HTC-Net: Hashimoto's thyroiditis ultrasound image classification model based on residual network reinforced by channel attention mechanism

Zhipeng Liang; Kang Chen; Tianchun Luo; Wenchao Jiang; Jianxuan Wen; Ling Zhao; Wei Song

doi:10.1007/s13755-023-00225-y

HTC-Net: Hashimoto's thyroiditis ultrasound image classification model based on residual network reinforced by channel attention mechanism

Health Inf Sci Syst. 2023 May 23;11(1):24. doi: 10.1007/s13755-023-00225-y. eCollection 2023 Dec.

Authors

Zhipeng Liang¹, Kang Chen¹, Tianchun Luo¹, Wenchao Jiang¹, Jianxuan Wen², Ling Zhao², Wei Song²

Affiliations

¹ School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, 510006 China.
² Department of Endocrinology, Guangdong Provincial Hospital of Chinese Medicine, Guangzhou, 510120 China.

PMID: 37234207
PMCID: PMC10205956 (available on 2024-12-01)
DOI: 10.1007/s13755-023-00225-y

Abstract

Convolutional neural network (CNN) is efficient in extracting and aggregating local features in the spatial dimension of the images. However, obtaining the inapparent texture information of the low-echo area in the ultrasound images is not easy, and it is especially challenging for the early lesion recognition in Hashimoto's thyroiditis (HT) ultrasound images. In this paper, a HT ultrasound image classification model HTC-Net based on residual network reinforced by channel attention mechanism is proposed. HTC-Net strengthens the features of the important channels by reinforced channel attention mechanism through which the high-level semantic information is enchanced and the low-level semantic information is suppressed. Residual network assists HTC-Net focus on the key local areas of the ultrasound images while pay attention to the global semantic information. Furthermore, in order to solve the problem of uneven distribution caused by large amount of difficult-to-classify samples in the data sets, a new feature loss function TanCELoss with weight factor dynamically adjusting is constructed. TanCELoss function can better assist HTC-Net to transform difficult-to-classify samples into easy-to-classify samples gradually, and improve the balancing distribution of the samples. The experiments are implemented based on data sets collected by the Endocrinology Department of four branches from Guangdong Provincial Hospital of Chinese Medicine. Both quantitative testing and visualization results show that HTC-Net obtains STOA performance for early lesions recognition in HT ultrasound images. HTC-Net has great application value especially under the condition of owning only small data samples.

Keywords: Attention mechanism; HTC-Net; Hashimoto’s thyroiditis (HT); Residual network; Ultrasound image.

© The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.