KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Medical Image Quality Assessment Tool Based on Chest X-ray

흉부 X-ray 기반 의료영상 품질평가 보조 도구 개발

  • 남기현 (아주대학교 전자공학과) ;
  • 유동연 (아주대학교 AI융합네트워크학과 전자공학전공) ;
  • 김양곤 (아주대학교 AI융합네트워크학과 전자공학전공) ;
  • 선주성 (아주대학교 의과대학 영상의학과) ;
  • 이정원 (아주대학교 전자공학과/AI융합네트워크학과)
  • Received : 2022.12.20
  • Accepted : 2023.03.14
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Chest X-ray is radiological examination for xeamining the lungs and haert, and is particularly widely used for diagnosing lung disease. Since the quality of these chest X-rays can affect the doctor's diagnosis, the process of evaluating the quality must necessarily go through. This process can involve the subjectivity of radiologists and is manual, so it takes a lot of time and csot. Therefore, in this paper, based on the chest X-ray quality assessment guidelines used in clinical settings, we propose a tool that automates the five quality assessments of artificial shadow, coverage, patient posture, inspiratory level, and permeability. The proposed tool reduces the time and cost required for quality judgment, and can be further utilized in the pre-processing process of selecting high-quality learning data for the development of a learning model for diagnosing chest lesions.

흉부 X-ray 영상은 폐와 심장을 검사하는 방사선 검사이며 특히, 폐 질환을 진단하는 데 널리 사용되고 있다. 이러한 흉부 X-ray의 품질은 의사의 진단에 영향을 줄 수 있으므로 품질을 평가하는 과정이 필수적으로 거쳐야 하는데, 이 과정은 영상의학과 전문의의 주관이 개입될 수 있고, 수작업으로 이루어지기 때문에 많은 시간과 비용이 소모된다. 또한, 이러한 품질평가는 X-ray 영상의 특징과 사용 목적에 따라 일반적인 품질평가와는 다른 평가 요소가 필요하다. 따라서 본 논문에서는 X-ray 영상에서 검출되는 장기의 해상도, ,해부학적인 구조, 균형 등을 고려하여 임상 현장에서 사용되는 흉부 X-ray 영상 화질 평가 가이드라인을 적용하여 품질요소를 5가지(인공음영, 포함범위, 환자자세, 흡기정도, 그리고 투과상태)로 나누고 이를 자동화하는 도구를 제안한다. 제안하는 도구는 수작업으로 품질평가를 진행하는 본래의 방식 대비 소요 시간과 비용을 줄여주고, 더 나아가 흉부 X-ray를 이용한 학습 모델 개발에 높은 품질의 학습데이터를 선별하는 과정에도 사용될 수 있다.

Keywords

Acknowledgement

본 연구는 과학기술정보통신부 및 정보통신기획평가원의 대학ICT연구센터지원사업의 연구결과로 수행되었음(IITP-2023-2020-0-01461).

References

  1. G. Chassagnon, M. Vakalopoulou, N. Paragios, and M. P. Revel, "Artificial intelligence applications for thoracic imaging," European Journal of Radiology, Vol.123, pp.108774, 2020.
  2. S. You, E. Kim, K. Park, and J. Sun, "Visual assessment of calcification in solitary pulmonary nodules on chest radiography: Correlation with volumetric quantification of calcification," European Radiology, Vol.29, No.8, pp.4324-4332, 2019. https://doi.org/10.1007/s00330-018-5883-3
  3. J. S. Whaley, B. D. Pressman, J. R. Wilson, L. Bravo, W. J. Sehnert, and D. H. Foos, "Investigation of the variability in the assessment of digital chest X-ray image quality," Journal of Digital Imaging, Vol.26, No.2, pp.217-226, 2013. https://doi.org/10.1007/s10278-012-9515-1
  4. W. K. Jeong and B. I. Choi, "Burnout among Radiologists in Korea: Prevalence, Risk Factors, and Remedies," Journal of the Korean Society of Radiology, Vol.83, No.4, pp.776-782, 2022. https://doi.org/10.3348/jksr.2022.0087
  5. X. Li et al., "Multi-resolution convolutional networks for chest X-ray radiograph based lung nodule detection," Artificial Intelligence in Medicine, Vol.103, pp.101744, 2020.
  6. C. Qin, D. Yao, Y. Shi, and Z. Song, "Computer-aided detection in chest radiography based on artificial intelligence: A survey," Biomedical Engineering Online, Vol.17, No.1, pp.1-23, 2018. https://doi.org/10.1186/s12938-017-0432-x
  7. Y. G. Kim, Y. S. Park, J. S. Sun, and J. W. Lee, "Open dataset quality evaluation for performance improvement of chest X-Ray image-based learning model," Korea Conference on Software Engineering, pp.43-51, 2022.
  8. S. B. Bea, Y. S. Park, J. S. Sung, and J. W. Lee, "Quality evaluation method for chest X-ray images using the reference patterns," 2022 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Korea, pp.266-269, 2022.
  9. H. J. Choi, S. B. Bea, Y. S. Park, and J. W. Lee, "Quality evaluation of chest X-ray images using region segmentation based on 3D histogram," 2021 Annual Conference of KIPS, pp.903-906, 2021.
  10. W. Wei, "An image quality assessment method based on HVS," 2007 41st Annual IEEE International Carnahan Conference on Security Technology, IEEE, 2007.
  11. L. S. Chow and R. Paramesran, "Review of medical image quality assessment," Biomedical Signal Processing and Control, Vol.27, pp.145-154, 2016. https://doi.org/10.1016/j.bspc.2016.02.006
  12. J. E. McManigle, R. R. Bartz, and L. Carin. "Y-Net for chest X-Ray preprocessing: Simultaneous classification of geometry and segmentation of annotations," 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE, 2020.
  13. Y. Meng et al., "Automatic no-reference quality assessment in chest radiographs based on deep convolutional neural networks," Research Square, 2022.
  14. M.-J. Chen, L. K. Cormack, and A. C. Bovik, "No-reference quality assessment of natural stereopairs," IEEE Transactions on Image Processing, Vol.22, No.9, pp.3379-3391, 2013. https://doi.org/10.1109/TIP.2013.2267393
  15. R. Fang, R. AI-Bayaty, and D. Wu, "BNB method for noreference image quality assessment," IEEE Transactions on Circuits and Systems for Video Technology, Vol.27, No.7, pp.1381-1391, 2017. https://doi.org/10.1109/TCSVT.2016.2539658
  16. Q. Li, W. Lin, J. Xu, and Y. Fang, "Blind image quality assessment using statistical structural and luminance features," IEEE Transactions on Multimedia, Vol.18, No.12, pp.2457-2469, 2016.  https://doi.org/10.1109/TMM.2016.2601028