Research Article
BibTex RIS Cite

R-CNN Metodoloji Vasıtasıyla Kütlelerin Tespit Edilerek Klasifiye Edilmesi; Türetilen Renkli Mamogramlar Üzerine Bir Çalışma

Year 2022, Volume: 2 Issue: 1, 1 - 9, 29.06.2022

Abstract

Bu çalışma, uzmanlara mamogram görüntülerinde meme kitlelerini tespit etmesine yardımcı olan bir hesaplamalı metodoloji sunmaktadır. Metodolojinin ilk aşaması, mamogram görüntüsünü iyileştirmeyi amaçlar. Bu aşama, memenin dışındaki nesnelerin çıkarılması, gürültünün azaltılması ve memenin iç yapılarının vurgulanmasından oluşur. Daha sonra, hücresel sinir ağları kütle içerebilecek bölgeleri bölümlere ayırmak için kullanılır. Bu sistem dahilinde; Maske R-CNN tabanlı vücut kütlesi tanıma segmentasyonu ile birlikte yönlendirilmiş renk tayfı ön işlemine tutulmuş mammogramlar kullanılmaktadır. Bu bölgelerin şekilleri, şekil tanımlayıcıları analiz edilir ve dokuları jeoistatistik fonksiyonlarla (Ripley's K fonksiyonu ve Moran's ve Geary's indeksleri) analiz edilir. Çok ölçekli morfolojik eleme, Maske R-CNN performansını iyileştirmek için kütle benzeri desenleri artırarak gri tonlamalı mamogramları yönlenmeli renkli resimlere dönüştürür. Genel veri seti üzerinde test edildiğinde, bu çalışma kapsamındaki vakaların ~%65'inin, uygun şekilde ayrılmış veya yayılmış 4687 pikselle temsil edildiği görüldü ve ortalama geçerli bir pozitif oran elde edildi.

References

  • 1. Siegel R, DeSantis C, Jemal A. Colorectal cancer statistics. CA Cancer J. Clin, 2014, 64(2): 104-17.
  • 2. Harford J.B. Breast-cancer early detection in low-income and middle-income countries: do what you can versus one size fits all. Lancet Oncol, 2011; 12(3): 306-12.
  • 3. Lerman C, Daly M, Sands C, Balshem A, Lustbader E, Heggan T, etal. Mammography adherence and psychological distress among women at risk for breast cancer. JNCI-J Natl Cancer I, 1993; 85(13): 1074-80.
  • 4. Tzikopoulos S.D, Mavroforakis M.E, Georgiou H.V, Dimitropoulos N, Theodoridis S. A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry. Comput Meth Prog Bıo, 2011; 102(1): 47-63.
  • 5. Sampaio W.B, Diniz E.M, Silva A.C, De Paiva A.C. Gattass M. Detection of masses in mammogram images using CNN geostatistic functions and SVM. Comput. Biol. Med, 2011; 41(8): 653-64.
  • 6. Taghanaki S.A, Kawahara J, Miles B, Hamarneh G. Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification. Comput. Methods Programs Biomed, 2017; 145: 85-93.
  • 7. Saidin N, Ngah UK, Sakim H.A.M, Siong D. N, Hoe M.K, Shuaib I.L. Density based breast segmentation for mammograms using graph cut and seed based region growing techniques. IEEE, 2010: 246-50.
  • 8. Wang Z, Li M, Wang H, Jiang H, Yao Y, Zhang H, etal. Breast cancer detection using extreme learning machine based on feature fusion with CNN deep features. IEEE Access, 2019; 7: 105146-58.
  • 9. Xu S, Liu H, Song E. Marker-controlled watershed for lesion segmentation in mammograms. J. Digit. Imaging, 2011; 24 (5): 754-63.
  • 10. Carneiro G, Nascimento J, Bradley A.P. Automated analysis of unregistered multi-view mammograms with deep learning. IEEE Trans Med Imaging, 2017; 36(11): 2355-65.
  • 11. Gan H, Li Z, Fan Y, Luo Z. Dual learning-based safe semi-supervised learning. IEEE Access, 2017; 6: 2615-21.
  • 12. Chiao J.Y, Chen K Y, Liao K.Y.K, Hsieh P.H, Zhang G. Huang T.C. Detection and classification the breast tumors using mask R-CNN on sonograms. Medicine, 2019;98(19):e15200. doi: 10.1097/MD.0000000000015200
  • 13. Soukup T, Davidson I. Visual data mining: Techniques and tools for data visualization and mining. New York, John Wiley & Sons, 2002.
  • 14. Zarándy Á, Roska T, Liszka G, Hegyesi J, Kék L, Rekeczky C. Design of analogic CNN algorithms for mammogram analysis. CNNA-94 Third IEEE International Workshop on Cellular Neural Networks and their Applications IEE, 1994.
  • 15. Costa D.D, Campos L.F, Barros A.K, Silva A.C. Independent component analysis in breast tissues mammograms images classification using lda and svm. 2007 6th International Special Topic Conference on Information Technology Applications in Biomedicine IEEE, 2007: 231-4.
  • 16. Pereira D.C, Nascimento M.Z, Ramos R.P, Dantas R. D. Automatic detection of breast masses using two-view mammography. World Congress on Medical Physics and Biomedical Engineering, 2009: 917-20.
  • 17. Ribli D, Horváth A, Unger Z, Pollner P, Csabai I. Detecting and classifying lesions in mammograms with deep learning. Sci. Rep, 2018; 8(1): 1-7.
  • 18. Agarwal R, Díaz O, Yap M.H, Llado X, Marti R. Deep learning for mass detection in Full Field Digital Mammograms. Comput. Biol. Med, 2020; 121: 103774.

Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms

Year 2022, Volume: 2 Issue: 1, 1 - 9, 29.06.2022

Abstract

This study provides a computational methodology that helps experts detect breast masses on mammogram images. The first phase of the methodology aims to improve the mammogram image. This phase consists of removing objects outside the breast, reducing noise, and emphasizing the internal structures of the breast. Then, cellular neural networks are used to compartmentalize regions that may contain mass. Masked R-CNN-based body mass recognition segmentation and guided color spectrum preprocessed mammograms are employed in this approach. The shapes, shape descriptors of these regions are analyzed and their textures are analyzed with geostatistical functions (Ripley's K function and Moran's and Geary's indices). Multiscale morphological screening improves Mask R-CNN performance by converting grayscale mammograms into directed color pictures by boosting mass-like patterns. When tested on the general dataset, ~65% of the cases covered in this study were represented by 4687 pixels appropriately separated or spanned, resulting in an average valid positive rate.

References

  • 1. Siegel R, DeSantis C, Jemal A. Colorectal cancer statistics. CA Cancer J. Clin, 2014, 64(2): 104-17.
  • 2. Harford J.B. Breast-cancer early detection in low-income and middle-income countries: do what you can versus one size fits all. Lancet Oncol, 2011; 12(3): 306-12.
  • 3. Lerman C, Daly M, Sands C, Balshem A, Lustbader E, Heggan T, etal. Mammography adherence and psychological distress among women at risk for breast cancer. JNCI-J Natl Cancer I, 1993; 85(13): 1074-80.
  • 4. Tzikopoulos S.D, Mavroforakis M.E, Georgiou H.V, Dimitropoulos N, Theodoridis S. A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry. Comput Meth Prog Bıo, 2011; 102(1): 47-63.
  • 5. Sampaio W.B, Diniz E.M, Silva A.C, De Paiva A.C. Gattass M. Detection of masses in mammogram images using CNN geostatistic functions and SVM. Comput. Biol. Med, 2011; 41(8): 653-64.
  • 6. Taghanaki S.A, Kawahara J, Miles B, Hamarneh G. Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification. Comput. Methods Programs Biomed, 2017; 145: 85-93.
  • 7. Saidin N, Ngah UK, Sakim H.A.M, Siong D. N, Hoe M.K, Shuaib I.L. Density based breast segmentation for mammograms using graph cut and seed based region growing techniques. IEEE, 2010: 246-50.
  • 8. Wang Z, Li M, Wang H, Jiang H, Yao Y, Zhang H, etal. Breast cancer detection using extreme learning machine based on feature fusion with CNN deep features. IEEE Access, 2019; 7: 105146-58.
  • 9. Xu S, Liu H, Song E. Marker-controlled watershed for lesion segmentation in mammograms. J. Digit. Imaging, 2011; 24 (5): 754-63.
  • 10. Carneiro G, Nascimento J, Bradley A.P. Automated analysis of unregistered multi-view mammograms with deep learning. IEEE Trans Med Imaging, 2017; 36(11): 2355-65.
  • 11. Gan H, Li Z, Fan Y, Luo Z. Dual learning-based safe semi-supervised learning. IEEE Access, 2017; 6: 2615-21.
  • 12. Chiao J.Y, Chen K Y, Liao K.Y.K, Hsieh P.H, Zhang G. Huang T.C. Detection and classification the breast tumors using mask R-CNN on sonograms. Medicine, 2019;98(19):e15200. doi: 10.1097/MD.0000000000015200
  • 13. Soukup T, Davidson I. Visual data mining: Techniques and tools for data visualization and mining. New York, John Wiley & Sons, 2002.
  • 14. Zarándy Á, Roska T, Liszka G, Hegyesi J, Kék L, Rekeczky C. Design of analogic CNN algorithms for mammogram analysis. CNNA-94 Third IEEE International Workshop on Cellular Neural Networks and their Applications IEE, 1994.
  • 15. Costa D.D, Campos L.F, Barros A.K, Silva A.C. Independent component analysis in breast tissues mammograms images classification using lda and svm. 2007 6th International Special Topic Conference on Information Technology Applications in Biomedicine IEEE, 2007: 231-4.
  • 16. Pereira D.C, Nascimento M.Z, Ramos R.P, Dantas R. D. Automatic detection of breast masses using two-view mammography. World Congress on Medical Physics and Biomedical Engineering, 2009: 917-20.
  • 17. Ribli D, Horváth A, Unger Z, Pollner P, Csabai I. Detecting and classifying lesions in mammograms with deep learning. Sci. Rep, 2018; 8(1): 1-7.
  • 18. Agarwal R, Díaz O, Yap M.H, Llado X, Marti R. Deep learning for mass detection in Full Field Digital Mammograms. Comput. Biol. Med, 2020; 121: 103774.
There are 18 citations in total.

Details

Primary Language English
Subjects Health Care Administration
Journal Section Research Articles
Authors

Şükran Yaman Atcı 0000-0002-6600-4157

Fatma Kosavalı Çavuş This is me 0000-0003-2725-2876

Publication Date June 29, 2022
Published in Issue Year 2022 Volume: 2 Issue: 1

Cite

APA Yaman Atcı, Ş., & Kosavalı Çavuş, F. (2022). Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms. Abant Sağlık Bilimleri Ve Teknolojileri Dergisi, 2(1), 1-9.
AMA Yaman Atcı Ş, Kosavalı Çavuş F. Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms. SABİTED. June 2022;2(1):1-9.
Chicago Yaman Atcı, Şükran, and Fatma Kosavalı Çavuş. “Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms”. Abant Sağlık Bilimleri Ve Teknolojileri Dergisi 2, no. 1 (June 2022): 1-9.
EndNote Yaman Atcı Ş, Kosavalı Çavuş F (June 1, 2022) Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms. Abant Sağlık Bilimleri ve Teknolojileri Dergisi 2 1 1–9.
IEEE Ş. Yaman Atcı and F. Kosavalı Çavuş, “Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms”, SABİTED, vol. 2, no. 1, pp. 1–9, 2022.
ISNAD Yaman Atcı, Şükran - Kosavalı Çavuş, Fatma. “Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms”. Abant Sağlık Bilimleri ve Teknolojileri Dergisi 2/1 (June 2022), 1-9.
JAMA Yaman Atcı Ş, Kosavalı Çavuş F. Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms. SABİTED. 2022;2:1–9.
MLA Yaman Atcı, Şükran and Fatma Kosavalı Çavuş. “Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms”. Abant Sağlık Bilimleri Ve Teknolojileri Dergisi, vol. 2, no. 1, 2022, pp. 1-9.
Vancouver Yaman Atcı Ş, Kosavalı Çavuş F. Body-Mass Recognition and Subdivision With R-CNN Methodology; A Case Study on Pseudocolor Mammograms. SABİTED. 2022;2(1):1-9.