A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort
Abstract Deep learning (DL) methods have demonstrated remarkable effectiveness in assisting with lung cancer risk prediction tasks using computed tomography (CT) scans. However, the lack of comprehensive comparison and validation of state-of-the-art (SOTA) models in practical settings limits their c...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-84193-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544675969728512 |
|---|---|
| author | Yifan Jiang Leyla Ebrahimpour Philippe Després Venkata SK. Manem |
| author_facet | Yifan Jiang Leyla Ebrahimpour Philippe Després Venkata SK. Manem |
| author_sort | Yifan Jiang |
| collection | DOAJ |
| description | Abstract Deep learning (DL) methods have demonstrated remarkable effectiveness in assisting with lung cancer risk prediction tasks using computed tomography (CT) scans. However, the lack of comprehensive comparison and validation of state-of-the-art (SOTA) models in practical settings limits their clinical application. This study aims to review and analyze current SOTA deep learning models for lung cancer risk prediction (malignant-benign classification). To evaluate our model’s general performance, we selected 253 out of 467 patients from a subset of the National Lung Screening Trial (NLST) who had CT scans without contrast, which are the most commonly used, and divided them into training and test cohorts. The CT scans were preprocessed into 2D-image and 3D-volume formats according to their nodule annotations. We evaluated ten 3D and eleven 2D SOTA deep learning models, which were pretrained on large-scale general-purpose datasets (Kinetics and ImageNet) and radiological datasets (3DSeg-8, nnUnet and RadImageNet), for their lung cancer risk prediction performance. Our results showed that 3D-based deep learning models generally perform better than 2D models. On the test cohort, the best-performing 3D model achieved an AUROC of 0.86, while the best 2D model reached 0.79. The lowest AUROCs for the 3D and 2D models were 0.70 and 0.62, respectively. Furthermore, pretraining on large-scale radiological image datasets did not show the expected performance advantage over pretraining on general-purpose datasets. Both 2D and 3D deep learning models can handle lung cancer risk prediction tasks effectively, although 3D models generally have superior performance than their 2D competitors. Our findings highlight the importance of carefully selecting pretrained datasets and model architectures for lung cancer risk prediction. Overall, these results have important implications for the development and clinical integration of DL-based tools in lung cancer screening. |
| format | Article |
| id | doaj-art-77fbd92f0b874fc9a5beaa897cdded6b |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-77fbd92f0b874fc9a5beaa897cdded6b2025-01-12T12:22:44ZengNature PortfolioScientific Reports2045-23222025-01-0115111210.1038/s41598-024-84193-7A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohortYifan Jiang0Leyla Ebrahimpour1Philippe Després2Venkata SK. Manem3Centre de recherche du CHU de Québec-Université LavalCentre de recherche du CHU de Québec-Université LavalDépartement de physique, de génie physique et d’optique, Université LavalCentre de recherche du CHU de Québec-Université LavalAbstract Deep learning (DL) methods have demonstrated remarkable effectiveness in assisting with lung cancer risk prediction tasks using computed tomography (CT) scans. However, the lack of comprehensive comparison and validation of state-of-the-art (SOTA) models in practical settings limits their clinical application. This study aims to review and analyze current SOTA deep learning models for lung cancer risk prediction (malignant-benign classification). To evaluate our model’s general performance, we selected 253 out of 467 patients from a subset of the National Lung Screening Trial (NLST) who had CT scans without contrast, which are the most commonly used, and divided them into training and test cohorts. The CT scans were preprocessed into 2D-image and 3D-volume formats according to their nodule annotations. We evaluated ten 3D and eleven 2D SOTA deep learning models, which were pretrained on large-scale general-purpose datasets (Kinetics and ImageNet) and radiological datasets (3DSeg-8, nnUnet and RadImageNet), for their lung cancer risk prediction performance. Our results showed that 3D-based deep learning models generally perform better than 2D models. On the test cohort, the best-performing 3D model achieved an AUROC of 0.86, while the best 2D model reached 0.79. The lowest AUROCs for the 3D and 2D models were 0.70 and 0.62, respectively. Furthermore, pretraining on large-scale radiological image datasets did not show the expected performance advantage over pretraining on general-purpose datasets. Both 2D and 3D deep learning models can handle lung cancer risk prediction tasks effectively, although 3D models generally have superior performance than their 2D competitors. Our findings highlight the importance of carefully selecting pretrained datasets and model architectures for lung cancer risk prediction. Overall, these results have important implications for the development and clinical integration of DL-based tools in lung cancer screening.https://doi.org/10.1038/s41598-024-84193-7 |
| spellingShingle | Yifan Jiang Leyla Ebrahimpour Philippe Després Venkata SK. Manem A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort Scientific Reports |
| title | A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort |
| title_full | A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort |
| title_fullStr | A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort |
| title_full_unstemmed | A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort |
| title_short | A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort |
| title_sort | benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohort |
| url | https://doi.org/10.1038/s41598-024-84193-7 |
| work_keys_str_mv | AT yifanjiang abenchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort AT leylaebrahimpour abenchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort AT philippedespres abenchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort AT venkataskmanem abenchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort AT yifanjiang benchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort AT leylaebrahimpour benchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort AT philippedespres benchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort AT venkataskmanem benchmarkofdeeplearningapproachestopredictlungcancerriskusingnationallungscreeningtrialcohort |