Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

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

DOI QR Code

The Effect of Type of Input Image on Accuracy in Classification Using Convolutional Neural Network Model

컨볼루션 신경망 모델을 이용한 분류에서 입력 영상의 종류가 정확도에 미치는 영향

  • Kim, Min Jeong (Department of Biomedical Engineering Kyungpook National University) ;
  • Kim, Jung Hun (Bio-Medical Research institute, Kyungpook National University Hospital) ;
  • Park, Ji Eun (Nonlinear Dynamics Research Center, Kyungpook National University) ;
  • Jeong, Woo Yeon (Department of Biomedical Engineering Kyungpook National University) ;
  • Lee, Jong Min (Department of Radiology, School of Medicine, Kyungpook National University)
  • 김민정 (경북대학교대학원 의용생체공학과) ;
  • 김정훈 (경북대학교병원 생명의학연구원) ;
  • 박지은 (경북대학교 비선형동역학연구소) ;
  • 정우연 (경북대학교대학원 의용생체공학과) ;
  • 이종민 (경북대학교 의과대학 영상의학교실)
  • Received : 2021.05.31
  • Accepted : 2021.08.12
  • Published : 2021.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

Keywords

References

  1. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553):436-444. https://doi.org/10.1038/nature14539
  2. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2012;25:1097-1105.
  3. Yap MH, Goyal M, Osman F, Ahmad E, Marti R, Denton E, Zwiggelaar R. End-to-end breast ultrasound lesions recognition with a deep learning approach. In Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging. International Society for Optics and Photonics. 2018;10578:1057819.
  4. Han S, Kang HK, Jeong JY, Park MH, Kim W, Bang WC, Seong YK. A deep learning framework for supporting the classification of breast lesions in ultrasound images. Physics in Medicine & Biology. 2017;62(19):7714. https://doi.org/10.1088/0031-9155/62/19/7714
  5. Sahiner B, Pezeshk A, Hadjiiski LM, Wang X, Drukker K, Cha KH, Giger ML. Deep learning in medical imaging and radiation therapy. Medical physics. 2019;46(1):e1-e36. https://doi.org/10.1002/mp.13264
  6. 송하연, 김지은, 김태년. 인공지능과 헬스 커뮤니케이션. 언론정보연구, 2020;57.3:196-238.
  7. Yang SH, Lee J-S, Kim CS. The Accuracy of Echocardiography and ECG in the Left Ventricular Hypertrophy. The Journal of the Korea Contents Association, 2016;16.2:666-672. https://doi.org/10.5392/JKCA.2016.16.02.666
  8. 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
  9. Amin H, Siddiqui WJ. Cardiomegaly. StatPearls [internet]. 2020.
  10. Alghamdi SS, et al. Study of cardiomegaly using chest x-ray. Journal of Radiation Research and Applied Sciences, 2020;13.1:460-467. https://doi.org/10.1080/16878507.2020.1756187
  11. 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.
  12. Tschandl P, Rosendahl C, Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data. 2018;5(1):1-9. https://doi.org/10.1038/s41597-018-0002-5
  13. Kwon SM. Change of Image Quality within Compression of AAPM CT Performance Phantom Image Using JPEG2000 in PACS. Journal of The Korean Society of Radiology. 2012;6(3):217-226. https://doi.org/10.7742/jksr.2012.6.3.217
  14. Kim JY, Ko SJ. Comparison of DICOM images and various types of images. Journal of the Institute of Convergence Signal Processing. 2017;18(2):76-83.
  15. Kabachinski J. TIFF, GIF, and PNG: get the picture?. Biomedical instrumentation & technology. 2007;41(4):297-300. https://doi.org/10.2345/0899-8205(2007)41[297:TGAPGT]2.0.CO;2
  16. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv. 2014;1409.1556.
  17. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016;770-778.
  18. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016;2818-2826.
  19. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2017;4700-4708.
  20. Zagoruyko S, Komodakis N. Wide residual networks. arXiv preprint arXiv. 2016;1605.07146.
  21. Huang Y, Cheng Y, Bapna A, Firat O, Chen D, Chen M, Wu Y. Gpipe: Efficient training of giant neural networks using pipeline parallelism. Advances in neural information processing systems. 2019;32:103-112.
  22. Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning. PMLR. 2019;6105-6114.
  23. Japkowicz N, Shah M. Evaluating learning algorithms: a classification perspective. Cambridge University Press, 2011.