pages><eissn>2397-768X</eissn><abstract>Abstract Breast cancer (BC) grade is a well-established subjective prognostic indicator of tumour aggressiveness. Tumour heterogeneity and subjective assessment result in high degree of variability among observers in BC grading. Here we propose an objective Haematoxylin &amp; Eosin (H&amp;E) image-based prognostic marker for early-stage luminal/Her2-negative BReAst CancEr that we term as the BRACE marker. The proposed BRACE marker is derived from AI based assessment of heterogeneity in BC at a detailed level using the power of deep learning. The prognostic ability of the marker is validated in two well-annotated cohorts (Cohort-A/Nottingham: n = 2122 and Cohort-B/Coventry: n = 311) on early-stage luminal/HER2-negative BC patients treated with endocrine therapy and with long-term follow-up. The BRACE marker is able to stratify patients for both distant metastasis free survival (p = 0.001, C-index: 0.73) and BC specific survival (p &lt; 0.0001, C-index: 0.84) showing comparable prediction accuracy to Nottingham Prognostic Index and Magee scores, which are both derived from manual histopathological assessment, to identify luminal BC patients that may be likely to benefit from adjuvant chemotherapy.</abstract><pub>Nature Portfolio</pub><doi>10.1038/s41698-023-00472-y</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2397-768X
ispartof NPJ precision oncology, 2023-11, Vol.7 (1), p.1-13
issn 2397-768X
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_a9e6a8e5c93b4edab4db8a7980977476
source PubMed Central Free; Publicly Available Content Database; Alma/SFX Local Collection; Springer Nature - nature.com Journals - Fully Open Access
title AI-enabled routine H E image based prognostic marker for early-stage luminal breast cancer
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T21%3A31%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-doaj&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AI-enabled%20routine%20H%20E%20image%20based%20prognostic%20marker%20for%20early-stage%20luminal%20breast%20cancer&rft.jtitle=NPJ%20precision%20oncology&rft.au=Noorul%20Wahab&rft.date=2023-11-01&rft.volume=7&rft.issue=1&rft.spage=1&rft.epage=13&rft.pages=1-13&rft.eissn=2397-768X&rft_id=info:doi/10.1038/s41698-023-00472-y&rft_dat=%3Cdoaj%3Eoai_doaj_org_article_a9e6a8e5c93b4edab4db8a7980977476%3C/doaj%3E%3Cgrp_id%3Ecdi_FETCH-doaj_primary_oai_doaj_org_article_a9e6a8e5c93b4edab4db8a79809774763%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true