Deep learning for detection and diagnosis of intrathoracic lymphadenopathy from endobronchial ultrasound multimodal videos: A multi-center study.
Authors
Affiliations (10)
Affiliations (10)
- Department of Respiratory Endoscopy, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Department of Respiratory and Critical Care Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Shanghai Engineering Research Center of Respiratory Endoscopy, Shanghai, China.
- Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China.
- Department of Ultrasound, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Department of Respiratory and Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou University People's Hospital, Zhengzhou, China.
- Department of Respiratory and Critical Care Medicine, The Affiliated Yantai Yuhuangding Hospital of Qingdao University, Yantai, China.
- Department of Interventional Pulmonology and Endoscopic Diagnosis and Treatment Center, Anhui Chest Hospital, Hefei, China.
- Department of Respiratory Medicine, Affiliated Hangzhou First People's Hospital, School of Medicine, Westlake University, Hangzhou, China.
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: [email protected].
- Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: [email protected].
- Department of Respiratory Endoscopy, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Department of Respiratory and Critical Care Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Shanghai Engineering Research Center of Respiratory Endoscopy, Shanghai, China. Electronic address: [email protected].
Abstract
Convex probe endobronchial ultrasound (CP-EBUS) ultrasonographic features are important for diagnosing intrathoracic lymphadenopathy. Conventional methods for CP-EBUS imaging analysis rely heavily on physician expertise. To overcome this obstacle, we propose a deep learning-aided diagnostic system (AI-CEMA) to automatically select representative images, identify lymph nodes (LNs), and differentiate benign from malignant LNs based on CP-EBUS multimodal videos. AI-CEMA is first trained using 1,006 LNs from a single center and validated with a retrospective study and then demonstrated with a prospective multi-center study on 267 LNs. AI-CEMA achieves an area under the curve (AUC) of 0.8490 (95% confidence interval [CI], 0.8000-0.8980), which is comparable to experienced experts (AUC, 0.7847 [95% CI, 0.7320-0.8373]; p = 0.080). Additionally, AI-CEMA is successfully transferred to a pulmonary lesion diagnosis task and obtains a commendable AUC of 0.8192 (95% CI, 0.7676-0.8709). In conclusion, AI-CEMA shows great potential in clinical diagnosis of intrathoracic lymphadenopathy and pulmonary lesions by providing automated, noninvasive, and expert-level diagnosis.