To develop a prediction model for non-small cell lung cancer based on radiomics
Principal Investigator
Name
Yang Ruiyi
Degrees
M.D.
Institution
China Medical University
Position Title
Student
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-1246
Initial CDAS Request Approval
May 16, 2024
Title
To develop a prediction model for non-small cell lung cancer based on radiomics
Summary
Non-small cell lung cancer (NSCLC) plays an important role in lung cancer, but the survival rate of metastatic patients is still low, and the choice of treatment is challenging. This review focuses on the application of machine learning and artificial intelligence in the treatment of NSCLC, especially the potential contribution in predicting response. Although progress has been made in chemotherapy, targeted therapy, and immunotherapy, the prognosis of stage III NSCLC remains unsatisfactory. Immunotherapy is only effective for a subset of patients, and the success rate of targeted therapy is limited. Traditional biomarkers and imaging examinations also have certain limitations, and more accurate non-invasive methods are needed to guide treatment decisions. The application of artificial intelligence, especially radiomics based on machine learning, provides new possibilities for the treatment of NSCLC. By combining CT imaging and artificial intelligence, the treatment effect can be predicted more accurately and help doctors optimize the treatment plan. This method is able to extract hundreds of abstract mathematical features from the image to further analyze the disease status of the patient. Successful applications include predicting the response to chemotherapy and targeted therapy by artificial intelligence combined with CT. Radiomics methods enable a more comprehensive assessment of the biological characteristics of lung cancer, which is expected to provide more precise individualized guidance for treatment
Aims
Based on a prospective cohort study design, radiomics features were extracted, and multimodal data including chest CT and clinical features were integrated by artificial intelligence to develop and validate a prognostic model for NSCLC.
Collaborators
Shengjing Hospital of China Medical University