Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

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

DOI QR Code

A Performance Comparison Study of Lesion Detection Model according to Gastroscopy Image Quality

위 내시경 이미지 품질에 따른 병변 검출 모델의 성능 비교 연구

  • Yul Hee Lee (Department of Nursing, College of Nursing, Gachon University) ;
  • Young Jae Kim (Department of Biomedical Engineering, College of Medicine, Gil Medical Center, Gachon University) ;
  • Kwang Gi Kim (Department of Biomedical Engineering, College of Medicine, Gil Medical Center, Gachon University)
  • 이율희 (가천대학교 간호대학 간호학과) ;
  • 김영재 (가천대학교 의과대학 의공학교실) ;
  • 김광기 (가천대학교 의과대학 의공학교실)
  • Received : 2023.02.20
  • Accepted : 2023.03.27
  • Published : 2023.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Many recent studies have reported that the quality of input learning data was vital to the detection of regions of interest. However, due to a lack of research on the quality of learning data on lesion detetcting using gastroscopy, we aimed to quantify the impact of quality difference in endoscopic images to lesion detection models using Image Quality Assessment (IQA) algorithms. Through IQA methods such as BRISQUE (Blind/Referenceless Image Spatial Quality Evaluation), Laplacian Score, and PSNR (Peak Signal-To-Noise) algorithm on 430 sheets of high quality data (HQD) and 430 sheets of low quality data (PQD), we showed that there were significant differences between high and low quality images in lesion detecting through BRISQUE and Laplacian scores (p<0.05). The PSNR value showed 10.62±1.76 dB on average, illustrating the lower lesion detection performance of PQD than HQD. In addition, F1-Score of HQD showed higher detection performance at 77.42±3.36% while F1-Score of PQD showed 66.82±9.07%. Through this study, we hope to contribute to future gastroscopy lesion detection assistance systems that involve IQA algorithms by emphasizing the importance of using high quality data over lower quality data.

Keywords

Acknowledgement

이 논문은 가천대길병원 산학연병공동과제(FRD2022-12)와 경기도의 경기도 지역협력연구센터 사업의 일환으로 수행하였음[GRRC-가천 2020(B02), AI 기반 의료영상 분석].

References

  1. Ferlay J, Ervik M, Lam F, Colombet M, Mery L, Pieros M, Bray F. Global cancer observatory: cancer today. Lyon, France: International Agency for Research on Cancer. 2018;3(20):1-2.
  2. https://www.who.int/news-room/fact-sheets/detail/cancer. Accessed on 3 Feb 2022. cancer.
  3. Choi ES, Jeon WH, Sohn HJ. Clinical study of early gastric carcinoma. Korean J Gastroenterol. 1995;27:31-38.
  4. Park IS, Lee YC, Kim WH, Noh SH, Lee KS, Kim H. Clinicopathologic characteristics of early gastric cancer in Korea. Yonsei Medical Journal. 2000;41(5):607-614. https://doi.org/10.3349/ymj.2000.41.5.607
  5. Song HT, Kim CD, Ryu HS, Hyun JH. A clinical study of early gastric cancer. Korean J Gastroenterol. 1994;26:789-799.
  6. National Cancer Center. Cancer Facts and Figures 2014. 2014;18-27.
  7. Lee SA, Cho HC. A New Image Augmentation Method for Improving Computer-aided Diagnosis System Performance. The transactions of The Korean Institute of Electrical Engineers. 2021;70(1):102-107. https://doi.org/10.5370/KIEE.2021.70.1.102
  8. Belle A, Kon MA, Najarian K. Biomedical informatics for computer-aided decision support systems: a survey. The Scientific World Journal. 2013;2013:1-8. https://doi.org/10.1155/2013/769639
  9. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y. Artificial intelligence in healthcare: past, present and future. Stroke and Vascular Neurology. 2017;2(4):230-243. https://doi.org/10.1136/svn-2017-000101
  10. Miller RA. Medical diagnostic decision support systems-past, present, and future: a threaded bibliography and brief commentary. Journal of the American Medical Informatics Association. 1994;1(1):8-27. https://doi.org/10.1136/jamia.1994.95236141
  11. Kim DH, Cho HC. Deep Learning based Computer-aided Diagnosis System for Gastric Lesion using Endoscope. The transactions of The Korean Institute of Electrical Engineers. 2018;67(7):928-933. https://doi.org/10.5370/KIEE.2018.67.7.928
  12. Lee SA, Cho HC, Cho HC. Computer-aided Diagnosis System for Abnormalities Classification in Gastric Endoscopy Images using Machine Learning. The Transactions of the Korean Institute of Electrical Engineers. 2020;69(1):107-113. https://doi.org/10.5370/KIEE.2020.69.1.107
  13. Park SH, Cho YB. An Effect of Genetic Algorithm for Creating a Dataset. Journal of Digital Contents Society. 2019;20(1):127-133. https://doi.org/10.9728/dcs.2019.20.1.127
  14. Lee JM, Ham GW, Bae KH, Park HK. Detection Ability of Occlusion Object in Deep Learning Algorithm depending on Image Qualities. Journal of the Korean Association of Geographic Information Studies. 2019;22(3):82-98. https://doi.org/10.11108/KAGIS.2019.22.3.082
  15. Yoon MS, Oh JH, Kang BG, Im JU, Kwon GT, Han DG. Effects of Image Extensions in Chest X-ray Deep Learning-Based Pneumothorax Detection Studies. Green Collection of the Korean Society of Emergency Medicine's Academic Conference. 2020;2020(2):75.
  16. Kim YJ, Kim KG. Development of an Optimized Deep Learning Model for Medical Imaging. Journal of the Korean Society of Radiology. 2020;81(6):1274-1289.
  17. Cho YK, Lee Y, Lee K. Quality Evaluation of Ultrasonographic Equipment Using an ATS-539 Multipurpose Phantom in Veterinary Medicine. Journal of Veterinary Clinics. 2022;39(3):114-120. https://doi.org/10.17555/jvc.2022.39.3.114
  18. Mittal A, Moorthy AK, Bovik AC. No-reference Image Quality Assessment in the Spatial Domain. IEEE Transactions on Image Processing. 2012;21(12):4695-4708. https://doi.org/10.1109/TIP.2012.2214050
  19. Bansal R, Raj G, Choudhury T. Blur image detection using Laplacian operator and Open-CV. in 2016 International Conference System Modeling & Advancement in Research Trends (SMART). 2016;63-67.
  20. He X, Cai D, Niyogi P. Laplacian score for feature selection, in proceeding of Advances in Neural Information Processing Systems. 2006;18:507-514.
  21. Rustam Z, Primasari I, Widya, D. Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and laplacian score. In AIP Conference Proceedings. 2018;2023(1):020234.
  22. Kang KS, Lee, J-H. PSNR appraisal of MRI image. Journal of the Korean Society of Radiology. 2009;3(4):13-21.
  23. Jung HK. Fundamentals of multimedia chapter 8, Lossy compression Algorithms. Hallym University. 2008.
  24. Lin TY, Goyal P, Girshick R, He K, Dollr P. Focal loss for dense object detection. in Proceedings of the IEEE international conference on computer vision. 2017;2980-2988.
  25. Lee JH. Radiological feature estimation and risk assessment of mammographic mass and density by computer-aided analysis. Department of Medical Science The Graduate School, Yonsei University. 2004;3-50.
  26. Cheng HD, Cui M. Mass lesion detection with a fuzzy neural network. Pattern Recognition. 2004;37(6):1189-1200. https://doi.org/10.1016/j.patcog.2003.11.002