Turkish Journal of Electrical Engineering and Computer Sciences




Deep learning (DL) models have performed tremendously well in image classification. This good performance can be attributed to the availability of massive data in most domains. However, some domains are known to have few datasets, especially the health sector. This makes it difficult to develop domain-specific high-performing DL algorithms for these fields. The field of health is critical and requires accurate detection of diseases. In the United States Gastrointestinal diseases are prevalent and affect 60 to 70 million people. Ulcerative colitis, polyps, and esophagitis are some gastrointestinal diseases. Colorectal polyps is the third most diagnosed malignancy in the world. This work, therefore proposes a variant Capsule Network (CapsNet) termed Denoising patch-and-amplify Gabor Capsule Network for detecting gastrointestinal tract diseases. The proposed model leverages the advantages of patching, feature amplification, and Gabor filters to enable the learning of meaningful information (from small datasets) needed to achieve intelligence in domain-specific models. During the experimental procedure, the proposed model achieved 95.10%, 85.50%, and 96.80% recognition accuracies on Fashion-MNIST, Cifar10, and Kvasir-v2 datasets. The proposed model performs comparably well with CapsNet models in the domain of gastrointestinal recognition.


Capsule Network, gastrointestinal tract, Gabor filters, deep learning

First Page


Last Page


Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.