Deep Learning Radiomic Signature Predicts the Overall Survival of Patients with Lung Adenocarcinoma by Reflecting the Tumor Heterogeneity and Microenvironment.
Authors
Affiliations (4)
Affiliations (4)
- Department of Cardiothoracic Surgery, Suzhou Municipal Hospital, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou, Jiangsu, China (C.D., Z.Y., J.X., J.Y.).
- Department of Oncology, Navy Medical Center of PLA, Naval Medical University, Huaihai West Road No. 338, Shanghai, China (B.H.).
- Department of Radiology, Changshu No.2 People's Hospital, The Affiliated Changshu Hospital of Nantong University, Changshu, Jiangsu, China (J.L.).
- Department of Cardiothoracic Surgery, Suzhou Municipal Hospital, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou, Jiangsu, China (C.D., Z.Y., J.X., J.Y.). Electronic address: [email protected].
Abstract
The need for prediction of overall survival (OS) in patients with lung adenocarcinoma (LUAD) has been increasingly recognized. We aimed to generate a computed tomography-derived radiomic signature for predicting prognosis in LUAD patients, and then explored the relationship between radiomic features and tumor heterogeneity and microenvironment. Data of 306 eligible LUAD patients from three institutions were obtained between January 2019 and January 2024. The mainstream Residual Network 50 (ResNet50) was used to develop an image-based deep learning radiomic signature (DLRS). We developed a clinical model and calculated the conventional radiomics score using pyradiomics package. An external cohort from a public database called The Cancer Imaging Archive was obtained for further validation. We performed the time-dependent receiver operator characteristic curve to assess the performance of the models. We divided the whole dataset into high and low-score groups with the help of the DLRS. The differences in tumor heterogeneity and microenvironment between different score groups were investigated using the sequencing data from the corresponding LUAD cohort from the Cancer Genome Atlas. In the test cohort, the DLRS outperformed the conventional radiomics score and clinical model, with the area under the curves (95%CI) for 1, 3, and 5-year OS of 0.912 (0.881-0.952), 0.851 (0.824-0.901), and 0.841 (0.807-0.878), respectively. Significant differences in survival time were observed between different groups stratified by this signature. It showed great discrimination, calibration, and clinical utility (all p<0.05). Distinct gene expression patterns were identified. The tumor heterogeneity and microenvironment significantly varied between different score groups. The DLRS could effectively predict the prognosis of LUAD patients by reflecting the tumor heterogeneity and microenvironment.