CAD System for Breast US Images with Speckle Noise Removal and Bio-inspired Segmentation

• Paulo Sergio S Rodrigues FEI University
• Guilherme Wachs FEI University
• Gilson Giraldi National Laboratory for Scientific Computing
• Celia A. Z. Barcelos Federal University of Uberlândia
• Luciana Vieira Federal University of Uberlândia
• Denise Guliato Federal University of Uberlândia
• Bikesh Singh National Institute of Technology

DOI: https://doi.org/10.5753/sibgrapi.2019.9781

Resumo

Ultrasound (US) images are highly susceptible to speckle-like noise which makes imperative to use specific techniques for image smoothing. However, this process can lead to undesirable side effects such as the degradation of the real contour of the region of interest (ROI). In such context, this paper presents a new methodology for computer aided diagnosis (CAD) systems whose heart is the combination of a method for speckle noise reduction, with histogram equalization and a technique for image segmentation that uses the bio-inspired firefly algorithm and Bayesian model. The segmentation approach and the equalization are applied in two distinct stages: globally and locally. The global application produces an initial coarse estimate of the ROI, and the local application defines this region more precisely. In the classification step we carried out experiments which show that the combination of features computed both within and below the lesion strongly influences the final accuracy. We show that the gray-scale distribution and statistical moments within the lesion together with gray-scale distribution and contrast of the region below the lesion is the combination that produces the better classification results. Experiments in a database of 250 US images of breast anomalies (100 benign and 150 malignant) show that the proposed methodology reaches performance of 95%.

Referências

J. S. Choi, B. K. Han, E. S. Ko, J. M. Bae, E. Y. Ko, S. H. Song, M. R. Kwon, J. H. Shin, S. Y. Hahn, "Effect of a deep learning framework-based computer-aided diagnosis system on the diagnostic performance of radiologists in differentiating between malignant and benign masses on breast ultrasonography", Korean journal of radiology, vol. no. 5, pp. 749-72019.

Z. Zhou, W. Wu, S. Wu, P. H. Tsui, C. C. Lin, L. Zhang, T. Wang, "Semi-automatic breast ultrasound image segmentation based on mean shift and graph cuts", Ultrasonic Imaging, pp. 1-2014.

X. Shi, H. D. Cheng, L. Hu, W. Ju, J. Tian, "Detection and classification of masses in breast ultrasound images", Digital Signal Processing, no. 3, pp. 824-82010.

K. M. Prabusankarlal, T. P, R. Manavalan, "Segmentation of breast lesions in ultrasound images through multiresolution analysis using undecimated discrete wavelet transform", Ultrasonic Imaging, pp. 1-2015.

L. B., H. D. Cheng, J. Huang, J. Tian, X. Tang, J. Liu, "Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images", Pattern Recognition, no. 1, pp. 280-298, 2010.

K. Drukker, C. A. Sennett, M. L. Giger, "Computerized detection of breast cancer on automated breast ultrasound imaging of women with dense breast", Medical Physics, no. 1, pp. 1-2014.

Y. Guo, A. Sengur, J.-W. Tian, "A novel breast ultrasound image segmentation algorithm based on neutrosophic similarity score and level set", Computer Methods and Programs in Biomedicine, vol. 1pp. 43-2016.

C. Barcelos, L. Vieira, "Ultrasound speckle noise reduction via an adaptive edge-controlled variational method", Proceedings of International Conference on Systems Man and Cybernetics (SMC), 2014.

P. Rodrigues, G. Wachs-Lopes, G. Giraldi, H. Erdmann, M. Ribeiro, "Improving a firefly meta-heuristic for multilevel image segmentation using tsallis entropy", Pattern Analysis and Application, vol. no. 1, pp. 1-2015.

B. Ribeiro-Neto, I. Silva, R. Muntz, F. Crestani, G. Pasi, "Bayesian network models for IR" in Soft Computing in Information Retrieval Techniques and Applications, Springer Verlag, pp. 259-291, 2000.

P. S. Rodrigues, G. A. Giraldi, M. Provenzano, M. D. Faria, R. Chang, J. S. Suri, "A new methodology based on q-entropy for breast lesion classification in 3-d ultrasound images", 2006 Int. Conf. of the IEEE Engin. in Medicine and Biology Society, pp. 1048-10Aug 2006.

M. Xian, Y. Zhang, H.-D. Cheng, F. Xu, B. Zhang, J. Ding, "Automatic breast ultrasound image segmentation: A survey", Pattern Recognition, vol. no. 340–32018.

S. Liu, Y. Wang, X. Yang, B. Lei, L. Liu, S. X. Li, D. Ni, T. Wang, "Deep learning in medical ultrasound analysis: A review", Engineering, vol. 5, no. 2, pp. 261-22019.

C. M. Lo, R. T. Chen, Y. C. Chang, Y. W. Yang, M. J. Hung, C. S. Huang, R. F. Chang, "Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed", IEEE Trans. on Medical Imaging, no. 7, pp. 1503-152014.

Z. Zhou, S. Wu, K. J. Chang, W. R. Chen, Y. S. Chen, W. H. Kuo, C. C. Lin, P. H. Tsui, "Classification of benign and malignant breast tumors in ultrasound images with posterior acoustic shadowing using half-contour features", J. Med. Biol. Eng., pp. 178-187, 2015.

A. S. Becker, M. P. Mueller, E. Stoffel, M. Marcon, S. Ghafoor, A. Boss, "Classification of breast cancer in ultrasound imaging using a generic deep learning analysis software: a pilot study", The British journal of radiology, vol. 91, no. 10pp. 1-8, 2017.

S. Han, H.-K. Kang, J.-Y. Jeong, M.-H. Park, W. Kim, W.-C. Bang, Y.-K. Seong, "A deep learning framework for supporting the classification of breast lesions in ultrasound images", Physics in Medicine & Biology, vol. no. pp. 7714-77sep 2017.

V. N. Vapnik, Statistical Learning Theory, John Wiley & Sons, INC., 1998.

Download from Dropbox url, [online] Available: https://goo.gl/ld5dFO.

T. Fawcett, "An introduction to roc analysis", Pattern Recogn. Lett., vol. no. 8, pp. 861-8Jun. 2006.

A. Garcia-Garcia, S. Orts, S. Oprea, V. Villena-Martinez, P. Martinez-Gonzalez, J. G. Rodriguez, "A survey on deep learning techniques for image and video semantic segmentation", Appl. Soft Comput., vol. pp. 41-2018.