EP-CapsNet

Abstract

Serum electrophoresis test detects the abnormality of protein patterns. Electrophoresis (EP) test separates protein components based on their density. Patterns exhibited by this test mostly show very close approximation, making it difficult to examine test results within a short amount of time as it has many variations of patterns and requires a significant amount of knowledge to discern them properly. Therefore, to help clinical examiners save time and produce consistent results, our study seeks to automate the process by utilizing the deep learning technique. Computer vision along deep learning has shown promising results in various medical fields. Consequently, this study was carried out to produce a newly developed Capsule Network embedded with inception module to classify abnormal and normal electrophoresis patterns by making use of deep learning to improve both accuracy and sensitivity. Instead of extracting features from the image, we used the whole image as an input to the classifier. This study used 39,484 electrophoresis graph images and utilized capsule network as the foundation of the deep learning architecture to learn the images without data augmentation. The results show that our proposed architecture achieved 96% as its accuracy, 94.5% Balanced Classification Rate, and 0.88 Matthew's Correlation Coefficient, and 97% sensitivity rate, showing that the proposed deep learning model outperform the baseline models.