TY - JOUR
T1 - End-to-end reproducible AI pipelines in radiology using the cloud
AU - Bontempi, Dennis
AU - Nuernberg, Leonard
AU - Pai, Suraj
AU - Krishnaswamy, Deepa
AU - Thiriveedhi, Vamsi
AU - Hosny, Ahmed
AU - Mak, Raymond H.
AU - Farahani, Keyvan
AU - Kikinis, Ron
AU - Fedorov, Andrey
AU - Aerts, Hugo J. W. L.
PY - 2024/8/13
Y1 - 2024/8/13
N2 - Artificial intelligence (AI) algorithms hold the potential to revolutionize radiology. However, a significant portion of the published literature lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Although several reporting guidelines have been proposed, identifying practical means to address these issues remains challenging. Here, we show the potential of cloud-based infrastructure for implementing and sharing transparent and reproducible AI-based radiology pipelines. We demonstrate end-to-end reproducibility from retrieving cloud-hosted data, through data pre-processing, deep learning inference, and post-processing, to the analysis and reporting of the final results. We successfully implement two distinct use cases, starting from recent literature on AI-based biomarkers for cancer imaging. Using cloud-hosted data and computing, we confirm the findings of these studies and extend the validation to previously unseen data for one of the use cases. Furthermore, we provide the community with transparent and easy-to-extend examples of pipelines impactful for the broader oncology field. Our approach demonstrates the potential of cloud resources for implementing, sharing, and using reproducible and transparent AI pipelines, which can accelerate the translation into clinical solutions.A significant portion of the scientific literature on AI for radiology lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Here, the authors offer a blueprint for transparent AI pipelines on cloud platforms, focusing on lung cancer prediction and biomarker discovery.
AB - Artificial intelligence (AI) algorithms hold the potential to revolutionize radiology. However, a significant portion of the published literature lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Although several reporting guidelines have been proposed, identifying practical means to address these issues remains challenging. Here, we show the potential of cloud-based infrastructure for implementing and sharing transparent and reproducible AI-based radiology pipelines. We demonstrate end-to-end reproducibility from retrieving cloud-hosted data, through data pre-processing, deep learning inference, and post-processing, to the analysis and reporting of the final results. We successfully implement two distinct use cases, starting from recent literature on AI-based biomarkers for cancer imaging. Using cloud-hosted data and computing, we confirm the findings of these studies and extend the validation to previously unseen data for one of the use cases. Furthermore, we provide the community with transparent and easy-to-extend examples of pipelines impactful for the broader oncology field. Our approach demonstrates the potential of cloud resources for implementing, sharing, and using reproducible and transparent AI pipelines, which can accelerate the translation into clinical solutions.A significant portion of the scientific literature on AI for radiology lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Here, the authors offer a blueprint for transparent AI pipelines on cloud platforms, focusing on lung cancer prediction and biomarker discovery.
KW - ARTIFICIAL-INTELLIGENCE
KW - HEALTH
KW - INFORMATION
U2 - 10.1038/s41467-024-51202-2
DO - 10.1038/s41467-024-51202-2
M3 - Article
SN - 2041-1723
VL - 15
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 6931
ER -