乳腺癌中人类表皮生长因子受体 2 免疫组化评分的全自动人工智能解决方案:多阅读器研究。

IF 5.3 2区 医学 Q1 ONCOLOGY
JCO precision oncology Pub Date : 2024-10-01 Epub Date: 2024-10-11 DOI:10.1200/PO.24.00353
Savitri Krishnamurthy, Stuart J Schnitt, Anne Vincent-Salomon, Rita Canas-Marques, Eugenia Colon, Kanchan Kantekure, Marina Maklakovski, Wilfrid Finck, Jeanne Thomassin, Yuval Globerson, Lilach Bien, Giuseppe Mallel, Maya Grinwald, Chaim Linhart, Judith Sandbank, Manuela Vecsler
{"title":"乳腺癌中人类表皮生长因子受体 2 免疫组化评分的全自动人工智能解决方案:多阅读器研究。","authors":"Savitri Krishnamurthy, Stuart J Schnitt, Anne Vincent-Salomon, Rita Canas-Marques, Eugenia Colon, Kanchan Kantekure, Marina Maklakovski, Wilfrid Finck, Jeanne Thomassin, Yuval Globerson, Lilach Bien, Giuseppe Mallel, Maya Grinwald, Chaim Linhart, Judith Sandbank, Manuela Vecsler","doi":"10.1200/PO.24.00353","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>The proven efficacy of human epidermal growth factor receptor 2 (HER2) antibody-drug conjugate therapy for treating HER2-low breast cancers necessitates more accurate and reproducible HER2 immunohistochemistry (IHC) scoring. We aimed to validate performance and utility of a fully automated artificial intelligence (AI) solution for interpreting HER2 IHC in breast carcinoma.</p><p><strong>Materials and methods: </strong>A two-arm multireader study of 120 HER2 IHC whole-slide images from four sites assessed HER2 scoring by four surgical pathologists without and with the aid of an AI HER2 solution. Both arms were compared with high-confidence ground truth (GT) established by agreement of at least four of five breast pathology subspecialists according to ASCO/College of American Pathologists (CAP) 2018/2023 guidelines.</p><p><strong>Results: </strong>The mean interobserver agreement among GT pathologists across all HER2 scores was 72.4% (N = 120). The AI solution demonstrated high accuracy for HER2 scoring, with 92.1% agreement on slides with high confidence GT (n = 92). The use of the AI tool led to improved performance by readers, interobserver agreement increased from 75.0% for digital manual read to 83.7% for AI-assisted review, and scoring accuracy improved from 85.3% to 88.0%. For the distinction of HER2 0 from 1+ cases (n = 58), pathologists supported by AI showed significantly higher interobserver agreement (69.8% without AI <i>v</i> 87.4% with AI) and accuracy (81.9% without AI <i>v</i> 88.8% with AI).</p><p><strong>Conclusion: </strong>This study demonstrated utility of a fully automated AI solution to aid in scoring HER2 IHC accurately according to ASCO/CAP 2018/2023 guidelines. Pathologists supported by AI showed improvements in HER2 IHC scoring consistency and accuracy, especially for distinguishing HER2 0 from 1+ cases. This AI solution could be used by pathologists as a decision support tool for enhancing reproducibility and consistency of HER2 scoring and particularly for identifying HER2-low breast cancers.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"8 ","pages":"e2400353"},"PeriodicalIF":5.3000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11485213/pdf/","citationCount":"0","resultStr":"{\"title\":\"Fully Automated Artificial Intelligence Solution for Human Epidermal Growth Factor Receptor 2 Immunohistochemistry Scoring in Breast Cancer: A Multireader Study.\",\"authors\":\"Savitri Krishnamurthy, Stuart J Schnitt, Anne Vincent-Salomon, Rita Canas-Marques, Eugenia Colon, Kanchan Kantekure, Marina Maklakovski, Wilfrid Finck, Jeanne Thomassin, Yuval Globerson, Lilach Bien, Giuseppe Mallel, Maya Grinwald, Chaim Linhart, Judith Sandbank, Manuela Vecsler\",\"doi\":\"10.1200/PO.24.00353\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>The proven efficacy of human epidermal growth factor receptor 2 (HER2) antibody-drug conjugate therapy for treating HER2-low breast cancers necessitates more accurate and reproducible HER2 immunohistochemistry (IHC) scoring. We aimed to validate performance and utility of a fully automated artificial intelligence (AI) solution for interpreting HER2 IHC in breast carcinoma.</p><p><strong>Materials and methods: </strong>A two-arm multireader study of 120 HER2 IHC whole-slide images from four sites assessed HER2 scoring by four surgical pathologists without and with the aid of an AI HER2 solution. Both arms were compared with high-confidence ground truth (GT) established by agreement of at least four of five breast pathology subspecialists according to ASCO/College of American Pathologists (CAP) 2018/2023 guidelines.</p><p><strong>Results: </strong>The mean interobserver agreement among GT pathologists across all HER2 scores was 72.4% (N = 120). The AI solution demonstrated high accuracy for HER2 scoring, with 92.1% agreement on slides with high confidence GT (n = 92). The use of the AI tool led to improved performance by readers, interobserver agreement increased from 75.0% for digital manual read to 83.7% for AI-assisted review, and scoring accuracy improved from 85.3% to 88.0%. For the distinction of HER2 0 from 1+ cases (n = 58), pathologists supported by AI showed significantly higher interobserver agreement (69.8% without AI <i>v</i> 87.4% with AI) and accuracy (81.9% without AI <i>v</i> 88.8% with AI).</p><p><strong>Conclusion: </strong>This study demonstrated utility of a fully automated AI solution to aid in scoring HER2 IHC accurately according to ASCO/CAP 2018/2023 guidelines. Pathologists supported by AI showed improvements in HER2 IHC scoring consistency and accuracy, especially for distinguishing HER2 0 from 1+ cases. This AI solution could be used by pathologists as a decision support tool for enhancing reproducibility and consistency of HER2 scoring and particularly for identifying HER2-low breast cancers.</p>\",\"PeriodicalId\":14797,\"journal\":{\"name\":\"JCO precision oncology\",\"volume\":\"8 \",\"pages\":\"e2400353\"},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11485213/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JCO precision oncology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1200/PO.24.00353\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/10/11 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JCO precision oncology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1200/PO.24.00353","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/11 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的:人类表皮生长因子受体 2 (HER2) 抗体-药物共轭疗法治疗 HER2 低水平乳腺癌的疗效已得到证实,因此有必要提高 HER2 免疫组织化学 (IHC) 评分的准确性和可重复性。我们的目的是验证全自动人工智能(AI)解决方案在解释乳腺癌HER2 IHC方面的性能和实用性:一项双臂多载体研究对来自四个地点的 120 张 HER2 IHC 全切片图像进行了评估,由四位外科病理学家在没有人工智能 HER2 解决方案的情况下和在该解决方案的帮助下进行 HER2 评分。根据 ASCO/College of American Pathologists (CAP) 2018/2023 指南,两组数据均与五位乳腺病理亚专科医生中至少四位达成一致所建立的高置信度地面实况(GT)进行了比较:在所有 HER2 评分中,GT 病理学家之间的平均观察者间一致性为 72.4%(N = 120)。人工智能解决方案显示出较高的HER2评分准确性,在高置信度GT(n = 92)切片上的一致性为92.1%。人工智能工具的使用提高了阅读者的工作效率,观察者之间的一致性从数字人工阅读的 75.0% 提高到人工智能辅助审查的 83.7%,评分准确性从 85.3% 提高到 88.0%。在区分 HER2 0 和 1+ 病例(n = 58)时,人工智能支持下的病理学家的观察者间一致性(无人工智能时为 69.8% ,有人工智能时为 87.4%)和准确性(无人工智能时为 81.9% ,有人工智能时为 88.8%)均显著提高:这项研究表明,全自动人工智能解决方案有助于根据 ASCO/CAP 2018/2023 指南对 HER2 IHC 进行准确评分。病理学家在人工智能的支持下提高了 HER2 IHC 评分的一致性和准确性,尤其是在区分 HER2 0 和 1+ 病例方面。病理学家可将该人工智能解决方案用作决策支持工具,以提高HER2评分的可重复性和一致性,尤其是在识别HER2低的乳腺癌方面。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Fully Automated Artificial Intelligence Solution for Human Epidermal Growth Factor Receptor 2 Immunohistochemistry Scoring in Breast Cancer: A Multireader Study.

Purpose: The proven efficacy of human epidermal growth factor receptor 2 (HER2) antibody-drug conjugate therapy for treating HER2-low breast cancers necessitates more accurate and reproducible HER2 immunohistochemistry (IHC) scoring. We aimed to validate performance and utility of a fully automated artificial intelligence (AI) solution for interpreting HER2 IHC in breast carcinoma.

Materials and methods: A two-arm multireader study of 120 HER2 IHC whole-slide images from four sites assessed HER2 scoring by four surgical pathologists without and with the aid of an AI HER2 solution. Both arms were compared with high-confidence ground truth (GT) established by agreement of at least four of five breast pathology subspecialists according to ASCO/College of American Pathologists (CAP) 2018/2023 guidelines.

Results: The mean interobserver agreement among GT pathologists across all HER2 scores was 72.4% (N = 120). The AI solution demonstrated high accuracy for HER2 scoring, with 92.1% agreement on slides with high confidence GT (n = 92). The use of the AI tool led to improved performance by readers, interobserver agreement increased from 75.0% for digital manual read to 83.7% for AI-assisted review, and scoring accuracy improved from 85.3% to 88.0%. For the distinction of HER2 0 from 1+ cases (n = 58), pathologists supported by AI showed significantly higher interobserver agreement (69.8% without AI v 87.4% with AI) and accuracy (81.9% without AI v 88.8% with AI).

Conclusion: This study demonstrated utility of a fully automated AI solution to aid in scoring HER2 IHC accurately according to ASCO/CAP 2018/2023 guidelines. Pathologists supported by AI showed improvements in HER2 IHC scoring consistency and accuracy, especially for distinguishing HER2 0 from 1+ cases. This AI solution could be used by pathologists as a decision support tool for enhancing reproducibility and consistency of HER2 scoring and particularly for identifying HER2-low breast cancers.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
9.10
自引率
4.30%
发文量
363
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信