Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma

Abstract Programmed cell death ligend-1 (PD-L1) expression by immunohistochemistry (IHC) assays is a predictive marker of anti-PD-1/PD-L1 therapy response. With the popularity of anti-PD-1/PD-L1 inhibitor drugs, quantitative assessment of PD-L1 expression becomes a new labor for pathologists. Manual...

Full description

Bibliographic Details
Main Authors: Jingxin Liu, Qiang Zheng, Xiao Mu, Yanfei Zuo, Bo Xu, Yan Jin, Yue Wang, Hua Tian, Yongguo Yang, Qianqian Xue, Ziling Huang, Lijun Chen, Bin Gu, Xianxu Hou, Linlin Shen, Yan Guo, Yuan Li
Format: Article
Language:English
Published: Nature Publishing Group 2021-08-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-021-95372-1
id doaj-b35f67f9350b49faac9dce59092b8302
record_format Article
spelling doaj-b35f67f9350b49faac9dce59092b83022021-08-08T11:23:45ZengNature Publishing GroupScientific Reports2045-23222021-08-011111910.1038/s41598-021-95372-1Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinomaJingxin Liu0Qiang Zheng1Xiao Mu2Yanfei Zuo3Bo Xu4Yan Jin5Yue Wang6Hua Tian7Yongguo Yang8Qianqian Xue9Ziling Huang10Lijun Chen11Bin Gu12Xianxu Hou13Linlin Shen14Yan Guo15Yuan Li16Department of Pathology, Fudan University Shanghai Cancer CenterDepartment of Pathology, Fudan University Shanghai Cancer CenterHisto Pathology Diagnostic CenterHisto Pathology Diagnostic CenterHisto Pathology Diagnostic CenterDepartment of Pathology, Fudan University Shanghai Cancer CenterDepartment of Pathology, Fudan University Shanghai Cancer CenterDepartment of Pathology, Yangzhou Jiangdu People’s HospitalDepartment of Pathology, Yangzhou Jiangdu People’s HospitalDepartment of Pathology, Fudan University Shanghai Cancer CenterDepartment of Pathology, Fudan University Shanghai Cancer CenterDepartment of Pathology, Fudan University Shanghai Cancer CenterHisto Pathology Diagnostic CenterComputer Vision Institute, School of Computer Science and Software Engineering, Shenzhen UniversityComputer Vision Institute, School of Computer Science and Software Engineering, Shenzhen UniversityHisto Pathology Diagnostic CenterDepartment of Pathology, Fudan University Shanghai Cancer CenterAbstract Programmed cell death ligend-1 (PD-L1) expression by immunohistochemistry (IHC) assays is a predictive marker of anti-PD-1/PD-L1 therapy response. With the popularity of anti-PD-1/PD-L1 inhibitor drugs, quantitative assessment of PD-L1 expression becomes a new labor for pathologists. Manually counting the PD-L1 positive stained tumor cells is an obviously subjective and time-consuming process. In this paper, we developed a new computer aided Automated Tumor Proportion Scoring System (ATPSS) to determine the comparability of image analysis with pathologist scores. A three-stage process was performed using both image processing and deep learning techniques to mimic the actual diagnostic flow of the pathologists. We conducted a multi-reader multi-case study to evaluate the agreement between pathologists and ATPSS. Fifty-one surgically resected lung squamous cell carcinoma were prepared and stained using the Dako PD-L1 (22C3) assay, and six pathologists with different experience levels were involved in this study. The TPS predicted by the proposed model had high and statistically significant correlation with sub-specialty pathologists’ scores with Mean Absolute Error (MAE) of 8.65 (95% confidence interval (CI): 6.42–10.90) and Pearson Correlation Coefficient (PCC) of 0.9436 ( $$p < 0.001$$ p < 0.001 ), and the performance on PD-L1 positive cases achieved by our method surpassed that of non-subspecialty and trainee pathologists. Those experimental results indicate that the proposed automated system can be a powerful tool to improve the PD-L1 TPS assessment of pathologists.https://doi.org/10.1038/s41598-021-95372-1
collection DOAJ
language English
format Article
sources DOAJ
author Jingxin Liu
Qiang Zheng
Xiao Mu
Yanfei Zuo
Bo Xu
Yan Jin
Yue Wang
Hua Tian
Yongguo Yang
Qianqian Xue
Ziling Huang
Lijun Chen
Bin Gu
Xianxu Hou
Linlin Shen
Yan Guo
Yuan Li
spellingShingle Jingxin Liu
Qiang Zheng
Xiao Mu
Yanfei Zuo
Bo Xu
Yan Jin
Yue Wang
Hua Tian
Yongguo Yang
Qianqian Xue
Ziling Huang
Lijun Chen
Bin Gu
Xianxu Hou
Linlin Shen
Yan Guo
Yuan Li
Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma
Scientific Reports
author_facet Jingxin Liu
Qiang Zheng
Xiao Mu
Yanfei Zuo
Bo Xu
Yan Jin
Yue Wang
Hua Tian
Yongguo Yang
Qianqian Xue
Ziling Huang
Lijun Chen
Bin Gu
Xianxu Hou
Linlin Shen
Yan Guo
Yuan Li
author_sort Jingxin Liu
title Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma
title_short Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma
title_full Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma
title_fullStr Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma
title_full_unstemmed Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma
title_sort automated tumor proportion score analysis for pd-l1 (22c3) expression in lung squamous cell carcinoma
publisher Nature Publishing Group
series Scientific Reports
issn 2045-2322
publishDate 2021-08-01
description Abstract Programmed cell death ligend-1 (PD-L1) expression by immunohistochemistry (IHC) assays is a predictive marker of anti-PD-1/PD-L1 therapy response. With the popularity of anti-PD-1/PD-L1 inhibitor drugs, quantitative assessment of PD-L1 expression becomes a new labor for pathologists. Manually counting the PD-L1 positive stained tumor cells is an obviously subjective and time-consuming process. In this paper, we developed a new computer aided Automated Tumor Proportion Scoring System (ATPSS) to determine the comparability of image analysis with pathologist scores. A three-stage process was performed using both image processing and deep learning techniques to mimic the actual diagnostic flow of the pathologists. We conducted a multi-reader multi-case study to evaluate the agreement between pathologists and ATPSS. Fifty-one surgically resected lung squamous cell carcinoma were prepared and stained using the Dako PD-L1 (22C3) assay, and six pathologists with different experience levels were involved in this study. The TPS predicted by the proposed model had high and statistically significant correlation with sub-specialty pathologists’ scores with Mean Absolute Error (MAE) of 8.65 (95% confidence interval (CI): 6.42–10.90) and Pearson Correlation Coefficient (PCC) of 0.9436 ( $$p < 0.001$$ p < 0.001 ), and the performance on PD-L1 positive cases achieved by our method surpassed that of non-subspecialty and trainee pathologists. Those experimental results indicate that the proposed automated system can be a powerful tool to improve the PD-L1 TPS assessment of pathologists.
url https://doi.org/10.1038/s41598-021-95372-1
work_keys_str_mv AT jingxinliu automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT qiangzheng automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT xiaomu automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT yanfeizuo automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT boxu automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT yanjin automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT yuewang automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT huatian automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT yongguoyang automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT qianqianxue automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT zilinghuang automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT lijunchen automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT bingu automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT xianxuhou automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT linlinshen automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT yanguo automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
AT yuanli automatedtumorproportionscoreanalysisforpdl122c3expressioninlungsquamouscellcarcinoma
_version_ 1721216089688375296