Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung Cancer

ABSTRACT Background Non‐small‐cell lung cancer (NSCLC) remains a global health challenge, driving morbidity and mortality. The emerging field of radiogenomics utilizes statistical methods to correlate radiographic tumor features with genomic characteristics from biopsy samples. Radiomic techniques a...

Full description

Saved in:
Bibliographic Details
Main Authors: Shrey S. Sukhadia, Christoph Sadée, Olivier Gevaert, Shivashankar H. Nagaraj
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Cancer Medicine
Subjects:
Online Access:https://doi.org/10.1002/cam4.70509
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832593694286413824
author Shrey S. Sukhadia
Christoph Sadée
Olivier Gevaert
Shivashankar H. Nagaraj
author_facet Shrey S. Sukhadia
Christoph Sadée
Olivier Gevaert
Shivashankar H. Nagaraj
author_sort Shrey S. Sukhadia
collection DOAJ
description ABSTRACT Background Non‐small‐cell lung cancer (NSCLC) remains a global health challenge, driving morbidity and mortality. The emerging field of radiogenomics utilizes statistical methods to correlate radiographic tumor features with genomic characteristics from biopsy samples. Radiomic techniques automate the precise extraction of imaging features from tumor regions in radiographic scans, which are subjected to machine learning (ML) to predict genomic attributes. Methods In a retrospective study of two NSCLC patient cohorts separated by 5 years, we performed a radiogenomic analysis of previously disseminated data from 2018 (n = 116) and newly acquired data from 2023 (n = 44) using RNA sequencing and lung CT images. Combining the data from two cohorts post binarization (of gene expression) or batch normalization (of radiomic features) in each cohort proved to be a better approach as compared to training the model on one cohort and validating on the other. Results Our ML‐based radiogenomic modeling identified specific imaging features—wavelet, three‐dimensional local binary patterns, and logarithmic sigma of gray‐level variance—as predictive indicators for high (1) vs. low (0) gene expression of pivotal NSCLC‐related genes: SLC35C1, BCL2L1, and MAPK1. These genes have recognized implications in a variety of biological pathways and mechanisms of drug resistance pertinent to NSCLC. Conclusion The successful integration of heterogeneous radiogenomic datasets underscores the potential of imaging biomarkers in uncovering NSCLC biological processes through gene expression profiles.
format Article
id doaj-art-9fe2dafd0b9046c5849de9cd186e4f53
institution Kabale University
issn 2045-7634
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Cancer Medicine
spelling doaj-art-9fe2dafd0b9046c5849de9cd186e4f532025-01-20T10:51:32ZengWileyCancer Medicine2045-76342024-12-011324n/an/a10.1002/cam4.70509Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung CancerShrey S. Sukhadia0Christoph Sadée1Olivier Gevaert2Shivashankar H. Nagaraj3Centre for Genomics and Personalized Health and School of Biomedical Sciences Queensland University of Technology Brisbane Queensland AustraliaStanford Center for Biomedical Informatics Research, Department of Medicine and Biomedical Data Science Stanford University California USAStanford Center for Biomedical Informatics Research, Department of Medicine and Biomedical Data Science Stanford University California USACentre for Genomics and Personalized Health and School of Biomedical Sciences Queensland University of Technology Brisbane Queensland AustraliaABSTRACT Background Non‐small‐cell lung cancer (NSCLC) remains a global health challenge, driving morbidity and mortality. The emerging field of radiogenomics utilizes statistical methods to correlate radiographic tumor features with genomic characteristics from biopsy samples. Radiomic techniques automate the precise extraction of imaging features from tumor regions in radiographic scans, which are subjected to machine learning (ML) to predict genomic attributes. Methods In a retrospective study of two NSCLC patient cohorts separated by 5 years, we performed a radiogenomic analysis of previously disseminated data from 2018 (n = 116) and newly acquired data from 2023 (n = 44) using RNA sequencing and lung CT images. Combining the data from two cohorts post binarization (of gene expression) or batch normalization (of radiomic features) in each cohort proved to be a better approach as compared to training the model on one cohort and validating on the other. Results Our ML‐based radiogenomic modeling identified specific imaging features—wavelet, three‐dimensional local binary patterns, and logarithmic sigma of gray‐level variance—as predictive indicators for high (1) vs. low (0) gene expression of pivotal NSCLC‐related genes: SLC35C1, BCL2L1, and MAPK1. These genes have recognized implications in a variety of biological pathways and mechanisms of drug resistance pertinent to NSCLC. Conclusion The successful integration of heterogeneous radiogenomic datasets underscores the potential of imaging biomarkers in uncovering NSCLC biological processes through gene expression profiles.https://doi.org/10.1002/cam4.70509gene expression and non‐small cell lung cancermachine learningradiogenomicsradiomics
spellingShingle Shrey S. Sukhadia
Christoph Sadée
Olivier Gevaert
Shivashankar H. Nagaraj
Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung Cancer
Cancer Medicine
gene expression and non‐small cell lung cancer
machine learning
radiogenomics
radiomics
title Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung Cancer
title_full Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung Cancer
title_fullStr Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung Cancer
title_full_unstemmed Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung Cancer
title_short Machine Learning Enabled Prediction of Biologically Relevant Gene Expression Using CT‐Based Radiomic Features in Non‐Small Cell Lung Cancer
title_sort machine learning enabled prediction of biologically relevant gene expression using ct based radiomic features in non small cell lung cancer
topic gene expression and non‐small cell lung cancer
machine learning
radiogenomics
radiomics
url https://doi.org/10.1002/cam4.70509
work_keys_str_mv AT shreyssukhadia machinelearningenabledpredictionofbiologicallyrelevantgeneexpressionusingctbasedradiomicfeaturesinnonsmallcelllungcancer
AT christophsadee machinelearningenabledpredictionofbiologicallyrelevantgeneexpressionusingctbasedradiomicfeaturesinnonsmallcelllungcancer
AT oliviergevaert machinelearningenabledpredictionofbiologicallyrelevantgeneexpressionusingctbasedradiomicfeaturesinnonsmallcelllungcancer
AT shivashankarhnagaraj machinelearningenabledpredictionofbiologicallyrelevantgeneexpressionusingctbasedradiomicfeaturesinnonsmallcelllungcancer