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
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
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 rel- atively 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.
Abstract
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 rel- atively 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.
참고문헌 (15)
- 최지혜, "개에서 복강내 잔존한 거즈 이물의 진단영상", 한국임상수의학회지, 28(1), pp.94~100 (2011), 한국임상수의학회
- 강동백, "Gossypiboma에 의한 골반종양", Obstetrics & Gynecology Science, 52(4), pp.476~479 (2009), 대한산부인과학회
- 오재윤, "아스페르질루스종으로 오진된 수술 후 남겨진 폐내 거즈 -1예 보고-", Journal of Chest Surgery, 40(8) (2007), 대한심장혈관흉부외과학회
- Abdul-Karim FW, "Case report 736 : Retained surgical sponge(gossypiboma)with a foreign body reaction and remote and organizing hematoma", Skeletal radiology, 21(7), pp.466~469 (1992)
- Gebhard F, "Navigation at the spine", Injury, 35(1), pp.35~45 (2004)
- 조영철, "내시경과 C-arm을 이용한 얼굴 이물질 제거 치험례", 대한구강악안면외과학회지, 37(3), pp.234~236 (2011), 대한구강악안면외과학회
- Hussin R, "Digital image processing techniques for object detection from complex background image", Procedia Engineering, 41, pp.340~344 (2012)
- Lim BH, "Deep Learning Method for Improv-ing Contamination Dectection of Xoray Inspection System", The Korean Institute of Information and Communication Sciences Conference, pp.460~462 (2021)
- 홍준용, "AI 의료영상 분석의 개요 및 연구 현황에 대한 고찰", 방사선기술과학, 43(3), pp.195~208 (2020), 대한방사선과학회
- 노시형, "머신러닝기반 간 경화증 진단을 위한 웹 서비스 개발", 정보처리학회논문지. 컴퓨터 및 통신시스템, 10(10), pp.285~290 (2021), 한국정보처리학회
- Provost F, "Machine Learning from Imbalanced Data Sets 101", ~ (2018)
- Chlap P, "A review of medical image data augmentation techniques for deep learning applications", J Med Imaging Radiat Oncol, 65(5), pp.545~563 (2021)
- 오민지, "제조 설비 이상탐지를 위한 지도학습 및비지도학습 모델 설계에 관한 연구", 한국빅데이터학회 학회지, 6(1), pp.23~35 (2021), 사)한국빅데이터학회[DOI]
- Redmon J, "You only look once: Unified, real-time object detection", 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.779~788 (2016)
- 이용환, "객체 검출을 위한 CNN과 YOLO 성능 비교 실험", 반도체디스플레이기술학회지, 19(1), pp.85~92 (2020), 한국반도체디스플레이기술학회