Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Aug;30(4):477-486.
doi: 10.1007/s10278-017-9997-y.

Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network

Jianning Chi  1 , Ekta Walia  2 , Paul Babyn  3 , Jimmy Wang  3 , Gary Groot  4 , Mark Eramian  2
Affiliations

Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network

Jianning Chi et al. J Digit Imaging. 2017 Aug.

Abstract

With many thyroid nodules being incidentally detected, it is important to identify as many malignant nodules as possible while excluding those that are highly likely to be benign from fine needle aspiration (FNA) biopsies or surgeries. This paper presents a computer-aided diagnosis (CAD) system for classifying thyroid nodules in ultrasound images. We use deep learning approach to extract features from thyroid ultrasound images. Ultrasound images are pre-processed to calibrate their scale and remove the artifacts. A pre-trained GoogLeNet model is then fine-tuned using the pre-processed image samples which leads to superior feature extraction. The extracted features of the thyroid ultrasound images are sent to a Cost-sensitive Random Forest classifier to classify the images into "malignant" and "benign" cases. The experimental results show the proposed fine-tuned GoogLeNet model achieves excellent classification performance, attaining 98.29% classification accuracy, 99.10% sensitivity and 93.90% specificity for the images in an open access database (Pedraza et al. 16), while 96.34% classification accuracy, 86% sensitivity and 99% specificity for the images in our local health region database.

Keywords: Computer vision; Convolutional neural network; Deep learning; Fine-tuning; Machine learning; Thyroid nodules; Ultrasonography.

PubMed Disclaimer

Conflict of interest statement

Funding

This research was funded through a Collaborative Innovation Development Grant from the Saskatchewan Health Research Foundation.

Figures

Fig. 1
Fig. 1
Example of artifacts made by radiologist on the thyroid ultrasound image. a Ultrasound image with artifacts covering the textures. b Details of how the artifact covers the ultrasound textures in the image, bounded by the red rectangle in a
Fig. 2
Fig. 2
The process of the thyroid images classification based on fine-tuned GoogLeNet network
Fig. 3
Fig. 3
Detection of pixels deemed to be ticks by intensity thresholding. a Input thyroid ultrasound image. b Thirty percent right region of the input image where the thresholding was applied. c Binary image showing the pixels deemed likely to be ticks, and red line in d represents the column containing the tick bar
Fig. 4
Fig. 4
Example of removing artifacts from the thyroid image. a Original thyroid image with artifacts on the textures. b Thyroid image after removing the artifacts by the thresholding method. c Thyroid image after restoring the artifact-removed regions with textures similar to neighbourhood
Fig. 5
Fig. 5
The process of fine-tuning GoogLeNet. The new sample images from the target domain are sent to the pre-trained GoogLeNet, changed the three classification layers and run the GoogLeNet, and then the parameters of the network are fine-tuned automatically
Fig. 6
Fig. 6
The ROC curves of classifying image samples from database 1
Fig. 7
Fig. 7
The ROC curves of classifying image samples from database 2
See this image and copyright information in PMC

References

    1. Diana Gaitini, Rhodri M Evans, and Gordana Ivanac, Chapter 16: thyroid ultrasound. EFSUMB Course Book, 2011.
    1. Kwak JY, Han KH, Yoon JH, Moon HJ, Son EJ, Park SH, Jung HK, Choi JS, Kim BM, Kim E-K. Thyroid imaging reporting and data system for us features of nodules: a step in establishing better stratification of cancer risk. Radiology. 2011;260(3):892–899. doi: 10.1148/radiol.11110206. - DOI - PubMed
    1. Lingam RK, Qarib MH, Tolley NS. Evaluating thyroid nodules: predicting and selecting malignant nodules for fine-needle aspiration (fna) cytology. Insights Imaging. 2013;4(5):617–624. doi: 10.1007/s13244-013-0256-6. - DOI - PMC - PubMed
    1. Chen S-J, Chang C-Y, Chang K-Y, Tzeng J-E, Chen Y-T, Lin C-W, Hsu W-C, Wei C-K. Classification of the thyroid nodules based on characteristic sonographic textural feature and correlated histopathology using hierarchical support vector machines. Ultrasound Med Biol. 2010;36(12):2018–2026. doi: 10.1016/j.ultrasmedbio.2010.08.019. - DOI - PubMed
    1. Chang C-Y, Liu H-Y, Tseng C-H, Shih S-R. Computer-aided diagnosis for thyroid Graves’ disease in ultrasound images. Biomed Eng: Appl Basis Commun. 2010;22(02):91–99.

MeSH terms