(Learn more about this study)
Initial CDAS Request Approval
Sep 12, 2019
A Deep Learning Model for Improved Cancer Risk Prediction in Lung Screening Low-Dose Chest Computed Tomography
Together with collaborators at the Massachusetts Institute of Technology we will analyze the low-dose computed tomography (LDCT) examinations of the chest obtained in participants in the National Lung Screening Trial prior to the tissue diagnosis of lung cancer. The LDCT examinations of patients diagnosed with lung cancer will be compared with LDCT examinations of patients who did not develop lung cancer during the trial matched for age, gender and smoking exposure. We postulate that a deep learning algorithm can be trained to estimate the risk for developing a clinically active lung cancer within the next 12 months (1-year risk) and within the next 24 months (2-year risk). Additionally, we will explore the degree to which non-lung, smoking-related cancers may be predicted from LDCT using deep learning.
- Identify imaging features on low-dose computed tomography examinations of the chest obtained for screening that predict lung cancer
- Predict risk of all smoking-related cancers from LDCT
Lecia V. Sequist, MD (Massachusetts General Hospital)
Regina Barzilay, PhD (Massachusetts Institute of Technology)
Adam Yala, PhD candidate (Massachusetts Institute of Technology)
Sybil: A Validated Deep Learning Model to Predict Future Lung Cancer Risk From a Single Low-Dose Chest Computed Tomography.
Mikhael PG, Wohlwend J, Yala A, Karstens L, Xiang J, Takigami AK, Bourgouin PP, Chan P, Mrah S, Amayri W, Juan YH, Yang CT, Wan YL, Lin G, Sequist LV, Fintelmann FJ, Barzilay R
J Clin Oncol
. 2023 Jan 12; Pages JCO2201345