Deep learning radiopathomics predicts targeted therapy sensitivity in EGFR-mutant lung adenocarcinoma
Taotao Yang1,2, Xianqi Wang1,2, Yuan Jin3
1Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038, China.
Background:
Ttyrosine kinase inhibitors (TKIs) represent the standard first-line treatment for patients with epidermal growth factor receptor (EGFR)-mutant lung adenocarcinoma. However, not all patients with EGFR mutations respond to TKIs. This study aims to develop a deep learning radiological-pathological-clinical (DLRPC) model that integrates computed tomography (CT) images, hematoxylin and eosin (H&E)-stained aspiration biopsy samples, and clinical data to predict the response in EGFR-mutant lung adenocarcinoma patients undergoing TKIs treatment.
Methods:
We retrospectively analyzed data from 214 lung adenocarcinoma patients who received TKIs treatment from two medical centers between September 2013 and June 2023. The DLRPC model leverages paired CT, pathological images and clinical data, incorporating a clinical-based attention mask to further explore the cross-modality associations. To evaluate its diagnostic performance, we compared the DLRPC model against single-modality models and a decision level fusion model based on Dempster-Shafer theory. Model performances metrics, including area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were used for evaluation. The Delong test assessed statistically significantly differences in AUC among models.
Results:
The DLRPC model demonstrated strong performance, achieving an AUC value of 0.8424. It outperformed the single-modality models (AUC = 0.6894, 0.7753, 0.8052 for CT model, pathology model and clinical model, respectively. P < 0.05). Additionally, the DLRPC model surpassed the decision level fusion model (AUC = 0.8132, P < 0.05).
Conclusion:
The DLRPC model effectively predicts the response of EGFR-mutant lung adenocarcinoma patients to TKIs, providing a promising tool for personalized treatment decisions in lung cancer management.
Insights
A new deep learning model integrating CT scans, pathology, and clinical data accurately predicts treatment response in EGFR-mutant lung adenocarcinoma patients receiving tyrosine kinase inhibitors (TKIs). This tool aids personalized lung cancer therapy.
Area of Science:
- Oncology
- Radiology
- Pathology
- Artificial Intelligence
Background:
- Tyrosine kinase inhibitors (TKIs) are standard first-line therapy for EGFR-mutant lung adenocarcinoma.
- Treatment response to TKIs varies among patients with EGFR mutations.
- Predicting TKI response is crucial for optimizing lung cancer treatment strategies.
Purpose of the Study:
- To develop a deep learning radiological-pathological-clinical (DLRPC) model.
- To integrate CT images, H&E-stained biopsy samples, and clinical data for response prediction.
- To evaluate the DLRPC model's efficacy in predicting TKI response in EGFR-mutant lung adenocarcinoma.
Main Methods:
- Retrospective analysis of 214 lung adenocarcinoma patients treated with TKIs.
- Development of a DLRPC model incorporating CT, pathology, and clinical data with a clinical-based attention mask.
- Comparison of DLRPC model performance against single-modality models and a Dempster-Shafer decision level fusion model using AUC, accuracy, sensitivity, specificity, PPV, and NPV.
Main Results:
- The DLRPC model achieved a high Area Under the Curve (AUC) of 0.8424.
- DLRPC significantly outperformed single-modality CT (AUC=0.6894), pathology (AUC=0.7753), and clinical models (AUC=0.8052).
- The DLRPC model also demonstrated superior performance compared to the decision level fusion model (AUC=0.8132).
Conclusions:
- The DLRPC model is an effective tool for predicting TKI response in EGFR-mutant lung adenocarcinoma.
- This integrated approach offers a promising avenue for personalized treatment decisions in lung cancer.
- The DLRPC model enhances precision medicine for lung adenocarcinoma patients.
