Department of Otolaryngology, Zhujiang Hospital, Southern Medical University, Guangzhou, China.
Department of Otolaryngology, Shenzhen Children's Hospital, Shenzhen, China.
Laryngoscope. 2021 Jul;131(7):E2344-E2351. doi: 10.1002/lary.29302. Epub 2020 Dec 28.
OBJECTIVES/HYPOTHESIS: To create a new strategy for monitoring pediatric otitis media (OM), we developed a brief, reliable, and objective method for automated classification using convolutional neural networks (CNNs) with images from otoscope.
Prospective study.
An otoscopic image classifier for pediatric OM was built upon the idea of deep learning and transfer learning using the two most widely used CNN architectures named Xception and MobileNet-V2. Otoscopic images, including acute otitis media (AOM), otitis media with effusion (OME), and normal ears were obtained from our institution. Among qualified otoendoscopic images, 10,703 images were used for training, and 1,500 images were used for testing. In addition, 102 images captured by smartphone with WI-FI connected otoscope were used as a prospective test set to evaluate the model for home screening and monitoring.
For all diagnoses combined in the test set, the Xception model and the MobileNet-V2 model had similar overall accuracies of 97.45% (95% CI 96.81%-97.94%) and 95.72% (95% CI 95.12%-96.16%). The overall accuracies of two models with smartphone images were 90.66% (95% CI 90.21%-90.98%) and 88.56% (95% CI 87.86%-90.05%). The class activation map results showed that the extracted features of smartphone images were the same as those of otoendoscopic images.
We have developed deep learning algorithms for the successfully automated classification of pediatric AOM and OME with otoscopic images. With a smartphone-enabled wireless otoscope, artificial intelligence may assist parents in early detection and continuous monitoring at home to decrease the visit frequencies.
NA Laryngoscope, 131:E2344-E2351, 2021.
目的/假设：为了创建一种新的小儿中耳炎（OM）监测策略，我们开发了一种使用耳镜图像的卷积神经网络（CNN）进行自动分类的简短、可靠和客观的方法。
前瞻性研究。
基于深度学习和迁移学习的理念，使用两种使用最广泛的 CNN 架构（Xception 和 MobileNet-V2）构建了小儿 OM 的耳镜图像分类器。从我们的机构获得了包括急性中耳炎（AOM）、分泌性中耳炎（OME）和正常耳朵在内的耳镜图像。在合格的耳内镜图像中，有 10703 张图像用于训练，1500 张图像用于测试。此外，还使用了通过 WI-FI 连接的耳镜拍摄的 102 张智能手机图像作为前瞻性测试集，以评估用于家庭筛查和监测的模型。
在测试集中，对于所有诊断组合，Xception 模型和 MobileNet-V2 模型的总体准确率相似，分别为 97.45%（95%CI 96.81%-97.94%）和 95.72%（95%CI 95.12%-96.16%）。使用智能手机图像的两种模型的总体准确率分别为 90.66%（95%CI 90.21%-90.98%）和 88.56%（95%CI 87.86%-90.05%）。类激活图的结果表明，智能手机图像提取的特征与耳内镜图像相同。
我们已经开发了用于小儿 AOM 和 OME 的耳镜图像自动分类的深度学习算法。通过使用支持智能手机的无线耳镜，人工智能可能有助于家长在家中进行早期检测和持续监测，以减少就诊频率。
无。喉科学，131：E2344-E2351，2021。
