Inception V3를 이용한 뇌 실질 MRI 영상 분류의 정확도 평가

Accuracy Evaluation of Brain Parenchymal MRI Image Classification Using Inception V3

  • 김지율 (부산가톨릭대학교 보건과학대학 방사선학과) ;
  • 예수영 (부산가톨릭대학교 보건과학대학 방사선학과)
  • Kim, Ji-Yul (Dept. of Radiological Science, Catholic University of Pusan) ;
  • Ye, Soo-Young (Dept. of Radiological Science, Catholic University of Pusan)
  • 투고 : 2019.09.24
  • 심사 : 2019.09.30
  • 발행 : 2019.09.30

초록

의료영상으로 생성된 데이터의 양은 전문적인 시각적 분석 한계를 점점 초과하여, 자동화된 의료영상 분석의 필요성이 증가되고 있는 실정이다. 이러한 이유 등으로 인하여 본 논문에서는 정상소견과 종양소견을 보이는 각각의 뇌 실질 MRI 의료영상을 이용하여 Inception V3 딥러닝 모델을 이용한 종양 유무에 따른 분류 및 정확도를 평가하였다. 연구 결과, 딥러닝 모델의 정확도 평가는 학습 데이터 세트의 경우 90%, 검증 데이터 세트의 경우 86%의 정확도를 나타내었다. 손실률 평가에서는 학습 데이터 세트의 경우 0.56, 검증 데이터 세트의 경우 1.28의 손실률을 나타내었다. 향 후 연구에서는 딥러닝 모델의 성능 향상 및 평가의 신뢰성 확보를 위하여 공개된 의료영상의 데이터를 충분히 확보하고, 라벨링 분류 작업을 통한 라벨링의 정확도를 개선하여 모델링을 구현해 볼 필요가 있다고 사료된다.

The amount of data generated from medical images is increasingly exceeding the limits of professional visual analysis, and the need for automated medical image analysis is increasing. For this reason, this study evaluated the classification and accuracy according to the presence or absence of tumor using Inception V3 deep learning model, using MRI medical images showing normal and tumor findings. As a result, the accuracy of the deep learning model was 90% for the training data set and 86% for the validation data set. The loss rate was 0.56 for the training data set and 1.28 for the validation data set. In future studies, it is necessary to secure the data of publicly available medical images to improve the performance of the deep learning model and to ensure the reliability of the evaluation, and to implement modeling by improving the accuracy of labeling through labeling classification.

키워드

참고문헌

  1. Sin hong Kim, "Brain MRI semi-automatic segmentation algorithm for medical image contents," The Korea Contents Society, vol. 5, no. 3, pp. 45-51, Jun, 2005.
  2. Da him Choi, Seongeun Hong, "Medical Image based Cancer Prognosis Prediction AI Technology : Mainly on lung cancer,"The Journal of The Korean institute of Communication Sciences, vol. 36, no. 4, pp. 10-18, April, 2019.
  3. Gyuhwan Jung, "Current Address and Future Prospects of Artificial Intelligence Technology," Korea Internet Self-governance Organization, vol. 33, pp. 11-15, December, 2018.
  4. Yeong mo Kim , Jung Woo Lee, "Diagnosis of brain tumor with deep learning,"Proceedings of Symposium of the Korean Institute of communications and Information Sciences, vol 144, No. 3, pp. 1156-1157, July, 2018.
  5. Rolf A. Heckemann, Joseph V. Hajnal, Paul Aljabar,"Automatic anatomical brain MRI segmentation combining label,"NeuroImage, vol. 33, pp. 115-126, 2006. https://doi.org/10.1016/j.neuroimage.2006.05.061
  6. Mingyeong Joen, Hyeonseok Lee1, Sungchan Kim "Empirical analysis of the relation between the complexity and accuracy of CNN models for the diagnosis of Alzheimer disease based on MRI," The Korean Institute of Information Scientists and Engineers, pp. 902-904, July, 2018.
  7. Alzheimer's Disease International (ADI), "The benefits of early diagnosis and intervention", Alzheimer Disease International. World Alzheimer Report 2011, 2011.
  8. M. Liu, D. Zhang, E. Adeli-Mosabbeb, and D.Shen, "Inherent structure based multi-view learning with multitemplate feature representation for Alzheimer's disease diagnosis", IEEE Transactions on Biomedical Engineering, vol. 63, No. 7, pp. 1473-148, 2015. https://doi.org/10.1109/TBME.2015.2496233
  9. https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection, Dataset.
  10. Karen Simonyan, Andrew Zisserman,"Very Deep Convolutional Networks for Large-Scale Image Recognition", arXiv preprint arXiv, pp. 1409-1556, 2014.
  11. J.Y. Kim, S.J. Ko "Comparison of DICOM images and various types of images", The Journal of Korea Institute of Signal Processing and Systems, vol. 18, No. 2, pp. 76-83, 2017.
  12. J M. Havaei et al., "Brain Tumor Segmentation with Deep Neural Networks," Medical Image Analysis, Vol. 35, pp. 18-31, 2017. https://doi.org/10.1016/j.media.2016.05.004
  13. S. Rathore, M. Habes, MA. Iftikhar, "A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages. NeuroImage. vol. 155, pp. 530-548, 2017. https://doi.org/10.1016/j.neuroimage.2017.03.057
  14. Gyeong u Kim, Jin kuk Kim, "Technical Trends of Medical Image Diagnostic Equipment," The Korean Information Display Society, vol. 19, No. 4, pp. 18-23.