• 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.

• Journal of the Korean Society of Radiology
• /
• v.15 no.6
• /
• pp.891-897
• /
• 2021

With the development of Amyloid PET Tracer, the accuracy of Alzheimer's diagnosis can be improved through the identification of beta-amyloid neurites. However, the long image acquisition time of 20 minutes can be difficult for the patient. PET/CT scans are sensitive to patient movement and may partially affect test results. In this study, we studied the proper image acquisition time without affecting the quantitative evaluation of the image through the list mode acquisition method according to the time of the distribution of radioactive drugs in the body. The list mode includes information about time compared to the existing frame mode, and it is easy to analyze data because it can reconstruct images about the time that researchers want. The research method obtained a reconstructed image by time using a list mode of 5min frame/bed, 10min frame/bed, 15min frame/bed, and 20min frame/bed to compare the difference between signal-to-pons take ratio (SNR) and lesion-to-pons uptake ratio (LPR) and the difference in reading time to obtain an appropriate image. As a result of quantitative analysis, when measuring in list mode, SUVmean values decreased in 6 regions of interest as the image acquisition time increased, but showed the largest difference in 5 min/bed images, followed by 10 min/bed and 15 min/bed. As a result, the difference in SUVmean values decreased. Therefore, it was found that SUVmean values at 15 min/bed did not differ enough to not affect image evaluation. There was no difference in LPR values. As a result of the qualitative analysis, there was no change in the reading findings according to the PET image acquisition time and there was no significant difference in the qualitative analysis score of the image reconstruction according to time. As a result of the study, there is no significant difference between 15 min/bed and 20 min/bed images during the ¹⁸F-flutemetamol PET/CT test, so it can be said that it is clinically useful to reduce the image acquisition time selectively using 15 min/bed via list mode depending on the patient's condition.

• Investigative Magnetic Resonance Imaging
• /
• v.18 no.4
• /
• pp.303-313
• /
• 2014

Purpose : In-vivo conductivity reconstruction using transmit field ($B_1{^+}$) information of MRI was proposed. We assessed the accuracy of conductivity reconstruction in the presence of statistical noise in complex $B_1{^+}$ map and provided a parametric model of the conductivity-to-noise ratio value. Materials and Methods: The $B_1{^+}$ distribution was simulated for a cylindrical phantom model. By adding complex Gaussian noise to the simulated $B_1{^+}$ map, quantitative conductivity estimation error was evaluated. The quantitative evaluation process was repeated over several different parameters such as Larmor frequency, object radius and SNR of $B_1{^+}$ map. A parametric model for the conductivity-to-noise ratio was developed according to these various parameters. Results: According to the simulation results, conductivity estimation is more sensitive to statistical noise in $B_1{^+}$ phase than to noise in $B_1{^+}$ magnitude. The conductivity estimate of the object of interest does not depend on the external object surrounding it. The conductivity-to-noise ratio is proportional to the signal-to-noise ratio of the $B_1{^+}$ map, Larmor frequency, the conductivity value itself and the number of averaged pixels. To estimate accurate conductivity value of the targeted tissue, SNR of $B_1{^+}$ map and adequate filtering size have to be taken into account for conductivity reconstruction process. In addition, the simulation result was verified at 3T conventional MRI scanner. Conclusion: Through all these relationships, quantitative conductivity estimation error due to statistical noise in $B_1{^+}$ map is modeled. By using this model, further issues regarding filtering and reconstruction algorithms can be investigated for MREPT.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.2
• /
• pp.23-32
• /
• 2020

The compression sensing technology, CAFB, was developed to obtain the raw signal of the target structure by compressing it into a signal of the intended frequency range. At this point, for compression sensing, the CAFB can be optimized for various reference signals depending on the desired frequency range of the target structure. In addition, optimized CAFB should be able to efficiently compress the effective structural answers of the target structure even in sudden/dangerous conditions such as earthquakes. In this paper, the targeted frequency range for efficient structural integrity monitoring of relatively flexible structures was set below 10Hz, and the optimization method of CAFB for this purpose and the seismic response performance of CAFB in seismic conditions were evaluated experimentally. To this end, in this paper, CAFB was first optimized using Kobe seismic waveform, and embedded it in its own wireless IDAQ system. In addition, seismic response tests were conducted on two span bridges using Kobe seismic waveform. Finally, using an IDAQ system with built-in CAFB, the seismic response of the two-span bridge was wirelessly obtained, and the compression signal obtained was cross-referenced with the raw signal. From the results of the experiment, the compression signal showed excellent response performance and data compression effects in relation to the raw signal, and CAFB was able to effectively compress and sensitize the effective structural response of the structure even in seismic situations. Finally, in this paper, the optimization method of CAFB was presented to suit the intended frequency range (less than 10Hz), and CAFB proved to be an economical and efficient data compression sensing technology for instrumentation-monitoring of seismic conditions.

• Korean Journal of Radiology
• /
• v.19 no.6
• /
• pp.1119-1129
• /
• 2018

Objective: To compare the image quality of low-tube-voltage and low-iodine-concentration-contrast-medium (LVLC) computed tomography urography (CTU) with iterative reconstruction (IR) with that of conventional CTU. Materials and Methods: This prospective, multi-institutional, randomized controlled trial was performed at 16 hospitals using CT scanners from various vendors. Patients were randomly assigned to the following groups: 1) the LVLC-CTU (80 kVp and 240 mgI/mL) with IR group and 2) the conventional CTU (120 kVp and 350 mgI/mL) with filtered-back projection group. The overall diagnostic acceptability, sharpness, and noise were assessed. Additionally, the mean attenuation, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and figure of merit (FOM) in the urinary tract were evaluated. Results: The study included 299 patients (LVLC-CTU group: 150 patients; conventional CTU group: 149 patients). The LVLC-CTU group had a significantly lower effective radiation dose ($5.73{\pm}4.04$ vs. $8.43{\pm}4.38mSv$) compared to the conventional CTU group. LVLC-CTU showed at least standard diagnostic acceptability (score ${\geq}3$), but it was non-inferior when compared to conventional CTU. The mean attenuation value, mean SNR, CNR, and FOM in all pre-defined segments of the urinary tract were significantly higher in the LVLC-CTU group than in the conventional CTU group. Conclusion: The diagnostic acceptability and quantitative image quality of LVLC-CTU with IR are not inferior to those of conventional CTU. Additionally, LVLC-CTU with IR is beneficial because both radiation exposure and total iodine load are reduced.

• Korean Journal of Radiology
• /
• v.22 no.4
• /
• pp.624-633
• /
• 2021

Objective: To evaluate the reliability of CT measurements of muscle quantity and quality using variable CT parameters. Materials and Methods: A phantom, simulating the L2-4 vertebral levels, was used for this study. CT images were repeatedly acquired with modulation of tube voltage, tube current, slice thickness, and the image reconstruction algorithm. Reference standard muscle compartments were obtained from the reference maps of the phantom. Cross-sectional area based on the Hounsfield unit (HU) thresholds of muscle and its components, and the mean density of the reference standard muscle compartment, were used to measure the muscle quantity and quality using different CT protocols. Signal-to-noise ratios (SNRs) were calculated in the images acquired with different settings. Results: The skeletal muscle area (threshold, -29 to 150 HU) was constant, regardless of the protocol, occupying at least 91.7% of the reference standard muscle compartment. Conversely, normal attenuation muscle area (30-150 HU) was not constant in the different protocols, varying between 59.7% and 81.7% of the reference standard muscle compartment. The mean density was lower than the target density stated by the manufacturer (45 HU) in all cases (range, 39.0-44.9 HU). The SNR decreased with low tube voltage, low tube current, and in sections with thin slices, whereas it increased when the iterative reconstruction algorithm was used. Conclusion: Measurement of muscle quantity using HU threshold was reliable, regardless of the CT protocol used. Conversely, the measurement of muscle quality using the mean density and narrow HU thresholds were inconsistent and inaccurate across different CT protocols. Therefore, further studies are warranted in future to determine the optimal CT protocols for reliable measurements of muscle quality.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.105-114
• /
• 2006

In this paper, 3D input and output systems for a web-based real-time 3D video communication system using IEEE 1394 digital cameras, Intel Xeon Server system and Microsoft Directshow library is proposed. And some conditions for optimizing the operations of the stereo camera, 3D display and signal processing system are analyzed. Input & output systems are carefully selected, which can satisfy the required optimization conditions and the final 3D video communication system is implemented by using three optimized devices. The overall control system is developed with Microsoft Visual C++.Net and Microsoft DirectX 9.1 SDK. Some experimental results show that the observer can feel the natural presence from multi-view(4-view) 3D video of server system in real-time and also can feel the natural presence from 3D video of client system and finally suggest an application possibility of the proposed web-based real-time 3D video communication in real fields.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.25-31
• /
• 2012

The audio vision system was developed for visually impaired people and usability was verified. In this study ten normal volunteers were included in the subject group and their mean age was 28.8 years old. Male and female ratio was 7:3. The usability of audio vision system was verified by as follows. First, volunteers learned distance of obstacles and up-down discrimination. After learning of audio vision system, indoor and outdoor walking examination was performed. The test was scored by ability of up-down and lateral discrimination, distance recognition and walking without collision. Each parameter was scored by 1 to 5. The results were 93.5 +- SD(ranges, 86 to 100) of 100. In this study, we could convert visual information to auditory information by audio-vision system and verified possibility of applying to daily life for visually impaired people.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.484-494
• /
• 2018

The uniform motion blur removing algorithm of Cho et al. has the problem that the edge region of the image cannot be restored clearly. We propose the effective algorithm to overcome this problem by using shock filter that reconstructs a blurred step signal into a sharp edge, and convolutional neural network (CNN) that learns by extracting features from the image. Then uniform motion blur kernel is estimated from the latent sharp image to remove blur in the image. The proposed algorithm improved the disadvantages of the conventional algorithm by reconstructing the latent sharp image using shock filter and CNN. Through the experimental results, it was confirmed that the proposed algorithm shows excellent reconstruction performance in objective and subjective image quality than the conventional algorithm.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.12
• /
• pp.843-855
• /
• 2015

This study developed a band-pass filter based artificial filter bank(BAFB) based on that in order to efficiently obtain the significant dynamic responses. The BAFB was then optimized about the El-centro earthquake wave which was often used in the construction research, and the software implementation of BAFB was finally embedded in the wireless unified management system(WiUMS). For the evaluation of the developed BAFB, a real time dynamic response experiment was performed on a cable-stayed bridge model, and the response of the cable-stayed bridge model was measured using both the traditional wired system and the developed BAFB-based WiUMS. The experiment results showed that the compressed dynamic response acquired by the BAFB-based WiUMS matched significantly with that of the traditional wired system while still carrying sufficient modal information of the cable-stayed bridge. Finally, the developed BAFB was able to reconstruct or re-sample the dynamic response wholly from the compressed response signal, and it can be applied as a new kind of measurement system for a wireless sensor networks based structural health monitoring system that secures both economy and efficiency.