Ultrasonic thyroid nodule detection method based on U-Net network

OBJECTIVE Aiming at the time consuming processing of existing thyroid nodule detection and difficulty in feature extraction, U-Net-based thyroid nodule detection is proposed to perform computed aided diagnosis. METHOD This paper proposes a mark-guided ultrasound deep network segmentation model of thyroid nodules. By comparing with VGG19, Inception V3, DenseNet 161, segmentation accuracy, segmentation edge and network operation time, it is found that the algorithm in this paper has relative advantages. RESULTS U-Net network-based ultrasound thyroid nodules segmented the nodule area overlapped with the manually depicted nodule area close to 100%, the segmentation accuracy rate was as high as 0.9785, and the U-Net segmentation result was closer to the manually depicted nodule. The accuracy of U-Net segmentation of the thyroid is about 3% higher than the other three networks. CONCLUSION The segmentation of nodules based on U-Net proposed in this paper significantly improves the segmentation accuracy of thyroid nodules with a small training data set, and provides a comprehensive reference for clinical diagnosis and treatment.

[1]  Bruno Mussoi de Macedo,et al.  Reliability of Thyroid Imaging Reporting and Data System (TI-RADS), and ultrasonographic classification of the American Thyroid Association (ATA) in differentiating benign from malignant thyroid nodules , 2018, Archives of endocrinology and metabolism.

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

[3]  Nikunj H. Domadiya,et al.  An Improved EMHS Algorithm for Privacy Preserving in Association Rule Mining on Horizontally Partitioned Database , 2014, SSCC.

[4]  J. Abdul Samath,et al.  An Intelligent Recurrent Neural Network with Long Short-Term Memory (LSTM) BASED Batch Normalization for Medical Image Denoising , 2019, Journal of Medical Systems.

[5]  Dimitrios K. Iakovidis,et al.  Efficient and Effective Ultrasound Image Analysis Scheme for Thyroid Nodule Detection , 2007, ICIAR.

[6]  Yuan Zhang,et al.  SIFT Matching with CNN Evidences for Particular Object Retrieval , 2017, Neurocomputing.

[7]  R. Chang,et al.  The adaptive computer‐aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound , 2017, Ultrasonics.

[8]  Michalis A. Savelonas,et al.  A genetically optimized level set approach to segmentation of thyroid ultrasound images , 2007, Applied Intelligence.

[9]  Yongmin Kim,et al.  Differential diagnosis of thyroid nodules with ultrasound elastography based on support vector machines , 2010, 2010 IEEE International Ultrasonics Symposium.

[10]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[12]  Yu Ren.  An Integrated Intrusion Detection System by Combining SVM with AdaBoost , 2014 .

[13]  Yan Xu,et al.  A modified spatial fuzzy clustering method based on texture analysis for ultrasound image segmentation , 2009, 2009 IEEE International Symposium on Industrial Electronics.

[14]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[15]  Dorin Comaniciu,et al.  Database-guided breast tumor detection and segmentation in 2D ultrasound images , 2010, Medical Imaging.

[16]  George Papandreou,et al.  Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[18]  Elli Angelopoulou,et al.  Using Power Watersheds to Segment Benign Thyroid Nodules in Ultrasound Image Data , 2011, Bildverarbeitung für die Medizin.

[19]  Michael Hahsler,et al.  Visualizing association rules in hierarchical groups , 2016, Journal of Business Economics.

[20]  Ouahiba Azouaoui,et al.  Road intersection detection and classification using hierarchical SVM classifier , 2014, Adv. Robotics.

[21]  Jitendra Malik,et al.  Normalized Cuts and Image Segmentation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Hao Wang,et al.  A thyroid nodule classification method based on TI-RADS , 2017, International Conference on Digital Image Processing.

[23]  Michalis A. Savelonas,et al.  Segmentation of Medical Images with Regional Inhomogeneities , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[24]  Gilles Russ,et al.  Risk stratification of thyroid nodules on ultrasonography with the French TI-RADS: description and reflections , 2015, Ultrasonography.

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

[26]  Jiangwen Deng,et al.  A fast level set method for segmentation of low contrast noisy biomedical images , 2002, Pattern Recognit. Lett..

[27]  Yanjun Qi,et al.  Association Rule Mining with the Micron Automata Processor , 2015, 2015 IEEE International Parallel and Distributed Processing Symposium.

[28]  Jin Young Kwak,et al.  Thyroid imaging reporting and data system for US features of nodules: a step in establishing better stratification of cancer risk. , 2011, Radiology.

[29]  N. Letendre,et al.  The Bethesda Classification for Thyroid Fine Needle Aspiration: A Predictor or an Alarmist? , 2018, The American surgeon.

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

[31]  K. Matre,et al.  Effects of velocity distribution, diameter measurement and velocity tracing on the accuracy of cardiac output measurement by pulsed Doppler echocardiography in the aortic annulus of pigs. , 1997, Ultrasound in medicine & biology.

[32]  Dimitrios K. Iakovidis,et al.  ΤND: A Thyroid Nodule Detection System for Analysis of Ultrasound Images and Videos , 2012, Journal of Medical Systems.

[33]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[34]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..

[35]  Chien-Liang Liu,et al.  Characterization of thyroid nodules using the proposed thyroid imaging reporting and data system (TI‐RADS) , 2013, Head & neck.

[36]  Nikos Dimitropoulos,et al.  A variable background active contour model for automatic detection of thyroid nodules in ultrasound images , 2005, IEEE International Conference on Image Processing 2005.

[37]  Tien-Chun Chang.  The Role of Computer-aided Detection and Diagnosis System in the Differential Diagnosis of Thyroid Lesions in Ultrasonography , 2015 .