Cargando…
Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning
A thyroid nodule, which is defined as abnormal growth of thyroid cells, indicates excessive iodine intake, thyroid degeneration, inflammation, and other diseases. Although thyroid nodules are always non-malignant, the malignancy likelihood of a thyroid nodule grows steadily every year. In order to r...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9335944/ https://www.ncbi.nlm.nih.gov/pubmed/35912199 http://dx.doi.org/10.3389/fonc.2022.905955 |
_version_ | 1784759441814454272 |
---|---|
author | Yang, Jingya Shi, Xiaoli Wang, Bing Qiu, Wenjing Tian, Geng Wang, Xudong Wang, Peizhen Yang, Jiasheng |
author_facet | Yang, Jingya Shi, Xiaoli Wang, Bing Qiu, Wenjing Tian, Geng Wang, Xudong Wang, Peizhen Yang, Jiasheng |
author_sort | Yang, Jingya |
collection | PubMed |
description | A thyroid nodule, which is defined as abnormal growth of thyroid cells, indicates excessive iodine intake, thyroid degeneration, inflammation, and other diseases. Although thyroid nodules are always non-malignant, the malignancy likelihood of a thyroid nodule grows steadily every year. In order to reduce the burden on doctors and avoid unnecessary fine needle aspiration (FNA) and surgical resection, various studies have been done to diagnose thyroid nodules through deep-learning-based image recognition analysis. In this study, to predict the benign and malignant thyroid nodules accurately, a novel deep learning framework is proposed. Five hundred eight ultrasound images were collected from the Third Hospital of Hebei Medical University in China for model training and validation. First, a ResNet18 model, pretrained on ImageNet, was trained by an ultrasound image dataset, and a random sampling of training dataset was applied 10 times to avoid accidental errors. The results show that our model has a good performance, the average area under curve (AUC) of 10 times is 0.997, the average accuracy is 0.984, the average recall is 0.978, the average precision is 0.939, and the average F1 score is 0.957. Second, Gradient-weighted Class Activation Mapping (Grad-CAM) was proposed to highlight sensitive regions in an ultrasound image during the learning process. Grad-CAM is able to extract the sensitive regions and analyze their shape features. Based on the results, there are obvious differences between benign and malignant thyroid nodules; therefore, shape features of the sensitive regions are helpful in diagnosis to a great extent. Overall, the proposed model demonstrated the feasibility of employing deep learning and ultrasound images to estimate benign and malignant thyroid nodules. |
format | Online Article Text |
id | pubmed-9335944 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-93359442022-07-30 Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning Yang, Jingya Shi, Xiaoli Wang, Bing Qiu, Wenjing Tian, Geng Wang, Xudong Wang, Peizhen Yang, Jiasheng Front Oncol Oncology A thyroid nodule, which is defined as abnormal growth of thyroid cells, indicates excessive iodine intake, thyroid degeneration, inflammation, and other diseases. Although thyroid nodules are always non-malignant, the malignancy likelihood of a thyroid nodule grows steadily every year. In order to reduce the burden on doctors and avoid unnecessary fine needle aspiration (FNA) and surgical resection, various studies have been done to diagnose thyroid nodules through deep-learning-based image recognition analysis. In this study, to predict the benign and malignant thyroid nodules accurately, a novel deep learning framework is proposed. Five hundred eight ultrasound images were collected from the Third Hospital of Hebei Medical University in China for model training and validation. First, a ResNet18 model, pretrained on ImageNet, was trained by an ultrasound image dataset, and a random sampling of training dataset was applied 10 times to avoid accidental errors. The results show that our model has a good performance, the average area under curve (AUC) of 10 times is 0.997, the average accuracy is 0.984, the average recall is 0.978, the average precision is 0.939, and the average F1 score is 0.957. Second, Gradient-weighted Class Activation Mapping (Grad-CAM) was proposed to highlight sensitive regions in an ultrasound image during the learning process. Grad-CAM is able to extract the sensitive regions and analyze their shape features. Based on the results, there are obvious differences between benign and malignant thyroid nodules; therefore, shape features of the sensitive regions are helpful in diagnosis to a great extent. Overall, the proposed model demonstrated the feasibility of employing deep learning and ultrasound images to estimate benign and malignant thyroid nodules. Frontiers Media S.A. 2022-07-15 /pmc/articles/PMC9335944/ /pubmed/35912199 http://dx.doi.org/10.3389/fonc.2022.905955 Text en Copyright © 2022 Yang, Shi, Wang, Qiu, Tian, Wang, Wang and Yang https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Oncology Yang, Jingya Shi, Xiaoli Wang, Bing Qiu, Wenjing Tian, Geng Wang, Xudong Wang, Peizhen Yang, Jiasheng Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning |
title | Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning |
title_full | Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning |
title_fullStr | Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning |
title_full_unstemmed | Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning |
title_short | Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning |
title_sort | ultrasound image classification of thyroid nodules based on deep learning |
topic | Oncology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9335944/ https://www.ncbi.nlm.nih.gov/pubmed/35912199 http://dx.doi.org/10.3389/fonc.2022.905955 |
work_keys_str_mv | AT yangjingya ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning AT shixiaoli ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning AT wangbing ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning AT qiuwenjing ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning AT tiangeng ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning AT wangxudong ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning AT wangpeizhen ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning AT yangjiasheng ultrasoundimageclassificationofthyroidnodulesbasedondeeplearning |