학술논문
치주질환 예측을 위한 치과 X-선 영상에서의 초해상화 알고리즘 적용 가능성 연구
Investigation of the Super-resolution Algorithm for the Prediction of Periodontal Disease in Dental X-ray Radiography
Investigation of the Super-resolution Algorithm for the Prediction of Periodontal Disease in Dental X-ray Radiography
Document Type
Article
Author
Source
한국방사선학회논문지 / Journal of the Korean Society of Radiology (JKSR). Apr 30, 2021 15(2):153
Subject
Language
Korean
English
English
ISSN
1976-0620
Abstract
치주질환의 조기 진단률 및 예측 정확도 향상을 위한 X-선 영상 분석은 매우 중요한 분야이다. 이러한 치과 X-선 영상의 화질 개선을 위한 인공 지능 기반의 알고리즘 개발 및 적용에 관한 연구는 전 세계적으로 널리 수행 중이다. 따라서 본 연구의 목표는 치주질환 예측을 위한 치과 X-선 영상에서의 초해상화 알고리즘의 모델링 및 적용 가능성에 관하여 평가하는 것이다. 초해상화 알고리즘은 convolution layer와 ReLU를 기반으로 구성하였고, 저해상도 영상을 2배로 업샘플링 한 영상을 입력으로 사용하였다. 딥러닝 훈련을 위해 사용한 치과 X-선 데이터는 1,500장을 사용하였다. 영상의 정량적 평가는 2가지 영상의 비교를 통해 유사도를 측정할 수 있는 인자인 root mean square error와 structural similarity를 사용하였다. 이와 더불어 최근에 개발된 no-reference 기반으로 사용되는 natural image quality evaluator 와 blind/referenceless image spatial quality evaluator를 추가적으로 분석하였다. 결과적으로 기존에 사용되던 bicubic 기반의 업샘플링 기법을 사용하였을 때에 비하여 제안하는 방법이 치과 X-선 영상에서 평균적으로 유사도와 no-reference 기반의 평가 인자가 각각 1.86 그리고 2.14배 향상됨을 확인하였다. 결론적으로 치주질환의 예측을 위한 초해상화 알고리즘의 치과 X-선 영상에서의 유용성을 증명하였고 향후 다양한 분야에서의 적용 가능성이 높을 것으로 기대된다.
X-ray image analysis is a very important field to improve the early diagnosis rate and prediction accuracy of periodontal disease. Research on the development and application of artificial intelligence-based algorithms to improve the quality of such dental X-ray images is being widely conducted worldwide. Thus, the aim of this study was to design a super-resolution algorithm for predicting periodontal disease and to evaluate its applicability in dental X-ray images. The super-resolution algorithm was constructed based on the convolution layer and ReLU, and an image obtained by up-sampling a low-resolution image by 2 times was used as an input data. Also, 1,500 dental X-ray data used for deep learning training were used. Quantitative evaluation of images used root mean square error and structural similarity, which are factors that can measure similarity through comparison of two images. In addition, the recently developed no-reference based natural image quality evaluator and blind/referenceless image spatial quality evaluator were additionally analyzed. According to the results, we confirmed that the average similarity and no-reference-based evaluation values were improved by 1.86 and 2.14 times, respectively, compared to the existing bicubic-based upsampling method when the proposed method was used. In conclusion, the super-resolution algorithm for predicting periodontal disease proved useful in dental X-ray images, and it is expected to be highly applicable in various fields in the future.
X-ray image analysis is a very important field to improve the early diagnosis rate and prediction accuracy of periodontal disease. Research on the development and application of artificial intelligence-based algorithms to improve the quality of such dental X-ray images is being widely conducted worldwide. Thus, the aim of this study was to design a super-resolution algorithm for predicting periodontal disease and to evaluate its applicability in dental X-ray images. The super-resolution algorithm was constructed based on the convolution layer and ReLU, and an image obtained by up-sampling a low-resolution image by 2 times was used as an input data. Also, 1,500 dental X-ray data used for deep learning training were used. Quantitative evaluation of images used root mean square error and structural similarity, which are factors that can measure similarity through comparison of two images. In addition, the recently developed no-reference based natural image quality evaluator and blind/referenceless image spatial quality evaluator were additionally analyzed. According to the results, we confirmed that the average similarity and no-reference-based evaluation values were improved by 1.86 and 2.14 times, respectively, compared to the existing bicubic-based upsampling method when the proposed method was used. In conclusion, the super-resolution algorithm for predicting periodontal disease proved useful in dental X-ray images, and it is expected to be highly applicable in various fields in the future.