Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

An Automatic Breast Mass Segmentation based on Deep Learning on Mammogram

유방 영상에서 딥러닝 기반의 유방 종괴 자동 분할 연구

  • Kwon, So Yoon (Dept. of Biomedical Eng., School of Health Science, Gachon University) ;
  • Kim, Young Jae (Dept. of Biomedical Eng., School of Medicine, Gachon University) ;
  • Kim, Gwang Gi (Dept. of Biomedical Eng., School of Medicine, Gachon University)
  • Received : 2018.09.04
  • Accepted : 2018.10.26
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Breast cancer is one of the most common cancers in women worldwide. In Korea, breast cancer is most common cancer in women followed by thyroid cancer. The purpose of this study is to evaluate the possibility of using deep - run model for segmentation of breast masses and to identify the best deep-run model for breast mass segmentation. In this study, data of patients with breast masses were collected at Asan Medical Center. We used 596 images of mammography and 596 images of gold standard. In the area of interest of the medical image, it was cut into a rectangular shape with a margin of about 10% up and down, and then converted into an 8-bit image by adjusting the window width and level. Also, the size of the image was resampled to $150{\times}150$. In Deconvolution net, the average accuracy is 91.78%. In U-net, the average accuracy is 90.09%. Deconvolution net showed slightly better performance than U-net in this study, so it is expected that deconvolution net will be better for breast mass segmentation. However, because of few cases, there are a few images that are not accurately segmented. Therefore, more research is needed with various training data.

Keywords

MTMDCW_2018_v21n12_1363_f0001.png 이미지

Fig. 1. Deconvolution net for automated segmentation of breast mass.

MTMDCW_2018_v21n12_1363_f0002.png 이미지

Fig. 2. U-net for automated segmentation of breast mass.

MTMDCW_2018_v21n12_1363_f0003.png 이미지

Fig. 3. Results of breast mass segmentation. (a) Original, (b) Gold standard, (c) Deconvolution net, (d) U-net.

MTMDCW_2018_v21n12_1363_f0004.png 이미지

Fig. 4. Bland-Altman plot on comparison of Gold standard and Deconvolution net.

MTMDCW_2018_v21n12_1363_f0005.png 이미지

Fig. 5. Bland-Altman plot on comparison of Gold standard and U-net.

MTMDCW_2018_v21n12_1363_f0006.png 이미지

Fig. 6. Results that are not accurately segmented. (a) Original, (b) Gold standard, (c) Deconvolution net, (d) U-net.

Table 1. Comparison of Deconvolution net and U-net.

MTMDCW_2018_v21n12_1363_t0001.png 이미지

References

  1. Korea Breast Cancer Foundation, http://www.kbcf.or.kr/bhi/bhi_info/present/occurrence_rate_foreign.do (accessed Aug., 11, 2018).
  2. National Cancer Information Center, https://www.cancer.go.kr/lay1/program/S1T211C217/cancer/view.do?cancer_seq=4757 (accessed Aug., 11, 2018).
  3. B.R. Lee and M.J. Lee, "Automatic Detection of Initial Positions for Mass Segmentation in Digital Mammograms," Journal of Korea Multimedia Society, Vol. 13, No. 5, pp. 702-709, 2010.
  4. Diagnosis and Reatment of Breast Cancer, http://www.ksoem.or.kr/files/_etc/edu_data/1511927 858393_05_%EC%9C%A0%EB%B0%A9%EC%95%94_%EA%B9%80%EC%84%B8%EC%A4%91.pdf (accessed Aug., 11, 2018).
  5. J.E. Oh, Y.W. Bae, K.G. Kim, E.Y. Chae, H.H. Kim, S.Y. Lee, et al., "Automatic Computer-Aided Detection of Mass using Digital Mammography with Dense Breast," Proceeding of The Institute of Electronics Engineers of Korea, pp. 1484-1487, 2016.
  6. Trends of Cognitive Radio, http://www.itfind.or.kr/publication/regular/periodical/read.do?selectedId=02-001-150915-000002 (accessed Aug., 11, 2018).
  7. Misdiagnosis(2017), https://www.kca.go.kr/brd/m_32/down.do?brd_id=G004&seq=2269&data_tp=A&file_seq=1 (accessed Aug., 11, 2018).
  8. H. Lee, M. Park, and J. Kim, "Deep Learning in Medical Imaging," The Korean Society of Radiology, Vol. 20, No. 1, pp. 13-18, 2014.
  9. A. Isin, C. Direkoglu, and M. Sah, “Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods,” Procedia Computer Science, Vol. 102, No. 50, pp. 317-324, 2016. https://doi.org/10.1016/j.procs.2016.09.407
  10. A. Pinto, V. Alves, and C.A. Silva, “Brain Tumor Segmentation using Convolutional Neural Networks in MRI Images,” IEEE Transactions on Medical Imaging, Vol. 35, No. 5, pp. 1240-1251, 2016. https://doi.org/10.1109/TMI.2016.2538465
  11. J. Zhang, A. Saha, Z. Zhu, and M.A. MZazurowski, "Breast Tumor Segmentation in DCEMRI using Fully Convolutional Networks with an Application in Radiogenomics," Proceeding of Medical Imaging 2018: Computer-Aided Diagnosis, pp. 105750U, 2018.
  12. G. Carneiro and A.P. Bradley, "Deep structured learning for mass segmentation from mammograms," Proceeding of IEEE International Conference on Image Processing, pp. 2950-2954, 2015.
  13. J. Long, E. Shelhamer, and T. Darrell, "Fully Convolutional Networks for Semantic Segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, Issue 4, pp. 3431-3440, 2015.
  14. H. Noh, S. Hong, and B. Han, "Learning Deconvolution Network for Semantic Segmentation," Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1520-1528, 2015.
  15. O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," Proceeding of International Conference on Medical Image Computing and Computer-Assisted intervention, pp. 234-241, 2015.
  16. T. von Eicken, a. Basu, V. Buch, and W. Vogels, "U-Net," Proceeding of the Fifteenth ACM Symposium on Operating Systems Principles, Vol. 29, No. 5, pp. 40-53, 1995.
  17. A. Popovic, M. de la Fuente, M. Engelhardt, and K. Radermacher, “Statistical Validation Metric for Accuracy Assessment in Medical Image Segmentation,” International Journal of Computer Assisted Radiology and Surgery, Vol. 2, No. 3-4, pp. 169-181, 2007. https://doi.org/10.1007/s11548-007-0125-1

Cited by

  1. Classification of Alzheimer's Disease with Stacked Convolutional Autoencoder vol.23, pp.2, 2018, https://doi.org/10.9717/kmms.2020.23.2.216
  2. 딥러닝 기술을 이용한 캐비테이션 자동인식에 대한 연구 vol.58, pp.2, 2018, https://doi.org/10.3744/snak.2021.58.2.105