Deformable CAE 모형을 이용한 효율적인 CT 영상 잡음제거
Efficient CT Image Denoising Using Deformable Convolutional AutoEncoder Model
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
CT 영상의 획득 및 전송 등의 과정에서 발생하는 잡음은 영상의 질을 저하시키는 요소로 작용한다. 따라서 이를 해결하기 위한 잡음제거는 영상처리에서 중요한 전처리 과정이다. 본 논문에서는 딥러닝의 convolutional autoencoder (CAE) 모형에서 기존 컨볼루션 연산 대신 deformable 컨볼루션 연산을 적용한 deformable convolutional autoencoder (DeCAE) 모형을 이용하여 잡음을 제거하고자 한다. 여기서 deformable 컨볼루션 연산은 기존 컨볼루션 연산보다 유연한 영역에서 영상의 특징들을 추출할 수 있다. 제안된 DeCAE 모형은 기존 CAE 모형과 같은 인코더-디코더 구조로 되어있으나 효율적인 잡음제거를 위해 인코더는 deformable 컨볼루션 층으로 구성하고, 디코더는 기존 컨볼루션 층으로 구성하였다. 본 논문에서 제안된 DeCAE 모형의 성능 평가를 위해 다양한 잡음, 즉, 가우시안 잡음, 임펄스 잡음 그리고 포아송 잡음에 의해 훼손된 CT 영상을 대상으로 실험하였다. 성능 실험 결과, DeCAE 모형은 전통적인 필터 즉, Mean 필터, Median 필터와 이를 개선한 Bilateral 필터, NL-means 방법 뿐만 아니라 기존의 CAE 모형보다 정성적이고, 정량적인 척도즉, MAE (Mean Absolute Error), PSNR (Peak Signal-to-Noise Ratio) 그리고 SSIM (Structural Similarity Index Measure) 면에서 우수한 결과를 보였다.
Abstract
Noise generated during the acquisition and transmission of CT images acts as a factor that degrades image quality. Therefore, noise removal to solve this problem is an important preprocessing process in image processing. In this paper, we remove noise by using a deformable convolutional autoencoder (DeCAE) model in which deformable convolution operation is applied instead of the existing convolution operation in the convolutional autoencoder (CAE) model of deep learning. Here, the deformable convolution operation can extract features of an image in a more flexible area than the conventional convolution operation. The proposed DeCAE model has the same encoder-decoder structure as the existing CAE model, but the encoder is composed of deformable convolutional layers and the decoder is composed of conventional convolutional layers for efficient noise removal. To evaluate the performance of the DeCAE model proposed in this paper, experiments were conducted on CT images corrupted by various noises, that is, Gaussian noise, impulse noise, and Poisson noise. As a result of the performance experiment, the DeCAE model has more qualitative and quantitative measures than the traditional filters, that is, the Mean filter, Median filter, Bilateral filter and NL-means method, as well as the existing CAE models, that is, MAE (Mean Absolute Error), PSNR (Peak Signal-to-Noise Ratio) and SSIM. (Structural Similarity Index Measure) showed excellent results.
참고문헌 (27)
- M. Ameen, "An Extensive Review of Medical Image Denoising Techniques", Global Journal of Medical Research: D, 16(2), pp.1~6 (2016)
- N.Rajesh Kumar, "A Spatial Mean and Median Filter For Noise Removal in Digital Images", International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 04(01), pp.246~253 (2015), Ess & Ess Research Publications[DOI]
- P, Saxena, "Intelligent Multidimensional Data and Image Processing", pp.220~239 (2018)
- C. Tomasi, "Bilateral filtering for gray and color images", Proc Int Conf Computer Vision, pp.839~846 (1998)
- A. Buades, "A Review of Image Denoising Algorithms, with a New One", Multiscale Modeling and Simulation (SIAM Interdisciplinary Journal), 4(2), pp.490~530 (2005), Society for Industrial & Applied Mathematics (SIAM)[DOI]
- B. K. Shreyamsha Kumar, "Image denoising based on non-local means filter and its method noise thresholding", Signal, Image and Video Processing, 7(6), pp.1211~1227 (2012), Springer Science and Business Media LLC[DOI]
- 송정훈, "영상에서 convolutional denoising autoencoder 모형을 이용한 영상복원", 한국데이터정보과학회지, 31(1), pp.25~40 (2020), 한국데이터정보과학회[DOI]
- 김정희, "CT 영상에서 Inception 모형을 이용한 잡음제거", 한국데이터정보과학회지, 31(3), pp.487~501 (2020), 한국데이터정보과학회[DOI]
- Woong-Hee Lee, "Noise Learning-Based Denoising Autoencoder", IEEE Communications Letters, 25(9), pp.2983~2987 (2021), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- 성언승, "의료영상에서 convolutional dual-decoder autoencoder 모형을 이용한 잡음제거", 한국데이터정보과학회지, 33(6), pp.1065~1083 (2022), 한국데이터정보과학회
- Elena Solovyeva, "Dual Autoencoder Network with Separable Convolutional Layers for Denoising and Deblurring Images", Journal of Imaging, 8(9), pp.250~ (2022), MDPI AG[DOI]
- J. Dai, "Deformable Convolutional Networks", IEEE International Conference on Computer Vision (ICCV), 5, pp.764~773 (2017)
- Di Wang, "A Deformable Convolutional Neural Network with Spatial-Channel Attention for Remote Sensing Scene Classification", Remote Sensing, 13(24), pp.5076~ (2021), MDPI AG[DOI]
- Jaya Prakash Allam, "A deformable CNN architecture for predicting clinical acceptability of ECG signal", Biocybernetics and Biomedical Engineering, 43(1), pp.335~351 (2023), Elsevier BV[DOI]
- Chanyu Lee, "Improved Mask R-CNN with Deformable Convolutions for Accurate Liver Lesion Detection in Multiphase CT Images", Innovation in Medicine and Healthcare, 308, pp.141~148 (2022), Springer Nature Singapore[DOI]
- 김민종, "Deformable convolutional network를 기반으로 한 Mask R-CNN", 한국데이터정보과학회지, 31(6), pp.993~1008 (2020), 한국데이터정보과학회[DOI]
- Z. Wang, "Image Quality Assessment: From Error Visibility to Structural Similarity", IEEE Transactions on Image Processing, 13(4), pp.600~612 (2004), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Umme Sara, "Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study", Journal of Computer and Communications, 07(03), pp.8~18 (2019), Scientific Research Publishing, Inc.[DOI]
- L. Gondara, "Medical Image Denoising using Convolutional Denoising Autoencoders", IEEE 16th International Conference on Data Mining Workshops, pp.1~6 (2016)
- Emmanuel Pintelas, "A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets", Sensors, 21(22), pp.7731~ (2021), MDPI AG[DOI]
- P. Venkataraman, "Image Denoising Using Convolutional Autoencoder", Computer Vision and Pattern Recognition, 24 (2022)[DOI]
- D. Soydaner, "A Comparison of Optimization Algorithms for Deep Learning", International Journal of Pattern Recognition and Artificial Intelligence, 34, pp.1~26 (2020)[DOI]
- Youming Wang, "A convolutional neural network method based on Adam optimizer with power-exponential learning rate for bearing fault diagnosis", Journal of Vibroengineering, 24(4), pp.666~678 (2022), JVE International Ltd.[DOI]
- Surya Pavan Kumar Gudla, "A Study on Effect of Learning Rates Using Adam Optimizer in LSTM Deep Intelligent Model for Detection of DDoS Attack to Support Fog Based IoT Systems", Communications in Computer and Information Science, pp.27~38 (2022), Springer Nature Switzerland[DOI]
- Tawsifur Rahman, "Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images", Computers in Biology and Medicine, 132, pp.104319~ (2021), Elsevier BV[DOI]
- "COVID-19 Radiography Database"[URL]
- Qi Zhang, "A robust deformed convolutional neural network (CNN) for image denoising", CAAI Transactions on Intelligence Technology, 8(2), pp.1~12 (2022), Institution of Engineering and Technology (IET)[DOI]