Gastrointestinal tract disease recognition based on denoising capsule network
Today, cancer is one of the leading causes of death in humans in the world. Cancers affect different parts of the human anatomy in different ways. There are significantly more deaths associated with gastrointestinal cancers such as colorectal cancer than with all other cancers. With computer-aided d...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2022-12-01
|
Series: | Cogent Engineering |
Subjects: | |
Online Access: | https://www.tandfonline.com/doi/10.1080/23311916.2022.2142072 |
_version_ | 1797758766019510272 |
---|---|
author | Yaw Afriyie Benjamin A. Weyori Alex A. Opoku |
author_facet | Yaw Afriyie Benjamin A. Weyori Alex A. Opoku |
author_sort | Yaw Afriyie |
collection | DOAJ |
description | Today, cancer is one of the leading causes of death in humans in the world. Cancers affect different parts of the human anatomy in different ways. There are significantly more deaths associated with gastrointestinal cancers such as colorectal cancer than with all other cancers. With computer-aided diagnosis systems, medical practitioners can recognize a variety of illnesses more quickly than with manual procedures. It is possible to reduce mortality significantly by detecting and removing precancerous lesions early. Due to the time-consuming and challenging nature of manual diagnosis, researchers have developed computational algorithms that are used to identify and classify diseases such as gastrointestinal (GI) diseases. Computer-aided diagnosis relies heavily on the classification of medical images, which is a challenging task. Therefore, this study presents a less sophisticated but still effective pre-processing technique for identifying endoscopic images known as denoising capsule networks (Dn-CapsNets). Moreover, we constructed activation maps (AM) using the feature representations to visualize the results. As a result of these evaluations, the trained model achieved 94.16%, 83.1%, 86.7%, 96.1%, 86.6%, and +0.69 respectively in terms of accuracy, precision, sensitivity, specificity, F1-score, and Matthew’s correlation. Comparisons between the proposed method and the current state-of-the-art have shown improved accuracy. |
first_indexed | 2024-03-12T18:34:51Z |
format | Article |
id | doaj.art-54650a3ae640453cad6dfd086347ca6f |
institution | Directory Open Access Journal |
issn | 2331-1916 |
language | English |
last_indexed | 2024-03-12T18:34:51Z |
publishDate | 2022-12-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | Cogent Engineering |
spelling | doaj.art-54650a3ae640453cad6dfd086347ca6f2023-08-02T08:03:54ZengTaylor & Francis GroupCogent Engineering2331-19162022-12-019110.1080/23311916.2022.2142072Gastrointestinal tract disease recognition based on denoising capsule networkYaw Afriyie0Benjamin A. Weyori1Alex A. Opoku2Department of Computer Science and Informatics, School of Sciences, University of Energy and Natural Resources, Sunyani, GhanaDepartment of Computer Science and Informatics, School of Sciences, University of Energy and Natural Resources, Sunyani, GhanaDepartment of Mathematics & Statistics, School of Sciences, University of Energy and Natural Resources, Sunyani, GhanaToday, cancer is one of the leading causes of death in humans in the world. Cancers affect different parts of the human anatomy in different ways. There are significantly more deaths associated with gastrointestinal cancers such as colorectal cancer than with all other cancers. With computer-aided diagnosis systems, medical practitioners can recognize a variety of illnesses more quickly than with manual procedures. It is possible to reduce mortality significantly by detecting and removing precancerous lesions early. Due to the time-consuming and challenging nature of manual diagnosis, researchers have developed computational algorithms that are used to identify and classify diseases such as gastrointestinal (GI) diseases. Computer-aided diagnosis relies heavily on the classification of medical images, which is a challenging task. Therefore, this study presents a less sophisticated but still effective pre-processing technique for identifying endoscopic images known as denoising capsule networks (Dn-CapsNets). Moreover, we constructed activation maps (AM) using the feature representations to visualize the results. As a result of these evaluations, the trained model achieved 94.16%, 83.1%, 86.7%, 96.1%, 86.6%, and +0.69 respectively in terms of accuracy, precision, sensitivity, specificity, F1-score, and Matthew’s correlation. Comparisons between the proposed method and the current state-of-the-art have shown improved accuracy.https://www.tandfonline.com/doi/10.1080/23311916.2022.2142072capsule networkcolorectal cancerCNNsgastrointestinal diseases |
spellingShingle | Yaw Afriyie Benjamin A. Weyori Alex A. Opoku Gastrointestinal tract disease recognition based on denoising capsule network Cogent Engineering capsule network colorectal cancer CNNs gastrointestinal diseases |
title | Gastrointestinal tract disease recognition based on denoising capsule network |
title_full | Gastrointestinal tract disease recognition based on denoising capsule network |
title_fullStr | Gastrointestinal tract disease recognition based on denoising capsule network |
title_full_unstemmed | Gastrointestinal tract disease recognition based on denoising capsule network |
title_short | Gastrointestinal tract disease recognition based on denoising capsule network |
title_sort | gastrointestinal tract disease recognition based on denoising capsule network |
topic | capsule network colorectal cancer CNNs gastrointestinal diseases |
url | https://www.tandfonline.com/doi/10.1080/23311916.2022.2142072 |
work_keys_str_mv | AT yawafriyie gastrointestinaltractdiseaserecognitionbasedondenoisingcapsulenetwork AT benjaminaweyori gastrointestinaltractdiseaserecognitionbasedondenoisingcapsulenetwork AT alexaopoku gastrointestinaltractdiseaserecognitionbasedondenoisingcapsulenetwork |