Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Improvement of Accuracy of Cardiomegaly Classification Based on InceptionV3

InceptionV3 기반의 심장비대증 분류 정확도 향상 연구

  • Jeong, Woo Yeon (Department of Biomedical Engineering Kyungpook National University) ;
  • Kim, Jung Hun (Bio-Medical Research institute, Kyungpook National University Hospital)
  • 정우연 (경북대학교대학원 의용생체공학과) ;
  • 김정훈 (경북대학교병원 생명의학연구원)
  • Received : 2021.08.19
  • Accepted : 2022.02.17
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study is to improve the classification accuracy compared to the existing InceptionV3 model by proposing a new model modified with the fully connected hierarchical structure of InceptionV3, which showed excellent performance in medical image classification. The data used for model training were trained after data augmentation on a total of 1026 chest X-ray images of patients diagnosed with normal heart and Cardiomegaly at Kyungpook National University Hospital. As a result of the experiment, the learning classification accuracy and loss of the InceptionV3 model were 99.57% and 1.42, and the accuracy and loss of the proposed model were 99.81% and 0.92. As a result of the classification performance evaluation for precision, recall, and F1 score of Inception V3, the precision of the normal heart was 78%, the recall rate was 100%, and the F1 score was 88. The classification accuracy for Cardiomegaly was 100%, the recall rate was 78%, and the F1 score was 88. On the other hand, in the case of the proposed model, the accuracy for a normal heart was 100%, the recall rate was 92%, and the F1 score was 96. The classification accuracy for Cardiomegaly was 95%, the recall rate was 100%, and the F1 score was 97. If the chest X-ray image for normal heart and Cardiomegaly can be classified using the model proposed based on the study results, better classification will be possible and the reliability of classification performance will gradually increase.

Keywords

References

  1. Philbin EF, Garg R, Danisa K, Denny DM, Gosselin G, Hassapoyannes C. Digitalis Investigation Group. The relationship between cardiothoracic ratio and left ventricular ejection fraction in congestive heart failure. Archives of internal medicine. 1998;158(5):501-506. https://doi.org/10.1001/archinte.158.5.501
  2. Anderson JC, Baltaxe HA, Wolf GL. Inability to show clot: one limitation of ultrasonography of the abdominal aorta. Radiology. 1979;132(3):693-696. https://doi.org/10.1148/132.3.693
  3. Moon HJ, Kim EK, Park JS, Kwak JY. Thyroid Ultrasound: Change of Inter-observer Variability and Diagnostic Performance after Training. Journal of Korean Society of Ultrasound in Medicine. 2011;30(1):23-28.
  4. Frohlich ED. Left ventricular hypertrophy as a risk factor. Cardiology clinics. 1986;4(1):137-144. https://doi.org/10.1016/s0733-8651(18)30642-8
  5. Levy D, Anderson KM, Savage DD, Kannel WB, Christiansen JC, Castelli WP. Echocardiographically detected left ventricular hypertrophy: prevalence and risk factors: the Framingham Heart Study. Annals of internal medicine. 1988;108(1):7-13. https://doi.org/10.7326/0003-4819-108-1-7
  6. Lim S, Lee M. A Computer Aided Diagnosis Algorithm for Classification of Malignant Melanoma Based on Deep Learning. Journal of the Korea Society of Digital Industry and Information Management. 2018;14(4):69-77. https://doi.org/10.17662/KSDIM.2018.14.4.069
  7. Almeida J, Klima O. On the insertion of n-powers. arXiv preprint arXiv. 2017;1711.05525.
  8. Yao L, Poblenz E, Dagunts D, Covington B, Bernard D, Lyman K. Learning to diagnose from scratch by exploiting dependencies among labels. arXiv preprint arXiv. 2017;1710.10501.
  9. Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proceedings of the IEEE conference on computer vision and pattern recognition; 2017;2097-2106.
  10. Kim JY, Ye SY. Diagnostic Classification of Chest X-ray Pneumonia using Inception V3 Modeling. Journal of the Korean Society of Radiology. 2020;14(6):773-780. https://doi.org/10.7742/JKSR.2020.14.6.773
  11. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Rabinovich A. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition; 2015;1-9.
  12. Lambert J, Sener O, Savarese S. Deep learning under privileged information using heteroscedastic dropout. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018;8886-8895.
  13. Song HJ, Lee EB, Jo HJ, Park SY, Kim SY, Kim HJ, Hong JW. Evaluation of Classification and Accuracy in Chest Xray Images using Deep Learning with Convolution Neural Network. Journal of the Korean Society of Radiology. 2020;14(1):39-44. https://doi.org/10.7742/JKSR.2019.14.1.39
  14. Google. Advanced Guide to Inception v3 on Cloud TPU. https://cloud.google.com/tpu/docs/inception-v3-advanced?hl=en
  15. 이종근, 김선진, 곽내정, 김동우, 안재형. 흉부 디지털 영상의 병변 유무 판단을 위한 딥러닝 모델. 한국정보통신학회논문지. 2020;24(2):212-218. https://doi.org/10.6109/JKIICE.2020.24.2.212
  16. Song KD, Kim M, Do S. The latest trends in the use of deep learning in radiology illustrated through the stages of deep learning algorithm development. Journal of the Korean Society of Radiology. 2019;80(2):202-212. https://doi.org/10.3348/jksr.2019.80.2.202
  17. Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv; 2012;1207.0580.
  18. Philbin EF, Garg R, Danisa K, Denny DM, Gosselin G, Hassapoyannes C. Digitalis Investigation Group. The relationship between cardiothoracic ratio and left ventricular ejection fraction in congestive heart failure. Archives of internal medicine. 1998;158(5):501-506. https://doi.org/10.1001/archinte.158.5.501
  19. Tieleman T, Hinton G. Divide the gradient by a running average of its recent magnitude. coursera: Neural networks for machine learning. Technical Report; 2017.
  20. 정원준. 국내 인공지능 (AI) 의료기기 현황 및 규제 이슈. 주간기술동향. IITP; 2018.
  21. Japkowicz N, Shah M. Evaluating learning algorithms: a classification perspective. Cambridge University Press; 2011.