Default header image

End to end analysis of non-small cell lung cancer using Low Dose CT images

Main Contributor: Jenita Priya Rajamanickam Manokaran

In this project, we are working on developing a fully automated tumor detection and segmentation algorithm suitable for CT scan acquired from NSCLC patients. Detected tumors will then be registered across multiple CT time series with the intended purpose of monitoring tumor progression/regression. Segmented lungs as input, a 3D state-of-the-art deep learning model will be developed for tumor detection and segmentation. Since a 3-year follow up scans are also available in the dataset, a 5-year predict survival using time series based on transformer model will be performed and further the results obtained will be compared with the conventional methods.