Multimodal Lung Disease Classification using Deep Convolutional Neural Network

Lung disease is the most common cause of severe illness and death in the World. The early diagnosis and treatment of the disease are of great importance in the medical field. The computer-assisted systems for lung disease recognition are effective methods to help physicians diagnose the diseases effectively. Therefore, this paper studies the multimodal recognition of lung sound using spectrograms. Based on the classification of lung diseases by deep convolutional neural networks, an integrated network Multimodal Lung Disease Classification (MLDC) model was used with advanced pre-processing techniques to assess the classification accuracy acceptable in the medical field. The research has three main contributions. First, we have performed data pre-processing using two techniques Data Normalization and Data Augmentation. The data were normalized by removing the unwanted noise and adjusting the peak values in a sound signal. For training purposes, the publicly available data was insufficient. Hence we applied advanced data augmentation techniques to generate some additional data without affecting the categories. Secondly, we have extracted the spectrograms from lung sound and used them as features and images for signal and image processing. Finally, we created an integrated model for the high-performance classification of lung diseases. We have compared the audio and spectrogram image-based results where we found the image-based approach is cost-effective, efficient, and reliable.