Journal of radiological science and technology (대한방사선기술학회지:방사선기술과학)

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

DOI QR Code

An Accuracy Evaluation on Convolutional Neural Network Assessment of Orientation Reversal of Chest X-ray Image

흉부 방사선영상의 좌, 우 반전 발생 여부 컨벌루션 신경망 기반 정확도 평가

  • Lee, Hyun-Woo (Department of Radiological Technology, Shingu College) ;
  • Oh, Joo-Young (Department of Biomedical Engineering Graduate School, Chungbuk National University) ;
  • Lee, Joo-Young (Department of Radiological Technology, Songho University) ;
  • Lee, Tae-Soo (Department of Biomedical Engineering Graduate School, Chungbuk National University) ;
  • Park, Hoon-Hee (Department of Radiological Technology, Shingu College)
  • Received : 2020.03.20
  • Accepted : 2020.04.22
  • Published : 2020.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

PA(postero-anterior) and AP(antero-posterior) chest projections are the most sought-after types of all kinds of projections. But if a radiological technologist puts wrong information about the position in the computer, the orientation of left and right side of an image would be reversed. In order to solve this problem, we utilized CNN(convolutional neural network) which has recently utilized a lot for studies of medical imaging technology and rule-based system. 70% of 111,622 chest images were used for training, 20% of them were used for testing and 10% of them were used for validation set in the CNN experiment. The same amount of images which were used for testing in the CNN experiment were used in rule-based system. Python 3.7 version and Tensorflow r1.14 were utilized for data environment. As a result, rule-based system had 66% accuracy on evaluating whether the orientation reversal on chest x-ray image. But the CNN had 97.9% accuracy on that. Being overcome limitations by CNN which had been shown on rule-based system and shown the high accuracy can be considered as a meaningful result. If some problems which can occur for tasks of the radiological technologist can be separated by utilizing CNN, It can contribute a lot to optimize workflow.

Keywords

References

  1. Choi KT. Real-time Artificial Neural Network for High-dimensional Medical Image. Journal of the Korean Society of Radiology [Internet]. 2016 Dec; 10(8):637-43. Available from: https://doi.org/10.7742/JKSR.2016.10.8.637.
  2. Szegedy C, et al. Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition [Internet]. 2015:1-9. Available from: https://ieeexplore.ieee.org/document/7298594.
  3. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [Internet]. arXiv. 2014. Avialable from: https://arxiv.org/abs/1409.1556.
  4. Abiyev RH, Ma'aitah MKS. Deep convolutional neural networks for chest diseases detection [Internet]. Journal of Healthcare Engineering. 2018. Available from: https://www.hindawi.com/journals/jhe/2018/4168538/.
  5. Xu S, Wu H, Bie R. Anomaly Detection on Chest X-Rays With Image-Based Deep Learning. IEEE Access. 2019;7:4466-77. https://doi.org/10.1109/ACCESS.2018.2885997
  6. Dunnmon JA, Yi D, Langlotz CP, et al. Assessment of Convolutional Neural Networks for Automated Classification of Chest Radiographs. Radiology. 2019;290(2):537-44. https://doi.org/10.1148/radiol.2018181422
  7. Baltruschat IM, Nickisch H, Grass M. Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification. Sci Rep. 2019;9(1):6381. https://doi.org/10.1038/s41598-019-42294-8
  8. Gil JW, Park JH, Park MH, Park CY, Kim SY, Shin DW, et al. Estimated Exposure Dose and Usage of Radiological Examination of the National Health Screening. Journal of Radiation Protection. 2014 Sep;39(3):142-9. https://doi.org/10.14407/jrp.2014.39.3.142
  9. Nahm KB. Automatic detection of the lung orientation in digital PA chest radiographs. Journal of the Optical Society of Korea. 1997;1(1):60-4. https://doi.org/10.3807/JOSK.1997.1.1.060
  10. Strickland NH. PACS (picture archiving and communication systems) filmless radiology. Arch dis Child. 2000;83:82-6. https://doi.org/10.1136/adc.83.1.82
  11. Boone JM, Seshagiri S, Steiner RM. Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks. Journal of digital imaging. 1992;5(3):190-3. https://doi.org/10.1007/BF03167769
  12. Sakai Y, Takahashi K, Shimizu Y, et al. Clinical application of biological fingerprints extracted from averaged chest radiographs and template-matching technique for preventing left-right flipping mistakes in chest radiography. Radiol Phys Technol. 2019;12(2):216-23. https://doi.org/10.1007/s12194-019-00504-y
  13. Shmizu Y, Matsunobu Y, Morishita J. Evaluation of the usefulness of modified biological fingerprints in chest radiographs for patient recognition and identification. Raiol Phys Technol. 2016;9(2):240-4. https://doi.org/10.1007/s12194-016-0355-4
  14. Shimizu Y, Morishita J. Development of a method of automated extraction of biological fingerprints from chest radiographs as preprocessing of patient recognition and identification. Radiol Phys Technol. 2017;10(3):376-81. https://doi.org/10.1007/s12194-017-0400-y
  15. Morishita J, Katsragawa S, Ssaki Y, Doi K. Potential Usefulness of Biological Fingerprints in Chest Radiographs for Automated Patient Recognition and Identification. Acad Radiol. 2004;11(3):309-15. https://doi.org/10.1016/S1076-6332(03)00655-X