Automated classification of the tympanic membrane using a convolutional neural network

Abstract

Precise evaluation of the tympanicmembrane (TM) is required for accurate diagnosis ofmiddle ear diseases. However, making an accurate assessment is sometimes difficult. Artificial intelligence is often employed for image processing, especially for performing high level analysis such as image classification, segmentation and matching. In particular, convolutional neural networks (CNNs) are increasingly used in medical image recognition. This study demonstrates the usefulness and reliability of CNNs in recognizing the side and perforation of TMs in medical images. CNN was constructed with typically six layers. After random assignment of the available images to the training, validation and test sets, training was performed. The accuracy of the CNN model was consequently evaluated using a new dataset. A class activation map (CAM) was used to evaluate feature extraction. The CNN model accuracy of detecting the TMside in the test dataset was 97.9%, whereas that of detecting the presence of perforation was 91.0%. The side of the TMand the presence of a perforation affect the activation sites. The results show that CNNs can be a useful tool for classifying TMlesions and identifying TMsides. Further research is required to consider real-time analysis and to improve classification accuracy.