Shujun Zhou
ABSTRACT
Segmentation of thyroid nodules in the ultrasound image is a chal lenging task not only because of the speckle noise in ultrasound images but also the heterogeneous appearance and blurry bound aries of thyroid nodules. In this paper, we apply U-Net, a fully convolutional neural network, to thyroid nodule segmentation, and further proposed an interactive segmentation method based on it and the guidance of annotation marks. Firstly, the four end-points of the major and minor axes of a nodule are determined manually. Then, four white spots are directly drawn at the four points on the image to guide the training and inference of the deep neural network. Our method is evaluated on a dataset composed of 900 ultrasound thyroid images. The experimental results indicate that our mark-guided segmentation method is able to delineate nodules accurately with little human intervention and achieve a remarkable improvement over its automatic counterpart.
- Zhang J, Zhou SK, Comaniciu D, Brunke S, Lowery C (2010) Database-guided breast tumor detection and segmentation in 2d ultrasound images. SPIE MI, 7624(1): 666--673.Google Scholar
- Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE TPAMI, 22(8): 888--905. Google ScholarDigital Library
- Deng J, Tsui HT (2002) A fast level set method for segmentation of low contrast noisy biomedical images. Pattern Recogn Lett, 23(1--3): 161--169. Google ScholarDigital Library
- Iakovidis DK, Savelonas MA, Karkanis SA, Maroulis DE (2006) Segmentation of Medical Images with Regional Inhomogeneities{C}. International Conference on Pattern Recognition. IEEE Computer Society, 3: 976--979. Google ScholarDigital Library
- Chan TF, Vesse LA (2001) Active Contours Without Edges. IEEE Trans. Image Processing. 7: 266--277. Google ScholarDigital Library
- Savelonas M, Maroulis D, Iakovidis D, Karkanis S (2005) A variable background active contour model for automatic detection of thyroid nodules in ultrasound images{C}. International Conference on Image Processing, 1: I-17--20.Google ScholarCross Ref
- Iakovidis DK, Savelonas MA, Karkanis SA, Maroulis DE (2007) A genetically optimized level set approach to segmentation of thyroid ultrasound images. Appl Intell, 27(3): 193--203. Google ScholarDigital Library
- Deepika Koundal, Savita Guptab, Sukhwinder Singhb (2018) Computer aided thyroid nodule detection system using medical ultrasound images. Biomedical Signal Processing and Control, 40: 117--130.Google ScholarCross Ref
- Keramidas EG, Iakovidis DK, Maroulis D, Karkanis S (2007) Efficient and Effective Ultrasound Image Analysis Scheme for Thyroid Nodule Detection{C}. International Conference on Image Analysis and Recognition. Springe-Verlag, 4633: 1052--1060. Google ScholarDigital Library
- Xu Y (2009) A modified spatial fuzzy clustering method based on texture analysis for ultrasound image segmentation. IEEE International Symposium on Industrial Electronics, pp.746--751.Google Scholar
- Kollorz E, Angelopoulou E, Beck M, Schmidt D, Kuwert T (2011) Using Power Watersheds to Segment Benign Thyroid Nodules in Ultrasound Image Data{J}. pp.124--128.Google Scholar
- Kwak JI, Kim SH, Kim NC (2005) RD-based seeded region growing for extraction of breast tumor in an ultrasound volume. International Conference on Computational Intelligence and Security Springer-Verlag, 3801: 799--808. Google ScholarDigital Library
- Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Proceedings of the 2012 Advances in Neural Information Processing Systems, 60(2): 1097--1105. Google ScholarDigital Library
- Girshick R, Donahue J, Darrell T, Malik J (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation{J}. IEEE Conference on Computer Vision and Pattern Recognition. pp.580--587. Google ScholarDigital Library
- Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 79(10): 3431--3440.Google ScholarCross Ref
- Dan CC, Giusti A, Gambardella LM, Schmidhuber fk2012ft Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images{J}. Advances in Neural Information Processing Systems, 25: 2852--2860.Google Scholar
- Ciresan D, Giusti A, Gambardella LM, Schmidhuber J (2013) Mitosis detection in breast cancer histology images with deep neural networks. 16:411--418.Google Scholar
- Turaga SC, Murray JF, Jain V, Roth F, Helmstaedter M, Briggman K, Denk W, Seung HS (2010) Convolutional networks can learn to generate affinity graphs for image segmentation. Neural Comput, 22(2): 511--538. Google ScholarDigital Library
- Ma J, Wu F, Jiang T, Zhao Q, Kong D (2017) Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks. Int J Comput Assist Radiol Surg, 11: 1--16.Google Scholar
- Vorontsov E, Chartrand G, Tang A, Pal C, Kadoury S (2017) Liver lesion segmentation informed by joint liver segmentation.Google Scholar
- Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 9351: 234--241.Google Scholar
- Milletari F, Navab N, Ahmadi SA (2016) V-net: Fully convolutional neural networks for volumetric medical image segmentation{C}. Fourth International Conference on 3d Vision. IEEE Computer Society, pp.565--571.Google ScholarCross Ref
- Dubost F, Bortsova G, Adams H, Ikram A, Niessen WJ, Vernooij M (2017) GP-Unet: Lesion Detection from Weak Labels with a 3D Regression Network{C}. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, pp.214--221.Google ScholarDigital Library
- Nie D, Wang L, Gao Y, Sken D (2016) Fully convolutional networks for multimodality isointense infant brain image segmentation{C}. IEEE, International Symposium on Biomedical Imaging, 2016: 1342.Google Scholar
- Andrioli M, Carzaniga C, Persani L (2013) Standardized Ultrasound Report for Thyroid Nodules: The Endocrinologist's Viewpoint{J}. Eur Thyroid J, 2(1): 37--48.Google ScholarCross Ref
- Osher S, Sethian J (1988) Fronts Propagating with Curvature- Dependent Speed: Algorithms Based on the Hamilton-Jacobi Formulations. Journal Of Computational Physics, 79: 12--49. Google ScholarDigital Library
- Mumford D, Shah J (1989) Optimal Approximation by Piecewise Smooth Functions and Associated Variational Problems. Commun. Pure Appl. Math., 42: 577--685.Google ScholarCross Ref
- Chang CY, Lei YF, Tseng CH, Shih SR (2010) Thyroid Segmentation and Volume Estimation in Ultrasound Images{J}. IEEE Transactions on Biomedical Engineering, 57(6): 1348--1357.Google ScholarCross Ref
Index Terms
- Mark-Guided Segmentation of Ultrasonic Thyroid Nodules Using Deep Learning
Recommendations
Research on Ultrasonic Image Segmentation of Thyroid Nodules Based on Improved U-net++
BIC 2022: 2022 2nd International Conference on Bioinformatics and Intelligent ComputingThe ultrasound image of thyroid nodules has low contrast and severe speckle noise, and the morphology of thyroid nodules in different patients is quite different, which makes it extremely difficult for doctors to accurately and quickly diagnose the ...
Diagnostic value of multi-parameter MRI and colour B-ultrasound elastography in benign and malignant thyroid nodules
BACKGROUND:The early diagnosis of thyroid cancer depends on the popularisation and development of diagnostic imaging techniques and the continuous improvement of physician diagnosis.
OBJECTIVE: ...Prior Region Mask R-CNN for Thyroid Nodule Segmentation in Ultrasound Images
Intelligent Robotics and ApplicationsAbstractThe incidence of thyroid nodules has gradually increased in recent years, and its main detection method is ultrasonography. Segmentation of thyroid nodules in ultrasound images is important for the diagnosis of benign and malignant conditions. ...
Comments