Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications
Kirsten Rat Sarcoma viral oncogene homolog (KRAS) is a frequently occurring mutation in non-small-cell lung cancer (NSCLC) and influences cancer treatment and disease progression. In this study, a machine learning (ML) pipeline was applied to radiomic features extracted from public and internal CT i...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/15/1/83 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588111287156736 |
|---|---|
| author | Mirjam Schöneck Nicolas Rehbach Lars Lotter-Becker Thorsten Persigehl Simon Lennartz Liliana Lourenco Caldeira |
| author_facet | Mirjam Schöneck Nicolas Rehbach Lars Lotter-Becker Thorsten Persigehl Simon Lennartz Liliana Lourenco Caldeira |
| author_sort | Mirjam Schöneck |
| collection | DOAJ |
| description | Kirsten Rat Sarcoma viral oncogene homolog (KRAS) is a frequently occurring mutation in non-small-cell lung cancer (NSCLC) and influences cancer treatment and disease progression. In this study, a machine learning (ML) pipeline was applied to radiomic features extracted from public and internal CT images to identify KRAS mutations in NSCLC patients. Both datasets were analyzed using parametric (<i>t</i> test) and non-parametric statistical tests (Mann–Whitney U test) and dimensionality reduction techniques. Afterwards, the proposed ML pipeline was applied to both datasets using a five-fold cross-validation on the training set (70/30 train/test split) before being validated on the other dataset. The results show that the radiomic features are significantly different (Mann–Whitney U test; <i>p</i> < 0.05) between the two datasets, despite the use of identical feature extraction methods. Model transferability is therefore difficult to achieve, which became evident during external testing (F1 score = 0.41). Oversampling, undersampling, clustering and harmonization techniques were applied to balance and harmonize the datasets, but did not improve the classification of KRAS mutation presence. In general, due to only a single moderate result (highest test F1 score = 0.67), the accuracy of KRAS prediction is not sufficient for clinical application. In future work, the complexity of KRAS mutation might be addressed by taking submutations into consideration. Larger multicentric datasets with balanced tumor stages, including multi-scanner datasets, seem to be necessary for building robust predictive models. |
| format | Article |
| id | doaj-art-189daae883ca44cb9138f2c9b9cda56b |
| institution | Kabale University |
| issn | 2075-1729 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj-art-189daae883ca44cb9138f2c9b9cda56b2025-01-24T13:38:43ZengMDPI AGLife2075-17292025-01-011518310.3390/life15010083Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and ImplicationsMirjam Schöneck0Nicolas Rehbach1Lars Lotter-Becker2Thorsten Persigehl3Simon Lennartz4Liliana Lourenco Caldeira5Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, GermanyInstitute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, GermanyInstitute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, GermanyInstitute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, GermanyInstitute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, GermanyInstitute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, GermanyKirsten Rat Sarcoma viral oncogene homolog (KRAS) is a frequently occurring mutation in non-small-cell lung cancer (NSCLC) and influences cancer treatment and disease progression. In this study, a machine learning (ML) pipeline was applied to radiomic features extracted from public and internal CT images to identify KRAS mutations in NSCLC patients. Both datasets were analyzed using parametric (<i>t</i> test) and non-parametric statistical tests (Mann–Whitney U test) and dimensionality reduction techniques. Afterwards, the proposed ML pipeline was applied to both datasets using a five-fold cross-validation on the training set (70/30 train/test split) before being validated on the other dataset. The results show that the radiomic features are significantly different (Mann–Whitney U test; <i>p</i> < 0.05) between the two datasets, despite the use of identical feature extraction methods. Model transferability is therefore difficult to achieve, which became evident during external testing (F1 score = 0.41). Oversampling, undersampling, clustering and harmonization techniques were applied to balance and harmonize the datasets, but did not improve the classification of KRAS mutation presence. In general, due to only a single moderate result (highest test F1 score = 0.67), the accuracy of KRAS prediction is not sufficient for clinical application. In future work, the complexity of KRAS mutation might be addressed by taking submutations into consideration. Larger multicentric datasets with balanced tumor stages, including multi-scanner datasets, seem to be necessary for building robust predictive models.https://www.mdpi.com/2075-1729/15/1/83radiomicsNSCLCKirsten Rat Sarcoma viral oncogene homolog (KRAS)machine learningtransfer learning |
| spellingShingle | Mirjam Schöneck Nicolas Rehbach Lars Lotter-Becker Thorsten Persigehl Simon Lennartz Liliana Lourenco Caldeira Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications Life radiomics NSCLC Kirsten Rat Sarcoma viral oncogene homolog (KRAS) machine learning transfer learning |
| title | Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications |
| title_full | Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications |
| title_fullStr | Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications |
| title_full_unstemmed | Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications |
| title_short | Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications |
| title_sort | machine learning based radiomics analysis for identifying kras mutations in non small cell lung cancer from ct images challenges insights and implications |
| topic | radiomics NSCLC Kirsten Rat Sarcoma viral oncogene homolog (KRAS) machine learning transfer learning |
| url | https://www.mdpi.com/2075-1729/15/1/83 |
| work_keys_str_mv | AT mirjamschoneck machinelearningbasedradiomicsanalysisforidentifyingkrasmutationsinnonsmallcelllungcancerfromctimageschallengesinsightsandimplications AT nicolasrehbach machinelearningbasedradiomicsanalysisforidentifyingkrasmutationsinnonsmallcelllungcancerfromctimageschallengesinsightsandimplications AT larslotterbecker machinelearningbasedradiomicsanalysisforidentifyingkrasmutationsinnonsmallcelllungcancerfromctimageschallengesinsightsandimplications AT thorstenpersigehl machinelearningbasedradiomicsanalysisforidentifyingkrasmutationsinnonsmallcelllungcancerfromctimageschallengesinsightsandimplications AT simonlennartz machinelearningbasedradiomicsanalysisforidentifyingkrasmutationsinnonsmallcelllungcancerfromctimageschallengesinsightsandimplications AT lilianalourencocaldeira machinelearningbasedradiomicsanalysisforidentifyingkrasmutationsinnonsmallcelllungcancerfromctimageschallengesinsightsandimplications |