EGFR mutation detection in Whole Slide Images of non-small cell lung cancers using a two-stage deep transfer learning approach

Background: Lung cancer (LC) is the leading cause of cancer death worldwide. Non-small cell lung cancer is the most frequent and includes adenocarcinoma and squamous cell carcinoma. Currently, LC treatment is based on tumor molecular profiling. LC may display Epidermal Growth Factor Receptor (EGFR) gene mutation. Detecting mutation in EGFR gene is crucial for the tyrosine kinase inhibitory therapy. Methods: This study used a computer-based methodology with two Convolutional Neural Networks (CNNs) based on InceptionResNet-V2, applied to Whole Slide Images, to distinguish healthy from cancerous tissue and then EGFR mutated tumor tissue samples. The analysis was conducted on 259 lung cancer cases collected from three different centers (Florence, Rome and Sassari). Results: This methodology achieved an accuracy of 96.17% in distinguishing healthy from cancerous tissue, with specificity of 87.89%, sensitivity of 98.43%, an F1 score of 97.59% and an AUC of 0.99. Additionally, the Cohen’s Kappa indicated a consistency of 0.7982 and the confusion matrix showed a correct classification rate of 96.2%. For EGFR mutation detection in cancer tissue, slide-level performance after aggregation reached accuracy of 76.67% with specificity of 80.77%, sensitivity 73.53%, an F1 score of 78.12%, a consistency of 0.5583 of Cohen’s Kappa and an AUC of 0.77. In addition to the confusion matrix showing 76.7% as a correct classification rate. Conclusion: The two tested CNNs showed potential for assisting LC diagnosis, especially in distinguishing healthy from tumor tissue. While the direct detection of EGFR mutational status remains challenging, the results suggest that relevant predictive signals can still be extracted from routine H&E slides.