Development and Validation of a Pathology Image Analysis-based Predictive Model for Lung Adenocarcinoma Prognosis - A Multi-cohort Study

Xin Luo, Shen Yin, Lin Yang, Junya Fujimoto, Yikun Yang, Cesar Moran, Neda Kalhor, Annikka Weissferdt, Yang Xie, Adi F Gazdar, John D Minna, Ignacio Ivan Wistuba, Yousheng Mao, Guanghua Xiao

Research output: Contribution to journalArticle

Abstract

Prediction of disease prognosis is essential for improving cancer patient care. Previously, we have demonstrated the feasibility of using quantitative morphological features of tumor pathology images to predict the prognosis of lung cancer patients in a single cohort. In this study, we developed and validated a pathology image-based predictive model for the prognosis of lung adenocarcinoma (ADC) patients across multiple independent cohorts. Using quantitative pathology image analysis, we extracted morphological features from H&E stained sections of formalin fixed paraffin embedded (FFPE) tumor tissues. A prediction model for patient prognosis was developed using tumor tissue pathology images from a cohort of 91 stage I lung ADC patients from the Chinese Academy of Medical Sciences (CAMS), and validated in ADC patients from the National Lung Screening Trial (NLST), and the UT Special Program of Research Excellence (SPORE) cohort. The morphological features that are associated with patient survival in the training dataset from the CAMS cohort were used to develop a prognostic model, which was independently validated in both the NLST (n = 185) and the SPORE (n = 111) cohorts. The association between predicted risk and overall survival was significant for both the NLST (Hazard Ratio (HR) = 2.20, pv = 0.01) and the SPORE cohorts (HR = 2.15 and pv = 0.044), respectively, after adjusting for key clinical variables. Furthermore, the model also predicted the prognosis of patients with stage I ADC in both the NLST (n = 123, pv = 0.0089) and SPORE (n = 68, pv = 0.032) cohorts. The results indicate that the pathology image-based model predicts the prognosis of ADC patients across independent cohorts.

Original languageEnglish (US)
Article number6886
JournalScientific Reports
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Cohort Studies
Pathology
Adenocarcinoma
Lung
Neoplasms
Research
Survival
Adenocarcinoma of lung
Paraffin
Formaldehyde
Lung Neoplasms
Patient Care

ASJC Scopus subject areas

  • General

Cite this

Development and Validation of a Pathology Image Analysis-based Predictive Model for Lung Adenocarcinoma Prognosis - A Multi-cohort Study. / Luo, Xin; Yin, Shen; Yang, Lin; Fujimoto, Junya; Yang, Yikun; Moran, Cesar; Kalhor, Neda; Weissferdt, Annikka; Xie, Yang; Gazdar, Adi F; Minna, John D; Wistuba, Ignacio Ivan; Mao, Yousheng; Xiao, Guanghua.

In: Scientific Reports, Vol. 9, No. 1, 6886, 01.12.2019.

Research output: Contribution to journalArticle

Luo, Xin ; Yin, Shen ; Yang, Lin ; Fujimoto, Junya ; Yang, Yikun ; Moran, Cesar ; Kalhor, Neda ; Weissferdt, Annikka ; Xie, Yang ; Gazdar, Adi F ; Minna, John D ; Wistuba, Ignacio Ivan ; Mao, Yousheng ; Xiao, Guanghua. / Development and Validation of a Pathology Image Analysis-based Predictive Model for Lung Adenocarcinoma Prognosis - A Multi-cohort Study. In: Scientific Reports. 2019 ; Vol. 9, No. 1.
@article{8b2d4a98b4544c388f5493ca50c320f4,
title = "Development and Validation of a Pathology Image Analysis-based Predictive Model for Lung Adenocarcinoma Prognosis - A Multi-cohort Study",
abstract = "Prediction of disease prognosis is essential for improving cancer patient care. Previously, we have demonstrated the feasibility of using quantitative morphological features of tumor pathology images to predict the prognosis of lung cancer patients in a single cohort. In this study, we developed and validated a pathology image-based predictive model for the prognosis of lung adenocarcinoma (ADC) patients across multiple independent cohorts. Using quantitative pathology image analysis, we extracted morphological features from H&E stained sections of formalin fixed paraffin embedded (FFPE) tumor tissues. A prediction model for patient prognosis was developed using tumor tissue pathology images from a cohort of 91 stage I lung ADC patients from the Chinese Academy of Medical Sciences (CAMS), and validated in ADC patients from the National Lung Screening Trial (NLST), and the UT Special Program of Research Excellence (SPORE) cohort. The morphological features that are associated with patient survival in the training dataset from the CAMS cohort were used to develop a prognostic model, which was independently validated in both the NLST (n = 185) and the SPORE (n = 111) cohorts. The association between predicted risk and overall survival was significant for both the NLST (Hazard Ratio (HR) = 2.20, pv = 0.01) and the SPORE cohorts (HR = 2.15 and pv = 0.044), respectively, after adjusting for key clinical variables. Furthermore, the model also predicted the prognosis of patients with stage I ADC in both the NLST (n = 123, pv = 0.0089) and SPORE (n = 68, pv = 0.032) cohorts. The results indicate that the pathology image-based model predicts the prognosis of ADC patients across independent cohorts.",
author = "Xin Luo and Shen Yin and Lin Yang and Junya Fujimoto and Yikun Yang and Cesar Moran and Neda Kalhor and Annikka Weissferdt and Yang Xie and Gazdar, {Adi F} and Minna, {John D} and Wistuba, {Ignacio Ivan} and Yousheng Mao and Guanghua Xiao",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-42845-z",
language = "English (US)",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Development and Validation of a Pathology Image Analysis-based Predictive Model for Lung Adenocarcinoma Prognosis - A Multi-cohort Study

AU - Luo, Xin

AU - Yin, Shen

AU - Yang, Lin

AU - Fujimoto, Junya

AU - Yang, Yikun

AU - Moran, Cesar

AU - Kalhor, Neda

AU - Weissferdt, Annikka

AU - Xie, Yang

AU - Gazdar, Adi F

AU - Minna, John D

AU - Wistuba, Ignacio Ivan

AU - Mao, Yousheng

AU - Xiao, Guanghua

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Prediction of disease prognosis is essential for improving cancer patient care. Previously, we have demonstrated the feasibility of using quantitative morphological features of tumor pathology images to predict the prognosis of lung cancer patients in a single cohort. In this study, we developed and validated a pathology image-based predictive model for the prognosis of lung adenocarcinoma (ADC) patients across multiple independent cohorts. Using quantitative pathology image analysis, we extracted morphological features from H&E stained sections of formalin fixed paraffin embedded (FFPE) tumor tissues. A prediction model for patient prognosis was developed using tumor tissue pathology images from a cohort of 91 stage I lung ADC patients from the Chinese Academy of Medical Sciences (CAMS), and validated in ADC patients from the National Lung Screening Trial (NLST), and the UT Special Program of Research Excellence (SPORE) cohort. The morphological features that are associated with patient survival in the training dataset from the CAMS cohort were used to develop a prognostic model, which was independently validated in both the NLST (n = 185) and the SPORE (n = 111) cohorts. The association between predicted risk and overall survival was significant for both the NLST (Hazard Ratio (HR) = 2.20, pv = 0.01) and the SPORE cohorts (HR = 2.15 and pv = 0.044), respectively, after adjusting for key clinical variables. Furthermore, the model also predicted the prognosis of patients with stage I ADC in both the NLST (n = 123, pv = 0.0089) and SPORE (n = 68, pv = 0.032) cohorts. The results indicate that the pathology image-based model predicts the prognosis of ADC patients across independent cohorts.

AB - Prediction of disease prognosis is essential for improving cancer patient care. Previously, we have demonstrated the feasibility of using quantitative morphological features of tumor pathology images to predict the prognosis of lung cancer patients in a single cohort. In this study, we developed and validated a pathology image-based predictive model for the prognosis of lung adenocarcinoma (ADC) patients across multiple independent cohorts. Using quantitative pathology image analysis, we extracted morphological features from H&E stained sections of formalin fixed paraffin embedded (FFPE) tumor tissues. A prediction model for patient prognosis was developed using tumor tissue pathology images from a cohort of 91 stage I lung ADC patients from the Chinese Academy of Medical Sciences (CAMS), and validated in ADC patients from the National Lung Screening Trial (NLST), and the UT Special Program of Research Excellence (SPORE) cohort. The morphological features that are associated with patient survival in the training dataset from the CAMS cohort were used to develop a prognostic model, which was independently validated in both the NLST (n = 185) and the SPORE (n = 111) cohorts. The association between predicted risk and overall survival was significant for both the NLST (Hazard Ratio (HR) = 2.20, pv = 0.01) and the SPORE cohorts (HR = 2.15 and pv = 0.044), respectively, after adjusting for key clinical variables. Furthermore, the model also predicted the prognosis of patients with stage I ADC in both the NLST (n = 123, pv = 0.0089) and SPORE (n = 68, pv = 0.032) cohorts. The results indicate that the pathology image-based model predicts the prognosis of ADC patients across independent cohorts.

UR - http://www.scopus.com/inward/record.url?scp=85065205285&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065205285&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-42845-z

DO - 10.1038/s41598-019-42845-z

M3 - Article

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 6886

ER -