Breast cancer diagnosis using abnormalities on ipsilateral views of digital mammograms

• Autorzy: Sapate Suhas , Talbar Sanjay , Mahajan Abhishek , Sable Nilesh , Desai Subhash , Thakur Meenakshi

Identyfikatory

DOI

10.1016/j.bbe.2019.04.008

• Języki publikacji: EN

Abstrakty

EN

Ipsilateral views of digital mammograms help radiologists to localize and confirm abnormal lesions during diagnosis of breast cancers. This study aims at developing algorithms which improve accuracy of computer-aided diagnosis (CADx) for analyzing breast abnormalities on ipsilateral views. The proposed system is a fusion of single and two view systems. Single view approach detects and characterizes suspicious lesions on craniocaudal (CC) and mediolateral oblique (MLO) view separately using geometric and textural features. Lesions detected on each view are paired with potential lesions on another view. The proposed algorithm computes the correspondence score of each lesion pair. Single view information is fused with two views correspondence score to discriminate malignant tumours from benign masses using the SVM classifier. Performance of SVM classifier is assessed using five-fold cross validation (CV), Kappa metric and ROC analysis. Algorithms are applied to 110 pairs of mammograms from local dataset and 74 pairs from open dataset. Single view scheme yielded image-based sensitivity of 91.63% and 88.17% at 1.35 and 1.51 false positives per image (FPs/I) on local and open dataset respectively. Single view classification yielded FPs/I of 1.03 and 1.20 with sensitivity of 70%. Fusion based two views scheme using SVM classifier produced average case-based sensitivity of 75.91% at 0.69 FPs/I and 73.65% at 0.72 FPs/I on local and open dataset respectively. Fusion of single view features with two view correspondence score leads to improved case-based detection sensitivity. Proposed fusion based approach results into accurate and reliable diagnosis of breast abnormalities than single view approach.

Słowa kluczowe

EN

breast cancer; digital mammogram; ipsilateral views; radiomic features; image based sensitivity; case based sensitivity

PL

rak piersi; mammografia cyfrowa; cechy radiomiczne

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 1
• Strony: 290--305
• Opis fizyczny: Bibliogr. 49 poz., rys., tab., wykr.

Twórcy

autor

Sapate Suhas

• SGGS Institute of Engineering & Technology, Nanded, Maharashtra 431606, India; Dept. of CSE, Ashokrao Mane Group of Institutions, Vathar, Kolhapur, Maharashtra, India

autor

Talbar Sanjay

• SGGS Institute of Engineering & Technology, Nanded, Maharashtra, India

autor

Mahajan Abhishek

• Department of Radiodiagnosis, Tata Memorial Centre, Parel, Mumbai, Maharashtra, India

autor

Sable Nilesh

• Department of Radiodiagnosis, Tata Memorial Centre, Parel, Mumbai, Maharashtra, India

autor

Desai Subhash

• Department of Radiodiagnosis, Tata Memorial Centre, Parel, Mumbai, Maharashtra, India

autor

Thakur Meenakshi

• Department of Radiodiagnosis, Tata Memorial Centre, Parel, Mumbai, Maharashtra, India

Bibliografia

• [1] Mahajan A, Goh V, Basu S, Vaish R, Weeks A, Thakur M, et al. Bench to bedside molecular functional imaging in translational cancer medicine: to image or to imagine? Clin Radiol 2015;70(10):1060–82.
• [2] Pawar MM, Talbar SN, Dudhane A. Local binary patterns descriptor based on sparse curvelet coefficients for false-positive reduction in mammograms. J Healthcare Eng 2018;1–16.
• [3] Tzias D, O'Flynn EAM, Allen SD, Wilson ARM. Current status and new developments in breast cancer diagnosis and detection. Eur Oncol Haematol 2013;9(1):21–6.
• [4] He W, Juette A, Denton ERE, Oliver A, Martí R, Zwiggelaar R. A review on automatic mammographic density and parenchymal segmentation. Int J Breast Cancer 2015;1–31 [article ID 276217].
• [5] Giger ML, Karssemeijer N, Schnabel JA. Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer. Annu Rev Biomed Eng 2013;15:327–57.
• [6] Wei J, Chan HP, Sahiner B, Zhou C, Hadjiiski LM, Roubidoux MA, et al. Computer-aided detection of breast masses on mammograms: dual system approach with two-view analysis. Med Phys 2009;36(10):4451–60.
• [7] Sun X, Wei Q, Song D. Ipsilateral-mammogram computer-aided detection of breast cancer. Comput Med Imaging Graph 2004;28:151–8.
• [8] Goudarzi M, Maghooli K. Extraction of fuzzy rules at different concept levels related to image features of mammography for diagnosis of breast cancer. Biocybern Biomed Eng 2018;38(4):1004–14.
• [9] Paquerault S, Petrick N, Chan HP, Sahiner B, Helvie MA. Improvement of computerized mass detection on mammograms: fusion of two-view information. Med Phys 2002;29:238–47.
• [10] Celaya-Padilla Jose M, Guzmán-Valdivia Cesar H, Galván- Tejada Carlos E, Galván-Tejada Jorge I, Gamboa-Rosales Hamurabi, Garza-Veloz Idalia. Contralateral asymmetry for breast cancer detection: a CADx approach. Biocybern Biomed Eng 2018;38:115–25.
• [11] Qian W, Song D, Lei M, Sankar R, Eikman E. Computer-aided mass detection based on ipsilateral multiview mammograms. Acad Radiol 2007;14(5):530–8.
• [12] Blanks RG, Wallis MG, Given-Wilson RM. Observer variability in cancer detection during routine repeat (incident) mammographic screening in a study of two versus one view mammography. J Med Screen 1999;6:152–8.
• [13] Kim SA, Chang JM, Cho N, Yi A, Moon WK. Characterization of breast lesions: comparison of digital breast tomosynthesis and ultrasonography. Korean J Radiol 2015;16(2):229–38.
• [14] Houssami N, Abraham LA, Miglioretti DL, Sickles EA, Kerlikowske K, Buist DSM, et al. Accuracy and outcomes of screening mammography in women with a personal history of early-stage breast cancer. J Am Med Assoc 2011;305(8):790–9.
• [15] Qian W, Song D, Lei M, Sankar R, Eikman E. Computer-aided mass detection based on ipsilateral multiview mammograms. Acad Radiol 2007;14:530–8.
• [16] Sun W, Tseng T, Qian W, Saltzstein EC, Zheng B, Yu H, et al. A new near-term breast cancer risk prediction scheme based on the quantitative analysis of ipsilateral view mammograms. Comput Methods Programs Biomed 2018;155:29–38.
• [17] Vignesh AA, Bonnie NJ, Natalya ML, Jessica WTL, James Brenner R, Flowers CI, et al. Benefit of semiannual ipsilateral mammographic surveillance following breast conservation therapy. Radiology 2012;264(2):371–7.
• [18] Doi K. Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 2007;31:198–211.
• [19] Good WF, Zheng B, Chang YH, Wang ZH, Maitz GS, Gur D. Multi-image CAD employing features derived from ipsilateral mammographic views. Proc. 1999 SPIE 3661 Conference; 1999.
• [20] Chang YH, Good WF, Sumkin JH, Zheng B, Gur D. Computerized localization of breast lesions from two views: an experimental comparison of two methods. Invest Radiol 1999;34(9):585–8.
• [21] Paquerault S, Petrick N, Chan HP, Sahiner B, Dolney AY. Improvement of mammographic lesion detection by fusion of information from different views. Proc. 2001 SPIE 4322; 2001.
• [22] Sahiner B, Petrick N, Chan HP, Paquerault S, Helvie MA, Hadjiiski LM. Recognition of lesion correspondence on two mammographic views – a new method of false-positive reduction for computerized mass detection. Proc. 2001 SPIE 4322; 2001.
• [23] Engeland S, Timp S, Karssemeijer N. Finding corresponding regions of interest in mediolateral oblique and craniocaudal mammographic views. Med Phys 2006;33:3203.
• [24] Zheng B, Leader JK, Abrams GS, Lu AH, Wallace LP, Maitz GS, et al. Multiview-based computer-aided detection scheme for breast masses. Med Phys 2006;33(9):3135–43.
• [25] Yuan Y, Giger ML, Li H, Sennett C. Correlative feature analysis on FFDM. Med Phys 2008;35(12):5490–500.
• [26] Padayachee J, Alport MJ, Rae WD. Mammographic CAD: correlation of regions in ipsilateral views – a pilot study. South Africa J Radiol 2009;48–54.
• [27] Zheng B, Tan B, Ganott MA, Chough DM, Gur D. Matching breast masses depicted on different views: a comparison of three methods. Acad Radiol 2009;16(11):1338–47.
• [28] Samulski M, Karssemeijer N. Optimizing case-based detection performance in a multiview CAD system for mammography. IEEE Trans Med Imaging 2011;30 (4):1001–9.
• [29] Tanner C, Schie G, Lesniak J, Karssemeijer N, Székely G. Improved location features for linkage of regions across ipsilateral mammograms. Med Image Anal 2013;17:1265–72.
• [30] Heath M, Bowyer K, Kopans D. Current status of the digital database for screening mammography. Proc. 1998 4th International Workshop on Digital Mammography; 1998. pp. 457–60.
• [31] Pawar MM, Talbar SN. Local entropy maximization based image fusion for contrast enhancement of mammogram. J King Saud Univ - Comput Inform Sci 2018.
• [32] Gandhamal AP, Talbar SN, Gajre SS, Hani AFM, Kumar D. Local gray level S-curve transformation – a generalized contrast enhancement technique for medical images. Comput Biol Med 2017;83:120–33.
• [33] Baid U, Talbar SS, Talbar SN. Comparative study of K-means, GMM and fuzzy clustering for brain tumour segmentation. Proc. 2016 ICCASP BATU, Lonere International Conference; 2016.
• [34] Bezdek J, Ehrlich R, Full W. Cluster validity with fuzzy sets. Comput Geosci 1984;10(3):191–203.
• [35] Oliver A, Tortajada M, Lladó X, et al. Breast density analysis using an automatic density segmentation algorithm. J Digit Imaging 2015;28(5):604–12.
• [36] Sapate SG, Talbar SN. An overview of pectoral muscle extraction algorithms applied to digital mammograms. In: Dey N, et al., editors. Medical imaging in clinical applications. Singapore: Springer; 2016 [chapter 2].
• [37] Baid U, Talbar SS, Talbar SN. Brain tumour segmentation based on non-negative matrix factorization and fuzzy clustering. Proc. 2017 Int. Conf. on BioImaging; 2017.
• [38] Shirley SS, Shenbaga D. Automatic seed point selection in ultrasound echography images of breast using texture features. Biocybern Biomed Eng 2015;35(3):157–68.
• [39] Sapate SG, Mahajan A, Talbar SN, Sable N, Desai S, Thakur M. Radiomics based detection and characterization of suspicious lesions on full field digital mammograms. Comput Meth Program Biomed 2018;163:1–20.
• [40] Wierzchowska MD, Borys D, Billewicz BB, Jarzab M, Swierniak A. Simplification of breast deformation modelling to support breast cancer treatment planning. Biocybern Biomed Eng 2016;36:531–6.
• [41] Lahmiri S, Boukadoum M. DWT and RT-based approach for feature extraction and classification of mammograms with SVM. Proc. 2011 IEEE Biomedical Circuits and Systems Conference (BioCAS); 2011.
• [42] Lahmiri S, Boukadoum M. Hybrid discrete wavelet transform and Gabor filter banks processing for mammogram features extraction. Proc. 2011 IEEE 9th International New Circuits and Systems Conference; 2011.
• [43] Vert JP, Tsuda K, Bernhard S. A primer on kernel methods. Kernel Meth Comput Biol 2004;47:35–70.
• [44] Lahmiri S, Boukadoum M. Hybrid discrete wavelet transform and Gabor filter banks processing for features extraction from biomedical images. J Med Eng 2013;13 [article ID 104684].
• [45] Tourassi GD, Vargas-Voracek R, Catarious DM, Floyd CE. Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information. Med Phys 2003;30(8):2123–30.
• [46] Filev P, Hadjiiski L, Sahiner B, Chan H, Helvie M. Comparison of similarity measures for the task of template matching of masses on serial mammograms. Med Phys 2005;32(2):515–29.
• [47] Samulski M, Karssemeijer N. Matching mammographic regions in mediolateral oblique and cranio caudal views: a probabilistic approach. In: Giger ML, Karssemeijer N, editors. Proc. 2008 SPIE Medical Imaging Conference. 2008.
• [48] Lahmiri S, Boukadoum M. Hybrid cosine and Radon transform-based processing for digital mammogram feature extraction and classification with SVM. Proc. 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2011.
• [49] Chapelle O. Training a support vector machine in the primal. Neural Comput 2007;19(5):1155–78.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).