Deep Learning Radiomic Signature Predicts the Overall Survival of Patients with Lung Adenocarcinoma by Reflecting the Tumor Heterogeneity and Microenvironment
Academic Radiology · 2026-01 · 33 (1) · 224-235
DOI: 10.1016/j.acra.2025.09.033 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academic Radiology, 2026-01. Verfasst von Chunlei Dai und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiothoracic Surgery, Suzhou Municipal Hospital, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou, Jiangsu, China…. Hauptthemen laut MEDLINE: Deep Learning, Lung Neoplasms, Tumor Microenvironment, Adenocarcinoma of Lung. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
RATIONALE AND OBJECTIVES: 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. MATERIALS AND METHODS: 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. RESULTS: 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
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- 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: doctoryang001@163.com.
Zitieren
APA
Dai, C., Huang, B., Yu, Z., Xu, J., Li, J., & Yang, J. (2026). Deep Learning Radiomic Signature Predicts the Overall Survival of Patients with Lung Adenocarcinoma by Reflecting the Tumor Heterogeneity and Microenvironment. Academic Radiology, 33(1), 224-235. https://doi.org/10.1016/j.acra.2025.09.033
Vancouver
Dai C, Huang B, Yu Z, Xu J, Li J, Yang J. Deep Learning Radiomic Signature Predicts the Overall Survival of Patients with Lung Adenocarcinoma by Reflecting the Tumor Heterogeneity and Microenvironment. Academic Radiology. 2026;33(1):224-235. doi:10.1016/j.acra.2025.09.033
BibTeX
@article{Dai2026,
author = {Dai, Chunlei and Huang, Bo and Yu, Zhe and Xu, Jingwei and Li, Jian and Yang, Jian},
title = {Deep Learning Radiomic Signature Predicts the Overall Survival of Patients with Lung Adenocarcinoma by Reflecting the Tumor Heterogeneity and Microenvironment},
journal = {Academic Radiology},
year = {2026},
volume = {33},
number = {1},
pages = {224--235},
doi = {10.1016/j.acra.2025.09.033}
}
EUVIMED