Variable Background Active Contour Model for Computer-Aided Delineation of Nodules in Thyroid Ultrasound Images

This paper presents a computer-aided approach for nodule delineation in thyroid ultrasound (US) images. The developed algorithm is based on a novel active contour model, named variable background active contour (VBAC), and incorporates the advantages of the level set region-based active contour without edges (ACWE) model, offering noise robustness and the ability to delineate multiple nodules. Unlike the classic active contour models that are sensitive in the presence of intensity inhomogeneities, the proposed VBAC model considers information of variable background regions. VBAC has been evaluated on synthetic images, as well as on real thyroid US images. From the quantification of the results, two major impacts have been derived: 1) higher average accuracy in the delineation of hypoechoic thyroid nodules, which exceeds 91%; and 2) faster convergence when compared with the ACWE model.

[1]  Mário A. T. Figueiredo,et al.  Automatic contour estimation in fetal ultrasound images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[2]  K. Boone,et al.  Effect of skin impedance on image quality and variability in electrical impedance tomography: a model study , 1996, Medical and Biological Engineering and Computing.

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

[4]  Ron Kikinis,et al.  Segmentation of Meningiomas and Low Grade Gliomas in MRI , 1999, MICCAI.

[5]  Helmut Pottmann,et al.  Fast model based segmentation of ultrasound data using an active image , 2002, Proceedings IEEE International Symposium on Biomedical Imaging.

[6]  J. Morel,et al.  Segmentation of images by variational methods: a constructive approach. , 1988 .

[7]  Dimitrios I. Fotiadis,et al.  An automated method for lumen and media-adventitia border detection in a sequence of IVUS frames , 2004, IEEE Transactions on Information Technology in Biomedicine.

[8]  H. Bogaard,et al.  The intra- and interobserver variability of impedance cardiography in patients at rest and during exercise. , 1996, Physiological measurement.

[9]  F. Greenspan,et al.  Thyroid nodules and thyroid cancer. , 1974, The Western journal of medicine.

[10]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[11]  Elsa D. Angelini,et al.  Segmentation of RT3D ultrasound with implicit deformable models without gradients , 2003, 3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the.

[12]  J. Sethian,et al.  FRONTS PROPAGATING WITH CURVATURE DEPENDENT SPEED: ALGORITHMS BASED ON HAMILTON-JACOB1 FORMULATIONS , 2003 .

[13]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

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

[15]  Tony F. Chan,et al.  A Level-Set and Gabor-based Active Contour Algorithm for Segmenting Textured Images , 2002 .

[16]  James F. Greenleaf,et al.  A novel region growing method for segmenting ultrasound images , 2000, 2000 IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No.00CH37121).

[17]  James S. Duncan,et al.  Combinative Multi-scale Level Set Framework for Echocardiographic Image Segmentation , 2002, MICCAI.

[18]  H Yamashita,et al.  Ultrasonographic characteristics of thyroid nodules: prediction of malignancy. , 2001, Archives of surgery.

[19]  C M Chen,et al.  A dual-snake model of high penetrability for ultrasound image boundary extraction. , 2001, Ultrasound in medicine & biology.

[20]  Anna Crescenzi,et al.  Risk of malignancy in nonpalpable thyroid nodules: predictive value of ultrasound and color-Doppler features. , 2002, The Journal of clinical endocrinology and metabolism.

[21]  Ruey-Feng Chang,et al.  3-D snake for US in margin evaluation for malignant breast tumor excision using mammotome , 2003, IEEE Transactions on Information Technology in Biomedicine.

[22]  R. Mortimer,et al.  6: Thyroid nodules and thyroid cancer , 2004, The Medical journal of Australia.

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