LAUSR

Simple Summary Recent studies have found that the HOPX gene functions as a tumor suppressor, and its expression status influences patients’ survival in NSCLC. However, the gene expression derived from the wet biopsy sampling has not shown the entire tumor microenvironment because NSCLC is a very heterogeneous disease. This study established an imaging biopsy with the radiogenomic signatures that links HOPX expression status and CT images to aid the prediction of HOPX expression status and the prognosis for lung cancer patients. Detecting gene expression status from CT images might be helpful to improve the accuracy of wet biopsy. Abstract This study aimed to elucidate a computed tomography (CT) image-based biopsy with a radiogenomic signature to predict homeodomain-only protein homeobox (HOPX) gene expression status and prognosis in patients with non-small cell lung cancer (NSCLC). Patients were labeled as HOPX-negative or positive based on HOPX expression and were separated into training (n = 92) and testing (n = 24) datasets. In correlation analysis between genes and image features extracted by Pyradiomics for 116 patients, eight significant features associated with HOPX expression were selected as radiogenomic signature candidates from the 1218 image features. The final signature was constructed from eight candidates using the least absolute shrinkage and selection operator. An imaging biopsy model with radiogenomic signature was built by a stacking ensemble learning model to predict HOPX expression status and prognosis. The model exhibited predictive power for HOPX expression with an area under the receiver operating characteristic curve of 0.873 and prognostic power in Kaplan–Meier curves (p = 0.0066) in the test dataset. This study’s findings implied that the CT image-based biopsy with a radiogenomic signature could aid physicians in predicting HOPX expression status and prognosis in NSCLC.