Radiomics-based Support Vector Machine Distinguishes Molecular Events Driving Progression of Lung Adenocarcinoma

J Thorac Oncol. 2024 Sep 19:S1556-0864(24)02330-X. doi: 10.1016/j.jtho.2024.09.1431. Online ahead of print.

Abstract

Introduction: An increasing number of early-stage lung adenocarcinoma (LUAD) are detected as lung nodules. The radiological features related to LUAD progression remain further investigation. Exploration is required to bridge the gap between radiomics features and molecular characteristics of lung nodules.

Methods: Consensus clustering was applied to the radiomics features of 1,212 patients to establish stable clustering. Clusters were illustrated using clinicopathological and next-generation sequencing (NGS). A classifier was constructed to further investigate the molecular characteristic in patients with paired CT and RNA-seq data.

Results: Patients were clustered into 4 clusters. Cluster 1 was associated with a low consolidation-to-tumor ratio (CTR), pre-invasion, grade I disease and good prognosis. Clusters 2 and 3 showed increasing malignancy with higher CTR, higher pathological grade and poor prognosis. Cluster 2 possessed more spread through air spaces (STAS) and cluster 3 showed higher proportion of pleural invasion. Cluster 4 had similar clinicopathological features with cluster 1 except higher proportion of grade II disease. RNA-seq indicated that cluster 1 represented nodules with indolent growth and good differentiation, whereas cluster 4 showed progression in cell development but still had low proliferative activity. Nodules with high proliferation were classified into clusters 2 and 3. Additionally, the radiomics classifier distinguished cluster 2 as nodules harboring an activated immune environment, while cluster 3 represented nodules with a suppressive immune environment. Furthermore, gene signatures associated with the prognosis of early-stage LUAD were validated in external datasets.

Conclusion: Radiomics features can manifest molecular events driving progression of lung adenocarcinoma. Our study provides a molecular insight into radiomics features and assists in the diagnosis and treatment of early stage LUAD.

Keywords: NSCLC; lung adenocarcinoma; radiomics.