How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies

Abstract Programmed death ligand-1 (PD-L1) expression is a key biomarker to screen patients for PD-1/PD-L1-targeted immunotherapy. However, a subjective assessment guide on PD-L1 expression of tumor-infiltrating immune cells (IC) scoring is currently adopted in clinical practice with low concordance...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Xinran Wang, Liang Wang, Hong Bu, Ningning Zhang, Meng Yue, Zhanli Jia, Lijing Cai, Jiankun He, Yanan Wang, Xin Xu, Shengshui Li, Kaiwen Xiao, Kezhou Yan, Kuan Tian, Xiao Han, Junzhou Huang, Jianhua Yao, Yueping Liu
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Acceso en línea:https://doaj.org/article/dcd2ce87231243738367b9b9bb95ee4c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:dcd2ce87231243738367b9b9bb95ee4c
record_format dspace
spelling oai:doaj.org-article:dcd2ce87231243738367b9b9bb95ee4c2021-12-02T16:52:56ZHow can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies10.1038/s41523-021-00268-y2374-4677https://doaj.org/article/dcd2ce87231243738367b9b9bb95ee4c2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41523-021-00268-yhttps://doaj.org/toc/2374-4677Abstract Programmed death ligand-1 (PD-L1) expression is a key biomarker to screen patients for PD-1/PD-L1-targeted immunotherapy. However, a subjective assessment guide on PD-L1 expression of tumor-infiltrating immune cells (IC) scoring is currently adopted in clinical practice with low concordance. Therefore, a repeatable and quantifiable PD-L1 IC scoring method of breast cancer is desirable. In this study, we propose a deep learning-based artificial intelligence-assisted (AI-assisted) model for PD-L1 IC scoring. Three rounds of ring studies (RSs) involving 31 pathologists from 10 hospitals were carried out, using the current guideline in the first two rounds (RS1, RS2) and our AI scoring model in the last round (RS3). A total of 109 PD-L1 (Ventana SP142) immunohistochemistry (IHC) stained images were assessed and the role of the AI-assisted model was evaluated. With the assistance of AI, the scoring concordance across pathologists was boosted to excellent in RS3 (0.950, 95% confidence interval (CI): 0.936–0.962) from moderate in RS1 (0.674, 95% CI: 0.614–0.735) and RS2 (0.736, 95% CI: 0.683–0.789). The 2- and 4-category scoring accuracy were improved by 4.2% (0.959, 95% CI: 0.953–0.964) and 13% (0.815, 95% CI: 0.803–0.827) (p < 0.001). The AI results were generally accepted by pathologists with 61% “fully accepted” and 91% “almost accepted”. The proposed AI-assisted method can help pathologists at all levels to improve the PD-L1 assay (SP-142) IC assessment in breast cancer in terms of both accuracy and concordance. The AI tool provides a scheme to standardize the PD-L1 IC scoring in clinical practice.Xinran WangLiang WangHong BuNingning ZhangMeng YueZhanli JiaLijing CaiJiankun HeYanan WangXin XuShengshui LiKaiwen XiaoKezhou YanKuan TianXiao HanJunzhou HuangJianhua YaoYueping LiuNature PortfolioarticleNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENnpj Breast Cancer, Vol 7, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
spellingShingle Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
Xinran Wang
Liang Wang
Hong Bu
Ningning Zhang
Meng Yue
Zhanli Jia
Lijing Cai
Jiankun He
Yanan Wang
Xin Xu
Shengshui Li
Kaiwen Xiao
Kezhou Yan
Kuan Tian
Xiao Han
Junzhou Huang
Jianhua Yao
Yueping Liu
How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies
description Abstract Programmed death ligand-1 (PD-L1) expression is a key biomarker to screen patients for PD-1/PD-L1-targeted immunotherapy. However, a subjective assessment guide on PD-L1 expression of tumor-infiltrating immune cells (IC) scoring is currently adopted in clinical practice with low concordance. Therefore, a repeatable and quantifiable PD-L1 IC scoring method of breast cancer is desirable. In this study, we propose a deep learning-based artificial intelligence-assisted (AI-assisted) model for PD-L1 IC scoring. Three rounds of ring studies (RSs) involving 31 pathologists from 10 hospitals were carried out, using the current guideline in the first two rounds (RS1, RS2) and our AI scoring model in the last round (RS3). A total of 109 PD-L1 (Ventana SP142) immunohistochemistry (IHC) stained images were assessed and the role of the AI-assisted model was evaluated. With the assistance of AI, the scoring concordance across pathologists was boosted to excellent in RS3 (0.950, 95% confidence interval (CI): 0.936–0.962) from moderate in RS1 (0.674, 95% CI: 0.614–0.735) and RS2 (0.736, 95% CI: 0.683–0.789). The 2- and 4-category scoring accuracy were improved by 4.2% (0.959, 95% CI: 0.953–0.964) and 13% (0.815, 95% CI: 0.803–0.827) (p < 0.001). The AI results were generally accepted by pathologists with 61% “fully accepted” and 91% “almost accepted”. The proposed AI-assisted method can help pathologists at all levels to improve the PD-L1 assay (SP-142) IC assessment in breast cancer in terms of both accuracy and concordance. The AI tool provides a scheme to standardize the PD-L1 IC scoring in clinical practice.
format article
author Xinran Wang
Liang Wang
Hong Bu
Ningning Zhang
Meng Yue
Zhanli Jia
Lijing Cai
Jiankun He
Yanan Wang
Xin Xu
Shengshui Li
Kaiwen Xiao
Kezhou Yan
Kuan Tian
Xiao Han
Junzhou Huang
Jianhua Yao
Yueping Liu
author_facet Xinran Wang
Liang Wang
Hong Bu
Ningning Zhang
Meng Yue
Zhanli Jia
Lijing Cai
Jiankun He
Yanan Wang
Xin Xu
Shengshui Li
Kaiwen Xiao
Kezhou Yan
Kuan Tian
Xiao Han
Junzhou Huang
Jianhua Yao
Yueping Liu
author_sort Xinran Wang
title How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies
title_short How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies
title_full How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies
title_fullStr How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies
title_full_unstemmed How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies
title_sort how can artificial intelligence models assist pd-l1 expression scoring in breast cancer: results of multi-institutional ring studies
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/dcd2ce87231243738367b9b9bb95ee4c
work_keys_str_mv AT xinranwang howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT liangwang howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT hongbu howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT ningningzhang howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT mengyue howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT zhanlijia howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT lijingcai howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT jiankunhe howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT yananwang howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT xinxu howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT shengshuili howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT kaiwenxiao howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT kezhouyan howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT kuantian howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT xiaohan howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT junzhouhuang howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT jianhuayao howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
AT yuepingliu howcanartificialintelligencemodelsassistpdl1expressionscoringinbreastcancerresultsofmultiinstitutionalringstudies
_version_ 1718382949360992256