대한의용생체공학회:의공학회지 (Journal of Biomedical Engineering Research)

  • 제43권4호
  • /
  • Pages.290-297
  • /
  • 2022
  • /
  • 1229-0807(pISSN)
  • /
  • 2288-9396(eISSN)
대한의용생체공학회 (The Korean Society of Medical and Biological Engineering)
권호 표지
DOI QR코드

DOI QR Code

인공지능을 활용한 C-Arm에서 수술용 거즈 검출을 위한 데이터셋 구축 및 검출모델 적용에 관한 연구

A Study on the Dataset Construction and Model Application for Detecting Surgical Gauze in C-Arm Imaging Using Artificial Intelligence

  • 김진엽 (가톨릭대학교 은평성모병원) ;
  • 황호성 (을지대학교 일반대학원 의료인공지능학과) ;
  • 이병주 (가톨릭대학교 은평성모병원) ;
  • 최용진 (가톨릭대학교 은평성모병원) ;
  • 이강석 (가톨릭대학교 은평성모병원) ;
  • 김호철 (을지대학교 일반대학원 의료인공지능학과)
  • Kim, Jin Yeop (The Catholic Univ. of Korea Eunpyeong ST. Mary's Hospital) ;
  • Hwang, Ho Seong (Department of Medical Artificial Intelligent, Eulji University Graduate School) ;
  • Lee, Joo Byung (The Catholic Univ. of Korea Eunpyeong ST. Mary's Hospital) ;
  • Choi, Yong Jin (The Catholic Univ. of Korea Eunpyeong ST. Mary's Hospital) ;
  • Lee, Kang Seok (The Catholic Univ. of Korea Eunpyeong ST. Mary's Hospital) ;
  • Kim, Ho Chul (Department of Medical Artificial Intelligent, Eulji University Graduate School)
  • 투고 : 2022.08.01
  • 심사 : 2022.08.25
  • 발행 : 2022.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

During surgery, Surgical instruments are often left behind due to accidents. Most of these are surgical gauze, so radioactive non-permeable gauze (X-ray gauze) is used for preventing of accidents which gauze is left in the body. This gauze is divided into wire and pad type. If it is confirmed that the gauze remains in the body, gauze must be detected by radiologist's reading by imaging using a mobile X-ray device. But most of operating rooms are not equipped with a mobile X-ray device, but equipped C-Arm equipment, which is of poorer quality than mobile X-ray equipment and furthermore it takes time to read them. In this study, Use C-Arm equipment to acquire gauze image for detection and Build dataset using artificial intelligence and select a detection model to Assist with the relatively low image quality and the reading of radiology specialists. mAP@50 and detection time are used as indicators for performance evaluation. The result is that two-class gauze detection dataset is more accurate and YOLOv5 model mAP@50 is 93.4% and detection time is 11.7 ms.

키워드

참고문헌

  1. Choi JH, Kim GD, Keh SY, Jang JY, Choi HY, Yoon JH. Diagnostic Imaging Features of Abdominal Foreign Body in Dogs; Retained Surgical Gauze. Journal of veterinary clinics. 2011;28(1):94-100.
  2. Kang DB, Kim SH, Oh JT, Kim HY. Pelvic mass caused by gossypiboma. Obstetrics & Gynecology Science. 2009;52(4):476-9.
  3. Oh JY, Shin HK, Won YS, Lee JW, Yang JS. A Forgotten Surgical Gauze after Surgery that Mimicked Aspergilloma - A case report -. The Korean Journal of Thoracic and Cardiovascular Surgery. 2007;40(8):590-2.
  4. Abdul-Karim FW, Benevenia J, Pathria M, Makley J. Case report 736: Retained surgical sponge (gossypiboma) with a foreign body reaction and remote and organizing hematoma. Skeletal radiology. 1992;21(7):466-9. https://doi.org/10.1007/BF00190994
  5. Gebhard F, Weidner A, Liener UC, Stockle U, Arand M. Navigation at the spine. Injury. 2004;35(1):35-45.
  6. Cho YC, Jang SM, Park SW, Choi BH, Ha JH, Son JH, Sung IY. Removal of foreign body on cheek using endoscope and C-arm fluoroscopy. Journal of the Korean Association of Oral and Maxillofacial Surgeons. 2011;37(3):234-6. https://doi.org/10.5125/jkaoms.2011.37.3.234
  7. Hussin R, Juhari MR, Kang NW, Ismail R, Kamarudin A. Digital image processing techniques for object detection from complex background image. Procedia Engineering. 2012;41:340-4. https://doi.org/10.1016/j.proeng.2012.07.182
  8. Lim BH, Jeong SS, Yu YS. Deep Learning Method for Improving Contamination Dectection of Xoray Inspection System. The Korean Institute of Information and Communication Sciences Conference. 2021;460-2.
  9. Hong JY, Park SH, Jung YJ. Artificial Intelligence Based Medical Imaging: An Overview. Journal of radiological science and technology. 2020;43(3):195-208. https://doi.org/10.17946/JRST.2020.43.3.195
  10. Noh SH, Kim JE, Lee CS, Kim TH, Kim KW, Yoon KH, Jeong CW. Development of Web Service for Liver Cirrhosis Diagnosis Based on Machine Learning. KIPS Transactions on Computer and Communication Systems. 2021;10(10):285-90. https://doi.org/10.3745/KTCCS.2021.10.10.285
  11. Provost F. Machine Learning from Imbalanced Data Sets 101. 2018.
  12. Chlap P, Min H, Vandenberg N, Dowling J, Holloway L, Haworth A. A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol. 2021;65(5):545-63. https://doi.org/10.1111/1754-9485.13261
  13. Oh MJ, Choi ES, Roh KW, Kim JS, Cho WS. A Study on the Design of Supervised and Unsupervised Learning Models for Fault and Anomaly Detection in Manufacturing Facilities. Korea Bigdata Society. 2021;6(1):23-35.
  14. Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016;779-88.
  15. Lee YH, Kim YS. Comparison of CNN and YOLO for Object Detection. Journal of the semiconductor & display technology. 2020;19(8):85-92.