Classification and Diagnosis of Residual Thyroid Tissue in SPECT Images Based on Fine-Tuning Deep Convolutional Neural Network

Yinxiang Guo; Jianing Xu; Xiangzhi Li; Lin Zheng; Wei Pan; Meiting Qiu; Shuyi Mao; Dongfei Huang; Xiaobo Yang

doi:10.3389/fonc.2021.762643

Classification and Diagnosis of Residual Thyroid Tissue in SPECT Images Based on Fine-Tuning Deep Convolutional Neural Network

Front Oncol. 2021 Oct 28:11:762643. doi: 10.3389/fonc.2021.762643. eCollection 2021.

Authors

Yinxiang Guo^{1

2

3}, Jianing Xu^{1

4}, Xiangzhi Li^{1

3}, Lin Zheng^{1

2

3}, Wei Pan⁵, Meiting Qiu¹, Shuyi Mao⁵, Dongfei Huang⁵, Xiaobo Yang^{1

3}

Affiliations

¹ Guangxi Key Laboratory on Precise Prevention and Treatment for Thyroid Tumor, The Second Affiliated Hospital, Guangxi University of Science and Technology, Liuzhou, China.
² School of Science, Guangxi University of Science and Technology, Liuzhou, China.
³ Department of Public Health, School of Medicine, Guangxi University of Science and Technology, Liuzhou, China.
⁴ School of Microelectronics and Materials Engineering, Guangxi University of Science and Technology, Liuzhou, China.
⁵ Department of Nuclear Medicine, The Second Affiliated Hospital of Guangxi University of Science and Technology, Liuzhou, China.

Abstract

Patients with thyroid cancer will take a small dose of ¹³¹I after undergoing a total thyroidectomy. Single-photon emission computed tomography (SPECT) is used to diagnose whether thyroid tissue remains in the body. However, it is difficult for human eyes to observe the specificity of SPECT images in different categories, and it is difficult for doctors to accurately diagnose the residual thyroid tissue in patients based on SPECT images. At present, the research on the classification of thyroid tissue residues after thyroidectomy is still in a blank state. This paper proposes a ResNet-18 fine-tuning method based on the convolutional neural network model. First, preprocess the SPECT images to improve the image quality and remove background interference. Secondly, use the preprocessed image samples to fine-tune the pretrained ResNet-18 model to obtain better features and finally use the Softmax classifier to diagnose the residual thyroid tissue. The method has been tested on SPECT images of 446 patients collected by local hospital and compared with the widely used lightweight network SqueezeNet model and ShuffleNetV2 model. Due to the small data set, this paper conducted 10 random grouping experiments. Each experiment divided the data set into training set and test set at a ratio of 3:1. The accuracy and sensitivity rates of the model proposed in this paper are 96.69% and 94.75%, which are significantly higher than other models (p < 0.05). The specificity and precision rates are 99.6% and 99.96%, respectively, and there is no significant difference compared with other models. (p > 0.05). The area under the curve of the proposed model, SqueezeNet, and ShuffleNetv2 are 0.988 (95% CI, 0.941-1.000), 0.898 (95% CI, 0.819-0.951) (p = 0.0257), and 0.885 (95% CI, 0.803-0.941) (p = 0.0057) (p < 0.05). We prove that this thyroid tissue residue classification system can be used as a computer-aided diagnosis method to effectively improve the diagnostic accuracy of thyroid tissue residues. While more accurately diagnosing patients with residual thyroid tissue in the body, we try our best to avoid the occurrence of overtreatment, which reflects its potential clinical application value.

Keywords: SPECT image; classification diagnosis; deep learning; fine-tuning; overtreatment; thyroid cancer.