A Radiogenomics Pipeline for Lung Nodules Segmentation and Prediction of EGFR Mutation Status from CT Scans

TL;DR

This paper introduces a novel radiogenomics pipeline combining a new segmentation architecture and deep classifiers to non-invasively predict EGFR mutation status from CT scans, showing superior performance on public datasets.

Contribution

The study presents a novel mixed architecture (RA-Seg) for lung nodule segmentation and deep feature classifiers for EGFR mutation prediction, advancing radiogenomics methods.

Findings

Segmentation achieved 73.54 Dice score.

Classification achieved 93 F1 score.

Outperformed existing baseline and SOTA approaches.

Abstract

Lung cancer is a leading cause of death worldwide. Early-stage detection of lung cancer is essential for a more favorable prognosis. Radiogenomics is an emerging discipline that combines medical imaging and genomics features for modeling patient outcomes non-invasively. This study presents a radiogenomics pipeline that has: 1) a novel mixed architecture (RA-Seg) to segment lung cancer through attention and recurrent blocks; and 2) deep feature classifiers to distinguish Epidermal Growth Factor Receptor (EGFR) mutation status. We evaluate the proposed algorithm on multiple public datasets to assess its generalizability and robustness. We demonstrate how the proposed segmentation and classification methods outperform existing baseline and SOTA approaches (73.54 Dice and 93 F1 scores).