Document Type : Original Article


1 Department of Control and Computer Engineering, Politecnico di Torino, Italy

2 Institute of Computer Engineering, University of Luebeck, Luebeck, Germany

3 School of Electronics and Computer Science, University of Southampton, UK


Breast cancer is the most common cancer between women worldwide. Although it is the leading cause of cancer death of women in the world, it can be prevented if it is detected and diagnosed at the early stages. There are various ways of detecting breast cancer varying from mammography to some basic clinical tests and procedures. Automated 3-D breast ultrasound (ABUS) is one of the most advanced breast cancer detection systems which is used as a complementary modality to mammography for early detection of breast cancer. However, it is notable that screening mammograms is so difficult and time consuming for radiologists due to the large variety in shape, size, and texture of 3-D masses in these images. Hence, computer-aided detection (CADe) systems could be considered as a second interpreter in order to assist radiologists to increase accuracy and speed. In this paper, we assess different approaches that have been implemented to segment masses in ABUS images. These approaches vary from pure image processing methods to deep neural networks based on which limits, advantages and disadvantages over each other have been compared.


[1] Jemal, A., Bray, F., Center, M. M., Ferlay, J., Ward, E., Forman, D. (2011). Global cancer statistics, CA. Cancer J. Clin., 61(2), 69–90.
[2] Kozegar, E. (2012). Implementing an efficient algorithm for mass detection in mammograms, MSc thesis, Iran University of Science and Technology.
[3] Siegel, R. L., Miller, K. D., Jemal, A. (2016). “Cancer statistics, 2016,” CA. Cancer J. Clin., 66(1), 7–30.
[4] Fayyaz, H., Soryani, M., Ehsan, K. (2018).  Mass Segmentation in Automated 3D Breast Ultrasound using Deep Learning, Iran. J. Biomed. Eng., 12(2), 137–146.
[5] Kozegar, E., Soryani, M., Behnam, H.,  Salamati, M.,  Tan, T. (2020). Computer aided detection in automated 3-D breast ultrasound images: a survey, Artif. Intell. Rev., 53 (3), 1919-1941.
[6] Tan, T., Gubern-Merida, A.,  Borelli, C., Manniesing, R., Zelst, J., Wang, L., Zhang, W.,  Platel, B.,  Mann, R. M., Karssemeijer, N. (2016). Segmentation of malignant lesions in 3D breast ultrasound using a depth-dependent model, Med. Phys., 43(7), 4074–4084.
[7] Kozegar, E. (2018). Development of Edge-based deformable Model for Mass Segmentation in 3-D Automated Breast Ultrasound Images, Ph.D. thesis School of Computer Engineering, Iran University of Science and Technology.
[8] Cheng, H.D., Shan, J., Ju, W., Guo, Y., Zhang, L. (2010). Automated breast cancer detection and classification using ultrasound images: A survey, Pattern Recognit., 43( 1), 299–317.
[9] Kozegar, E., Soryani, M., Behnam, H.,  Salamati, M.,  Tan, T. (2018). Mass Segmentation in Automated 3-D Breast Ultrasound Using Adaptive Region Growing and Supervised Edge-Based Deformable Model, IEEE Trans. Med. Imaging, 37(4), 918–928.
[10] Kuo, H.C., Giger,  M. L., Reiser, I., Drukker, K., Edwards, A., Sennett, C. A.  (2013). Automatic 3D lesion segmentation on breast ultrasound images, Proceedings of the SPIE, 867025.
[11] Li, C.,  Xu, C.,  Gui, C., Fox, M. D. (2005).Level Set Evolution without Re-Initialization: A New Variational Formulation, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 1, 430–436.
[12] Wang, J., Engelmann, R., Li, Q. (2007). Segmentation of pulmonary nodules in three-dimensional CT images by use of a spiral-scanning technique, Med. Phys., 34(12), 4678–4689.
[13] Kozegar, E., Soryani, M., Behnam, H.,  Salamati, M.,  Tan, T. (2017). Determining Mass Boundary in 3D Automated Breast Ultrasound Images Using a Deformable Model, Iranian Quarterly Journal of Breast Disease, 10(2), 16-26.
[14] Ciresan, D., Giusti, A., Gambardella, L., Schmidhuber, J. (2012). Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images, Advanced in neural information processing systems, 2, 2843-2851.
[15] Ronneberger, O., Fischer, P., Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation,  234-241.
[16] Çiçek, O., Abdulkadir, A., Lienkamp, S. S., Brox, T., Ronneberger. O. (2016). 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. 424-432.