Convolutional Neural Network with Batch Normalization for Classification of Endoscopic Gastrointestinal Diseases

• Published in: Machine Learning and Big Data Analytics Paradigms: Analysis, Applications and Challenges Vol. 77; pp. 113 - 128
• Main Authors: Ezzat, Dalia, Afify, Heba M., Taha, Mohamed Hamed N., Hassanien, Aboul Ella
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2020; Springer International Publishing
• Series: Studies in Big Data
• Subjects: Batch normalization (BN); Convolutional neural network (CNN); Endoscopic gastrointestinal (GI) images; Exponential linear unit (ELU); Kvasir dataset
• ISBN: 3030593371; 9783030593377
• ISSN: 2197-6503; 2197-6511
• DOI: 10.1007/978-3-030-59338-4_7

In this paper, an approach for classifying gastrointestinal (GI) diseases from endoscopic images is proposed. The proposed approach is built using a convolutional neural network (CNN) with batch normalization (BN) and an exponential linear unit (ELU) as the activation function. The proposed approach consists of eight layers (six convolutional and two fully connected layers) and is used to identify eight types of GI diseases in version two of the Kvasir dataset. The proposed approach was compared with other CNN architectures (VGG16, VGG19, and Inception-v3) using five elements (number of convolutional layers, number of total parameters of the convolutional layers, number of epochs, validation accuracy and test accuracy). The proposed approach achieved good results compared to the compared architectures. It achieved a validation accuracy of 88%, which is superior to other architectures and a test accuracy of 87%, which outperforms the Inception-v3 architecture. Therefore, the proposed approach has less trained images and less computational complexity in the training phase.