Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review
Elastography complements traditional medical imaging modalities by mapping tissue stiffness to identify tumors in the endocrine system, and machine learning models can further improve diagnostic accuracy and reliability. Our objective in this review was to summarize the applications and performance...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/15/3/837 |
_version_ | 1797624960667090944 |
---|---|
author | Ye-Jiao Mao Li-Wen Zha Andy Yiu-Chau Tam Hyo-Jung Lim Alyssa Ka-Yan Cheung Ying-Qi Zhang Ming Ni James Chung-Wai Cheung Duo Wai-Chi Wong |
author_facet | Ye-Jiao Mao Li-Wen Zha Andy Yiu-Chau Tam Hyo-Jung Lim Alyssa Ka-Yan Cheung Ying-Qi Zhang Ming Ni James Chung-Wai Cheung Duo Wai-Chi Wong |
author_sort | Ye-Jiao Mao |
collection | DOAJ |
description | Elastography complements traditional medical imaging modalities by mapping tissue stiffness to identify tumors in the endocrine system, and machine learning models can further improve diagnostic accuracy and reliability. Our objective in this review was to summarize the applications and performance of machine-learning-based elastography on the classification of endocrine tumors. Two authors independently searched electronic databases, including PubMed, Scopus, Web of Science, IEEEXpress, CINAHL, and EMBASE. Eleven (<i>n</i> = 11) articles were eligible for the review, of which eight (<i>n</i> = 8) focused on thyroid tumors and three (<i>n</i> = 3) considered pancreatic tumors. In all thyroid studies, the researchers used shear-wave ultrasound elastography, whereas the pancreas researchers applied strain elastography with endoscopy. Traditional machine learning approaches or the deep feature extractors were used to extract the predetermined features, followed by classifiers. The applied deep learning approaches included the convolutional neural network (CNN) and multilayer perceptron (MLP). Some researchers considered the mixed or sequential training of B-mode and elastographic ultrasound data or fusing data from different image segmentation techniques in machine learning models. All reviewed methods achieved an accuracy of ≥80%, but only three were ≥90% accurate. The most accurate thyroid classification (94.70%) was achieved by applying sequential training CNN; the most accurate pancreas classification (98.26%) was achieved using a CNN–long short-term memory (LSTM) model integrating elastography with B-mode and Doppler images. |
first_indexed | 2024-03-11T09:50:04Z |
format | Article |
id | doaj.art-59a82af10aff44c28b197cedf9910d24 |
institution | Directory Open Access Journal |
issn | 2072-6694 |
language | English |
last_indexed | 2024-03-11T09:50:04Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Cancers |
spelling | doaj.art-59a82af10aff44c28b197cedf9910d242023-11-16T16:17:54ZengMDPI AGCancers2072-66942023-01-0115383710.3390/cancers15030837Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping ReviewYe-Jiao Mao0Li-Wen Zha1Andy Yiu-Chau Tam2Hyo-Jung Lim3Alyssa Ka-Yan Cheung4Ying-Qi Zhang5Ming Ni6James Chung-Wai Cheung7Duo Wai-Chi Wong8Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Bioengineering, Imperial College London, London SW7 2AZ, UKDepartment of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Electronic Engineering, Faculty of Engineering, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Orthopaedics, Tongji Hospital Affiliated to Tongji University, Shanghai 200065, ChinaDepartment of Orthopaedics, Shanghai Pudong New Area People’s Hospital, Shanghai 201299, ChinaDepartment of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaElastography complements traditional medical imaging modalities by mapping tissue stiffness to identify tumors in the endocrine system, and machine learning models can further improve diagnostic accuracy and reliability. Our objective in this review was to summarize the applications and performance of machine-learning-based elastography on the classification of endocrine tumors. Two authors independently searched electronic databases, including PubMed, Scopus, Web of Science, IEEEXpress, CINAHL, and EMBASE. Eleven (<i>n</i> = 11) articles were eligible for the review, of which eight (<i>n</i> = 8) focused on thyroid tumors and three (<i>n</i> = 3) considered pancreatic tumors. In all thyroid studies, the researchers used shear-wave ultrasound elastography, whereas the pancreas researchers applied strain elastography with endoscopy. Traditional machine learning approaches or the deep feature extractors were used to extract the predetermined features, followed by classifiers. The applied deep learning approaches included the convolutional neural network (CNN) and multilayer perceptron (MLP). Some researchers considered the mixed or sequential training of B-mode and elastographic ultrasound data or fusing data from different image segmentation techniques in machine learning models. All reviewed methods achieved an accuracy of ≥80%, but only three were ≥90% accurate. The most accurate thyroid classification (94.70%) was achieved by applying sequential training CNN; the most accurate pancreas classification (98.26%) was achieved using a CNN–long short-term memory (LSTM) model integrating elastography with B-mode and Doppler images.https://www.mdpi.com/2072-6694/15/3/837neoplasianeoplasmcancerneuroendocrine tumorcomputer-aided diagnosisdeep learning |
spellingShingle | Ye-Jiao Mao Li-Wen Zha Andy Yiu-Chau Tam Hyo-Jung Lim Alyssa Ka-Yan Cheung Ying-Qi Zhang Ming Ni James Chung-Wai Cheung Duo Wai-Chi Wong Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review Cancers neoplasia neoplasm cancer neuroendocrine tumor computer-aided diagnosis deep learning |
title | Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review |
title_full | Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review |
title_fullStr | Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review |
title_full_unstemmed | Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review |
title_short | Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review |
title_sort | endocrine tumor classification via machine learning based elastography a systematic scoping review |
topic | neoplasia neoplasm cancer neuroendocrine tumor computer-aided diagnosis deep learning |
url | https://www.mdpi.com/2072-6694/15/3/837 |
work_keys_str_mv | AT yejiaomao endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT liwenzha endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT andyyiuchautam endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT hyojunglim endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT alyssakayancheung endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT yingqizhang endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT mingni endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT jameschungwaicheung endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview AT duowaichiwong endocrinetumorclassificationviamachinelearningbasedelastographyasystematicscopingreview |