Data augmented lung cancer prediction framework using the nested case control NLST cohort
PurposeIn the context of lung cancer screening, the scarcity of well-labeled medical images poses a significant challenge to implement supervised learning-based deep learning methods. While data augmentation is an effective technique for countering the difficulties caused by insufficient data, it ha...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1492758/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850189416780267520 |
|---|---|
| author | Yifan Jiang Yifan Jiang Venkata S. K. Manem Venkata S. K. Manem Venkata S. K. Manem |
| author_facet | Yifan Jiang Yifan Jiang Venkata S. K. Manem Venkata S. K. Manem Venkata S. K. Manem |
| author_sort | Yifan Jiang |
| collection | DOAJ |
| description | PurposeIn the context of lung cancer screening, the scarcity of well-labeled medical images poses a significant challenge to implement supervised learning-based deep learning methods. While data augmentation is an effective technique for countering the difficulties caused by insufficient data, it has not been fully explored in the context of lung cancer screening. In this research study, we analyzed the state-of-the-art (SOTA) data augmentation techniques for lung cancer binary prediction.MethodsTo comprehensively evaluate the efficiency of data augmentation approaches, we considered the nested case control National Lung Screening Trial (NLST) cohort comprising of 253 individuals who had the commonly used CT scans without contrast. The CT scans were pre-processed into three-dimensional volumes based on the lung nodule annotations. Subsequently, we evaluated five basic (online) and two generative model-based offline data augmentation methods with ten state-of-the-art (SOTA) 3D deep learning-based lung cancer prediction models.ResultsOur results demonstrated that the performance improvement by data augmentation was highly dependent on approach used. The Cutmix method resulted in the highest average performance improvement across all three metrics: 1.07%, 3.29%, 1.19% for accuracy, F1 score and AUC, respectively. MobileNetV2 with a simple data augmentation approach achieved the best AUC of 0.8719 among all lung cancer predictors, demonstrating a 7.62% improvement compared to baseline. Furthermore, the MED-DDPM data augmentation approach was able to improve prediction performance by rebalancing the training set and adding moderately synthetic data.ConclusionsThe effectiveness of online and offline data augmentation methods were highly sensitive to the prediction model, highlighting the importance of carefully selecting the optimal data augmentation method. Our findings suggest that certain traditional methods can provide more stable and higher performance compared to SOTA online data augmentation approaches. Overall, these results offer meaningful insights for the development and clinical integration of data augmented deep learning tools for lung cancer screening. |
| format | Article |
| id | doaj-art-c168ffcbb29b401c9466cfed0a606e1e |
| institution | OA Journals |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-c168ffcbb29b401c9466cfed0a606e1e2025-08-20T02:15:37ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-02-011510.3389/fonc.2025.14927581492758Data augmented lung cancer prediction framework using the nested case control NLST cohortYifan Jiang0Yifan Jiang1Venkata S. K. Manem2Venkata S. K. Manem3Venkata S. K. Manem4Centre de Recherche du CHU de Québec, Université Laval, Québec, QC, CanadaDépartement de Biologie Moléculaire, Biochimie Médicale et Pathologie, Université Laval, Québec, QC, CanadaCentre de Recherche du CHU de Québec, Université Laval, Québec, QC, CanadaDépartement de Biologie Moléculaire, Biochimie Médicale et Pathologie, Université Laval, Québec, QC, CanadaInstitut Universitaire de Cardiologie et de Pneumologie de Québec, Québec, QC, CanadaPurposeIn the context of lung cancer screening, the scarcity of well-labeled medical images poses a significant challenge to implement supervised learning-based deep learning methods. While data augmentation is an effective technique for countering the difficulties caused by insufficient data, it has not been fully explored in the context of lung cancer screening. In this research study, we analyzed the state-of-the-art (SOTA) data augmentation techniques for lung cancer binary prediction.MethodsTo comprehensively evaluate the efficiency of data augmentation approaches, we considered the nested case control National Lung Screening Trial (NLST) cohort comprising of 253 individuals who had the commonly used CT scans without contrast. The CT scans were pre-processed into three-dimensional volumes based on the lung nodule annotations. Subsequently, we evaluated five basic (online) and two generative model-based offline data augmentation methods with ten state-of-the-art (SOTA) 3D deep learning-based lung cancer prediction models.ResultsOur results demonstrated that the performance improvement by data augmentation was highly dependent on approach used. The Cutmix method resulted in the highest average performance improvement across all three metrics: 1.07%, 3.29%, 1.19% for accuracy, F1 score and AUC, respectively. MobileNetV2 with a simple data augmentation approach achieved the best AUC of 0.8719 among all lung cancer predictors, demonstrating a 7.62% improvement compared to baseline. Furthermore, the MED-DDPM data augmentation approach was able to improve prediction performance by rebalancing the training set and adding moderately synthetic data.ConclusionsThe effectiveness of online and offline data augmentation methods were highly sensitive to the prediction model, highlighting the importance of carefully selecting the optimal data augmentation method. Our findings suggest that certain traditional methods can provide more stable and higher performance compared to SOTA online data augmentation approaches. Overall, these results offer meaningful insights for the development and clinical integration of data augmented deep learning tools for lung cancer screening.https://www.frontiersin.org/articles/10.3389/fonc.2025.1492758/fulldata augmentationlung cancercancer risk predictioncomputed tomographyArtificial Intelliegncemachine learning |
| spellingShingle | Yifan Jiang Yifan Jiang Venkata S. K. Manem Venkata S. K. Manem Venkata S. K. Manem Data augmented lung cancer prediction framework using the nested case control NLST cohort Frontiers in Oncology data augmentation lung cancer cancer risk prediction computed tomography Artificial Intelliegnce machine learning |
| title | Data augmented lung cancer prediction framework using the nested case control NLST cohort |
| title_full | Data augmented lung cancer prediction framework using the nested case control NLST cohort |
| title_fullStr | Data augmented lung cancer prediction framework using the nested case control NLST cohort |
| title_full_unstemmed | Data augmented lung cancer prediction framework using the nested case control NLST cohort |
| title_short | Data augmented lung cancer prediction framework using the nested case control NLST cohort |
| title_sort | data augmented lung cancer prediction framework using the nested case control nlst cohort |
| topic | data augmentation lung cancer cancer risk prediction computed tomography Artificial Intelliegnce machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1492758/full |
| work_keys_str_mv | AT yifanjiang dataaugmentedlungcancerpredictionframeworkusingthenestedcasecontrolnlstcohort AT yifanjiang dataaugmentedlungcancerpredictionframeworkusingthenestedcasecontrolnlstcohort AT venkataskmanem dataaugmentedlungcancerpredictionframeworkusingthenestedcasecontrolnlstcohort AT venkataskmanem dataaugmentedlungcancerpredictionframeworkusingthenestedcasecontrolnlstcohort AT venkataskmanem dataaugmentedlungcancerpredictionframeworkusingthenestedcasecontrolnlstcohort |