Jia Wenjuan, Yang Ming, Wang Shui-Hua
School of Computer Science and Engineering, Nanjing Normal University, Wenyuan, Nanjing, 210023, People's Republic of China.
Department of Radiology, Children's Hospital of Nanjing Medical University, Nanjing, 210008, People's Republic of China.
J Med Syst. 2017 Sep 11;41(10):165. doi: 10.1007/s10916-017-0814-4.
Hearing loss, a partial or total inability to hear, is known as hearing impairment. Untreated hearing loss can have a bad effect on normal social communication, and it can cause psychological problems in patients. Therefore, we design a three-category classification system to detect the specific category of hearing loss, which is beneficial to be treated in time for patients. Before the training and test stages, we use the technology of data augmentation to produce a balanced dataset. Then we use deep autoencoder neural network to classify the magnetic resonance brain images. In the stage of deep autoencoder, we use stacked sparse autoencoder to generate visual features, and softmax layer to classify the different brain images into three categories of hearing loss. Our method can obtain good experimental results. The overall accuracy of our method is 99.5%, and the time consuming is 0.078 s per brain image. Our proposed method based on stacked sparse autoencoder works well in classification of hearing loss images. The overall accuracy of our method is 4% higher than the best of state-of-the-art approaches.
听力损失，即部分或完全丧失听力，被称为听力障碍。未经治疗的听力损失会对正常社交沟通产生不良影响，并可能导致患者出现心理问题。因此，我们设计了一个三类分类系统来检测听力损失的具体类别，这有利于患者及时接受治疗。在训练和测试阶段之前，我们使用数据增强技术来生成一个平衡的数据集。然后我们使用深度自动编码器神经网络对脑部磁共振图像进行分类。在深度自动编码器阶段，我们使用堆叠式稀疏自动编码器来生成视觉特征，并使用softmax层将不同的脑部图像分为三类听力损失。我们的方法能够获得良好的实验结果。我们方法的总体准确率为99.5%，每幅脑部图像的耗时为0.078秒。我们提出的基于堆叠式稀疏自动编码器的方法在听力损失图像分类中表现良好。我们方法的总体准确率比现有最佳方法高出4%。
