EfficientNet-Based Convolutional Neural Networks for Tuberculosis Classification

Abstract

Tuberculosis (TB) is an infectious disease that remained as a major health threat in the world. The computer-aided diagnosis (CAD) system for TB is one of the automated methods in early diagnosis and treatment, particularly used in developing countries. Literature survey shows that many methods exist based on machine learning for TB classification using X-ray images. Recently, deep learning approaches have been used instead of machine learning in many applications. This is mainly due to the reason that deep learning can learn optimal features from the raw dataset implicitly and obtains better performances. Due to the lack of X-ray image TB datasets, there are a small number of works on deep learning addressing the image-based classification of TB. In addition, the existing works can only classify X-ray images of a patient as TB or Healthy. This work presents a detailed investigation and analysis of 26 pretrained convolutional neural network (CNN) models using a recently released and large public database of TB X-ray. The proposed models have the capability to classify X-ray of a patient as TB, Healthy, or Sick but non-TB. Various visualization methods are adopted to show the optimal features learnt by the pretrained CNN models. Most of the pretrained CNN models achieved above 99% accuracy and less than 0.005 loss with 15 epochs during the training. All 7 different types of EfficientNet (ENet)-based CNN models performed better in comparison to other models in terms of accuracy, average and macro precision, recall, F1 score. Moreover, the proposed ENet-based CNN models performed better than other existing methods such as VGG16 and ResNet-50 for TB classification tasks. These results demonstrate that ENet-based models can be effectively used as a useful tool for TB classification.