A systematic review on the role of artificial intelligence in sonographic diagnosis of thyroid cancer: Past, present and future

Thyroid cancer is common worldwide, with a rapid increase in prevalence across North America in recent years. While most patients present with palpable nodules through physical examination, a large number of small and medium-sized nodules are detected by ultrasound examination. Suspicious nodules are then sent for biopsy through fine needle aspiration. Since biopsies are invasive and sometimes inconclusive, various research groups have tried to develop computer-aided diagnosis systems. Earlier approaches along these lines relied on clinically relevant features that were manually identified by radiologists. With the recent success of artificial intelligence (AI), various new methods are being developed to identify these features in thyroid ultrasound automatically. In this paper, we present a systematic review of state-of-the-art on AI application in sonographic diagnosis of thyroid cancer. This review follows a methodology-based classification of the different techniques available for thyroid cancer diagnosis. With more than 50 papers included in this review, we reflect on the trends and challenges of the field of sonographic diagnosis of thyroid malignancies and potential of computer-aided diagnosis to increase the impact of ultrasound applications on the future of thyroid cancer diagnosis. Machine learning will continue to play a fundamental role in the development of future thyroid cancer diagnosis frameworks.

[1]  Tao Jiang,et al.  Computer-aided diagnosis of malignant or benign thyroid nodes based on ultrasound images , 2017, European Archives of Oto-Rhino-Laryngology.

[2]  U. Rajendra Acharya,et al.  ThyroScreen system: High resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform , 2012, Comput. Methods Programs Biomed..

[3]  Christian Hansen,et al.  Comparison of thyroid segmentation techniques for 3D ultrasound , 2017, Medical Imaging.

[4]  Filipe Caseiro-Alves,et al.  Differentiating malignant thyroid nodule with statistical classifiers based on demographic and ultrasound features , 2017, 2017 IEEE 5th Portuguese Meeting on Bioengineering (ENBENG).

[5]  Pina Marziliano,et al.  Speckle Patch Similarity for Echogenicity-Based Multiorgan Segmentation in Ultrasound Images of the Thyroid Gland , 2017, IEEE Journal of Biomedical and Health Informatics.

[6]  Young Jun Chai.  Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules , 2018 .

[7]  Jianhua Huang,et al.  An improved quantitative measurement for thyroid cancer detection based on elastography. , 2012, European journal of radiology.

[8]  Joongseek Lee,et al.  Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules , 2019, Medicine.

[9]  Fa Wu,et al.  Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks , 2017, International Journal of Computer Assisted Radiology and Surgery.

[10]  Alfredo Illanes,et al.  Parametrical modelling for texture characterization—A novel approach applied to ultrasound thyroid segmentation , 2019, PloS one.

[11]  Fa Wu,et al.  Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images , 2017, Medical physics.

[12]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Paul Babyn,et al.  Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network , 2017, Journal of Digital Imaging.

[14]  Bin Zhang,et al.  Machine Learning-Assisted System for Thyroid Nodule Diagnosis. , 2019, Thyroid : official journal of the American Thyroid Association.

[15]  Weiwei Liu,et al.  An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images , 2018, Scientific Reports.

[16]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[17]  Jing Yu,et al.  Classification of thyroid nodules in ultrasound images using deep model based transfer learning and hybrid features , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Anjan Biswas,et al.  Thyroid Nodule Recognition Based on Feature Selection and Pixel Classification Methods , 2013, Journal of Digital Imaging.

[19]  William D Middleton,et al.  Thyroid Ultrasound Reporting Lexicon: White Paper of the ACR Thyroid Imaging, Reporting and Data System (TIRADS) Committee. , 2015, Journal of the American College of Radiology : JACR.

[20]  Eun-Kyung Kim,et al.  Deep convolutional neural network for the diagnosis of thyroid nodules on ultrasound , 2019, Head & neck.

[21]  L. Cozzi,et al.  Texture analysis and machine learning to characterize suspected thyroid nodules and differentiated thyroid cancer: Where do we stand? , 2018, European journal of radiology.

[22]  Chuan-Yu Chang,et al.  Application of support-vector-machine-based method for feature selection and classification of thyroid nodules in ultrasound images , 2010, Pattern Recognit..

[23]  M. Gurcan,et al.  Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study. , 2019, The Lancet. Oncology.

[24]  Aimin Hao,et al.  Learning from Weakly-Labeled Clinical Data for Automatic Thyroid Nodule Classification in Ultrasound Images , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[25]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Alfredo Illanes,et al.  Evaluation of Commonly Used Algorithms for Thyroid Ultrasound Images Segmentation and Improvement Using Machine Learning Approaches , 2018, Journal of healthcare engineering.

[27]  F. Ouyang,et al.  Comparison between linear and nonlinear machine-learning algorithms for the classification of thyroid nodules. , 2019, European journal of radiology.

[28]  Hong Zhou,et al.  Ultrasound-based differentiation of malignant and benign thyroid Nodules: An extreme learning machine approach , 2017, Comput. Methods Programs Biomed..

[29]  Joel E. W. Koh,et al.  Thyroid lesion classification in 242 patient population using Gabor transform features from high resolution ultrasound images , 2016, Knowl. Based Syst..

[30]  Savita Gupta,et al.  Automated delineation of thyroid nodules in ultrasound images using spatial neutrosophic clustering and level set , 2016, Appl. Soft Comput..

[31]  Nawres Khlifa,et al.  A review on Deep Learning in thyroid ultrasound Computer-Assisted Diagnosis systems , 2018, 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS).

[32]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[33]  Aimin Hao,et al.  Multitask Cascade Convolution Neural Networks for Automatic Thyroid Nodule Detection and Recognition , 2019, IEEE Journal of Biomedical and Health Informatics.

[34]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Nikos Dimitropoulos,et al.  Morphological and wavelet features towards sonographic thyroid nodules evaluation , 2009, Comput. Medical Imaging Graph..

[36]  Zhuang Fu,et al.  An image augmentation method using convolutional network for thyroid nodule classification by transfer learning , 2017, 2017 3rd IEEE International Conference on Computer and Communications (ICCC).

[37]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Chuan-Yu Chang,et al.  Thyroid segmentation and volume estimation in ultrasound images , 2010, 2008 IEEE International Conference on Systems, Man and Cybernetics.

[39]  Zenglin Xu,et al.  Mark-Guided Segmentation of Ultrasonic Thyroid Nodules Using Deep Learning , 2018, ISICDM 2018.

[40]  Agnieszka Witkowska,et al.  A Review on Ultrasound-Based Thyroid Cancer Tissue Characterization and Automated Classification , 2014, Technology in cancer research & treatment.

[41]  Kang Ryoung Park,et al.  Artificial Intelligence-Based Thyroid Nodule Classification Using Information from Spatial and Frequency Domains , 2019, Journal of clinical medicine.

[42]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[43]  Mei Yu,et al.  Fully Convolutional Networks for Ultrasound Image Segmentation of Thyroid Nodules , 2018, 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS).

[44]  Christoph Reiners,et al.  Sonographic diagnosis of thyroid cancer with support of AI , 2019, Nature Reviews Endocrinology.

[45]  Daniel Smutek,et al.  Patch-based classification of thyroid nodules in ultrasound images using direction independent features extracted by two-threshold binary decomposition , 2019, Comput. Medical Imaging Graph..

[46]  Fabián Narváez,et al.  An open access thyroid ultrasound image database , 2015, Other Conferences.

[47]  Shujian Yang,et al.  Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network , 2019, World Journal of Surgical Oncology.

[48]  Jeong Hyun Lee,et al.  Deep Learning-Based Computer-Aided Diagnosis System for Localization and Diagnosis of Metastatic Lymph Nodes on Ultrasound: A Pilot Study. , 2018, Thyroid : official journal of the American Thyroid Association.

[49]  Savita Gupta,et al.  Computer aided thyroid nodule detection system using medical ultrasound images , 2018, Biomed. Signal Process. Control..