흉부 방사선영상의 좌, 우 반전 발생 여부 컨벌루션 신경망 기반 정확도 평가
An Accuracy Evaluation on Convolutional Neural Network Assessment of Orientation Reversal of Chest X-ray Image
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (15)
- 최권택, "고차원 의료 영상을 위한 실시간 인공 신경망", 한국방사선학회논문지, 10(8), pp.637~643 (2016), 한국방사선학회[DOI]
- Szegedy C, "Going deeper with convolutions", IEEE Conference on Computer Vision and Pattern Recognition, pp.1~9 (2015)
- "Very deep convolutional networks for large-scale image recognition" (2014)[URL]
- "Journal of Healthcare Engineering", 2018, ~
- Xu S, "Anomaly Detection on Chest X-Rays With Image-Based Deep Learning", IEEE Access, 7, pp.4466~4477 (2019)
- Dunnmon JA, "Assessment of Convolutional Neural Networks for Automated Classification of Chest Radiographs", Radiology, 290(2), pp.537~544 (2019)
- Baltruschat IM, "Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification", Sci Rep, 9(1), pp.6381~ (2019)
- 길종원, "국가건강검진의 방사선검사 이용량 및 피폭선량 추정", 방사선방어학회지, 39(3), pp.142~149 (2014), 테스트학회
- Nahm KB, "Automatic detection of the lung orientation in digital PA chest radiographs", Journal of the Optical Society of Korea, 1(1), pp.60~64 (1997)
- Strickland NH, "PACS(picture archiving and communication systems)filmless radiology", Arch dis Child, 83, pp.82~86 (2000)
- Boone JM, "Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks", Journal of digital imaging, 5(3), pp.190~193 (1992)
- Sakai Y, "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, 12(2), pp.216~223 (2019)
- Shmizu Y, "Evaluation of the usefulness of modified biological fingerprints in chest radiographs for patient recognition and identification", Raiol Phys Technol, 9(2), pp.240~244 (2016)
- Shimizu Y, "Development of a method of automated extraction of biological fingerprints from chest radiographs as preprocessing of patient recognition and identification", Radiol Phys Technol, 10(3), pp.376~381 (2017)
- Morishita J, "Potential Usefulness of Biological Fingerprints in Chest Radiographs for Automated Patient Recognition and Identification", Acad Radiol, 11(3), pp.309~315 (2004)