Radiomics-Driven Predictive Lung Cancer Models

Principal Investigator

Name
Patrice Essien

Degrees
MS

Institution
George Washington University

Position Title
Diagnostic Medical Physicist

Email
patriceessien@gmail.com

About this CDAS Project

Study
NLST (Learn more about this study)

Project ID
NLST-1347

Initial CDAS Request Approval
Nov 5, 2024

Title
Radiomics-Driven Predictive Lung Cancer Models

Summary
The core contribution of this work is to extract radiomics features that capture intricate details of tumor textures and microenvironment interactions from the dataset. These features are to be utilized to develop a predictive model with the goal of achieving at least 95% accuracy in distinguishing between malignant and benign tumors.

Aims

-Identifying which radiomics features most significantly impact the accuracy and predictive power of lung cancer models
-Testing if radiomics-driven model achieve an accuracy of 95% or better
-Analyzing which machine learning algorithms are most effective for utilizing radiomics data in predicting patient-specific outcomes

Collaborators

Patrice Essien