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

Abstract

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.