Cover Image

An adaptive feature extraction model for classification of thyroid lesions in ultrasound images

The thyroid is the chief hormonal gland that controls the growth, metabolism, and maturation of the body. However, the function of the thyroid gland could be disrupted if it produces too much or too little hormones. Furthermore, there could be abnormal growth in thyroid cell tissue, leading to the f...

Full description

Saved in:
Bibliographic Details
Main Authors: Mugasa, Hatwib, Dua, Sumeet, Koh, Joel E. W., Hagiwara, Yuki, Lih, Oh Shu, Madla, Chakri, Kongmebhol, Pailin, Ng, Kwan Hoong, Acharya, U. Rajendra
Format: Article
Published: Elsevier 2020
Subjects:
QA75 Electronic computers. Computer science
R Medicine
Online Access:http://eprints.um.edu.my/36856/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.36856
record_format eprints
spelling my.um.eprints.368562023-10-05T04:13:41Z http://eprints.um.edu.my/36856/ An adaptive feature extraction model for classification of thyroid lesions in ultrasound images Mugasa, Hatwib Dua, Sumeet Koh, Joel E. W. Hagiwara, Yuki Lih, Oh Shu Madla, Chakri Kongmebhol, Pailin Ng, Kwan Hoong Acharya, U. Rajendra QA75 Electronic computers. Computer science R Medicine The thyroid is the chief hormonal gland that controls the growth, metabolism, and maturation of the body. However, the function of the thyroid gland could be disrupted if it produces too much or too little hormones. Furthermore, there could be abnormal growth in thyroid cell tissue, leading to the formation of a benign or malignant thyroid lesion. Ultrasound is a typical non-invasive diagnosis approach to check for cancerous thyroid lesions. However, the visual interpretation of the ultrasound thyroid images is challenging and time-consuming. Hence, a feature engineering model is proposed to overcome these challenges. We propose to transform image pixel intensity values into high dimensional structured data set before fitting a Regression analysis framework to estimate kernel parameters for an image filter model. We then adopt a Bayesian network inference to estimate a subset for the textural features with a significant conditional dependency in the classification of thyroid lesions. The analysis of the proposed feature engineering model showed that the classification performance had an overall significant improvement over other image filter models. We achieve 96.00% classification accuracy with a sensitivity and specificity of 99.64% and 90.23% respectively for a filter size of 13 x 13. The analysis of results indicate that the diagnosis of ultrasound images thyroid nodules is significantly boosts by adaptively learning filter parameters for feature engineering model. (C) 2020 Elsevier B.V. All rights reserved. Elsevier 2020-03 Article PeerReviewed Mugasa, Hatwib and Dua, Sumeet and Koh, Joel E. W. and Hagiwara, Yuki and Lih, Oh Shu and Madla, Chakri and Kongmebhol, Pailin and Ng, Kwan Hoong and Acharya, U. Rajendra (2020) An adaptive feature extraction model for classification of thyroid lesions in ultrasound images. Pattern Recognition Letters, 131. pp. 463-473. ISSN 0167-8655, DOI https://doi.org/10.1016/j.patrec.2020.02.009 <https://doi.org/10.1016/j.patrec.2020.02.009>. 10.1016/j.patrec.2020.02.009
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic QA75 Electronic computers. Computer science
R Medicine
spellingShingle QA75 Electronic computers. Computer science
R Medicine
Mugasa, Hatwib
Dua, Sumeet
Koh, Joel E. W.
Hagiwara, Yuki
Lih, Oh Shu
Madla, Chakri
Kongmebhol, Pailin
Ng, Kwan Hoong
Acharya, U. Rajendra
An adaptive feature extraction model for classification of thyroid lesions in ultrasound images
description The thyroid is the chief hormonal gland that controls the growth, metabolism, and maturation of the body. However, the function of the thyroid gland could be disrupted if it produces too much or too little hormones. Furthermore, there could be abnormal growth in thyroid cell tissue, leading to the formation of a benign or malignant thyroid lesion. Ultrasound is a typical non-invasive diagnosis approach to check for cancerous thyroid lesions. However, the visual interpretation of the ultrasound thyroid images is challenging and time-consuming. Hence, a feature engineering model is proposed to overcome these challenges. We propose to transform image pixel intensity values into high dimensional structured data set before fitting a Regression analysis framework to estimate kernel parameters for an image filter model. We then adopt a Bayesian network inference to estimate a subset for the textural features with a significant conditional dependency in the classification of thyroid lesions. The analysis of the proposed feature engineering model showed that the classification performance had an overall significant improvement over other image filter models. We achieve 96.00% classification accuracy with a sensitivity and specificity of 99.64% and 90.23% respectively for a filter size of 13 x 13. The analysis of results indicate that the diagnosis of ultrasound images thyroid nodules is significantly boosts by adaptively learning filter parameters for feature engineering model. (C) 2020 Elsevier B.V. All rights reserved.
format Article
author Mugasa, Hatwib
Dua, Sumeet
Koh, Joel E. W.
Hagiwara, Yuki
Lih, Oh Shu
Madla, Chakri
Kongmebhol, Pailin
Ng, Kwan Hoong
Acharya, U. Rajendra
author_facet Mugasa, Hatwib
Dua, Sumeet
Koh, Joel E. W.
Hagiwara, Yuki
Lih, Oh Shu
Madla, Chakri
Kongmebhol, Pailin
Ng, Kwan Hoong
Acharya, U. Rajendra
author_sort Mugasa, Hatwib
title An adaptive feature extraction model for classification of thyroid lesions in ultrasound images
title_short An adaptive feature extraction model for classification of thyroid lesions in ultrasound images
title_full An adaptive feature extraction model for classification of thyroid lesions in ultrasound images
title_fullStr An adaptive feature extraction model for classification of thyroid lesions in ultrasound images
title_full_unstemmed An adaptive feature extraction model for classification of thyroid lesions in ultrasound images
title_sort adaptive feature extraction model for classification of thyroid lesions in ultrasound images
publisher Elsevier
publishDate 2020
url http://eprints.um.edu.my/36856/
_version_ 1781704505201524736
score 13.211869

Similar Items