Journal of radiological science and technology (대한방사선기술학회지:방사선기술과학)

Korean Society of Radiological Science (대한방사선과학회)
권호 표지
DOI QR코드

DOI QR Code

Application of Deep Learning-Based Nuclear Medicine Lung Study Classification Model

딥러닝 기반의 핵의학 폐검사 분류 모델 적용

  • Received : 2021.11.23
  • Accepted : 2022.01.09
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.

Keywords

References

  1. David M. Artificial Intelligence in the Industry 4.0, and Its Impact on Poverty, Innovation, Infrastructure Development, and the Sustainable Development Goals: Lessons from Emerging Economies? Sustainability. 2021;13(11):5788. https://doi.org/10.3390/su13115788
  2. Humphreys D, Kupresanin A, Boyer MD, Canik J, Chang CS, Cyr EC, et al. Advancing Fusion with Machine Learning Research Needs Workshop Report. Journal of Fusion Energy. 2020;39:123-55. https://doi.org/10.1007/s10894-020-00258-1
  3. Christian J, Patrick Z, Kai H. Machine learning and deep learning. Electronic Markets. 2021;31:685-95. https://doi.org/10.1007/s12525-021-00475-2
  4. Zhong-Qiu Z, Peng Z, Shou-tao X, Xindong W. Object Detection with Deep Learning: A Review. IEEE Transactions on Neural Networks and Learning Systems. 2019 Jan;30(11):3212-32. https://doi.org/10.1109/tnnls.2018.2876865
  5. Alexander Selvikvag L, Arvid L. An overview of deep learning in medical imaging focusing on MRI. Zeitschrift fur Medizinische Physik. 2019 May; 29(2):102-27. https://doi.org/10.1016/j.zemedi.2018.11.002
  6. Keisuke K, Sho F, Kenji H, Chietsugu K, Osamu M, Kentaro K, et al. A convolutional neural network-based system to classify patients using FDG PET/CT examinations. BMC Cancer [Internet]. 2020 [published 2020 Mar 17]; 20(227):1-10. Available from: https://doi.org/10.1186/s12885-020-6694-x
  7. Ajda S, Damjana H, Jure F, Marko G. Lung scintigraphy in the diagnosis of pulmonary embolism: Current methods and interpretation criteria in clinical practice. Radiol Oncol. 2014;48(2):113-9. https://doi.org/10.2478/raon-2013-0060
  8. Hasan HK, Rahmita OKR, Dimon MZ. Components and implementation of a picture archiving and communication system in a prototype application. Reports in Medical Imaging. 2019;12:1-8.
  9. Chen-Hua C, Chi-Lun W, Hung-Wen C. Automatic classification of medical image modality and anatomical location using convolutional neural network. PLoS ONE [Internet]. 2021 [published 2021 Jun 11]; 16(6):e0253205. Available from: https://doi.org/10.1371/journal.pone.0253205
  10. Kicky G. van L, Maarten de R, Steven S, Bram van G, Matthieu JCMR. How does artificial intelligence in radiology improve efficiency and health outcomes? Pediatr Radiology [Internet]. 2021 [published 2021 Jun 12]. Available from: https://doi.org/10.1007/s00247-021-05114-8
  11. Dulari B, Chirag P, Hardik T, Jigar P, Rasmika V, Sharnil P, et al. CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope. Electronics [Internet]. 2021 [published 2021 Oct 11]; 10(20):2470. Available from: https://doi.org/10.3390/electronics10202470
  12. Danish N, Khurram Azeem H, Alain P, Marcus L, Didier S, Muhammad Zeshan A. HybridTabNet: Towards Better Table Detection in Scanned Document Images. applied sciences [Internet]. 2021 [published 2021 Sep 11]; 11(18):8396. Available from: https://doi.org/10.3390/app11188396
  13. Ibon M, Jon A, Anthony R, Basilio S. 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts. Sensors [Internet]. 2021 [published 2021 Feb 4]; 21(4):1078. Available from: https://doi.org/10.3390/s21041078
  14. Karen S, Andrew Z. Very Deep Convolutional Networks for Large-Scale Image Recognition. International Conference on Learning Representations(ICLR) [Internet]. 2015 [last revised 2015 Apr 10]; arXiv:1049.1556v6. Available from: https://arxiv.org/abs/1409.1556v6
  15. Kaiming H, Xiangyu Z, Shaoqing R, Jian S. Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision and Pattern Recognition(CVPR). 2016;1:770-8.