International Conference on Computer and Knowledge Engineering

Home / 14th International Conference on Computer and Knowledge Engineering

Frame Classification in Video Capsule Endoscopy Using an Improved Capsule Network

Authors :

Amirhossein Ghaemi¹ Habibollah Danyali² Alireza Ghaemi³

1- Department of Electrical Engineering Shiraz University of Technology Shiraz, Iran 2- Department of Electrical Engineering Shiraz University of Technology Shiraz, Iran 3- Department of Electrical Engineering Shiraz University of Technology Shiraz, Iran

Keywords :

Capsule network،Convolutional neural network،Classification،Lightweight network،Gastrointestinal diseases،Video capsule endoscopy،Kvasir-Capsule

Abstract :

The non-invasive technique of Video Capsule Endoscopy (VCE) enables a thorough examination of the human intestinal tract, generating numerous images from various segments of the gastrointestinal system. Since manual image analysis is labor-intensive and time-consuming, there is a high demand for automated diagnostic systems to identify digestive disorders from VCE frames. Most existing studies rely on Convolutional Neural Networks (CNNs). These approaches demonstrate limited efficacy in capturing spatial relationships between features and recognizing objects across various poses and variations within VCE images. Therefore, this paper proposes an improved capsule network to increase the preservation and comprehension of spatial connections between features, hence improving the recognition of patterns and objects that have been rotated, scaled, or otherwise transformed. The proposed network employs convolutional-capsule layers with a modified routing algorithm between capsules to encode and extract characteristics, resulting in part-whole relationships. Furthermore, the network applies vector length calculations to feature vectors obtained via the layers mentioned above to determine the classification of images as normal or abnormal. The proposed network attains state-of-the-art performance, with a notable accuracy of 96.78% on the public Kvasir-Capsule dataset, while requiring considerably fewer parameters than competing classification networks.

Papers List

List of archived papers

Towards Transparent and Accurate Story Point Estimation via Interpretable BERT-based Modeling

Seyed Emad Baradaran Hosseini - Maryam Khodabakhsh - Alireza Tajary - Seyedehfatemeh Karimi

Deep Learning-based Processing of Autonomous Vehicle Radar Data to Achieve High Resolution

Nima Abdolrahimi Shahamat - Vahideh Moghtadaiee - Esfandiar Mehrshahi

Adaptive Prioritization in Experience Replay Using Feedback from Multiple Learning Signals

Seyed Hossein Mostafavi - Mohammad Bagher Naghibi Sistani

Introducing Meta-Contrastive Adaptive Autoencoder to Tackle Cold-Start Challenges in Sparse Domains

Hossein Rashid - Erfan Arzhmand - Fatemeh Hosseini

Explainable Error Detection Method for Structured Data using HoloDetect framework

Abolfazl Mohajeri Khorasani - Sahar Ghassabi - Behshid Behkamal - Mostafa Milani

Evaluation of Efficient Electrocardiomatrix-based Identification Using Deep Learning Methods

Amirhossein Safari - Narges Mokhtari - Mohsen Hooshmand - Sadegh Sadeghi - Peyman Pahlevani

A Stacking Ensemble Framework for Ransomware Detection on the Bitcoin Blockchain Using Transaction Graph Analytics

Mohammad Mobin Teymourpour - Parsa Hedayatnia - Mohammad Allahbakhsh - Haleh Amintoosi

Efficient T-Count Fault-tolerant Quantum Clifford+T Multiplexer

Negin Mashayekhi - Shekoofeh Moghimi - Mohammad Reza Reshadinezhad

DTranIDS: A Two-Tiered Intrusion Detection System for RPL-based IoT Networks based on Decision Tree and Transformer Models

Mohammad Fazeli - Mohsen Raji - Mohammad Mahdi Fazeli

Generating Hand-Written Symbols With Trajectory Planning Using A Robotic Arm

Arya Parvizi - Armin Salimi-Badr