• Journal of Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.80-85
• /
• 2021

We developed a model to classify the absence of cervical cancer using deep learning from the cervical image to which the histogram equalization algorithm was applied, and to compare the performance of each model. A total of 4259 images were used for this study, of which 1852 images were normal and 2407 were abnormal. And this paper applied Image Sharpening(IS), Histogram Equalization(HE), and Contrast Limited Adaptive Histogram Equalization(CLAHE) to the original image. Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity index for Measuring image quality(SSIM) were used to assess the quality of images objectively. As a result of assessment, IS showed 81.75dB of PSNR and 0.96 of SSIM, showing the best image quality. CLAHE and HE showed the PSNR of 62.67dB and 62.60dB respectively, while SSIM of CLAHE was shown as 0.86, which is closer to 1 than HE of 0.75. Using ResNet-50 model with transfer learning, digital image-processed images are classified into normal and abnormal each. In conclusion, the classification accuracy of each model is as follows. 90.77% for IS, which shows the highest, 90.26% for CLAHE and 87.60% for HE. As this study shows, applying proper digital image processing which is for cervical images to Computer Aided Diagnosis(CAD) can help both screening and diagnosing.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.21-32
• /
• 2022

Image labeling must be preceded in order to perform object detection, and this task is considered a significant burden in building a deep learning model. Tens of thousands of images need to be trained for building a deep learning model, and human labelers have many limitations in labeling these images manually. In order to overcome these difficulties, this study proposes a method to perform object detection without significant performance degradation, even though labeling some images rather than the entire image. Specifically, in this study, low-resolution oriental painting images are converted into high-quality images using a super-resolution algorithm, and the effect of SSIM and PSNR derived in this process on the mAP of object detection is analyzed. We expect that the results of this study can contribute significantly to constructing deep learning models such as image classification, object detection, and image segmentation that require efficient image labeling.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.819-825
• /
• 2023

In this study, among chest CT examination conditions, the tube voltage was changed to 100 and 80 kVp and the reconstruction algorithm was changed to FBP, ASIR-V, and DLIR to compare and analyze changes in examination dose and image quality. As a result, when applying ASIR-V and DLIR at a tube voltage of 100 kVp, which is lower than the existing tube voltage, the dose is lowered while achieving image quality most similar to that when applying 120 kVp and FBP. especially, DLIR reconstructed images had excellent SNR and CNR at all tube voltages. In addition, the SSIM index was analyzed to be closest to 1, showing the highest similarity to the original image. Therefore, when performing repeated chest CT examinations, the application of DLIR can reduce the examination dose by about 29.7%, which is expected to help solve some of the biggest problems with CT examinations, namely radiation exposure due to the examination.

• Journal of the Korean Society of Radiology
• /
• v.16 no.3
• /
• pp.295-302
• /
• 2022

Sparse-view computed tomography (CT) imaging technique is able to reduce radiation dose, ensure the uniformity of image characteristics among projections and suppress noise. However, the reconstructed images obtained by the sparse-view CT imaging technique suffer from severe artifacts, resulting in the distortion of image quality and internal structures. In this study, we proposed a convolutional neural network (CNN) with wavelet transformation and residual learning for reducing artifacts in sparse-view CT image, and the performance of the trained model was quantitatively analyzed. The CNN consisted of wavelet transformation, convolutional and inverse wavelet transformation layers, and input and output images were configured as sparse-view CT images and residual images, respectively. For training the CNN, the loss function was calculated by using mean squared error (MSE), and the Adam function was used as an optimizer. Result images were obtained by subtracting the residual images, which were predicted by the trained model, from sparse-view CT images. The quantitative accuracy of the result images were measured in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The results showed that the trained model is able to improve the spatial resolution of the result images as well as reduce artifacts in sparse-view CT images effectively. Also, the trained model increased the PSNR and SSIM by 8.18% and 19.71% in comparison to the imaging model trained without wavelet transformation and residual learning, respectively. Therefore, the imaging model proposed in this study can restore the image quality of sparse-view CT image by reducing artifacts, improving spatial resolution and quantitative accuracy.

• Journal of the Korean Society of Radiology
• /
• v.17 no.1
• /
• pp.37-46
• /
• 2023

This study aims to evaluate the usefulness of Deep Learning Image Reconstruction (TrueFidelity, TF), the image quality of existing Filtered Back Projection (FBP) and Adaptive Statistical Iterative Reconstruction-Veo (ASIR-V) were compared. Noise, CNR, and SSIM were measured by obtaining images with doses fixed at 17.29 mGy and altered to 10.37 mGy, 12.10 mGy, 13.83 mGy, and 15.56 mGy in reconstruction techniques of FBP, ASIR-V 50%, and TF-H. TF-H has superior image quality compared to FBP and ASIR-V when the reconstruction technique change is given at 17.29 mGy. When dose changes were made, Noise, CNR, and SSIM were significantly different when comparing 10.37 mGy TF-H and FBP (p<0.05), and no significant difference when comparing 10.37 mGy TF-H and ASIR-V 50% (p>0.05). TF-H has a dose-reduction effect of 30%, as the highest dose of 15.56 mGy ASIR-V has the same image quality as the lowest dose of 10.37 mGy TF-H. Thus, Deep Learning Reconstruction techniques (TF) were able to reduce dose compared to Iterative Reconstruction techniques (ASIR-V) and Filtered Back Projection (FBP). Therefore, it is considered to reduce the exposure dose of patients.

• Geophysics and Geophysical Exploration
• /
• v.25 no.3
• /
• pp.140-161
• /
• 2022

Seismic data with missing traces are often obtained regularly or irregularly due to environmental and economic constraints in their acquisition. Accordingly, seismic data interpolation is an essential step in seismic data processing. Recently, research activity on machine learning-based seismic data interpolation has been flourishing. In particular, convolutional neural network (CNN) and generative adversarial network (GAN), which are widely used algorithms for super-resolution problem solving in the image processing field, are also used for seismic data interpolation. In this study, CNN-based algorithm, U-Net and GAN-based algorithm, and conditional Wasserstein GAN (cWGAN) were used as seismic data interpolation methods. The results and performances of the methods were evaluated thoroughly to find an optimal interpolation method, which reconstructs with high accuracy missing seismic data. The work process for model training and performance evaluation was divided into two cases (i.e., Cases I and II). In Case I, we trained the model using only the regularly sampled data with 50% missing traces. We evaluated the model performance by applying the trained model to a total of six different test datasets, which consisted of a combination of regular, irregular, and sampling ratios. In Case II, six different models were generated using the training datasets sampled in the same way as the six test datasets. The models were applied to the same test datasets used in Case I to compare the results. We found that cWGAN showed better prediction performance than U-Net with higher PSNR and SSIM. However, cWGAN generated additional noise to the prediction results; thus, an ensemble technique was performed to remove the noise and improve the accuracy. The cWGAN ensemble model removed successfully the noise and showed improved PSNR and SSIM compared with existing individual models.

• Journal of the Korean Society of Radiology
• /
• v.17 no.2
• /
• pp.191-199
• /
• 2023

This study aimed to propose minimized radiation doses with an optimized abdomen x-ray image, which realizes a Deep Blind Image Super-Resolution Generative adversarial network (BSRGAN) technique. Entrance surface doses (ESD) measured were collected by changing exposure conditions. In the identical exposures, abdominal images were acquired and were processed with the BSRGAN. The images reconstructed by the BSRGAN were compared to a reference image with 80 kVp and 320 mA, which was evaluated by mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). In addition, signal profile analysis was employed to validate the effect of the images reconstructed by the BSRGAN. The exposure conditions with the lowest MSE (about 0.285) were shown in 90 kVp, 125 mA and 100 kVp, 100 mA, which decreased the ESD in about 52 to 53% reduction), exhibiting PSNR = 37.694 and SSIM = 0.999. The signal intensity variations in the optimized conditions rather decreased than that of the reference image. This means that the optimized exposure conditions would obtain reasonable image quality with a substantial decrease of the radiation dose, indicating it could sufficiently reflect the concept of As Low As Reasonably Achievable (ALARA) as the principle of radiation protection.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.1-8
• /
• 2010

This paper proposes a new frame rate up-conversion method. First, the proposed triple frame-based bidirectional motion estimation method reduce block artifacts in the interpolated frame by solving the wrong motion estimation in the area with similar characteristics. Second, the proposed motion vector smoothing reduces outliers, which result in block artifacts, considering the spatio-temporal neighboring motion vectors. In the experiments, the proposed frame rate up-conversion method improves the average PSNR and SSIM by up to 4.337 dB and 0.089, respectively, compared to the existing methods.

• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.448-463
• /
• 2017

Multimedia is a ubiquitous and indispensable part of our daily life and learning such as audio, image, and video. Objective and subjective quality evaluations play an important role in various multimedia applications. Blind image quality assessment (BIQA) is used to indicate the perceptual quality of a distorted image, while its reference image is not considered and used. Blur is one of the common image distortions. In this paper, we propose a novel BIQA index for Gaussian blur distortion based on the fact that images with different blur degree will have different changes through the same blur. We describe this discrimination from three aspects: color, edge, and structure. For color, we adopt color histogram; for edge, we use edge intensity map, and saliency map is used as the weighting function to be consistent with human visual system (HVS); for structure, we use structure tensor and structural similarity (SSIM) index. Numerous experiments based on four benchmark databases show that our proposed index is highly consistent with the subjective quality assessment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.3C
• /
• pp.241-248
• /
• 2007

In predictive image coding, a LS (Least Squares)-based adaptive predictor is an efficient method to improve image edge predictions. This paper proposes a hybrid interpolation with weighted edge detector. A hybrid approach of switching between bilinear interpolation and EDI (Edge-Directed Interpolation) is proposed in order to reduce the overall computational complexity The objective and subjective quality is also similar to the bilinear interpolation and EDI. Experimental results demonstrate that this hybrid interpolation method that utilizes a weighted edge detector can achieve reduction in complexity with minimal degradation in the interpolation results.