Automatic Segmentation of Ultrasound Tomography Image

Ultrasound tomography (UST) image segmentation is fundamental in breast density estimation, medicine response analysis, and anatomical change quantification. Existing methods are time consuming and require massive manual interaction. To address these issues, an automatic algorithm based on GrabCut (AUGC) is proposed in this paper. The presented method designs automated GrabCut initialization for incomplete labeling and is sped up with multicore parallel programming. To verify performance, AUGC is applied to segment thirty-two in vivo UST volumetric images. The performance of AUGC is validated with breast overlapping metrics (Dice coefficient (D), Jaccard (J), and False positive (FP)) and time cost (TC). Furthermore, AUGC is compared to other methods, including Confidence Connected Region Growing (CCRG), watershed, and Active Contour based Curve Delineation (ACCD). Experimental results indicate that AUGC achieves the highest accuracy (D = 0.9275 and J = 0.8660 and FP = 0.0077) and takes on average about 4 seconds to process a volumetric image. It was said that AUGC benefits large-scale studies by using UST images for breast cancer screening and pathological quantification.

[1]  Vladimir Kolmogorov,et al.  "GrabCut": interactive foreground extraction using iterated graph cuts , 2004, ACM Trans. Graph..

[2]  Neb Duric,et al.  Breast imaging with SoftVue: initial clinical evaluation , 2014, Medical Imaging.

[3]  Bryan J. Ranger,et al.  Breast ultrasound tomography versus MRI for clinical display of anatomy and tumor rendering: preliminary results. , 2012, AJR. American journal of roentgenology.

[4]  Patrick Pérez,et al.  Interactive Image Segmentation Using an Adaptive GMMRF Model , 2004, ECCV.

[5]  Anne L. Martel,et al.  Automatic atlas-based segmentation of the breast in MRI for 3D breast volume computation. , 2012, Medical physics.

[6]  Min-Ying Su,et al.  Template-based automatic breast segmentation on MRI by excluding the chest region. , 2013, Medical physics.

[7]  Soo-Hyung Kim,et al.  Unconstrained Object Segmentation Using GrabCut Based on Automatic Generation of Initial Boundary , 2013 .

[8]  Torsten Hopp,et al.  Segmentation of 3D ultrasound computer tomography reflection images using edge detection and surface fitting , 2014, Medical Imaging.

[9]  Wanqing Chen,et al.  Breast cancer in China. , 2014, The Lancet. Oncology.

[10]  Olivier Roy,et al.  Breast boundary detection with active contours , 2014, Medical Imaging.

[11]  N. Boyd,et al.  Breast density measurements with ultrasound tomography: a comparison with film and digital mammography. , 2013, Medical physics.

[12]  Mark Sak,et al.  Determinants of the reliability of ultrasound tomography sound speed estimates as a surrogate for volumetric breast density. , 2015, Medical physics.

[13]  Guido Gerig,et al.  User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability , 2006, NeuroImage.

[14]  Mark Sak,et al.  Using Speed of Sound Imaging to Characterize Breast Density. , 2017, Ultrasound in medicine & biology.

[15]  Sébastien Ourselin,et al.  Slic-Seg: Slice-by-Slice Segmentation Propagation of the Placenta in Fetal MRI Using One-Plane Scribbles and Online Learning , 2015, MICCAI.

[16]  Qianjin Feng,et al.  Segmentation of ultrasonic breast tumors based on homogeneous patch. , 2012, Medical physics.

[17]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  N. Duric,et al.  Volumetric breast density evaluation from ultrasound tomography images. , 2008, Medical physics.

[19]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[20]  N. Duric,et al.  Breast density measurements with ultrasound tomography: a comparison with non-contrast MRI , 2015, Breast Cancer Research.

[21]  C. Tappert,et al.  A Survey of Binary Similarity and Distance Measures , 2010 .

[22]  Sandra F. Jones,et al.  Implementation of the National Breast and Cervical Cancer Early Detection Program: The beginning , 2014, Cancer.

[23]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[24]  Cuiping Li,et al.  Waveform inversion with source encoding for breast sound speed reconstruction in ultrasound computed tomography , 2014, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[25]  Yaoqin Xie,et al.  Interactive contour delineation and refinement in treatment planning of image‐guided radiation therapy , 2014, Journal of applied clinical medical physics.

[26]  Gareth Funka-Lea,et al.  Graph Cuts and Efficient N-D Image Segmentation , 2006, International Journal of Computer Vision.

[27]  Neb Duric,et al.  Breast density measurements using ultrasound tomography for patients undergoing tamoxifen treatment , 2013, Medical Imaging.

[28]  G Y Sandhu,et al.  Frequency domain ultrasound waveform tomography: breast imaging using a ring transducer , 2015, Physics in medicine and biology.

[29]  Cristian Sminchisescu,et al.  CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Tarek Halabi,et al.  Automating checks of plan check automation , 2014, Journal of applied clinical medical physics.

[31]  N. Duric,et al.  In vivo breast sound-speed imaging with ultrasound tomography. , 2009, Ultrasound in medicine & biology.

[32]  A. Jemal,et al.  Breast cancer statistics, 2013 , 2014, CA: a cancer journal for clinicians.

[33]  Rangaraj M. Rangayyan,et al.  Review of recent advances in segmentation of the breast boundary and the pectoral muscle in mammograms , 2015, Medical & Biological Engineering & Computing.

[34]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[35]  Michael D Mills.  The Meaning of a Master of Science Degree in Medical Physics , 2014, Journal of applied clinical medical physics.

[36]  Sébastien Barré,et al.  Integrating segmentation methods from the Insight Toolkit into a visualization application , 2005, Medical Image Anal..

[37]  L. Tabár,et al.  The Impact of Mammography Screening on the Diagnosis and Management of Early-Phase Breast Cancer , 2014 .

[38]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[39]  N. Duric,et al.  Novel approach to evaluating breast density utilizing ultrasound tomography. , 2007, Medical physics.

[40]  N. Duric,et al.  Detection of breast cancer with ultrasound tomography: first results with the Computed Ultrasound Risk Evaluation (CURE) prototype. , 2007, Medical physics.

[41]  Martha Elizabeth Shenton,et al.  A 3D interactive multi-object segmentation tool using local robust statistics driven active contours , 2012, Medical Image Anal..

[42]  Ivana Jovanovic,et al.  Breast imaging with the SoftVue imaging system: first results , 2013, Medical Imaging.

[43]  Wenbing Tao,et al.  Image Segmentation Based on GrabCut Framework Integrating Multiscale Nonlinear Structure Tensor , 2009, IEEE Transactions on Image Processing.

[44]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .