Hyun Jun Park

Pusan National University, Tsau-liang-hai, Busan, South Korea

Are you Hyun Jun Park?

Claim your profile

Publications (77)111.08 Total impact

  • Source
    Kwang Baek Kim · Doo Heon Song · Hyun Jun Park
    [Show abstract] [Hide abstract]
    ABSTRACT: Deep Cervical Flexor (DCF) muscles are important in monitoring and controlling neck pain. While ultrasonographic analysis is useful in this area, it has intrinsic subjectivity problem. In this paper, we propose automatic DCF extractor/analyzer software based on computer vision. One of the major difficulties in developing such an automatic analyzer is to detect important organs and their boundaries under very low brightness contrast environment. Our fuzzy sigma binarization process is one of the answers for that problem. Another difficulty is to compensate information loss that happened during such image processing procedures. Many morphologically motivated image processing algorithms are applied for that purpose. The proposed method is verified as successful in extracting DCFs and measuring thicknesses in experiment using two hundred 800 × 600 DICOM ultrasonography images with 98.5% extraction rate. Also, the thickness of DCFs automatically measured by this software has small difference (less than 0.3 cm) for 89.8% of extracted DCFs.
    Full-text · Article · Feb 2016 · Computational and Mathematical Methods in Medicine
  • Kwang Baek Kim · Hyun Jun Park · Doo Heon Song
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose an intelligent self-health pre-diagnosis system for Korea traditional medicine (KTM). KTM is popularly used among general public with western medicine among Korean people worldwide. Our system consists of the standardised database constructed based on famous textbooks and government reports, fuzzy ART learning engine to extract top three most probable disease from user symptoms and a remote consultation communication platform. The database contents are verified by KTM doctors for reliability and the experiment verifies its functionality successfully. We expect this effort can improve the accessibility of healthcare among elderly people and people living in small towns where western type healthcare is not well equipped from community healthcare point of view.
    No preview · Article · Jan 2016 · International Journal of Information and Communication Technology
  • [Show abstract] [Hide abstract]
    ABSTRACT: Analyzing cervical vertebra is an important topic of caring patients with neck pains. While being noninvasive, cheap, and having real time convenience, ultrasound sonographic analysis has problems on subjectivity of inspectors. Thus, we need fully automatic assisting software for extracting major organs around cervical vertebrae. In this paper, we propose a method for automatic extraction of subcutaneous fat area with various image processing techniques. Carefully designed procedure including combining two types of binarization processes is the key point of the proposed method. Computationally heavy but sensitive adaptable fuzzy sigma binarization and simple thresholding binarization result are combined and the connectivity of the boundary lines is compensated by cubic spline interpolation. In experiment, the proposed method shows 97.6% success rate of extracting target area.
    No preview · Article · Jan 2016 · Asia life sciences
  • Hyun Jun Park · Kwang Baek Kim

    No preview · Article · Dec 2015
  • Source
    Kwang Baek Kim · Hyun Jun Park · Doo Heon Song · Sang-suk Han
    [Show abstract] [Hide abstract]
    ABSTRACT: Ultrasound examination (US) does a key role in the diagnosis and management of the patients with clinically suspected appendicitis which is the most common abdominal surgical emergency. Among the various sonographic findings of appendicitis, outer diameter of the appendix is most important. Therefore, clear delineation of the appendix on US images is essential. In this paper, we propose a new intelligent method to extract appendix automatically from abdominal sonographic images as a basic building block of developing such an intelligent tool for medical practitioners. Knowing that the appendix is located at the lower organ area below the bottom fascia line, we conduct a series of image processing techniques to find the fascia line correctly. And then we apply fuzzy ART learning algorithm to the organ area in order to extract appendix accurately. The experiment verifies that the proposed method is highly accurate (successful in 38 out of 40 cases) in extracting appendix.
    Full-text · Article · Jun 2015 · Computational and Mathematical Methods in Medicine
  • Hyun Jun Park · Sangmin Choe · Nam Cheol Park
    [Show abstract] [Hide abstract]
    ABSTRACT: To investigate the effects of Korean red ginseng (KRG) on semen parameters in male infertility patients in a randomized, double-blind, placebo-controlled study. A total of 80 male infertility patients with varicocele were recruited from April 2011 to February 2012. The subjects were then divided into the following four groups: non-varicocelectomy (V)+placebo (P) group, V+P group, non-V+KRG group (1.5-g KRG daily), and V+KGR group (1.5-g KRG daily). Semen analysis was performed and hormonal levels were measured in each treatment arm after 12 weeks. All groups but not the non-V+P group, showed significant improvements in sperm concentrations, motility, morphology, and viability at the end of the study. However, there were no significant differences in serum follicle-stimulating hormone, luteinizing hormone, and testosterone among groups. The incidence of adverse events was low, and all events were assumed to be unrelated to the treatments administered. Although the exact mechanism by which KRG improves spermatogenesis remains unclear, KRG may be a useful agent for the treatment of male infertility. Nevertheless, additional studies to evaluate the optimal dose and duration of treatment are needed.
    No preview · Article · May 2015 · Chinese Journal of Integrative Medicine
  • Source
    Ja Yoon Ku · Nam Cheol Park · Tae Gyeong Jeon · Hyun Jun Park
    [Show abstract] [Hide abstract]
    ABSTRACT: This study evaluated the demographics and semen parameters of males with cancer who banked their sperm prior to chemotherapy. This is a retrospective study of 66 cases referred for sperm banking prior to initiation of chemotherapy over a 15-year period (1999~2014). Patients who had previously received cancer treatment including chemotherapy or radiotherapy were not included in this study. We studied a total of 66 cancer patients referred for cryopreservation of sperm prior to chemotherapy. The mean age of the patients at the time of banking was 32.0±7.9 years (range, 19~58 years). The types of cancer were testicular cancer (31 cases, 47.0%), non-Hodgkin's disease (10 cases, 15.1%), Hodgkin's disease (5 cases, 7.6%), leukemia (8 cases, 12.1%), gastrointestinal malignancy (5 cases, 7.6%), and musculoskeletal malignancy (5 cases, 7.6%). There were significant differences in sperm concentration and viability among the various types of cancer, but no significant difference in semen volume or sperm motility and morphology. In this study we found that sperm quality could decrease even before chemotherapy. Because chemotherapy can also negatively affect spermatogenesis, sperm cryopreservation prior to treatment should be strongly recommended for cancer patients of reproductive age.
    Full-text · Article · Apr 2015
  • Seung Ik Park · Hyun Jun Park · Kwang Beak Kim
    [Show abstract] [Hide abstract]
    ABSTRACT: Diagnosis of appendicitis is an area of interest in clinical research since long. Specifically speaking, accurate diagnosis of acute appendicitis is important since it needs subsequent surgical operations and particularly if the patient is a pregnant woman or a child. However, after ultrasonography, medical expert's naked-eye examination is finally done, which is being practiced till date. Although developing full automatic appendicitis diagnosing software is a far reach goal to achieve since there are still many techniques and theories yet to be developed, but an automatic appendix extracting software can definitely developed in near future, which is now the interest of study of many researchers. In this paper, a method is proposed to extract appendix automatically from a ultrasound image. The proposed method uses various image processing techniques with morphological features of appendix. The advantages of Cubic Spline interpolation for extracting fascia area and subsequently applying K-Means clustering for extraction of appendix from the image is being discussed in this paper. Experimental result shows the appendix extracted through this method is acceptable to medical expert.
    No preview · Article · Feb 2015 · International Journal of Bio-Science and Bio-Technology
  • Hyun Jun Park · Kwang Baek Kim · Eui-Young Cha
    [Show abstract] [Hide abstract]
    ABSTRACT: In the ultrasound image, the gallbladder has a wide variety of shape, type, size, and slope, so the existing researches into contour-based gallbladder detection cannot be applied to the various types of gallbladder. Therefore, in this paper, we present a new approach to locate the gallbladder from ultrasound image using ends-in search stretching and self organizing map (SOM)-based color quantization. We use the ends-in search stretching technique to emphasize the difference in brightness among the structures, and SOM-based color quantization is used to classify pixels into the gallbladder and gallbladder wall. After SOM-based color quantization, we extract gallbladder candidates. To verify the gallbladder candidates, we define five morphologic characteristics-based rough conditions. We experiment using 30 ultrasound images. Experiment results shows the proposed method locates the gallbladder excellently despite gallbladders have a variety of shapes.
    No preview · Article · Feb 2015 · Current Medical Imaging Reviews
  • Source
    Hyun Jun Park · Kwang Baek Kim · Eui Young Cha
    [Show abstract] [Hide abstract]
    ABSTRACT: Color quantization is an important process for image processing and various applications. Up to now, many color quantization methods have been proposed. The self-organizing maps (SUM) method is one of the most effective color quantization methods, which gives excellent color quantization results. However, it is slow, so it is not suitable for real-time applications. In this paper, we present a color importance based SUM color quantization method. The proposed method dynamically adjusts the learning rate and the radius of the neighborhood using color importance. This makes the proposed method faster than the conventional SUM-based color quantization method. We compare the proposed method to 10 well-known color quantization methods to evaluate performance. The methods are compared by measuring mean absolute error (MAE), mean square error (MSE), and processing time. The experimental results show that the proposed method is effective and excellent for color quantization. Not only does the proposed method provide the best results compared to the other methods, but it uses only 67.18% of the processing time of the conventional SUM method.
    Preview · Article · Jan 2015 · Neural Network World
  • Source
    Do Hoon Kong · Chang Jin Yun · Hyun Jun Park · Nam Cheol Park
    [Show abstract] [Hide abstract]
    ABSTRACT: The aim of this study was to investigate the efficacy of mirodenafil in middle-aged male patients with chronic prostatitis/chronic pelvic pain syndrome (CP/CPPS). Eighty-eight males with CP/CPPS were randomized to receive either levofloxacin (500 mg/d) (group L, 40 patients) or levofloxacin (500 mg/d) and mirodenafil (50 mg/d) (group ML, 48 patients) for six weeks. The International Prostate Symptom Score (IPSS), National Institutes of Health Chronic Prostatitis Symptom Index (NIH-CPSI), and erectile function (EF) domain scores of the International Index of Erectile Function (IIEF) questionnaire were used to grade symptoms at baseline and 6 weeks after treatment. The mean change in total IPSS from baseline was higher in group ML than that in group L (group L, -1.1 vs. group ML, -4.3; p<0.05). Significant improvements were also seen in the IPSS voiding subscore (group L, -0.7 vs. group ML, -3.0; p<0.05). Changes observed in the NIH-CPSI of group ML at six weeks were greater than those at baseline (group L, -3.2 vs. group ML, -7.2; p<0.05). Significant improvements were seen in the NIH-CPSI voiding (group L, -0.5 vs. group ML, -1.7; p<0.05) and quality of life domains (group L, -1.0 vs. group ML, -1.8; p<0.05). Group ML showed a significantly greater increase in the IIEF-EF score than did group ML (group L, +0.2 vs. group ML, +7.8; p<0.05). Mirodenafil (50 mg once daily) was well tolerated and resulted in significant symptomatic improvement in middle-aged males with CP/CPPS.
    Preview · Article · Dec 2014
  • Kwang Baek Kim · Hyun Jun Park · Doo Heon Song
    [Show abstract] [Hide abstract]
    ABSTRACT: A sequence alignment algorithm is a basic building block for protein analysis and nucleic acid analysis in bioinformatics. Such alignment represents the similarities and differences of two or more compared sequences. Thus, there have been many algorithms and tools studied and developed. In this paper, we focus on the PHRED based sequence alignment algorithm using Needleman-Wunsch dynamic programming. Although it is well known and proven to be reliable to some extent, it suffers from the heavy computation of producing scoring matrix based on dynamic programming whose time complexity is O(mn). We propose a method applying quadrant method in that process to reduce the computational loads. Also, PHRED based algorithms suffer from the environment when low quality bases are frequently in tips of DNA fragments. Thus, we designed a fuzzy logic system to control the gap cost dynamically to improve the quality of the alignment. In the experiment using real genome data from NCBI (National Center for Biotechnology Information), we verify that the proposed method reduces the computational loads by half in producing scoring matrix and thus the alignment quality is also improved by our fuzzy inference system.
    No preview · Article · Nov 2014 · Current Bioinformatics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Lymphangioma is a rare, benign mesenchymal neoplasm, which is characterized by numerous intercommunicating cystic spaces containing lymphatic fluid. It is considered a congenital disease resulting from the obstruction of regional lymph drainage during the developmental period. Lymphangioma may be focal/unilateral or diffuse/bilateral, and in the latter case, it is referred to as lymphangiomatosis. Here, we report a case of a 38-year-old man with perirenal lymphangiomatosis. The patient's chief complaint was left flank pain, and left pleural effusion was found on radiological examination. After radical nephrectomy, the pathological examinations revealed that the kidney was enclosed by a multicystic mass with intrarenal cystic dilatations. We report the case and discuss the management of perirenal lymphangiomatosis with a literature review.
    Full-text · Article · Aug 2014
  • Kwang Baek Kim · Hyun Jun Park · Doo Heon Song · Sang-suk Han
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a method to extract sternocleidomastoid and longus capitis/colli automatically and measure the thickness of those muscles from cervical vertebrae ultrasound images. Extracting sternocleidomastoid is relatively easy but for longus capitis/colli case, due to the brightness sensitivity, it requires much more computationally burdensome procedures. In the binarization process, instead of simple and cheap thresholding method, we apply fuzzy sigma binarization to mitigate the sensitivity. Since that binarization procedure is computationally expensive we keep thresholding method for sternocleidomastoid case. With considerate image processing processes such as 4-directional contour analysis and Cubic Spline interpolation, we can successfully analyze features like muscle thickness. In experiment, the efficacy of the proposed method is verified as having 73 ~ 87% of real world cervical vertebrae images successfully analyzed meaning that only a small magnitude of errors in measuring thickness from medical expert's own measurement (less than 0.1 cm for sternocleidomastoid and less than 0.3 cm for longus capitis/colli). We hope such result encourages the use of automatic ultrasound analysis system for cervical vertebrae in rehabilitation practices.
    No preview · Article · Jul 2014 · Current Medical Imaging Reviews
  • Kwang Baek Kim · Hyun Jun Park · Gwang Ha Kim
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a new fully computerized image analysis method for measuring the thickness of muscles from ultrasound image obtained by muscle endurance test using morphological information of fascia and thoracic vertebra. Firstly, we divide the image into lumbar region and thoracolumbar region by the difference of density in image for measuring the thickness of muscles. In lumbar region, we notice that the intensity of fascia is relatively higher than other parts. Thus, we measure the thickness of muscles surrounding the fascia area. In the process, we apply median filter to candidate fascia areas for extracting candidate muscle layers between fascias. Then, the thickness of muscles we measure is that of the third layer. In thoracolumbar region, we apply region expansion method for classifying the region into subcutaneous fat part and part including thoracic vertebra. Then, we apply counting method and evolutionary computation search model to find the measuring location that is in between subcutaneous fat area and thoracic vertebra. In experiment, the proposed method is effective in measuring the thickness of muscles and avoids failures of previous studies. The performance of this approach is sufficiently comparable to that of medical experts.
    No preview · Article · Jul 2014 · Multimedia Tools and Applications
  • Kwang Baek Kim · Hyun Jun Park · Doo Heon Song
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a self-health diagnosis system based on Korea Traditional Medicine that has thousand years of history and popular in Korean general public. The system requires constructing a reliable diseases-symptoms database and classification learning method. Database construction is based on various reports submitted to the government about "Diseases burdensome to Korean Patients" in 2005 and medical contents "Engel Pharm" with 60 diseases. An enhanced ART2 algorithm that has dynamic control of boundary variables to control the number of clusters inside is used to extract top five most probable diseases generated by simple user input. The constructed database and test diagnosis results are verified by Korean Traditional medical doctors and the experiment also shows that the system is easily accessible and reliable in accuracy.
    No preview · Article · Jun 2014 · International Journal of Bio-Science and Bio-Technology
  • [Show abstract] [Hide abstract]
    ABSTRACT: Objective: To investigate the reasons for prescription change of α1-blockers in patients with lower urinary tract symptoms suggestive of benign prostatic hyperplasia. Methods: The ratio and interval of prescription change were assessed in 3200 patients who were eligible for the study and took 1 of 4 different α1-blockers (doxazosin, alfuzosin, tamsulosin, or silodosin). The reasons for prescription change and evaluation of efficacy were analyzed in 444 patients whose medical records were complete. Results: Prescription change to another α1-blocker occurred in 694 of 3200 patients (21.7%), and the mean duration of taking their first α1-blocker was 10.8 ± 8.2 weeks. Lack of efficacy (52.7%) was the main reason for changing α1-blockers, followed by adverse events (33.1%), relatively high cost compared with other α1-blockers (7.0%), inconvenience of taking drugs (4.1%), and cardiovascular comorbidity (3.2%). The mean duration of treatment according to each reason is as follows: increased adverse events: 6.3 ± 5.2 weeks, relatively high cost compared with other α1-blockers: 8.7 ± 4.5 weeks, cardiovascular comorbidity: 10.5 ± 6.8 weeks, inconvenience of taking drugs: 10.8 ± 3.9 weeks, and lack of efficacy: 14.8 ± 6.8 weeks. The proportion of prescription change (16.3%) and prescription change because of hemodynamic adverse events (2.4%) in the silodosin group were low compared with those in the other groups (P <.05 and P <.006, respectively), but prescription change because of a ejaculation disorder was high in the silodosin group (30.1%, P <.001). Conclusion: Major reasons for prescription change in patients taking α1-blockers were lack of efficacy and adverse events. In the silodosin group, the proportion of prescription change was significantly low compared with that in the other 3 groups.
    No preview · Article · Jun 2014 · Urology

  • No preview · Article · Apr 2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Phosphodiesterase type 5 (PDE5) inhibitors are the most commonly used treatment for erectile dysfunction (ED). Since the launch of sildenafil, several drugs-including mirodenafil, sildenafil citrate (sildenafil), tadalafil, vardenafil HCL (vardenafil), udenafil, and avanafil-have become available. Mirodenafil is a newly developed pyrrolopyrimidinone compound, which is a potent, reversible, and selective oral PDE5 inhibitor. Mirodenafil was launched in Korea in 2007, and an orally disintegrating film of mirodenafil was developed in 2011 for benefitting patients having difficulty in swallowing tablets. This study aimed to review the pharmacokinetic characteristic profile of mirodenafil and report evidence on its efficacy in the case of ED. In addition, we reviewed randomized controlled studies of mirodenafil's daily administration and efficacy for lower urinary tract symptoms.
    Preview · Article · Apr 2014
  • Hyun Jun Park · Nam Cheol Park

    No preview · Article · Apr 2014 · The Journal of Urology

Publication Stats

293 Citations
111.08 Total Impact Points

Institutions

  • 2006-2015
    • Pusan National University
      • • Department of Urology
      • • Division of Computer Science and Engineering
      • • Department of Ophthalmology
      Tsau-liang-hai, Busan, South Korea
  • 2012
    • University of Ulsan
      Urusan, Ulsan, South Korea