자궁경부 영상에서의 라디오믹스 기반 판독 불가 영상 분류 알고리즘 연구
A Radiomics-based Unread Cervical Imaging Classification Algorithm
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Recently, artificial intelligence for diagnosis system of obstetric diseases have been actively studied. Arti- ficial intelligence diagnostic assist systems, which support medical diagnosis benefits of efficiency and accuracy, may experience problems of poor learning accuracy and reliability when inappropriate images are the model's input data. For this reason, before learning, We proposed an algorithm to exclude unread cervical imaging. 2,000 images of read cervical imaging and 257 images of unread cervical imaging were used for this study. Experiments were conducted based on the statistical method Radiomics to extract feature values of the entire images for classification of unread images from the entire images and to obtain a range of read threshold values. The degree to which brightness, blur, and cervical regions were photographed adequately in the image was determined as classification indicators. We com- pared the classification performance by learning read cervical imaging classified by the algorithm proposed in this paper and unread cervical imaging for deep learning classification model. We evaluate the classification accuracy for unread Cervical imaging of the algorithm by comparing the performance. Images for the algorithm showed higher accuracy of 91.6% on average. It is expected that the algorithm proposed in this paper will improve reliability by effec- tively excluding unread cervical imaging and ultimately reducing errors in artificial intelligence diagnosis.
Abstract
Recently, artificial intelligence for diagnosis system of obstetric diseases have been actively studied. Arti- ficial intelligence diagnostic assist systems, which support medical diagnosis benefits of efficiency and accuracy, may experience problems of poor learning accuracy and reliability when inappropriate images are the model's input data. For this reason, before learning, We proposed an algorithm to exclude unread cervical imaging. 2,000 images of read cervical imaging and 257 images of unread cervical imaging were used for this study. Experiments were conducted based on the statistical method Radiomics to extract feature values of the entire images for classification of unread images from the entire images and to obtain a range of read threshold values. The degree to which brightness, blur, and cervical regions were photographed adequately in the image was determined as classification indicators. We com- pared the classification performance by learning read cervical imaging classified by the algorithm proposed in this paper and unread cervical imaging for deep learning classification model. We evaluate the classification accuracy for unread Cervical imaging of the algorithm by comparing the performance. Images for the algorithm showed higher accuracy of 91.6% on average. It is expected that the algorithm proposed in this paper will improve reliability by effec- tively excluding unread cervical imaging and ultimately reducing errors in artificial intelligence diagnosis.
참고문헌 (20)
- 최현주, "자궁경부암 진단을 위한 3차원 세포핵 질감 특성값 유의성 평가에 관한 연구", 한국컴퓨터정보학회논문지, 16(10), pp.83~92 (2011), 한국컴퓨터정보학회
- Alyafeai Z, "A fully-automated deep learning pipeline for cervical cancer classification", Expert Systems with Applications, pp.83~86 (2020)
- Chandran V, "Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images", BioMed Research International, pp.83~86 (2021)
- 설유진, "컬러 자궁경부 영상에서 딥러닝 기법에서의 영상영역 처리 방법에 따른 성능 비교 연구", 멀티미디어학회논문지, 23(7), pp.812~818 (2020), 한국멀티미디어학회
- Fei Jiang, "Artificial intelligence in healthcare : past, present and future", Stroke Vasc Neurol, 2(4), pp.230~243 (2017)
- 조영탁, "수술 동영상의 비식별화를 위한 개인식별정보 자동 검출 시스템 설계 및 구현", 융합보안 논문지, 19(5), pp.75~84 (2019), 한국융합보안학회[DOI]
- "Korean society of Obstetrics and Gynecology"[URL]
- Song E-H, "Spiral Brush in PapSure Test for Cervical Cancer Screening", Korean Journal of Gynecologic Oncology and Colposcopy, 13(4), pp.313~326 (2002)
- Hee HS, "Classify And Visualize The Fatty Liver Using Class Activation Maps And CNN", Korea Institute Of Communication Sciences, 18(10), pp.83~86 (2020)
- Bolei Zhou, "Learning Deep Features for Discriminative Localization", Computer Vision and Pattern Recognition, pp.2921~2929 (2016)
- 김상철, "프레임율 상향 변환에 부적합한 프레임들에 대한 밝기값 히스토그램과 모션 벡터 상관성 분석", 정보과학회 컴퓨팅의 실제 논문지, 22(10), pp.532~536 (2016), 한국정보과학회
- Blur image detection using Laplacian operator and Open-CV, "Raghav Bansal", IEEE, ~ (2017)
- Learning Fine-grained Image Similarity with Deep Ranking, "Wang J", IEEE, 1,386~1,393 (2014)
- 조재훈, "시간에 따라 변화하는 빗줄기 장면을 이용한 딥러닝 기반 비지도 학습 빗줄기 제거 기법", 멀티미디어학회논문지, 22(1), pp.1~9 (2019), 한국멀티미디어학회[DOI]
- 강형주, "ResNet-50 합성곱 신경망을 위한 고정 소수점 표현 방법", 한국정보통신학회논문지, 22(1), pp.1~8 (2018), 한국정보통신학회[DOI]
- Jeon S-S, "A Comparison Analysis on the Sales Price of Apartments according to G-SEED by Using T-test", Journal of the Autumn Academic Presentation Conference, 19(2), pp.207~208 (2019)