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

By Shuo Wang, Jingyun Shi, Z. Ye, Di Dong, Dongdong Yu, Mu Zhou, Ying Liu, Olivier Gevaert, Kun Wang, Yongbei Zhu and 3 more. European Respiratory Journal, 2019

369 citations recorded by the source corpus.

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. Deep learning provides a noninvasive method for EGFR mutation prediction (AUC 0.81) in lung adenocarcinoma, which shows significant improvement over using hand-crafted CT features or clinical characteristics http://ow.ly/LtDJ30nhc5Q

Subfields: Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/e3ce219d2df9a2502bf4545cb459ced9533003f9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Radiology, Nuclear Medicine and Imaging

1. Olivier Elemento
2. Anant Madabhushi
3. Faisal Mahmood
4. B. Bhinder
5. C. Gilvary
6. Neel S. Madhukar

Citations in the corpus

• A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis (2020, methodology): “In this 10 auxiliary training process, we trained the COVID-19Net to predict EGFR mutation 11 status (EGFR-mutant or EGFR wild type) use the lung-ROI [11].”
• Artificial Intelligence in Cancer Research and Precision Medicine (2021, background): “For example, a transfer learning–based DNN approach could determine EGFR mutation status directly from preoperative CT scans of 844 patients with lung adenocarcinoma with AUC > 0.81 (35).”
• Predicting cancer outcomes with radiomics and artificial intelligence in radiology (2021, methodology): “DL models developed using CT 139 and PET–CT scans 140 efficiently predicted EGFR mutational status in patients with NSCLC with AUCs of 0.81, for both CT and PET–CT.”
• Artificial intelligence for digital and computational pathology (2023, background): “5) and translational considerations for clinical deployment (Box 3).”
• From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. (2023, methodology): “51 When biopsy samples are available, it is still more reliable to measure genotypes using molecular methods that we discuss in the next section.”
• The Role of Imaging in the Detection and Management of COVID-19: A Review (2020, methodology): “Instead of using transfer learning from natural images, they collected 4106 lung cancer patients with EGFR gene mutation status [88] to pre-train the model.”