Identification of benign and malignant nodules in thyroid ultrasound images based on deep convolutional neural network
10.19405/j.cnki.issn1000-1492.2023.05.025
- Author:
Wenjun Yao
1
,
2
;
Chaoran Yin
3
,
4
;
Hongqing Zhu
1
;
Jianmin Jiang
5
;
Xiaoxi Pang
6
;
Yining Sun
2
Author Information
1. Dept ofRadiology,The Second Afiliated Hospital of Anhui Medical University,Hefei 230601
2. Intelligent Mechanization Institute ,Hefei Institute ofPhysical Matter, Chinese Academy of Sciences ,Hefei 230031
3. Dept of Ultrasonography,Anhui No. 2 Provincial People &prime
4. s Hospital ,Hefei 230011
5. School of Electronic and Information Engineering ,Anhui University,Hefei 230601
6. Dept of Nuclear Medicine , The Second Afiliated Hospital of Anhui Medical University,Hefei 230601
- Publication Type:Journal Article
- Keywords:
thyroid nodule;
ultrasound image;
deep convolutional neural networks;
YOLOv5 network
- From:
Acta Universitatis Medicinalis Anhui
2023;58(5):854-858
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To explore the clinical application value of deep convoluti onal neural network for automatic detection and classification of benign and malignant thyroid nodules ultrasound images.
Methods:A total of 1 012 ultrasound images of thyroid nodules were retrospectively selected and labeled. The YOLOv5 network model was constructed to accurately locate the location of thyroid nodules and automatically trim the area of the nodules. At the same time , a GoogLeNet network model was constructed to classify benign and malignant nodules after reduction.
Results :In the collected data set , the mean accuracy of the target detection network for thyroid nodule location detection was 96. 2% . Meanwhile , the sensitivity, specificity, accuracy and AUC of the classification network for benign and malignant nodules were 0. 885 ,0. 822 ,0. 866 and 0. 92 respectively ,which were significantly higher than those of the AlexNet model (0. 81) , VGG model (0. 86) and MobileNet model (0. 76) .
Conclusion :The deep convo⁃ lutional neural network model has high localization and recognition ability for benign and malignant thyroid nodules in ultrasound images ,which is helpful to improve the accuracy of automatic image diagnosis.
- Full text:2024081321594496472基于深度卷积神经网络的甲状...图像良恶性结节识别方法研究_姚文君.pdf
