• Journal of Biomedical Engineering Research
• /
• v.45 no.3
• /
• pp.118-127
• /
• 2024

Commonly deep learning methods for enhancing the quality of medical images use unpaired dataset due to the impracticality of acquiring paired dataset through commercial imaging system. In this paper, we propose a supervised learning method to enhance the quality of ultrasound images. The U-net model is designed by incorporating a divide-and-conquer approach that divides and processes an image into four parts to overcome data shortage and shorten the learning time. The proposed model is trained using paired dataset consisting of 828 pairs of low-quality and high-quality images with a resolution of 512x512 pixels obtained by varying the number of channels for the same subject. Out of a total of 828 pairs of images, 684 pairs are used as the training dataset, while the remaining 144 pairs served as the test dataset. In the test results, the average Mean Squared Error (MSE) was reduced from 87.6884 in the low-quality images to 45.5108 in the restored images. Additionally, the average Peak Signal-to-Noise Ratio (PSNR) was improved from 28.7550 to 31.8063, and the average Structural Similarity Index (SSIM) was increased from 0.4755 to 0.8511, demonstrating significant enhancements in image quality.

• International Journal of Contents
• /
• v.16 no.2
• /
• pp.8-18
• /
• 2020

Data is critical in deep learning but the scarcity of data often occurs in research, especially in the preparation of the paired training data. In this paper, document image binarization with unpaired data is studied by introducing adversarial learning, excluding the need for supervised or labeled datasets. However, the simple extension of the previous unpaired training to binarization inevitably leads to poor performance compared to paired data training. Thus, a new deep learning approach is proposed by introducing a multi-diversity of higher quality generated images. In this paper, a two-stage model is proposed that comprises the generative adversarial network (GAN) followed by the U-net network. In the first stage, the GAN uses the unpaired image data to create paired image data. With the second stage, the generated paired image data are passed through the U-net network for binarization. Thus, the trained U-net becomes the binarization model during the testing. The proposed model has been evaluated over the publicly available DIBCO dataset and it outperforms other techniques on unpaired training data. The paper shows the potential of using unpaired data for binarization, for the first time in the literature, which can be further improved to replace paired data training for binarization in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1486-1501
• /
• 2021

The removal of accessories from the face is one of the essential pre-processing stages in the field of face recognition. However, despite its importance, a robust solution has not yet been provided. This paper proposes a network and dataset construction methodology to remove only the glasses from facial images effectively. To obtain an image with the glasses removed from an image with glasses by the supervised learning method, a network that converts them and a set of paired data for training is required. To this end, we created a large number of synthetic images of glasses being worn using facial attribute transformation networks. We adopted the conditional GAN (cGAN) frameworks for training. The trained network converts the in-the-wild face image with glasses into an image without glasses and operates stably even in situations wherein the faces are of diverse races and ages and having different styles of glasses.

• Communications for Statistical Applications and Methods
• /
• v.3 no.1
• /
• pp.11-19
• /
• 1996

Canonical correlation analysis is a multivariate technique for identifying and quantifying the statistical relationship between two sets of variables. Like most multivariate techniques, the main objective of canonical correlation analysis is to reduce the dimensionality of the dataset. It would be particularly useful if high dimensional data can be represented in a low dimensional space. In this study, we will construct statistical graphs for paired sets of multivariate data. Specifically, plots of the observations as well as the variables are proposed. We discuss the geometric interpretation and goodness-of-fit of the proposed plots. We also provide a numerical example.

• Applied Microscopy
• /
• v.50
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2019

In this paper, we propose a video enhancement method using generative adversarial networks to remove raindrops and restore the background information on the removed region in the coastal wave video imagery distorted by raindrops during rainfall. Two experimental models are implemented: Pix2Pix network widely used for image-to-image translation and Attentive GAN, which is currently performing well for raindrop removal on a single images. The models are trained with a public dataset of paired natural images with and without raindrops and the trained models are evaluated their performance of raindrop removal and background information recovery of rainwater distortion of coastal wave video imagery. In order to improve the performance, we have acquired paired video dataset with and without raindrops at the real coast and conducted transfer learning to the pre-trained models with those new dataset. The performance of fine-tuned models is improved by comparing the results from pre-trained models. The performance is evaluated using the peak signal-to-noise ratio and structural similarity index and the fine-tuned Pix2Pix network by transfer learning shows the best performance to reconstruct distorted coastal wave video imagery by raindrops.

• Journal of the Korean Statistical Society
• /
• v.28 no.4
• /
• pp.469-478
• /
• 1999

We propose a Kolmogorov-Smirnov-type test for independence of paired failure times in the presence of independent censoring times. This independent censoring mechanism is often assumed in case-control studies. To do this end, we first introduce a process defined as the difference between the bivariate survival function estimator proposed by Wang and Wells (1997) and the product of the product-limit estimators (Kaplan and Meier (1958)) for the marginal survival functions. Then, we derive its asymptotic properties under the null hypothesis of independence. Finally, we assess the performance of the proposed test by simulations, and illustrate the proposed methodology with a dataset for remission times of 21 pairs of leukemia patients taken from Oakes(1982).

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.283-298
• /
• 2022

As Synthetic Aperture Radar (SAR) image can be acquired regardless of the weather and day or night, it is highly recommended to be used for Automatic Target Recognition (ATR) in the fields of surveillance, reconnaissance, and national security. However, there are some limitations in terms of cost and operation to build various and vast amounts of target images for the SAR-ATR system. Recently, interest in the development of an ATR system based on simulated SAR images using a target model is increasing. Attributed Scattering Center (ASC) matching and template matching mainly used in SAR-ATR are applied to target classification. The method based on ASC matching was developed by World View Vector (WVV) feature reconstruction and Weighted Bipartite Graph Matching (WBGM). The template matching was carried out by calculating the correlation coefficient between two simulated images reconstructed with adjacent points to each other. For the performance analysis of the two proposed methods, the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset was used, which has been recently published by the U.S. Defense Advanced Research Projects Agency (DARPA). We conducted experiments under standard operating conditions, partial target occlusion, and random occlusion. The performance of the ASC matching is generally superior to that of the template matching. Under the standard operating condition, the average recognition rate of the ASC matching is 85.1%, and the rate of the template matching is 74.4%. Also, the ASC matching has less performance variation across 10 targets. The ASC matching performed about 10% higher than the template matching according to the amount of target partial occlusion, and even with 60% random occlusion, the recognition rate was 73.4%.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.315-323
• /
• 2023

Post-mortem computed tomography (PMCT) is commonly employed in the field of forensic pathology. PMCT was mainly performed using a whole-body scan with a wide field of view (FOV), which lead to a decrease in spatial resolution due to the increased pixel size. This study aims to evaluate the potential for developing a super-resolution model based on conditional generative adversarial networks (CGAN) to enhance the image quality of CT. 1761 low-resolution images were obtained using a whole-body scan with a wide FOV of the head phantom, and 341 high-resolution images were obtained using the appropriate FOV for the head phantom. Of the 150 paired images in the total dataset, which were divided into training set (96 paired images) and validation set (54 paired images). Data augmentation was perform to improve the effectiveness of training by implementing rotations and flips. To evaluate the performance of the proposed model, we used the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and Deep Image Structure and Texture Similarity (DISTS). Obtained the PSNR, SSIM, and DISTS values of the entire image and the Medial orbital wall, the zygomatic arch, and the temporal bone, where fractures often occur during head trauma. The proposed method demonstrated improvements in values of PSNR by 13.14%, SSIM by 13.10% and DISTS by 45.45% when compared to low-resolution images. The image quality of the three areas where fractures commonly occur during head trauma has also improved compared to low-resolution images.

• Genomics & Informatics
• /
• v.16 no.3
• /
• pp.71-74
• /
• 2018

Because castration-resistant prostate cancer (CRPC) does not respond to androgen deprivation therapy and has a very poor prognosis, it is critical to identify a prognostic indicator for predicting high-risk patients who will develop CRPC. Here, we report a dataset of whole genomes from four pairs of primary prostate cancer (PC) and CRPC samples. The analysis of the paired PC and CRPC samples in the whole-genome data showed that the average number of somatic mutations per patients was 7,927 in CRPC tissues compared with primary PC tissues (range, 1,691 to 21,705). Our whole-genome sequencing data of primary PC and CRPC may be useful for understanding the genomic changes and molecular mechanisms that occur during the progression from PC to CRPC.