Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images

Abstract EGFR mutations are a major prognostic factor in lung adenocarcinoma. However, current detection methods require sufficient samples and are costly. Deep learning is promising for mutation prediction in histopathological image analysis but has limitations in that it does not sufficiently refl...

Full description

Saved in:
Bibliographic Details
Main Authors: Jun Hyeong Park, June Hyuck Lim, Seonhwa Kim, Chul‐Ho Kim, Jeong‐Seok Choi, Jun Hyeok Lim, Lucia Kim, Jae Won Chang, Dongil Park, Myung‐won Lee, Sup Kim, Il‐Seok Park, Seung Hoon Han, Eun Shin, Jin Roh, Jaesung Heo
Format: Article
Language:English
Published: Wiley 2024-11-01
Series:The Journal of Pathology: Clinical Research
Subjects:
Online Access:https://doi.org/10.1002/2056-4538.70004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850270160391241728
author Jun Hyeong Park
June Hyuck Lim
Seonhwa Kim
Chul‐Ho Kim
Jeong‐Seok Choi
Jun Hyeok Lim
Lucia Kim
Jae Won Chang
Dongil Park
Myung‐won Lee
Sup Kim
Il‐Seok Park
Seung Hoon Han
Eun Shin
Jin Roh
Jaesung Heo
author_facet Jun Hyeong Park
June Hyuck Lim
Seonhwa Kim
Chul‐Ho Kim
Jeong‐Seok Choi
Jun Hyeok Lim
Lucia Kim
Jae Won Chang
Dongil Park
Myung‐won Lee
Sup Kim
Il‐Seok Park
Seung Hoon Han
Eun Shin
Jin Roh
Jaesung Heo
author_sort Jun Hyeong Park
collection DOAJ
description Abstract EGFR mutations are a major prognostic factor in lung adenocarcinoma. However, current detection methods require sufficient samples and are costly. Deep learning is promising for mutation prediction in histopathological image analysis but has limitations in that it does not sufficiently reflect tumor heterogeneity and lacks interpretability. In this study, we developed a deep learning model to predict the presence of EGFR mutations by analyzing histopathological patterns in whole slide images (WSIs). We also introduced the EGFR mutation prevalence (EMP) score, which quantifies EGFR prevalence in WSIs based on patch‐level predictions, and evaluated its interpretability and utility. Our model estimates the probability of EGFR prevalence in each patch by partitioning the WSI based on multiple‐instance learning and predicts the presence of EGFR mutations at the slide level. We utilized a patch‐masking scheduler training strategy to enable the model to learn various histopathological patterns of EGFR. This study included 868 WSI samples from lung adenocarcinoma patients collected from three medical institutions: Hallym University Medical Center, Inha University Hospital, and Chungnam National University Hospital. For the test dataset, 197 WSIs were collected from Ajou University Medical Center to evaluate the presence of EGFR mutations. Our model demonstrated prediction performance with an area under the receiver operating characteristic curve of 0.7680 (0.7607–0.7720) and an area under the precision‐recall curve of 0.8391 (0.8326–0.8430). The EMP score showed Spearman correlation coefficients of 0.4705 (p = 0.0087) for p.L858R and 0.5918 (p = 0.0037) for exon 19 deletions in 64 samples subjected to next‐generation sequencing analysis. Additionally, high EMP scores were associated with papillary and acinar patterns (p = 0.0038 and p = 0.0255, respectively), whereas low EMP scores were associated with solid patterns (p = 0.0001). These results validate the reliability of our model and suggest that it can provide crucial information for rapid screening and treatment plans.
format Article
id doaj-art-6a9c3887e8b440d1b1ea3a8bc4bed933
institution OA Journals
issn 2056-4538
language English
publishDate 2024-11-01
publisher Wiley
record_format Article
series The Journal of Pathology: Clinical Research
spelling doaj-art-6a9c3887e8b440d1b1ea3a8bc4bed9332025-08-20T01:52:45ZengWileyThe Journal of Pathology: Clinical Research2056-45382024-11-01106n/an/a10.1002/2056-4538.70004Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide imagesJun Hyeong Park0June Hyuck Lim1Seonhwa Kim2Chul‐Ho Kim3Jeong‐Seok Choi4Jun Hyeok Lim5Lucia Kim6Jae Won Chang7Dongil Park8Myung‐won Lee9Sup Kim10Il‐Seok Park11Seung Hoon Han12Eun Shin13Jin Roh14Jaesung Heo15Department of Radiation Oncology Ajou University School of Medicine Suwon Republic of KoreaDepartment of Radiation Oncology Ajou University School of Medicine Suwon Republic of KoreaDepartment of Radiation Oncology Ajou University School of Medicine Suwon Republic of KoreaDepartment of Otolaryngology Ajou University School of Medicine Suwon Republic of KoreaDepartment of Otorhinolaryngology‐Head and Neck Surgery Inha University College of Medicine Incheon Republic of KoreaDivision of Pulmonology, Department of Internal Medicine Inha University College of Medicine Incheon Republic of KoreaDepartment of Pathology Inha University College of Medicine Incheon Republic of KoreaDepartment of Otolaryngology‐Head and Neck Surgery Chungnam National University Hospital Daejeon Republic of KoreaDivision of Pulmonary, Allergy and Critical Care Medicine, Critical Care Medicine, Department of Internal Medicine Chungnam National University Hospital Daejeon Republic of KoreaDivision of Hematology and Oncology, Department of Internal Medicine Chungnam National University Hospital Daejeon Republic of KoreaDepartment of Radiation Oncology Chungnam National University Hospital Daejeon Republic of KoreaDepartment of Otorhinolaryngology‐Head and Neck Surgery Hallym University Dontan Sacred Heart Hospital, Hallym University College of Medicine Hwaseong Republic of KoreaDepartment of Otorhinolaryngology‐Head and Neck Surgery Hallym University Dontan Sacred Heart Hospital, Hallym University College of Medicine Hwaseong Republic of KoreaDepartment of Pathology, Dongtan Sacred Heart Hospital Hallym University College of Medicine Hwaseong Republic of KoreaDepartment of Pathology Ajou University School of Medicine Suwon Republic of KoreaDepartment of Radiation Oncology Ajou University School of Medicine Suwon Republic of KoreaAbstract EGFR mutations are a major prognostic factor in lung adenocarcinoma. However, current detection methods require sufficient samples and are costly. Deep learning is promising for mutation prediction in histopathological image analysis but has limitations in that it does not sufficiently reflect tumor heterogeneity and lacks interpretability. In this study, we developed a deep learning model to predict the presence of EGFR mutations by analyzing histopathological patterns in whole slide images (WSIs). We also introduced the EGFR mutation prevalence (EMP) score, which quantifies EGFR prevalence in WSIs based on patch‐level predictions, and evaluated its interpretability and utility. Our model estimates the probability of EGFR prevalence in each patch by partitioning the WSI based on multiple‐instance learning and predicts the presence of EGFR mutations at the slide level. We utilized a patch‐masking scheduler training strategy to enable the model to learn various histopathological patterns of EGFR. This study included 868 WSI samples from lung adenocarcinoma patients collected from three medical institutions: Hallym University Medical Center, Inha University Hospital, and Chungnam National University Hospital. For the test dataset, 197 WSIs were collected from Ajou University Medical Center to evaluate the presence of EGFR mutations. Our model demonstrated prediction performance with an area under the receiver operating characteristic curve of 0.7680 (0.7607–0.7720) and an area under the precision‐recall curve of 0.8391 (0.8326–0.8430). The EMP score showed Spearman correlation coefficients of 0.4705 (p = 0.0087) for p.L858R and 0.5918 (p = 0.0037) for exon 19 deletions in 64 samples subjected to next‐generation sequencing analysis. Additionally, high EMP scores were associated with papillary and acinar patterns (p = 0.0038 and p = 0.0255, respectively), whereas low EMP scores were associated with solid patterns (p = 0.0001). These results validate the reliability of our model and suggest that it can provide crucial information for rapid screening and treatment plans.https://doi.org/10.1002/2056-4538.70004EGFRwhole‐slide image analysisdeep learning in histopathologymultiple‐instance learning
spellingShingle Jun Hyeong Park
June Hyuck Lim
Seonhwa Kim
Chul‐Ho Kim
Jeong‐Seok Choi
Jun Hyeok Lim
Lucia Kim
Jae Won Chang
Dongil Park
Myung‐won Lee
Sup Kim
Il‐Seok Park
Seung Hoon Han
Eun Shin
Jin Roh
Jaesung Heo
Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images
The Journal of Pathology: Clinical Research
EGFR
whole‐slide image analysis
deep learning in histopathology
multiple‐instance learning
title Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images
title_full Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images
title_fullStr Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images
title_full_unstemmed Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images
title_short Deep learning‐based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images
title_sort deep learning based analysis of egfr mutation prevalence in lung adenocarcinoma h e whole slide images
topic EGFR
whole‐slide image analysis
deep learning in histopathology
multiple‐instance learning
url https://doi.org/10.1002/2056-4538.70004
work_keys_str_mv AT junhyeongpark deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT junehyucklim deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT seonhwakim deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT chulhokim deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT jeongseokchoi deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT junhyeoklim deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT luciakim deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT jaewonchang deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT dongilpark deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT myungwonlee deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT supkim deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT ilseokpark deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT seunghoonhan deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT eunshin deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT jinroh deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages
AT jaesungheo deeplearningbasedanalysisofegfrmutationprevalenceinlungadenocarcinomahewholeslideimages