Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches

Abstract Traditional computer-aided diagnosis (CAD) processes include feature extraction, selection, and classification. Effective feature extraction in CAD is important in improving the classification’s performance. We introduce a machine-learning method and have designed an analysis procedure of b...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wei-Chung Shia, Li-Sheng Lin, Dar-Ren Chen
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/9881c42d79134a44b9eab012e9d49625
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9881c42d79134a44b9eab012e9d49625
record_format dspace
spelling oai:doaj.org-article:9881c42d79134a44b9eab012e9d496252021-12-02T14:01:38ZClassification of malignant tumours in breast ultrasound using unsupervised machine learning approaches10.1038/s41598-021-81008-x2045-2322https://doaj.org/article/9881c42d79134a44b9eab012e9d496252021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81008-xhttps://doaj.org/toc/2045-2322Abstract Traditional computer-aided diagnosis (CAD) processes include feature extraction, selection, and classification. Effective feature extraction in CAD is important in improving the classification’s performance. We introduce a machine-learning method and have designed an analysis procedure of benign and malignant breast tumour classification in ultrasound (US) images without a need for a priori tumour region-selection processing, thereby decreasing clinical diagnosis efforts while maintaining high classification performance. Our dataset constituted 677 US images (benign: 312, malignant: 365). Regarding two-dimensional US images, the oriented gradient descriptors’ histogram pyramid was extracted and utilised to obtain feature vectors. The correlation-based feature selection method was used to evaluate and select significant feature sets for further classification. Sequential minimal optimisation—combining local weight learning—was utilised for classification and performance enhancement. The image dataset’s classification performance showed an 81.64% sensitivity and 87.76% specificity for malignant images (area under the curve = 0.847). The positive and negative predictive values were 84.1 and 85.8%, respectively. Here, a new workflow, utilising machine learning to recognise malignant US images was proposed. Comparison of physician diagnoses and the automatic classifications made using machine learning yielded similar outcomes. This indicates the potential applicability of machine learning in clinical diagnoses.Wei-Chung ShiaLi-Sheng LinDar-Ren ChenNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Wei-Chung Shia
Li-Sheng Lin
Dar-Ren Chen
Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches
description Abstract Traditional computer-aided diagnosis (CAD) processes include feature extraction, selection, and classification. Effective feature extraction in CAD is important in improving the classification’s performance. We introduce a machine-learning method and have designed an analysis procedure of benign and malignant breast tumour classification in ultrasound (US) images without a need for a priori tumour region-selection processing, thereby decreasing clinical diagnosis efforts while maintaining high classification performance. Our dataset constituted 677 US images (benign: 312, malignant: 365). Regarding two-dimensional US images, the oriented gradient descriptors’ histogram pyramid was extracted and utilised to obtain feature vectors. The correlation-based feature selection method was used to evaluate and select significant feature sets for further classification. Sequential minimal optimisation—combining local weight learning—was utilised for classification and performance enhancement. The image dataset’s classification performance showed an 81.64% sensitivity and 87.76% specificity for malignant images (area under the curve = 0.847). The positive and negative predictive values were 84.1 and 85.8%, respectively. Here, a new workflow, utilising machine learning to recognise malignant US images was proposed. Comparison of physician diagnoses and the automatic classifications made using machine learning yielded similar outcomes. This indicates the potential applicability of machine learning in clinical diagnoses.
format article
author Wei-Chung Shia
Li-Sheng Lin
Dar-Ren Chen
author_facet Wei-Chung Shia
Li-Sheng Lin
Dar-Ren Chen
author_sort Wei-Chung Shia
title Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches
title_short Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches
title_full Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches
title_fullStr Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches
title_full_unstemmed Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches
title_sort classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/9881c42d79134a44b9eab012e9d49625
work_keys_str_mv AT weichungshia classificationofmalignanttumoursinbreastultrasoundusingunsupervisedmachinelearningapproaches
AT lishenglin classificationofmalignanttumoursinbreastultrasoundusingunsupervisedmachinelearningapproaches
AT darrenchen classificationofmalignanttumoursinbreastultrasoundusingunsupervisedmachinelearningapproaches
_version_ 1718392096925155328