Research Article
Abnormality Detection in Wireless Capsule Endoscopy Images Using Deep Features
@INPROCEEDINGS{10.1007/978-3-031-60665-6_13, author={Daniel G. P. de S\^{a} and Giulia de A. Freulonx and Marcio P. Ferreira and Alexandre C. P. Pessoa and Darlan B. P. Quintanilha and Arist\^{o}fanes C. Silva}, title={Abnormality Detection in Wireless Capsule Endoscopy Images Using Deep Features}, proceedings={Wireless Mobile Communication and Healthcare. 12th EAI International Conference, MobiHealth 2023, Vila Real, Portugal, November 29-30, 2023 Proceedings}, proceedings_a={MOBIHEALTH}, year={2024}, month={6}, keywords={Endoscopy Deep Features One-Class XGBoost}, doi={10.1007/978-3-031-60665-6_13} }- Daniel G. P. de Sá
Giulia de A. Freulonx
Marcio P. Ferreira
Alexandre C. P. Pessoa
Darlan B. P. Quintanilha
Aristófanes C. Silva
Year: 2024
Abnormality Detection in Wireless Capsule Endoscopy Images Using Deep Features
MOBIHEALTH
Springer
DOI: 10.1007/978-3-031-60665-6_13
Abstract
The capsule endoscopy examination is a common medical procedure used to diagnose and treat gastrointestinal tract diseases without the need for invasive procedures. Images captured during the examination can reveal a wide range of abnormalities, including lesions, inflammation, ulcers, bleeding, and tumors. However, interpreting these images can be a challenge for physicians since the videos contain a large number of frames (images) to be analyzed. To attempt to achieve an early diagnosis and reduce the lethality of gastrointestinal system pathologies, the use of artificial intelligence has been extensively studied to alleviate the workload of healthcare professionals, as the large number of images resulting from an examination makes manual categorization of each image challenging. This work studied the use of machine learning methods such as OneClassSVM and XGBoost based on features extracted from deep neural networks and compared them to traditional convolutional neural network methods, such as the ResNet152 network. The Kvasir-Capsule and ERS datasets were used to evaluate the proposed methods, focusing on classifying images as normal or abnormal. Among the evaluated methods, XGBoost showed the best results among others, with a weighted F1-score of 0.71 on the ERS dataset and 0.87 on the Kvasir-Capsule dataset. The class imbalance in both datasets proved to be a continuous challenge, adding to the challenge of the low quantity images in the ERS dataset.
