Main Article Content

Parinaz Eskandari Shahriar Baradaran Shokouhi


This study proposes a Computer-Aided Diagnosis (CAD) system to detect and identify breast lesions from Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI). The presented CAD system consists of four steps: breast segmentation, lesion detection, feature extraction and lesion classification. For breast segmentation, an atlas-based method using FCM is presented to separate the breast region. By using an Otsu threshold, lesions are detected, and False Positives (FPs) resulted by vessels are reduced using Hessian-based filter. Afterwards, efficient features that boost the discriminative power of classification are extracted from the detected lesions. Dual-Tree Complex Wavelet Transform (DT-CWT) has been extracted in a certain decomposition level as a new feature and then has been applied to improve the classification of tumours into classes of malignant and benign. Typically, tumours are in two forms: mass and non-mass. Since non-mass lesions are more challenging to explore, these types are considered more importantly. The Support Vector Machine (SVM) classifier along with different kernels and combination of Linear Discriminant Analysis (LDA) method and k-Nearest Neighbour (k-NN) classifier are used to evaluate the lesion classification process. By applying the DT-CWT to the SVM classifier, the AUC values of 0.71, 0.77 and 0.70 have been achieved for mass-like lesions, non-mass-like lesions and their combination, respectively. By applying the DT-CWT to the k-NN classifier, the AUC values of 0.70, 0.68 and 0.69 have been resulted for mass-like lesions, non-mass-like lesions and their combination, respectively.

Article Details


Breast DCE-MRI, Atlas-based segmentation, Dual-Tree Complex Wavelet Transform (DT-CWT), SVM classification

[1] F. Khalvati, C. Gallego-Ortiz, S. Balasingham, A.L. Martel. Automated segmentation of breast in 3-D MR images using a robust atlas. IEEE transactions on medical imaging. 34 (2014) 116-25.
[2] S. Hoffmann, J.D. Shutler, M. Lobbes, B. Burgeth, A. Meyer-Bäse. Automated analysis of non-mass-enhancing lesions in breast MRI based on morphological, kinetic, and spatio-temporal moments and joint segmentation-motion compensation technique. EURASIP Journal on Advances in Signal Processing. 2013 (2013) 1-10.
[3] S. Molani, M. Madadi, W. Wilkes. A partially observable Markov chain framework to estimate overdiagnosis risk in breast cancer screening: Incorporating uncertainty in patients adherence behaviors. Omega. 89 (2019) 40-53.
[4] S. Molani, M. Madadi, D. Williams. Investigating the Effectiveness of Breast Cancer Supplemental Screening Considering Radiologists' Bias. medRxiv. (2020).
[5] F.R. Fathabadi, J.L. Grantner, S.A. Shebrain, I. Abdel-Qader. Multi-Class Detection of Laparoscopic Instruments for the Intelligent Box-Trainer System Using Faster R-CNN Architecture. 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI). IEEE2021. pp. 000149-54.
[6] P. Eskandari, S.B. Shokouhi. Automated Atlas-Based Segmentation of Breast Region in 3-D Magnetic Resonance Imaging (MRI) Using FCM Method. Mapta Journal of Electrical and Computer Engineering (MJECE). 3 (2021) 28-34.
[7] F. Ayatollahi, P. Eskandari, S.B. Shokouhi. Differentiating between Benign and Malignant non-Mass Enhancing Lesions in Breast DCE-MRI by Using Curvelet-based Textural Features. 2018 4th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS). IEEE2018. pp. 101-5.
[8] D. Newell, K. Nie, J.-H. Chen, C.-C. Hsu, J.Y. Hon, O. Nalcioglu, et al. Selection of diagnostic features on breast MRI to differentiate between malignant and benign lesions using computer-aided diagnosis: differences in lesions presenting as mass and non-mass-like enhancement. European radiology. 20 (2010) 771-81.
[9] F. Retter, C. Plant, B. Burgeth, G. Botella, T. Schlossbauer, A. Meyer-Bäse. Computer-aided diagnosis for diagnostically challenging breast lesions in DCE-MRI based on image registration and integration of morphologic and dynamic characteristics. EURASIP Journal on Advances in Signal Processing. 2013 (2013) 1-9.
[10] A. Vignati, V. Giannini, M. De Luca, L. Morra, D. Persano, L.A. Carbonaro, et al. Performance of a fully automatic lesion detection system for breast DCE?MRI. Journal of Magnetic Resonance Imaging. 34 (2011) 1341-51.
[11] J. Seaberg, S. Kaabipour, S. Hemmati, J.D. Ramsey. A rapid millifluidic synthesis of tunable polymer-protein nanoparticles. European Journal of Pharmaceutics and Biopharmaceutics. 154 (2020) 127-35.
[12] A. Balal, S. Rukh, S. Balali. Designing a Dual Active Transformer DC-DC Forward Converter for DC Micro-Grid Applications Using LTSPICE. International Journal of Applied Engineering Research. 16 (2021) 327-31.
[13] A. Kokabi, M. Davoodi. Calculation of specific absorption rate (SAR) in human brain neurons using complex permittivity. Journal of medical engineering & technology. 43 (2019) 468-73.
[14] K. Tachibana. Current status of microplasma research. IEEJ Transactions on Electrical and Electronic Engineering. 1 (2006) 145-55.
[15] A. Fooladivanda, S.B. Shokouhi, N. Ahmadinejad. Localized-atlas-based segmentation of breast MRI in a decision-making framework. Australasian physical & engineering sciences in medicine. 40 (2017) 69-84.
[16] A. Fooladivanda, S.B. Shokouhi, N. Ahmadinejad, M.R. Mosavi. Automatic segmentation of breast and fibroglandular tissue in breast MRI using local adaptive thresholding. 2014 21th Iranian Conference on Biomedical Engineering (ICBME). IEEE2014. pp. 195-200.
[17] A. Fooladivanda, S.B. Shokouhi, M.R. Mosavi, N. Ahmadinejad. Atlas-based automatic breast MRI segmentation using pectoral muscle and chest region model. 2014 21th Iranian Conference on Biomedical Engineering (ICBME). IEEE2014. pp. 258-62.
[18] A.F. Frangi, W.J. Niessen, K.L. Vincken, M.A. Viergever. Multiscale vessel enhancement filtering. International conference on medical image computing and computer-assisted intervention. Springer1998. pp. 130-7.
[19] B. Maas, E. Zabeh, S. Arabshahi. QuickTumorNet: Fast Automatic Multi-Class Segmentation of Brain Tumors. 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER). IEEE2021. pp. 81-5.
[20] H. Rafieipour, A. Abdollah Zadeh, A. Moradan, Z. Salekshahrezaee. Study of Genes Associated With Parkinson Disease Using Feature Selection. Journal of Bioengineering Research. 2 (2020) 1-12.
[21] L. Pournajaf, F. Tahmasebian, L. Xiong, V. Sunderam, C. Shahabi. Privacy Preserving Reverse k-Nearest Neighbor Queries. 2018 19th IEEE International Conference on Mobile Data Management (MDM). IEEE Computer Society2018. pp. 177-86.
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The copyright in the text of individual articles (including research articles, opinion articles, book reviews, conference proceedings and abstracts) is the property of their respective authors, subject to a general license granted to Mapta Publishing Group and a Creative Commons CC-BY licence granted to all others, as specified below. The compilation of all content on this site, as well as the design and look and feel of this website are the exclusive property of Mapta Publishing Group.

All contributions to Mapta Publishig Group may be copied and re-posted or re-published in accordance with the Creative Commons licence referred to below.

Articles and other user-contributed materials may be downloaded and reproduced subject to any copyright or other notices.

As an author or contributor you grant permission to others to reproduce your articles, including any graphics and third-party materials supplied by you, in accordance with the Mapta Publishing GroupTerms and Conditions and subject to any copyright notices which you include in connection with such materials. The licence granted to third parties is a Creative Common Attribution ("CC BY") licence. The current version is CC-BY, version 4.0 (, and the licence will automatically be updated as and when updated by the Creative Commons organisation.

How to Cite

Eskandari, P., & Baradaran Shokouhi, S. (2021). DT-CWT: A New Feature for Tumor Classification in Breast DCE-MRI. Mapta Journal of Electrical and Computer Engineering (MJECE), 3(1), 35–39.