HT-RCM: Hashimoto's Thyroiditis Ultrasound Image Classification Model Based on Res-FCT and Res-CAM
- 10 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (2) , 941-951
Abstract
The early lesions of Hashimoto's thyroiditis are inconspicuous, and the ultrasonic features of these early lesions are indistinguishable from other thyroid diseases. This paper proposes a Hashimoto Thyroiditis ultrasound image classification model HT-RCM which consists of a Residual Full Convolution Transformer (Res-FCT) model and a Residual Channel Attention Module (Res-CAM). To collect the low-order information caused by hypoechoic signals accurately, the residual connection is injected between FCTs to form Res-FCT which helps HT-RCM superimpose the low-order input information and high-order output information together. Res-FCT can make HT-RCM focus more on hypoechoic information while avoiding gradient dispersion. The initial feature map is inserted into Res-FCT again through a down-sampling component, which further helps HT-RCM exact multi-level original semantic information in the ultrasound image. Res-CAM is constructed by implementing a residual connection between a channel attention module and a convolution layer. Res-CAM can effectively increase the weights of the lesion channels while suppressing the weights of the noise channels, which makes HT-RCM focus more on the lesion regions. The experimental results on our collected dataset show that HT-RCM outperforms the mainstream models and obtains state-of-the-art performance in HT ultrasound image classification.Keywords
Funding Information
- National Natural Scence Foundation of China (62072202)
- Guangdong Natural Science Fund Project (2021A1515011243)
- EU H2020 CLARIFY (860627, H2020-MSCA-ITN-2019)
- National Natural Science Foundation of China (62371305, 62001302)
- Basic and Applied Basic Research Foundation of Guangdong Province (2021A1515011348)
This publication has 41 references indexed in Scilit:
- Discordance of serological and sonographic markers for Hashimoto’s thyroiditis with gold standard histopathologyEuropean Journal of Endocrinology, 2019
- Auto-Selecting Receptive Field Network for Visual TrackingIEEE Access, 2019
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic studyThe Lancet Oncology, 2019
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- Stage Classification in Chronic Kidney Disease by Ultrasound Image2014
- Computer‐Aided Diagnostic System for Detection of Hashimoto Thyroiditis on Ultrasound Images From a Polish PopulationJournal of Ultrasound in Medicine, 2014
- Diagnosis of Hashimoto’s thyroiditis in ultrasound using tissue characterization and pixel classificationProceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 2013
- Hashimoto Thyroiditis: Part 1, Sonographic Analysis of the Nodular Form of Hashimoto ThyroiditisAmerican Journal of Roentgenology, 2010