Logo image
Predicting survival after radiosurgery in patients with lung cancer brain metastases using deep learning of radiomics and EGFR status
Journal article   Peer reviewed

Predicting survival after radiosurgery in patients with lung cancer brain metastases using deep learning of radiomics and EGFR status

Chien-Yi Liao, Cheng-Chia Lee, Huai-Che Yang, Ching-Jen Chen, Wen-Yuh Chung, Hsiu-Mei Wu, Wan-Yuo Guo, Ren-Shyan Liu and Chia-Feng Lu
Physical and Engineering Sciences in Medicine, Vol.46(2)
2023

Abstract

Brain Neoplasms Deep Learning ErbB Receptors Humans Lung Neoplasms Radiosurgery Retrospective Studies Brain Deep learning Diseases Forecasting Genes Magnetic resonance imaging Pathology Risk perception epidermal growth factor receptor EGFR protein, human epidermal growth factor receptor Brain metastasis Clinical information Deep learning Epidermal growth factor receptors Gamma knife radiosurgery Lung Cancer Magnetic resonance image radiomic Overall survival Radiosurgery Survival prediction adult aged Article brain metastasis cancer survival clinical feature cohort analysis controlled study deep learning DeepSurv diagnostic test accuracy study EGFR gene feature extraction female gamma knife radiosurgery gene mutation human information processing major clinical study male medical information middle aged mortality risk multilayer perceptron non small cell lung cancer nuclear magnetic resonance imaging overall survival personalized medicine prediction radiomics receiver operating characteristic retrospective study sensitivity and specificity very elderly brain tumor diagnostic imaging genetics lung tumor radiosurgery Magnetic resonance
The early prediction of overall survival (OS) in patients with lung cancer brain metastases (BMs) after Gamma Knife radiosurgery (GKRS) can facilitate patient management and outcome improvement. However, the disease progression is influenced by multiple factors, such as patient characteristics and treatment strategies, and hence satisfactory performance of OS prediction remains challenging. Accordingly, we proposed a deep learning approach based on comprehensive predictors, including clinical, imaging, and genetic information, to accomplish reliable and personalized OS prediction in patients with BMs after receiving GKRS. Overall 1793 radiomic features extracted from pre-GKRS magnetic resonance images (MRI), clinical information, and epidermal growth factor receptor (EGFR) mutation status were retrospectively collected from 237 BM patients who underwent GKRS. DeepSurv, a multi-layer perceptron model, with 4 different aggregation methods of radiomics was applied to predict personalized survival curves and survival status at 3, 6, 12, and 24 months. The model combining clinical features, EGFR status, and radiomics from the largest BM showed the best prediction performance with concordance index of 0.75 and achieved areas under the curve of 0.82, 0.80, 0.84, and 0.92 for predicting survival status at 3, 6, 12, and 24 months, respectively. The DeepSurv model showed a significant improvement (p < 0.001) in concordance index compared to the validated lung cancer BM prognostic molecular markers. Furthermore, the model provided a novel estimate of the risk-of-death period for patients. The personalized survival curves generated by the DeepSurv model effectively predicted the risk-of-death period which could facilitate personalized management of patients with lung cancer BMs. © 2023, Australasian College of Physical Scientists and Engineers in Medicine.

Metrics

6 Record Views

Details

Logo image