Abstract
Purpose
In this study, we propose a new computer-aided diagnosis (CADx) to distinguish between malign and benign mass and non-mass lesions in breast DCE-MRI. For this purpose, we introduce new frequency textural features.
Methods
In this paper, we propose novel normalized frequency-based features. These are obtained by applying the dual-tree complex wavelet transform to MRI slices containing a lesion for specific decomposition levels. The low-pass and band-pass frequency coefficients of the dual-tree complex wavelet transform represent the general shape and texture features, respectively, of the lesion. The extraction of these features is computationally efficient. We employ a support vector machine to classify the lesions, and investigate modified cost functions and under- and oversampling strategies to handle the class imbalance.
Results
The proposed method has been tested on a dataset of 80 patients containing 103 lesions. An area under the curve of 0.98 for the mass and 0.94 for the non-mass lesions is obtained. Similarly, accuracies of 96.9% and 89.8%, sensitivities of 93.8% and 84.6% and specificities of 98% and 92.3% are obtained for the mass and non-mass lesions, respectively.
Conclusion
Normalized frequency-based features can characterize benign and malignant lesions efficiently in both mass- and non-mass-like lesions. Additionally, the combination of normalized frequency-based features and three-dimensional shape descriptors improves the CADx performance.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
Different parameters are due to different protocols.
References
Fusco R, Sansone M, Filice S, Carone G, Amato DM, Sansone C, Petrillo A (2016) Pattern recognition approaches for breast cancer DCE-MRI classification: a systematic review. J Med Biol Eng 36(4):449–459
Teuwen J, Mann R, Moriakov N (2019) AI applications in breast imaging. Artif Hype 19(2):157–160
Wanders JO, Holland K, Veldhuis WB, Mann RM, Pijnappel RM, Peeters PH, van Gils CH, Karssemeijer N (2017) Volumetric breast density affects performance of digital screening mammography. Breast Cancer Res Treat 162:95–103
Emaus MJ, Bakker MF, Peeters PH, Loo CE, Mann RM, de Jong MD, Bisschops RH, Veltman J, Duvivier KM, Lobbes MB, Pijnappel RM, Karssemeijer N, de Koning HJ, van den Bosch MA, Monninkhof EM, Mali WP, Veldhuis WB, van Gils CH (2015) MR Imaging as an additional screening modality for the detection of breast cancer in women aged 50–75 years with extremely dense breasts: the DENSE trial study design. Radiology 277:527–537
Dalmiş MU, Gubern-Mérida A, Vreemann S, Bult P, Karssemeijer N, Mann R, Teuwen J (2019) Artificial intelligence-based classification of breast lesions imaged with a multiparametric breast MRI protocol with ultrafast DCE-MRI, T2, and DWI. Invest Radiol 54(6):325–332
Vreemann S, Gubern-Merida A, Lardenoije S, Bult P, Karssemeijer N, Pinker K, Mann R (2018) The frequency of missed breast cancers in women participating in a high-risk MRI screening program. Breast Cancer Res Treat 169(2):323–331
Singh S, Maxwell J, Baker JA, Nicholas JL, Lo JY (2011) Computer-aided classification of breast masses: performance and interobserver variability of expert radiologists versus residents. Radiology 258:73–80
Sahiner B, Chan HP, Roubidoux MA, Hadjiiski LM, Helvie MA, Paramagul C, Bailey J, Nees AV, Blane C (2007) Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy. Radiology 242:716–724
Edwards SD, Lipson JA, Ikeda DM, Lee JM (2013) Updates and revisions to the BI-RADS magnetic resonance imaging lexicon. Magn Resonance Imaging Clin 21(3):483–493
Gallego-Ortiz C, Martel AL (2014) Classification of breast lesions presenting as mass and non-mass lesions. Proc SPIE Med Imaging 9035:521–528. https://doi.org/10.1117/12.2043774
Cheng L, Li X (2012) Breast magnetic resonance imaging: non-mass-like enhancement. Gland Surg 1(3):176–188
Yabuuchi H, Matsuo Y, Kamitani T, Setoguchi T, Okafuji T, Soeda H, Sakai S, Hatakenaka M, Kubo M, Tokunaga E, Yamamoto H, Honda H (2010) Non-mass-like enhancement on contrast-enhanced breast MRI imaging: lesion characterization using combination of dynamic contrast-enhanced and diffusion-weighted mr images. Eur J Radiol 75:126–132
Hoffmann S, Shutler JD, Lobbes M, Burgeth B, Meyer-Bäse A (2013) 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 J Adv Signal Process 2013:172
Newell D, Nie K, Chen JH, Hsu CC, Yu HJ, Nalcioglu O, Su MY (2010) 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. Eur Radiol 20(4):771–781
Gallego-Ortiz C, Martel AL (2016) Improving the accuracy of computer-aided diagnosis for breast MR imaging by differentiating between mass and nonmass lesions. Radiology 278(3):679–688
Shokouhi SB, Fooladivanda A, Ahmadinejad N (2017) Computer-aided detection of breast lesions in DCE-MRI using region growing based on fuzzy C-means clustering and vesselness filter. EURASIP J Adv Signal Process 2017:39
Chen W, Giger ML, Bick U (2006) A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images. Acad Radiol 13(1):63–72
Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW (2010) elastix: a toolbox for intensity based medical image registration. IEEE Trans Med Imaging 29(1):196–205
Sansone M, Fusco R, Petrillo A, Petrillo M, Bracale M (2011) An expectation-maximisation approach for simultaneous pixel classification and tracer kinetic modelling in dynamic contrast enhanced-magnetic resonance imaging. Med Biol Eng Comput 49(4):485–495
Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithm. Plenum, New York
Kingsbury NG (2001) Complex wavelets for shift invariant analysis and filtering of signals. Appl Comput Harmonic Anal 10(3):234–253
Selesnick IW, Baraniuk RG, Kingsbury NG (2005) The dual-tree complex wavelet transform. IEEE Signal Process Mag 22(6):123–151
Ayatollahi F, Raie AA, Hajati F (2015) Expression-invariant face recognition using depth and intensity dual-tree complex wavelet transform features. J Electron Imaging 24(2):1–13
Huang YH, Chang YC, Huang CS, Wu TJ, Chen JH, Chang RF (2013) Computer-aided diagnosis of mass-like lesion in breast MRI: differential analysis of the 3-D morphology between benign and malignant tumors. Comput Methods Programs Biomed 112(3):508–517
Kang P, Cho S (2006) EUS SVMs: ensemble of under-sampled SVMs for data imbalance problems. In: International conference on neural information processing (ICONIP 2006), pp 837–846
Chawla NV, Bowyer K, Hall LO, Kegelmeyer W (2002) SMOTE: synthetic minority oversampling techniques. J Artif Intell Res 16:321–357
Agner SC, Soman S, Libfeld E, McDonald M, Thomas K, Englander S, Rosen MA, Chin D, Nosher J, Madabhushi A (2011) Textural kinetics: a novel dynamic contrast-enhanced (DCE)-MRI feature for breast lesion classification. J Digit Imaging 24(3):446–463
Milenković J, Hertl K, Košir A, Žibert J, Tasič JF (2013) Characterization of spatiotemporal changes for the classification of dynamic contrast-enhanced magnetic-resonance breast lesions. Artif Intell Med 58(2):101–114
Honda E, Nakayama R, Koyama H, Yamashita A (2016) Computer-aided diagnosis scheme for distinguishing between benign and malignant masses in breast DCE-MRI. J Digit Imaging 29(3):388–393
Lu W, Li Z, Chu J (2017) A novel computer-aided diagnosis system for breast MRI based on feature selection and ensemble learning. Comput Biol Med 83:157–165
Rasti R, Teshnehlab M, Phung SL (2017) Breast cancer diagnosis in DCE-MRI using mixture ensemble of convolutional neural networks. Pattern Recognit 72:381–390
Tahmassebi A, Ngo D, Garcia A, Castillo E, Morales DP, Pinker-Domenig K, Lobbes M, Meyer-Bäse A (2018) Multi-level analysis of spatio-temporal features in non-mass enhancing breast tumors. In: Smart biomedical and physiological sensor technology XV 10662
Retter F, Plant C, Burgeth B, Botella G, Schlossbauer T, Meyer-Bäse A (2013) Computer-aided diagnosis for diagnostically challenging breast lesions in DCE-MRI based on image registration and integration of morphologic and dynamic characteristics. EURASIP J Adv Signal Process 2013:157
Acknowledgements
This research is partially supported by the Iran National Science Foundation (INSF). The authors would like to thank the Noor Medical Imaging Center and the Valiasr MRI Center in Tehran, Iran, for their help and cooperation in providing the datasets used in this study.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. For this type of study, formal consent is not required.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ayatollahi, F., Shokouhi, S.B. & Teuwen, J. Differentiating benign and malignant mass and non-mass lesions in breast DCE-MRI using normalized frequency-based features. Int J CARS 15, 297–307 (2020). https://doi.org/10.1007/s11548-019-02103-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-019-02103-z