Intelligent lesion detection system for medical ultrasound images are aimed at reducing physicians’ effort during cancer diagnosis process. Automatic separation and classification of tumours in ultrasound images is challenging owing to the low contrast and noisy behavior of the image. A Computer aided detection (CAD) system that automatically segment and classify breast tumours in ultrasound (US) images is proposed in this paper. The proposed method is invariant to scale changes and does not require an operator defined initial region of interest. Wavelet modulus maxima points of the US image are analyzed to extract the tumour seed point. The lesions segmented using a region-based approach are classified using a support vector machine (SVM) classifier. Evaluation of various performance measures show that the performance of the proposed CAD system is promising.
American cancer society: Cancer facts and figures, 2018.
2.
BergW.A., BlumeJ.D., CormackJ.B., MendelsonE.B., LehrerDaniel, Marcela, et al., Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer, Journal of American Medical Association299(18) (2008), 2151–2163.
3.
YapM.H., EdirisingheE.A. and BezH.E., A novel algorithm for initial lesion detection in ultrasound breast images, Journal of applied clinical medical physics9(4) (2008), 181–199.
4.
JalalianS.B.A., Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review, Clinical imaging37(3) (2013), 420–426.
5.
ChenS.C., CheungY.C., SuC.H., ChenM.F., HwangT.L. and HsuehS., Analysis of sonographic features for the differentiation of benign and malignant breast tumors of different size, Ultrasound Obstet Gynecol23 (2004), 188–193.
6.
MoraruaL., MoldovanuaS. and BiswasA., Optimization of breast lesion segmentation in texture feature space approach, Medical engineering and Physics, 2013.
7.
PizuricaW.P.A., A Versatile Wavelet Domain Noise Filtration Technique for Medical Imaging, IEEE Transactions on Medical Imaging22(3) (2003), 323–331.
8.
CzerwinskisR.N., JonesD.L. and O’BrienW.D., Detection of Lines and Boundaries in Speckle Images: Application to Medical Ultrasound, IEEE Trans Med Imaging18(2) (1999), 126–136.
9.
ChenD.R., C. R. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks, Ultrasound Med Biol28(10) (2002), 1301–1310.
10.
HorschK., GigeraM.L., VentabL.A. and VybornyC.J., Computerized diagnosis of breast lesions on ultrasound, Med Phys29(2) (2002), 157–164.
11.
DrukkerK., GigerM.L., HorschK., KupinskiM.A. and VybornyC.J., Computerized lesion detection on breast ultrasound, Med Phys29(7) (2002), 1438–1446.
12.
MadabhushiA. and MetaxasD.N., Combining lowhigh-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions, IEEE Trans Med Imag22(2) (2003), 155–169.
13.
HuangY. and ChenD., Watershed segmentation for breast tumor in 2-D sonography, Ultrasound Med Biol30(5) (2004), 625–632.
14.
ChangR.F., WuW.J., MoonW.K. and ChenD., Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors, Breast Cancer Res Treat89 (2005), 179–185.
15.
ChangR.-F., and W.-J.-R, Improvement in Breast Tumor Discrimination By Support vector machine, Ultrasound in Med & Biol29(5) (2003), 679–686.
16.
SehgalC.M., CaryT.W., KangasS.A., WeinsteinS.P., SchultzS.M., ArgerP.H. and ConantE.F., Computer based Margin analysis of breast sonography for differentiating malignant and benign masses, Journal of Ultrasound Med23 (2004), 1201–1209.
17.
JooS., YangY.S., MoonW.K. and KimH., Computer-Aided Diagnosis of Solid Breast Nodules: Use of an artificial neural network based on multiple sonographic features, IEEE Transactions on Medical Imaging23(10) (2004), 1292–1300.
18.
MoonW.K., LoC.M., ChoN., ChangJ.M., HuangC.S., ChenJ.H., et al., Computer-aided diagnosis of breast masses using quantified BI-RADS findings, Computer Methods and Programs in Biomed111 (2013), 84–92.
19.
MoonW.K., ShenY.W., BaeM.S., HuangC.S., ChenJ.H. and ChangR.F., Computer-Aided Tumor Detection Based on Multi-Scale Blob Detection Algorithm in automated Breast Ultrasound Image, IEEE Transactions on medical imaging32(7) (2013), 1191–1200.
20.
JumaataA.K., ZarinaW.E., RahmanW.A., IbrahimA. and MahmudR., Segmentation of Masses from Breast Ultrasound Images using Parametric Active Contour Algorithm, Procedia Social and Behavioral Sciences2010(8), 640–647.
21.
ShanJ, ChengH.D. and WangY., Completely Automated Segmentation Approach for Breast Ultrasound Images Using Multiple-Domain Features, Ultrasound in Med & Biology38(2) (2012), 262–275.
22.
EasleyG., LabateD. and LimW.Q., Sparse directional image representation using the discrete shearlet transform, Applied and computational Harmonic Analysis25(1) (2008), 25–46.
23.
LimW.Q., The discrete shearlet transform: A new directional transform and compactly supported shearlet frames, IEEE Transaction on Image Processing19(5) (2010), 1166–1180.
24.
SmithS.M. and BradyJ.M., SUSAN – A new approach to low level image processing, International Journal of Computer Vision23(1) (1997), 45–78.
25.
OtsuN., A threshold selection method from gray-level histograms, IEEE Trans Sys9(1) (1979), 62–66.
26.
ShijiT.P., RemyaS. and ThomasV., Computer Aided Segmentation of Breast Ultrasound Images Using Scale Invariant Feature Transform (SIFT) and Bag Of Features, Procedia Computer Science, 2017.
27.
MallatS. and HwangW.L., Singularity detection and processing with wavelets, IEEE Trans on Inform Theory38(2), (1992).
28.
ReddyV.K., SiramojuK.K. and SircarP., Object Detection by 2-D Continuous Wavelet Transform, 2014. DOI: 10.1109/CSCI.2014.34
29.
DamervalC. and MeignenS., Blob detection with wavelet maxima lines, IEEE Signal processing letters14(1) (2007), 39–42.
30.
ZhouS., ShiJ., ZhuJ., CaiY. and WangR., Shearlet based texture feature extraction for classification of breast tumor in ultrasound image, Biomedical Signal Processing and Control (2013), 688–696.
31.
VapnikV.N., Statistical Learning Theory, John Wiley & Sons, New York, 1998.
32.
Xin-SheY. and DebS., Cuckoo Search via Levy flights, in Proceedings of World Congress on Nature & Biologically Inspired Computing. DOI 10.1109/NABIC.2009.5393690
33.
UdupaJ.K., LeBlancV.R., SchmidtH., ImielinskaC., SahaP.K., GreveraG.J., ZhugeY., CurrieL.M., MoholtP. and JinY., A methodology for evaluating image segmentation algorithms, Proc SPIE2 (2002), 266–277.
34.
ShanJ., ChengH.D. and WangY., A novel automatic seed point selection algorithm for breast ultrasound images, in 19th International Conference on Pattern Recognition, 2008.
35.
XianM., HuangJ., ZhangY. and TangX., (2012, September) Multiple domain knowledge based MRF model for tumor segmentation in breast ultrasound images. In 2012 19th IEEE international conference on image processing, IEEE, pp. 2021–2024.
36.
LiuY., ChengH.D., HuangJ.H., ZhangY.T. and TangX.L., An effective approach of Lesion segmentation within the breast ultrasound image based on cellular automata, J Digit Imaging25(5) (2012), 580–585.
37.
LiuL., LiK., QinW., WenT., LiL., WuJ. and GuJ., Automated breast tumor detection and segmentation with a novel computational framework of whole ultrasound images, Med Biol Eng Comput56(2) (2018), 183–199.
