Endoscopic Ultrasound

ORIGINAL ARTICLE
Year
: 2021  |  Volume : 10  |  Issue : 5  |  Page : 361--371

Deep learning with convex probe endobronchial ultrasound multimodal imaging: A validated tool for automated intrathoracic lymph nodes diagnosis


Jin Li1, Xinxin Zhi2, Junxiang Chen2, Lei Wang3, Mingxing Xu1, Wenrui Dai1, Jiayuan Sun2, Hongkai Xiong1 
1 School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
2 Department of Respiratory Endoscopy, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai; Department of Respiratory and Critical Care Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai; Shanghai Engineering Research Center of Respiratory Endoscopy, Shanghai, China
3 Department of Ultrasound, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, China

Correspondence Address:
Dr. Jiayuan Sun
Department of Respiratory Endoscopy, Department of Respiratory and Critical Care Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, 241 West Huaihai Road, Shanghai 200030
China
Dr. Wenrui Dai
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, Shanghai 200240
China

Background and Objectives: Along with the rapid improvement of imaging technology, convex probe endobronchial ultrasound (CP-EBUS) sonographic features play an increasingly important role in the diagnosis of intrathoracic lymph nodes (LNs). Conventional qualitative and quantitative methods for EBUS multimodal imaging are time-consuming and rely heavily on the experience of endoscopists. With the development of deep-learning (DL) models, there is great promise in the diagnostic field of medical imaging. Materials and Methods: We developed DL models to retrospectively analyze CP-EBUS images of 294 LNs from 267 patients collected between July 2018 and May 2019. The DL models were trained on 245 LNs to differentiate benign and malignant LNs using both unimodal and multimodal CP-EBUS images and independently evaluated on the remaining 49 LNs to validate their diagnostic efficiency. The human comparator group consisting of three experts and three trainees reviewed the same test set as the DL models. Results: The multimodal DL framework achieves an accuracy of 88.57% (95% confidence interval [CI] [86.91%–90.24%]) and area under the curve (AUC) of 0.9547 (95% CI [0.9451–0.9643]) using the three modes of CP-EBUS imaging in comparison to the accuracy of 80.82% (95% CI [77.42%–84.21%]) and AUC of 0.8696 (95% CI [0.8369–0.9023]) by experts. Statistical comparison of their average receiver operating curves shows a statistically significant difference (P < 0.001). Moreover, the multimodal DL framework is more consistent than experts (kappa values 0.7605 vs. 0.5800). Conclusions: The DL models based on CP-EBUS imaging demonstrated an accurate automated tool for diagnosis of the intrathoracic LNs with higher diagnostic efficiency and consistency compared with experts.


How to cite this article:
Li J, Zhi X, Chen J, Wang L, Xu M, Dai W, Sun J, Xiong H. Deep learning with convex probe endobronchial ultrasound multimodal imaging: A validated tool for automated intrathoracic lymph nodes diagnosis.Endosc Ultrasound 2021;10:361-371


How to cite this URL:
Li J, Zhi X, Chen J, Wang L, Xu M, Dai W, Sun J, Xiong H. Deep learning with convex probe endobronchial ultrasound multimodal imaging: A validated tool for automated intrathoracic lymph nodes diagnosis. Endosc Ultrasound [serial online] 2021 [cited 2022 Jan 27 ];10:361-371
Available from: http://www.eusjournal.com/article.asp?issn=2303-9027;year=2021;volume=10;issue=5;spage=361;epage=371;aulast=Li;type=0