Deep CNN Model Using CT Radiomics Feature Mapping Recognizes EGFR Gene Mutation Status of Lung Adenocarcinoma

To recognize the epidermal growth factor receptor (EGFR) gene mutation status in lung adenocarcinoma (LADC) has become a prerequisite of deciding whether EGFR-tyrosine kinase inhibitor (EGFR-TKI) medicine can be used. Polymerase chain reaction assay or gene sequencing is for measuring EGFR status, however, the tissue samples by surgery or biopsy are required. We propose to develop deep learning models to recognize EGFR status by using radiomics features extracted from non-invasive CT images. Preoperative CT images, EGFR mutation status and clinical data have been collected in a cohort of 709 patients (the primary cohort) and an independent cohort of 205 patients. After 1,037 CT-based radiomics features are extracted from each lesion region, 784 discriminative features are selected for analysis and construct a feature mapping. One Squeeze-and-Excitation (SE) Convolutional Neural Network (SE-CNN) has been designed and trained to recognize EGFR status from the radiomics feature mapping. SE-CNN model is trained and validated by using 638 patients from the primary cohort, tested by using the rest 71 patients (the internal test cohort), and further tested by using the independent 205 patients (the external test cohort). Furthermore, SE-CNN model is compared with machine learning (ML) models using radiomics features, clinical features, and both features. EGFR(-) patients show the smaller age, higher odds of female, larger lesion volumes, and lower odds of subtype of acinar predominant adenocarcinoma (APA), compared with EGFR(+). The most discriminative features are for texture (614, 78.3%) and the features of first order of intensity (158, 20.1%) and the shape features (12, 1.5%) follow. SE-CNN model can recognize EGFR mutation status with an AUC of 0.910 and 0.841 for the internal and external test cohorts, respectively. It outperforms the CNN model without SE, the fine-tuned VGG16 and VGG19, three ML models, and the state-of-art models. Utilizing radiomics feature mapping extracted from non-invasive CT images, SE-CNN can precisely recognize EGFR mutation status of LADC patients. The proposed method combining radiomics features and deep leaning is superior to ML methods and can be expanded to other medical applications. The proposed SE-CNN model may help make decision on usage of EGFR-TKI medicine.

Download Full-text

Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning

European Respiratory Journal ◽

10.1183/13993003.00986-2018 ◽

2019 ◽

Vol 53 (3) ◽

pp. 1800986 ◽

Cited By ~ 64

Author(s):

Shuo Wang ◽

Jingyun Shi ◽

Zhaoxiang Ye ◽

Di Dong ◽

Dongdong Yu ◽

...

Keyword(s):

Computed Tomography ◽

Deep Learning ◽

Lung Adenocarcinoma ◽

Egfr Mutation ◽

Treatment Guidelines ◽

Learning Model ◽

Ct Images ◽

Mutation Status ◽

Non Invasive ◽

Deep Learning Model

Epidermal growth factor receptor (EGFR) genotyping is critical for treatment guidelines such as the use of tyrosine kinase inhibitors in lung adenocarcinoma. Conventional identification of EGFR genotype requires biopsy and sequence testing which is invasive and may suffer from the difficulty of accessing tissue samples. Here, we propose a deep learning model to predict EGFR mutation status in lung adenocarcinoma using non-invasive computed tomography (CT).We retrospectively collected data from 844 lung adenocarcinoma patients with pre-operative CT images, EGFR mutation and clinical information from two hospitals. An end-to-end deep learning model was proposed to predict the EGFR mutation status by CT scanning.By training in 14 926 CT images, the deep learning model achieved encouraging predictive performance in both the primary cohort (n=603; AUC 0.85, 95% CI 0.83–0.88) and the independent validation cohort (n=241; AUC 0.81, 95% CI 0.79–0.83), which showed significant improvement over previous studies using hand-crafted CT features or clinical characteristics (p<0.001). The deep learning score demonstrated significant differences in EGFR-mutant and EGFR-wild type tumours (p<0.001).Since CT is routinely used in lung cancer diagnosis, the deep learning model provides a non-invasive and easy-to-use method for EGFR mutation status prediction.

Download Full-text

The Utility and Efficiency Of Diffusion Tensor Imaging Values to Determine Epidermal Growth Factor Receptor Gene Mutation Status in Brain Metastases From Lung Adenocarcinoma: A Preliminary Study

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405615666191122122207 ◽

2019 ◽

Vol 15 ◽

Author(s):

Mehmet Ali Gultekin ◽

Hacı Mehmet Turk ◽

Ismail Yurtsever ◽

Bahar Atasoy ◽

Altay Aliyev ◽

...

Keyword(s):

Brain Metastases ◽

Lung Adenocarcinoma ◽

Gene Mutation ◽

Egfr Mutation ◽

Wild Type ◽

Mutation Status ◽

Egfr Gene ◽

Group 2 ◽

Egfr Gene Mutation ◽

Group 1

Background: We aimed to investigate whether there were any diffusion tensor imaging (DTI) value differences in brain metastases (BM) due to lung adenocarcinoma based on the epidermal growth factor receptor (EGFR) gene mutation status. Material and Methods: 17 patients with 32 solid intracranial metastatic lesions from lung adenocarcinoma were included prospectively. Patients were divided according to the EGFR mutation status as EGFR (+) (group 1, n:8) and EGFR wild type (group 2, n:9). The fractional anisotropy (FA), apparent diffusion coefficient (ADC), normalized ADC (nADC), axial diffusivity (AD), and radial diffusivity (RD) values were measured from the solid component of the metastatic lesions and nADC values were calculated. DTI values were compared between group 1 and group 2. Receiver-operating characteristic analysis was used to obtain cut-off values for the parameters presenting a statistical difference between the EGFR gene mutation positive and wild type group. Results: There were statistically significant differences in measured ADC, nADC, AD, and RD values between group 1 and group 2. The ADC, nADC, AD, and RD values were significantly lower in group 1. There was no significant difference in FA values between two groups. Analysis by the ROC curve method revealed a cut-off value of ≤721 x 10-6 mm2/s for ADC (Sensitivity=72.7, Specificity=85.7); ≤0.820 for nADC (Sensitivity=72.7, Specificity=90.5), ≤886 for AD (Sensitivity=81.8, Specificity=81.0), and ≤588 for RD (Sensitivity=63.6, Specificity=90.5) in differentiating EGFR mutation (+) group from wild type group. Conclusion: Combination of the decreased ADC, nADC, AD, and RD values in BM due to lung adenocarcinoma can be important for predicting the EGFR gene mutation status. DTI features of the brain metastases from lung adenocarcinoma may be utilized to provide insight into the EGFR mutation status and guide the clinicians for initiation of targeted therapy.

Download Full-text