Mamogram Görüntülerindeki Anormallikler İçin LabVIEW ile Makine Öğrenmesi Tabanlı Bilgisayar Destekli Sistem Tasarımı

Abstract

Meme kanseri kadınlarda en sık görülen kanser türü olduğundan ve bu kanser türü genellikle ölüme neden olduğundan, günümüzde meme kanserini tespit etmenin en iyi yolu mamografidir. Birçok bilim insanı, doktor ve mühendis insan hayatındaki bu tür ciddi sorunlarla başa çıkmak için birlikte çalışmaktadır. Bu makalede, YSA ve DVM gibi makine öğrenmesi teknikleri kullanılarak mamogram görüntülerindeki anormallikleri tespit etmek için grafik kodlu bir dile sahip yeni bir bilgisayar destekli sistem geliştirilmesi amaçlanmıştır. Geliştirilen algoritma grafiksel bir kullanıcı arayüzüne (GUI) sahiptir ve tüm sonuçlar burada gösterilmektedir. Algoritma üç farklı aşama kullanılarak oluşturulmuştur. Bunlar görüntü işleme ve kütle segmentasyonu, özellik seçimi ve çıkarımı ve sınıflandırmadır. Sistemin doğruluğunu duyarlılık, özgüllük ve doğruluk olarak test etmek için kırk iyi huylu ve kırk kötü huylu kitle içeren mamogram görüntüleri kullanılmıştır. Duyarlılık, özgüllük ve doğruluk ölçümleri için elde edilen sonuçlar sırasıyla YSA için %95, %97,5 ve %96,25; DVM için %97,5, %97,5 ve %97,5'tir. Kullanıcı arayüzü sayesinde kullanıcı dostu olan algoritmanın, meme kanseri gibi birçok kanserli hücreyi yüksek doğrulukla tespit edebilmesi nedeniyle tercih edilebileceği söylenebilir.

Keywords

• Mamografi
• meme kanseri tespiti
• makine öğrenmesi
• grafiksel kullanıcı arayüzü.

The Design of Machine Learning-Based Computer-Aided System with LabVIEW For Abnormalities in Mammogram Images

Abstract

Mammogram is the best way of breast cancer detection nowadays, as breast cancer is the most common form of cancer in the female gender and this form of cancer usually causes death. Many scientists, doctors, and engineers are working together to deal with such serious issues in human life. This paper, it is aimed to develop a new computer-aided system with a graphical coded language to detect abnormalities in mammogram images by using machine learning technics such as ANN and SVM. The developed algorithm has a graphical user interface (GUI) and all results are shown in there. The algorithm was created using three different stages. These are image processing and mass segmentation, feature selection and extraction, and classification. To test the accuracy of the system as the sensitivity, specificity, and accuracy, mammogram images with forty benign and forty malignant masses were used. The obtained results for measuring the sensitivity, specificity, and accuracy are 95%, 97.5%, and 96.25% for ANN and 97.5%, 97.5%, and 97.5% for SVM, respectively. As can be said that the algorithm, user-friendly due to its user interface, can be preferred because it can detect many cancerous cells such as breast cancer with high accuracy.

Keywords

• Mammography
• breast cancer detection
• machine learning
• graphical user interface

References

1. Heber D. Nutritional oncology Elsevier.2011; 393-404.
2. Rangayyan RM, Neuman MR, Raton EB. Breast cancer and mammography. Biomedical Image Analysis 2005, 22-27.
3. Vanel D. The American College of Radiology (ACR) breast imaging and reporting data system (BI-RADS™): a step towards a universal radiological language?. Eur J Radiol 2007; 61(2): 183.
4. Smith RA, Saslow D, Sawyer KA, Burke W. Costanza ME, Evans III WP, & Sener S. American Cancer Society guidelines for breast cancer screening: update 2003, CA Cancer J Clin, 53(3), 141-169.
5. Alteri R, Barnes, C, Burke A, Gansler T, Gapstur S, Gaudet M, Xu JQ. Breast cancer facts & figures 2013-2014. Atlanta: American Cancer Society.2013,1-38,
6. Giuliano AE, Edge SB, Hortobagyi GN. Eighth edition of the AJCC cancer staging manual: breast cancer. Ann Surg Oncol, 2018; 25(7): 1783-1785.
7. Divyavani M, Kalpana G. An analysis on SVM & ANN using breast cancer dataset. Aegaeum J, 8,2021, 369-379.
8. Guzman- Cabrera R, Guzman-Sepulveda JR, Torres-Cisneros M, May- Arrioja D A, Ruiz-Pinales J, Ibarra-Manzano OG Avina Cervantes C, Gonzalez Parada A. Digital Image Processing Technique for Breast Cancer Detection, Int J Thermophys 2013, Springer Science Business Media New York 2012.

9. Monica Jenefer B, Cyrilraj V. An efcient Image Processing methods for Mammogram Breast Cancer detection, JATIT, 2014, vol,69 No.1.
10. Kumar AS, Bhupendra GA. Novel Approch for Breast Cancer detection and segmentation in a Mammogram. Procedia Comput Sci, 2015;54:676–82.
11. Sonal N. Early detection of Breast Cancer using ANN, IJIRCCE, 2016;4, issue ,14008-14013.
12. Angayarkanni N, Kumar D, Arunachalam G. The Application of Image Process- ing techniques for detection and classifcation of cancerous tissue in Digital Mammograms. JPSR. 2016;8(10):1179–83.
13. Habib D, Eslam AIM, Awais M, Wail E, Mohammed FN. Automated Breast Cancer Diagnosis based on Machine Learning Algorithms, Journal of Health Engineering, volume 2019, Article ID 425341.
14. Akay MF. Support vector machines combined with feature selection for breast cancer diagnosis. Expert Syst Appl 2009;36:3240–7.
15. Muhic I. Fuzzy analysis of breast cancer disease using fuzzy c-means and pattern recognition, Southeast Europe J Soft Comput, 2013;2(1).
16. Abien FMA. On breast cancer detection: an application of machine learning algorithms on the Wisconsin Diagnostic Dataset, ICMLSC 2018.
17. Taha M. Classifcation of mammograms for breast cancer detection using fusion of discrete cosine transform and discrete wavelet transform features. Biomed Res. 2016;27(2):322–7.
18. Ramik R. Breast Cancer Prediction using Machine Learning, JETIR, 2020;7(5).
19. Onega T, Hubbard R, Hill D, Lee CI, Haas JS, Carlos HA, Tosteson AN. Geographic access to breast imaging for US women. Jour of the American Coll of Radiology, 11(9), 874-882,2014.
20. Ball JE, Bruce LM. Digital mammogram spiculated mass detection and spicule segmentation using level sets. In 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,pp. 4979-4984,2007.
21. Ramos RL, Armán FA, García MR, Fariñas IC, Perez EC. Well-circumscribed breast carcinoma. Keys to face the challenge of malignant tumors with a benign appearance. European Congress of Radiology-ECR 2015.
22. Ayres FJ, & Rangayvan, R M. Characterization of architectural distortion in mammograms. IEEE Eng Med Biol Mag, 24(1), 59-67, 2005.
23. Tang J. et. Al, Computer-aided detection and diagnosis of breast cancer with mammography, recent advances. IEEE Trans Inf Technol Biomed, 2009,13(2), 236-251.
24. Smith A. Fundamentals of breast tomosynthesis. White Paper, Hologic Inc., WP-00007, 2008,8.
25. Suckling J, Parker J, Dance D. Mammographic Image Analysis Society (MIAS) database v1.21. [Dataset]. Apollo - University of Cambridge Repository, 2015, https://www.repository.cam.ac.uk/handle/1810/250394
26. Cheng HD, Shi XJ, Min R, Hu LM, Cai XP, Du HN. Approaches for automated detection and classification of masses in mammograms. Pattern Recognit, 2006, 39(4), 646-668.
27. Mencattini A, Salmeri M, Lojacono R, Frigerio M, Caselli F. Mammographic images enhancement and denoising for breast cancer detection using dyadic wavelet processing. IEEE Trans Instrum Meas 2008; 57(7): 1422-1430.
28. Tanyıldızı E, Orhan A. An introduction to variable and feature selection. Comput Appl Eeng Educ 2009; 17(2): 187-195.
29. Mini MG, Thomas T. A neural network method for mammogram analysis based on statistical features. In TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region, 2003, Vol. 4, pp. 1489-1492