Artificial Intelligence in Ultrasound Imaging: Current Research and Applications

doi:10.37015/AUDT.2019.190811

Abstract

Abstract:

Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent software or system based on big data information, machine learning and deep learning technologies. The rapid development of science and technology as well as internet communication has enabled AI and big data to gradually apply to many fields of health care. The modern imaging medicine is one of the first areas where AI can play an important role and applications. As cross-sectional imaging, ultrasound (US) is well suitable for AI technology to standardize imaging protocols and improve diagnostic accuracy. This article reviews current AI technology and related clinical applications in the fields of thyroid, breast and liver US.

Key words: Artificial intelligence; Machine learning; Deep learning; Ultrasound imaging; Thyroid; Breast; Liver

Shuo Wang, BS, Ji-Bin Liu, MD, Ziyin Zhu, MD, John Eisenbrey, PhD. Artificial Intelligence in Ultrasound Imaging: Current Research and Applications. Advanced Ultrasound in Diagnosis and Therapy, 2019, 3(3): 53-61.

Figures/Tables 9

Table 1

Table 2

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

References

[1]	Andreas K, Michael H. Siri, Siri in my hand: Who's the fairest in the land? On the interpretations, illustrations and implications of artificial intelligence. Business Horizons 2019; 62:15-25.
[2]	Takahashi R, Kajikawa Y. Computer-aided diagnosis: A survey with bibliometric analysis. Int J Med Inform 2017; 101:58-67
[3]	Cheng HD, Shan J, Ju W, Guo Y, Zhang L. Automated breast cancer detection and classification using ultrasound images: a survey. Pattern Recognition 2010; 43:299-317.
[4]	Mansoor A, Bagci U, Foster B, Xu Z, Papadakis GZ, Folio LR, et al. Segmentation and image analysis of abnormal lungs at CT: Current approaches, challenges, and future trends. RadioGraphics 2015; 35:1056-76.
[5]	Huang Q, Zhang F, Li X. Machine learning in ultrasound computer-aided diagnostic systems: A survey. Biomed Res Int 2018; 2018: 5137904.
[6]	Cherkassky V, Mulier F. Learning from data: Concepts, theory, and methods: Second Edition. Hoboken: John Wiley & Sons, Inc., Publisher; 2006: 1-538.
[7]	Laws KI. Image Understanding Workshop. Texture Energy Measures. 1979; pp. 47-51.
[8]	Abdel-Nasser M, Melendez J, Moreno A, Omer OA, Puig D. Breast tumor classification in ultrasound images using texture analysis and super-resolution methods. Engineering Applications of Artificial Intelligence 2017; 59:84-92.
[9]	Chen CM, Chou YH, Han KC, Hung GS, Tiu CM, Chiou HJ, et al. Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks. Radiology 2003; 226:504-14.
[10]	Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science 2006; 313:504-7.
[11]	Grossfeld B. A simple way to understand machine learning vs deep learning. Zendesk JULY 18, 2017.
[12]	Tony Kontzer. How AI and Deep Learning Will Enable Cancer Diagnosis Via Ultrasound. Nvida. June 6, 2018.
[13]	McBee MP, Awan OA, Colucci AT, Ghobadi CW, Kadom N, Kansagra AP,et al.Deep learning in radiology. Acad Radiol 2018; 25:1472-80.
[14]	NVIDIA Convolutional Neural Network. https://developer.nvidia.com/discover/convolutional-neural-network
[15]	U.S. Breast Cancer Statistics . 2019; https://www.breastcancer.org/
[16]	Feng X, Guo X, Huang Q. Systematic evaluation on speckle suppression methods in examination of ultrasound breast images. Applied Sciences 2017; 7:37.
[17]	Huang Q, Yang F, Liu L, Li X.Automatic segmentation of breast lesions for interaction in ultrasonic computer-aided diagnosis. Information Sciences 2015; 314:293-310.
[18]	Byra M, Galperin M, Ojeda-Fournier H, Olson L ,O'Boyle M, Comstock C,et al. Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion. Med Phys 2019; 46:746-55.
[19]	Drukker K, Gruszauskas NP, Sennett CA, Giger ML. Breast US computer-aided diagnosis workstation: performance with a large clinical diagnostic population. Radiology 2008; 248:392-7.
[20]	Zhang Q, Xiao Y, Dai W, Suo J, Wang C, Shi J, et al. Deep learning based classification of breast tumors with shear-wave elastography. Ultrasonics 2016; 72:150-7.
[21]	Cheng JZ, Ni D, Chou YH, Qin J, Tiu CM, Chang YC, et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Sci Rep 2016; 6:24454.
[22]	Shi J, Zhou S, Liu X, Zhang Q, Lu M, Wang T. Stacked deep polynomial network based representation learning for tumor classification with small ultrasound image dataset. Neurocomputing 2016; 194:87-94.
[23]	Gruszauskas AP, Drukker K, Giger ML, Sennett CA, Pesce LL . Performance of breast ultrasound computer-aided diagnosis: dependence on image selection. Acad Radiol 2008; 15:1234-45.
[24]	Chang RF, Kuo WJ, Chen DR, Huang YL, Lee JH, Chou YH. Computer-aided diagnosis for surgical office-based breast ultrasound. Arch Surg 2000; 135:696-9.
[25]	Han S, Kang HK, Jeong JY, Park MH, Kim W, Bang WC, et al. A deep learning framework for supporting the classification of breast lesions in ultrasound images. Phys Med Biol 2017; 62:7714-28.
[26]	Hu Y, Guo Y, Wang Y, Yu J, Li J, Zhou S, et al. Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model. Med Phys 2019; 46:215-28.
[27]	American Cancer Society Key Statistics for Thyroid Cancer.www.cancer.org/cancer/thyroid-cancer/about/key-statistics.html
[28]	Haugen BR, Alexander EK, Bible KC, Doherty GM, Mandel SJ, Nikiforov YE, et al. 2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer. Thyroid 2016; 26:1-133.
[29]	Ko SY, Lee JH, Yoon JH, Na H, Hong E, Han K, et al. Deep convolutional neural network for the diagnosis of thyroid nodules on ultrasound. Head Neck 2019; 41:885-91.
[30]	Wang L, Yang S, Yang S, Zhao C, Tian G, Gao Y, et al. Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network. World J Surg Oncol 2019; 17:12.
[31]	Zuo D, Han L, Chen K, Li C, Hua Z, Lin J. Extraction of calcification in ultrasonic images based on convolution neural network. Sheng Wu Gong Cheng Yi Xue Za Zhi. 2018; 35:679-87. [in Chinese]
[32]	Choi YJ, Baek JH, Park HS, Shim WH, Kim TY, Shong YK, et al. A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of thyroid nodules on ultrasound: Initial clinical assessment. Thyroid 2017; 27:546-52.
[33]	Ma J, Wu F, Jiang T, Zhu J, Kong D. Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images. Medical Physics 2017; 44:1678-91.
[34]	Centers for Disease Control and Prevention.Liver Cancer.
[35]	Hassan TM, Elmogy M, Sallam ES. Diagnosis of focal liver diseases based on deep learning technique for ultrasound images. Arabian Journal for Science and Engineering 2017; 42:3127-40.
[36]	Meng D, Zhang L, Cao G, Cao W, Zhang G, Hu B. Liver fibrosis classification based on transfer learning and FCNet for ultrasound images. IEEE Access 2017; 5:5804-10.
[37]	Liu X, Song JL, Wang SH, Zhao JW, Chen YQ. Learning to diagnose cirrhosis with liver capsule guided ultrasound image classification. Sensors (Basel) 2017; 17:149.
[38]	Byra M, Styczynski G, Szmigielski C, Kalinowski P, Micha?owski ?, Paluszkiewicz R, et al. Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images. Int J Comput Assist Radiol Surg 2018; 13:1895-903.
[39]	Launchbury J A DARPA perspective on artificial intelligence, 2017. www.darpa.mil/attachments/AIFull.pdf

Categories	Description	Algorithms/ Methods
Texture	Reflects the surface characteristics of a lesion and it is frequently used in traditional CAD system.	? Laws Texture Energy (LTE) ^[7] ? Contrast of Gray Level Values ^[5] ? Gray Level Cooccurrence Matrix (GLCM) ^[5] ? Local Binary Pattern (LBP) ^[8] ? Wavelet Features ^[5]
Morphology	More focus on lesion itself. Such as smoothness of lesion margin, length and width ratio of lesion and so on.	? Speculation ? Depth-to-Width Ration ? Elliptic-Normalized Circumference (ENC) ^[9] ? Elliptic-Normalized Skeleton (ENS) ^[9] ? Long Axis-to-Short Axis Ratio (L: S) ^[9]
sModel-based	Statistical model of the backscattered echo that can indicates the character of backscattered echo from tissues.	? Nakagami model-based features ? K-Distribution model-based features
Descriptor features	Different applications (diseases) create different descriptor features and features are generated by radiologist base on their experience.	? Shape ? Calcifications ? Posterior shadow or posterior echo ? Echo characteristic

Classifiers	Descriptions of characteristic
Linear Classifier	Linear discrimination analysis and logistic regression are two linear classifiers and reliable only with linear data.
Bayesian Classifier	It is involved in machine learning and it predicts posterior information base on analyzing previous data points.
Support Vector Machine	Kernel functions are utilized to find decision hyperplanes by computing the original data into the higher dimensional space. The complexity increases as dataset increases.
Decision Tree	Its structure is a flowchart and it computes classification rules from disordered data. The size of data and feature values affect the complexity of the decision structure.
Artificial Neural Network	It is a machine learning model base on human nervine system. The complexity of the network affects the training time.
AdaBoost	Integrating several weak classifiers and building a strong classifier based on prediction voting from weak classifiers.