Login Register Cart 0
Generic placeholder image

Current Bioinformatics

Editor-in-Chief

ISSN (Print): 1574-8936
ISSN (Online): 2212-392X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

A Machine Learning-based Diagnosis of Thyroid Cancer Using Thyroid Nodules Ultrasound Images

Author(s): Xuesi Ma, Baohang Xi, Yi Zhang, Lijuan Zhu, Xin Sui*, Geng Tian and Jialiang Yang*

Volume 15, Issue 4, 2020

Page: [349 - 358] Pages: 10

DOI: 10.2174/1574893614666191017091959

Price: $65

Abstract

Background: Ultrasound test is one of the routine tests for the diagnosis of thyroid cancer. The diagnosis accuracy depends largely on the correct interpretation of ultrasound images of thyroid nodules. However, human eye-based image recognition is usually subjective and sometimes error-prone especially for less experienced doctors, which presents a need for computeraided diagnostic systems.

Objective: To our best knowledge, there is no well-maintained ultrasound image database for the Chinese population. In addition, though there are several computational methods for image-based thyroid cancer detection, a comparison among them is missing. Finally, the effects of features like the choice of distance measures have not been assessed. The study aims to give the improvement of these limitations and proposes a highly accurate image-based thyroid cancer diagnosis system, which can better assist doctors in the diagnosis of thyroid cancer.

Methods: We first establish a novel thyroid nodule ultrasound image database consisting of 508 images collected from the Third Hospital of Hebei Medical University in China. The clinical information for the patients is also collected from the hospital, where 415 patients are diagnosed to be benign and 93 are malignant by doctors following a standard diagnosis procedure. We develop and apply five machine learning methods to the dataset including deep neural network, support vector machine, the center clustering method, k-nearest neighbor, and logistic regression.

Results: Experimental results show that deep neural network outperforms other diagnosis methods with an average cross-validation accuracy of 0.87 in 10 runs. Meanwhile, we also explore the performance of four image distance measures including the Euclidean distance, the Manhattan distance, the Chebyshev distance, and the Minkowski distance, among which the Chebyshev distance is the best. The resource can be directly used to aid doctors in thyroid cancer diagnosis and treatment.

Conclusions: The paper establishes a novel thyroid nodule ultrasound image database and develops a high accurate image-based thyroid cancer diagnosis system which can better assist doctors in the diagnosis of thyroid cancer.

Keywords: Machine learning, thyroid, ultrasound images, support vector machines, centre clustering, k-nearest neighbours, logistic regression, deep neural networks.

« Previous Next »
Graphical Abstract

[1]
Horvath E, Majlis S, Rossi R, et al. An ultrasonogram reporting system for thyroid nodules stratifying cancer risk for clinical management. J Clin Endocrinol Metab 2009; 94(5): 1748-51.
[http://dx.doi.org/10.1210/jc.2008-1724] [PMID: 19276237]
[2]
Welker MJ, Orlov D. Thyroid nodules. Am Fam Physician 2003; 67(3): 559-66.
[PMID: 12588078]
[3]
Blanco Carrera C, García-Díaz JD, Maqueda Villaizán E, Martínez-Onsurbe P, Peláez Torres N, Saavedra Vallejo P. [Diagnostic efficacy of fine needle aspiration biopsy in patients with thyroid nodular disease. Analysis of 510 cases]. Rev Clin Esp 2005; 205(8): 374-8.
[http://dx.doi.org/10.1157/13078248] [PMID: 16143084]
[4]
Koundal DGS, Singh S. Computer-aided diagnosis of thyroid nodule: a review. Int J Comput Sci Eng Survey 2012; 3(4): 67-83.
[http://dx.doi.org/10.5121/ijcses.2012.3406]
[5]
Newbury S, Godhardt-Cooper J, Poulsen KP, Cigel F, Balanoff L, Toohey-Kurth K. Prolonged intermittent virus shedding during an outbreak of canine influenza A H3N2 virus infection in dogs in three Chicago area shelters: 16 cases (March to May 2015). J Am Vet Med Assoc 2016; 248(9): 1022-6.
[http://dx.doi.org/10.2460/javma.248.9.1022] [PMID: 27074610]
[6]
Hirning T, Zuna I, Schlaps D, et al. Quantification and classification of echographic findings in the thyroid gland by computerized B-mode texture analysis. Eur J Radiol 1989; 9(4): 244-7.
[PMID: 2686993]
[7]
Mailloux G, Bertrand M, Stampfler R, Ethier S. Computer analysis of echographic textures in Hashimoto disease of the thyroid. J Clin Ultrasound 1986; 14(7): 521-7.
[http://dx.doi.org/10.1002/jcu.1870140705] [PMID: 3095379]
[8]
Savelonas MA, Iakovidis DK, Dimitropoulos N, Maroulis D. Computational characterization of thyroid tissue in the radon domain. Proc IEEE Int Symp Comp Bas Med Syst 189-92.
[http://dx.doi.org/10.1109/CBMS.2007.33]
[9]
Tsantis S, Cavouras D, Kalatzis I, Piliouras N, Dimitropoulos N, Nikiforidis G. Development of a support vector machine-based image analysis system for assessing the thyroid nodule malignancy risk on ultrasound. Ultrasound Med Biol 2005; 31(11): 1451-9.
[http://dx.doi.org/10.1016/j.ultrasmedbio.2005.07.009] [PMID: 16286024]
[10]
Al-Hilli Z, Strajina V, McKenzie TJ, Thompson GB, Farley DR, Richards ML. The role of lateral neck ultrasound in detecting single or multiple lymph nodes in papillary thyroid cancer. Am J Surg 2016; 212(6): 1147-53.
[http://dx.doi.org/10.1016/j.amjsurg.2016.09.014] [PMID: 27771031]
[11]
Chi J, Walia E, Babyn P, Wang J, Groot G, Eramian M. Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network. J Digit Imaging 2017; 30(4): 477-86.
[http://dx.doi.org/10.1007/s10278-017-9997-y] [PMID: 28695342]
[12]
Liu TJ, et al. Classification of Thyroid Nodules in Ultrasound Images Using Deep Model Based Transfer Learning and Hybrid Features. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (Icassp) USA 2017; 919-23.
[http://dx.doi.org/10.1109/ICASSP.2017.7952290]
[13]
Yu Q, Jiang T, Zhou A, Zhang L, Zhang C, Xu P. Computer-aided diagnosis of malignant or benign thyroid nodes based on ultrasound images. Eur Arch Otorhinolaryngol 2017; 274(7): 2891-7.
[http://dx.doi.org/10.1007/s00405-017-4562-3] [PMID: 28389809]
[14]
Lim KJ, Choi CS, Yoon DY, et al. Computer-aided diagnosis for the differentiation of malignant from benign thyroid nodules on ultrasonography. Acad Radiol 2008; 15(7): 853-8.
[http://dx.doi.org/10.1016/j.acra.2007.12.022] [PMID: 18572120]
[15]
Tsantis S, Dimitropoulos N, Cavouras D, Nikiforidis G. Morphological and wavelet features towards sonographic thyroid nodules evaluation. Comput Med Imaging Graph 2009; 33(2): 91-9.
[http://dx.doi.org/10.1016/j.compmedimag.2008.10.010] [PMID: 19111442]
[16]
Sangriotis M, Savelonas M, Maroulis D. A computer-aided system for malignancy risk assessment of nodules in thyroid US images based on boundary features. Comput Method Program Biomedicine 2009; 96: 25-32.
[17]
Gopinath B, Gupta B. Classification of thyroid carcinoma in fnab cytological microscopic images. Int J Healthc Inf Syst Inform 2010; 5(2): 60-72.
[http://dx.doi.org/10.4018/jhisi.2010040107]
[18]
Wang W, Ozolek JA, Rohde GK. Detection and classification of thyroid follicular lesions based on nuclear structure from histopathology images. Cytometry A 2010; 77(5): 485-94.
[http://dx.doi.org/10.1002/cyto.a.20853] [PMID: 20099247]
[19]
Chang CY, Chen SJ, Tsai MF. Application of support-vector-machine-based method for feature selection and classification of thyroid nodules in ultrasound images. Pattern Recognit 2010; 43: 3494-506.
[http://dx.doi.org/10.1016/j.patcog.2010.04.023]
[20]
Zhao RN, Zhang B, Yang X, Jiang YX, Lai XJ, Zhang XY. Logistic regression analysis of contrast-enhanced ultrasound and conventional ultrasound characteristics of sub-centimeter thyroid nodules. Ultrasound Med Biol 2015; 41(12): 3102-8.
[http://dx.doi.org/10.1016/j.ultrasmedbio.2015.04.026] [PMID: 26423183]
[21]
Ahmad W. A novel hybrid decision support system for thyroid disease forecasting soft computing 2018; 22: 5377-83.
[22]
Chandel K, Kunwar V, Sabitha S, Choudhury T, Mukherjee S. A comparative study on thyroid disease detection using k-nearest neighbor and naive bayes classification techniques. Csi Transactions on Ict 2016; 4: 313-9.
[http://dx.doi.org/10.1007/s40012-016-0100-5]
[23]
Shankar K, Lakshmanaprabu SK, Gupta D, Maseleno A, Albuquerque VHC. Optimal feature-based multi-kernel SVM approach for thyroid disease classification. J Supercomput 2018; (28): 1-16.
[24]
Zheng X, Zhai Z, Du G, LV G. Rapid and Low-Cost Detection of Thyroid Dysfunction Using Raman Spectroscopy and an Improved Support Vector Machine. IEEE Photonics J 2018; 10
[http://dx.doi.org/10.1109/JPHOT.2018.2876686]
[25]
Liu C, Huang Y, Ozolek JA, Hanna MG, Singh R, Rohde GK. SetSVM: An Approach to Set Classification in Nucleibased Cancer Detection IEEE J Biomed Health Inform 2019; 23(1): 351-61.
[26]
Persichetti A, Di Stasio E, Guglielmi R, et al. Predictive value of malignancy of thyroid nodule ultrasound classification systems: a prospective study. J Clin Endocrinol Metab 2018; 103(4): 1359-68.
[http://dx.doi.org/10.1210/jc.2017-01708] [PMID: 29408952]
[27]
Hu LY, Huang MW, Ke SW, Tsai CF. The distance function effect on k-nearest neighbor classification for medical datasets. Springerplus 2016; 5(1): 1304.
[http://dx.doi.org/10.1186/s40064-016-2941-7] [PMID: 27547678]
[28]
Chen W, Yang H, Feng P, Ding H, Lin H. iDNA4mC: identifying DNA N4-methylcytosine sites based on nucleotide chemical properties. Bioinformatics 2017; 33(22): 3518-23.
[http://dx.doi.org/10.1093/bioinformatics/btx479] [PMID: 28961687]
[29]
Chen W, Lv H, Nie F, Lin H. i6mA-Pred: identifying DNA N6-methyladenine sites in the rice genome. Bioinformatics 2019; 35(16): 2796-800.
[http://dx.doi.org/10.1093/bioinformatics/btz015] [PMID: 30624619]
[30]
Feng CQ, Zhang ZY, Zhu XJ, et al. iTerm-PseKNC: a sequence-based tool for predicting bacterial transcriptional terminators. Bioinformatics 2019; 35(9): 1469-77.
[http://dx.doi.org/10.1093/bioinformatics/bty827] [PMID: 30247625]

Rights & Permissions Print Cite
Article Metrics
16
1
© 2025 Bentham Science Publishers | Privacy Policy