Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images
Abstract Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microen...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-024-00765-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841545016428724224 |
|---|---|
| author | Sushant Patkar Alex Chen Alina Basnet Amber Bixby Rahul Rajendran Rachel Chernet Susan Faso Prashanth Ashok Kumar Devashish Desai Ola El-Zammar Christopher Curtiss Saverio J. Carello Michel R. Nasr Peter Choyke Stephanie Harmon Baris Turkbey Tamara Jamaspishvili |
| author_facet | Sushant Patkar Alex Chen Alina Basnet Amber Bixby Rahul Rajendran Rachel Chernet Susan Faso Prashanth Ashok Kumar Devashish Desai Ola El-Zammar Christopher Curtiss Saverio J. Carello Michel R. Nasr Peter Choyke Stephanie Harmon Baris Turkbey Tamara Jamaspishvili |
| author_sort | Sushant Patkar |
| collection | DOAJ |
| description | Abstract Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microenvironment (TME) composition directly from histopathology images of NSCLC patients. We show that HistoTME accurately predicts the expression of 30 distinct cell type-specific molecular signatures directly from whole slide images, achieving an average Pearson correlation of 0.5 with the ground truth on independent tumor cohorts. Furthermore, we find that HistoTME-predicted microenvironment signatures and their underlying interactions improve prognostication of lung cancer patients receiving immunotherapy, achieving an AUROC of 0.75 [95% CI: 0.61-0.88] for predicting treatment responses following first-line ICI treatment, utilizing an external clinical cohort of 652 patients. Collectively, HistoTME presents an effective approach for interrogating the TME and predicting ICI response, complementing PD-L1 expression, and bringing us closer to personalized immuno-oncology. |
| format | Article |
| id | doaj-art-f6e98ac8c44e49688f92956a90f0f380 |
| institution | Kabale University |
| issn | 2397-768X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-f6e98ac8c44e49688f92956a90f0f3802025-01-12T12:06:29ZengNature Portfolionpj Precision Oncology2397-768X2024-12-018111510.1038/s41698-024-00765-wPredicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology imagesSushant Patkar0Alex Chen1Alina Basnet2Amber Bixby3Rahul Rajendran4Rachel Chernet5Susan Faso6Prashanth Ashok Kumar7Devashish Desai8Ola El-Zammar9Christopher Curtiss10Saverio J. Carello11Michel R. Nasr12Peter Choyke13Stephanie Harmon14Baris Turkbey15Tamara Jamaspishvili16Artificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of HealthArtificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of HealthDepartment of Hematology and Oncology, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityDepartment of Hematology and Oncology, SUNY Upstate Medical UniversityDepartment of Hematology and Oncology, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityArtificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of HealthArtificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of HealthArtificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of HealthDepartment of Pathology and Laboratory Medicine, SUNY Upstate Medical UniversityAbstract Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microenvironment (TME) composition directly from histopathology images of NSCLC patients. We show that HistoTME accurately predicts the expression of 30 distinct cell type-specific molecular signatures directly from whole slide images, achieving an average Pearson correlation of 0.5 with the ground truth on independent tumor cohorts. Furthermore, we find that HistoTME-predicted microenvironment signatures and their underlying interactions improve prognostication of lung cancer patients receiving immunotherapy, achieving an AUROC of 0.75 [95% CI: 0.61-0.88] for predicting treatment responses following first-line ICI treatment, utilizing an external clinical cohort of 652 patients. Collectively, HistoTME presents an effective approach for interrogating the TME and predicting ICI response, complementing PD-L1 expression, and bringing us closer to personalized immuno-oncology.https://doi.org/10.1038/s41698-024-00765-w |
| spellingShingle | Sushant Patkar Alex Chen Alina Basnet Amber Bixby Rahul Rajendran Rachel Chernet Susan Faso Prashanth Ashok Kumar Devashish Desai Ola El-Zammar Christopher Curtiss Saverio J. Carello Michel R. Nasr Peter Choyke Stephanie Harmon Baris Turkbey Tamara Jamaspishvili Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images npj Precision Oncology |
| title | Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images |
| title_full | Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images |
| title_fullStr | Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images |
| title_full_unstemmed | Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images |
| title_short | Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images |
| title_sort | predicting the tumor microenvironment composition and immunotherapy response in non small cell lung cancer from digital histopathology images |
| url | https://doi.org/10.1038/s41698-024-00765-w |
| work_keys_str_mv | AT sushantpatkar predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT alexchen predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT alinabasnet predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT amberbixby predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT rahulrajendran predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT rachelchernet predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT susanfaso predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT prashanthashokkumar predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT devashishdesai predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT olaelzammar predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT christophercurtiss predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT saveriojcarello predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT michelrnasr predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT peterchoyke predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT stephanieharmon predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT baristurkbey predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages AT tamarajamaspishvili predictingthetumormicroenvironmentcompositionandimmunotherapyresponseinnonsmallcelllungcancerfromdigitalhistopathologyimages |