• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.160-171
• /
• 1994

The wide dynamic range and severely attenuated contrast in mediastinal area appearing in typical chest radiographs have often caused difficulties in effective visualization and diagnosis of lung diseases. This paper proposes a new adaptive image enhancement technique which potentially solves this problem and there by improves observer performance through image processing. In the proposed method image processing is applied to the chest radiograph with different processing parameters for the lung field and mediastinum adaptively since there are much differences in anatomical and imaging properties between these two regions. To achieve this the chest radiograph is divided into the lung and mediastinum by gray level thresholding using the cumulative histogram and the dynamic range compression and local contrast enhancement are carried out selectively in the mediastinal region. Thereafter a gray scale transformation is performed considering the JND(just noticeable difference) characteristic for effective image displa. The processed images showed apparenty improved contrast in mediastinum and maintained moderate brightness in the lung field. No artifact could be observed. In the visibility evaluation experiment with 5 radiologists the processed images with better visibility was observed for the 5 important anatomical structures in the thorax.

• Journal of the Korean Geophysical Society
• /
• v.6 no.2
• /
• pp.71-77
• /
• 2003

Generally the dynamic characteristics of stone wall structures depend on several factors such as contact, the type of interlocking bonding stones, and the filling materials. This paper describes a non-destructive technique for diagnosis of historic masonry stone structures using the measurement of natural frequency technique. For this purpose, the castle wall of Nag-An Folk Town located in Sunchon, Korea was selected as a model. The Nag-An Town Castle is one of the well maintained historical remains constructed in the Chosun Kingdom of Korea. The construction started in 1397 A.D and was finished in 1626 A.D. The non-mortar castle wall is 1470m long and the average height is 4m with a width of 3 4m. The exterior of the wall is bonded with 1 2 m rectangular rough-faced stone and the inside of the wall is filled with gravel. The traditional village still remains inside the Nag-An Town Castle, and they have a regional food festival every October. Transverse vibrations were measured at 8 points around the castle. The measured natural frequency of the first mode was 26Hz 41Hz, and the shear modulus of filling material was 2.142 x $10^3$ ~ 8.915 x $10^3$kgf/$cm^2$ . With these results, it may be assumed that the filling material is gravel or a sand-gravel mixture. It is expected that the information provided by this paper will be useful for addressing the maintenance problems of the old castle walls.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.500-521
• /
• 2021

Echocardiography, an ultrasound scan of the heart, is regarded as the primary physiological test for heart disease diagnoses. How an echocardiogram is interpreted also relies intensively on the determination of the view. Some of such views are identified as standard views because of the presentation and ease of the evaluations of the major cardiac structures of them. However, finding valid cardiac views has traditionally been time-consuming, and a laborious process because medical imaging is interpreted manually by the specialist. Therefore, this study aims to speed up the diagnosis process and reduce diagnostic error by providing an automated identification of standard cardiac views based on deep learning technology. More importantly, based on a brand-new echocardiogram dataset of the Asian race, our research considers and assesses some new neural network architectures driven by action recognition in video. Finally, the research concludes and verifies that these methods aggregating dynamic information will receive a stronger classification effect.

• Journal of Biomedical Engineering Research
• /
• v.42 no.5
• /
• pp.232-240
• /
• 2021

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of a cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cell morphology, which reflects the physiological state of the cell, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, we visualize morphology state-space by two-dimensional embedding as well as representative morphology clusters and trajectories. This cell morphology profiling strategy by hybrid learning enables simplification of the heterogeneous population of cancer.

• Journal of applied mathematics & informatics
• /
• v.41 no.6
• /
• pp.1257-1274
• /
• 2023

Rotating machines heavily rely on an intricate network of interconnected sub-components, with bearing failures accounting for a substantial proportion (40% to 90%) of all such failures. To address this issue, intelligent algorithms have been developed to evaluate vibrational signals and accurately detect faults, thereby reducing the reliance on expert knowledge and lowering maintenance costs. Within the field of machine learning, Artificial Immune Systems (AIS) have exhibited notable potential, with applications ranging from malware detection in computer systems to fault detection in bearings, which is the primary focus of this study. In pursuit of this objective, we propose a novel procedure for detecting novel instances of anomalies in varying operating conditions, utilizing only the signals derived from the healthy state of the analyzed machine. Our approach incorporates AIS augmented by Dynamic Time Warping (DTW). The experimental outcomes demonstrate that the AIS-DTW method yields a considerable improvement in anomaly detection rates (up to 53.83%) compared to the conventional AIS. In summary, our findings indicate that our method represents a significant advancement in enhancing the resilience of AIS-based novelty detection, thereby bolstering the reliability of rotating machines and reducing the need for expertise in bearing fault detection.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.9
• /
• pp.3595-3604
• /
• 2015

Hepatocellular carcinoma (HCC) has been one of the most fatal malignant tumors worldwide and its associated morbidity and mortality remain of significant concern. Based on in-depth reviews of serological diagnosis of HCC, in addition to AFP, there are other biomarkers: Lens culinaris agglutinin-reactive AFP (AFP-L3), descarboxyprothrombin (DCP), tyrosine kinase with Ig and eprdermal growth factor (EGF) homology domains 2 (TIE2)-espressing monocytes (TEMs), glypican-3 (GPC3), Golgi protein 73 (GP73), interleukin-6 (IL-6), and squamous cell carcinoma antigen (SCCA) have been proposed as biomarkers for the early detection of HCC. The diagnosis of HCC is primarily based on noninvasive standard imaging methods, such as ultrasound (US), dynamic multiphasic multidetector-row CT (MDCT) and magnetic resonance imaging (MRI). Some experts advocate gadolinium diethyl-enetriamine pentaacetic acid (Gd-EOB-DTPA) MRI and contrast-enhanced US as the promising imaging madalities of choice. With regard to recent advancements in tissue markers, many cuting-edge technologies using genome-wide DNA microarrays, qRT-PCR, and proteomic and inmunostaining studies have been implemented in an attempt to identify markers for early diagnosis of HCC. Only less than half of HCC patients at initial diagnosis are at an early stage treatable with curative options: local ablation, surgical resection, or liver transplant. Transarterial chemoembolization (TACE) is considered the standard of care with palliation for intermediate stage HCC. Recent innovative procedures using drug-eluting-beads and radioembolization using Yttrium-90 may exhibit beneficial effects in HCC treatment. During the past few years, several molecular targeted agents have been evaluated in clinical trials in advanced HCC. Sorafenib is currently the only approved systemic treatment for HCC. It has been approved for the therapy of asymptomatic HCC patients with well-preserved liver function who are not candidates for potentially curative treatments, such as surgical resection or liver transplantation. In the USA, Europe and particularly Japan, hepatitis C virus (HCV) related HCC accounts for most liver cancer, as compared with Asia-Pacific regions, where hepatitis B virus (HBV) may play a more important role in HCC development. HBV vaccination, while a vaccine is not yet available against HCV, has been recognized as a best primary prevention method for HBV-related HCC, although in patients already infected with HBV or HCV, secondary prevention with antiviral therapy is still a reasonable strategy. In addition to HBV and HCV, attention should be paid to other relevant HCC risk factors, including nonalcoholic fatty liver disease due to obesity and diabetes, heavy alcohol consumption, and prolonged aflatoxin exposure. Interestingly, coffee and vitamin K2 have been proven to provide protective effects against HCC. Regarding tertiary prevention of HCC recurrence after surgical resection, addition of antiviral treatment has proven to be a rational strategy.

• Journal of the Korean Society of Physical Medicine
• /
• v.8 no.4
• /
• pp.609-617
• /
• 2013

PURPOSE: This study aims to provide effects of therapeutic techniques as well as basic materials of safety by comparing and analyzing the effects of hamstring flexibility and dynamic stability of lower lumbar according to Stretching and Massage Techniques to adults with reduced the flexibility of hamstring. METHODS: This study conducted differential diagnosis through sit and reach test(SRT) and Schober test to select subjects who have shortened hamstring without any spinal problem. Selected subjects were divided into two groups randomly; HSG(Hamstring Stretching Group, n=8) and HMG(Hamstring Massage Group, n=8) and they received treatment for 2 weeks. To take statistics, SRT and dynamic view using x-ray were used. RESULTS: On SRT, HSG and HMG showed significant difference between pre and post test. A comparison of the difference value between HSG and HMG, HSG($9.73{\pm}1.78$) has more remarkable outcome than HMG($2.78{\pm}0.56$). Lower lumbar intervertebral disc length test for Intervertebral disc length(IDL)L45 and IDLL5S1 did not show significant differences between two groups and difference value. CONCLUSION: This study showed that stretching is more effective to improve hamstring flexibility than massage technique. Especially, flexibility increase of the hamstring in vertebral stabilization cannot affect improvement possibility will make a flexibility in order and the intervention and stabilization exercise of the spine.

• Structural Engineering and Mechanics
• /
• v.72 no.6
• /
• pp.689-712
• /
• 2019

Time-series models like AR-ARX and ARMAX, provide a robust way to capture the dynamic properties of structures, and their residuals can be effectively used as features for damage detection. Even though several research papers discuss the implementation of AR-ARX and ARMAX models for damage diagnosis, they are basically been exploited so far for detecting the time instant of damage and also the spatial location of the damage. However, the inverse problem associated with damage quantification i.e. extent of damage using time series models is not been reported in the literature. In this paper, an approach to detect the extent of damage by combining the ARMAX model by formulating the inverse problem as a multi-constrained optimization problem and solving using a newly developed hybrid adaptive differential search with dynamic interaction is presented. The proposed variant of the differential search technique employs small multiple populations which perform the search independently and exchange the information with the dynamic neighborhood. The adaptive features and local search ability features are built into the algorithm in order to improve the convergence characteristics and also the overall performance of the technique. The multi-constrained optimization formulations of the inverse problem, associated with damage quantification using time series models, attempted here for the first time, can considerably improve the robustness of the search process. Numerical simulation studies have been carried out by considering three numerical examples to demonstrate the effectiveness of the proposed technique in robustly identifying the extent of the damage. Issues related to modeling errors and also measurement noise are also addressed in this paper.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.281-282
• /
• 1998

Recently, there has been growing interest in the assessment of physiological parameters on brain perfusion that provide more information than pure morphologic diagnosis. Quantification of parameters that characterize cerebral micro-circulation with magnetic resonance imaging is of great relevance for clinical application. We determine the local tissue concentration by exponential relationship between the relative signal reduction S(t)/$S_0$ and local tissue concentration of contrast material $C_m(t)$ in dynamic susceptibility contrast enhanced MR imaging. And then we made relative regional blood volume map by calculating the area under the measured concentration-time curves $C_m(t)$ during first pass of paramagnetic contrast material as a preliminary step for perfusion map. These images make it possible to compare the rCBV in different brain regions in one individual at a time. We have it in contemplation to obtain arterial and brain signal time curves simultaneously to make absolute rCBV and perfusion (rCBF) map. These maps may provide the method of comparative investigations of different patients having strong variation in AIF.

• Journal of Veterinary Clinics
• /
• v.32 no.2
• /
• pp.200-204
• /
• 2015

A 12-year-old neutered male Shih Tzu presented with constipation and dyschezia. Abdominal radiographs showed distension of the descending colon and dorsal compression of the colon by a soft tissue mass. The mass was well-marginated with homogeneous soft tissue attenuation and showed no evidence of metastasis on computed tomography (CT). The dynamic CT showed a consistently mild contrast enhancement. The perfusion and capillary permeability were lower than those of the gluteal muscle. The tentative imaging diagnosis was a benign intrapelvic tumor, which rarely shows angiogenesis. The mass was excised, and a leiomyoma was confirmed by histopathologic examination.