• The Journal of Korean Orthopaedic Ultrasound Society
• /
• v.5 no.2
• /
• pp.61-65
• /
• 2012

Purpose: The aim of this study was to evaluate the effectiveness of ultrasound-guide steroid injection according to Morton's neuroma size. Materials and Methods: From October 2008 to September 2011, 17 patients (23 cases) diagnosed with Morton's neuroma were investigated. All cases were female and mean age was 52.6 years old. Neuroma were measured by the horizontal and longitudinal length of the mass and underwent ultrasound-guided steroid (5 mg dexamethasone) injection. The efficacy of the injection was determined by Visual Analogue Scale pain score and patient satisfaction(subdivided 4 group-much improved, improved, not improved, aggrevation) Results: 7 of 23(30.4%) cases showed much improved and improved satisfaction and mean longitudinal and horizontal length were $0.71{\pm}0.39cm$ and $0.47{\pm}0.24cm$, respectively. 16 of 23(69.6%) cases showed not improved and aggrevation satisfaction and mean longitudinal and horizontal length were $0.83{\pm}0.42cm$ and $0.54{\pm}0.14cm$, repectively. There was a significant difference in VAS and patient satisfaction in case longitudinal and horizontal length were smaller than 0.5 cm and 0.4 cm. (p<0.05) Conclusion: The ultrasonography is a important modality in diagnosis and treatment of morton's neuroma. Ultrasound-guide steroid injection is effective in case longitudinal and horizontal length were smaller than 0.5 cm and 0.4 cm, respectively.

• The Journal of the Korean bone and joint tumor society
• /
• v.13 no.1
• /
• pp.55-59
• /
• 2007

Synovial chondroma is an uncommon benign lesion characterized by metaplastic cartilage formation within the synovial connective tissue, usually intraarticular, commonly affects the knee, hip and elbow. We would like to present the case of a 65-year-old man suffering from synovial chondroma of the right elbow responsible for radial nerve entrapment neuropathy. This is a case of synovial chondroma of the right elbow in an 65-year-old man presenting with pain and restricted joint movement of the right elbow, loss of extension and sensation of the right thumb and wrist. Plain radiographs showed narrowing of elbow joint space, bony spur on the edge of the joint, and radio-opaque sclerotic change of subchondral area. MRI revealed $16{\times}12$ mm sized round mass on the radial head, homogenous low signal on T1WI, heterogenous high and low signal on T2WI. The patient underwent marginal excision of the mass, compressing the radial nerve. Diagnosis was confirmed by histologic examination.

• Journal of the Korean Orthopaedic Association
• /
• v.55 no.3
• /
• pp.229-236
• /
• 2020

Purpose: This study examined the utility of preliminary magnetic resonance imaging (MRI) measurements in the ultrasound-guided L4 selective nerve root block. Materials and Methods: As a retrospective study, 71 patients, who met the criteria for outpatient visits from March 2016 to December 2017, were included. From March 2016 to February 2017, 31 patients who underwent an L4 nerve root block without MRI were classified as group A, and 40 patients who underwent an L4 nerve root block through MRI measurements from March 2017 to December 2017 were classified as group B. Group A was injected under ultrasound-guidance through the pararadicular approach without a pre-interventional MRI evaluation, and group B was injected under ultrasound-guidance according to the preliminary MRI measurements. The results were assessed using the numeric rating scale scores before, three hours, and two, six, and 12 weeks after the procedure. Results: At three hours after the procedure, the proportion of patients better than good results were 51.6% in group A and 67.5% in group B. At two weeks after the procedure, the proportion of patients with better than good results were 48.4% and 70.0% in groups A and B, respectively; 58.1% and 62.5% of patient of groups A and B, respectively, showed better than good results after six weeks. In 12 weeks after the procedure, the results of group A and B were 67.7% and 62.5%, respectively. At three hours and two weeks after the procedure, group B showed significant symptom improvement than group A (p<0.05). The procedures were repeated 2.8 and 1.7 times in groups A and B, respectively, between two and six weeks for satisfactory pain relief (p<0.05). Conclusion: A pre-interventional MRI evaluation might improve pain relief within the initial two weeks after ultrasound-guided L4 selective nerve root block by improving the success rate of the procedure.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.167-177
• /
• 2022

In order to obtain satellite image products using the image transmitted to the ground station after capturing the satellite images, many image pre/post-processing steps are involved. During the pre/post-processing, when converting from level 1R images to level 1G images, geometric correction is essential. An interpolation method necessary for geometric correction is inevitably used, and the quality of the level 1G images is determined according to the accuracy of the interpolation method. Also, it is crucial to speed up the interpolation algorithm by the level processor. In this paper, we proposed a lightweight CNN-based interpolation method required for geometric correction when converting from level 1R to level 1G. The proposed method doubles the resolution of satellite images and constructs a deep learning network with a lightweight deep convolutional neural network for fast processing speed. In addition, a feature map fusion method capable of improving the image quality of multispectral (MS) bands using panchromatic (PAN) band information was proposed. The images obtained through the proposed interpolation method improved by about 0.4 dB for the PAN image and about 4.9 dB for the MS image in the quantitative peak signal-to-noise ratio (PSNR) index compared to the existing deep learning-based interpolation methods. In addition, it was confirmed that the time required to acquire an image that is twice the resolution of the 36,500×36,500 input image based on the PAN image size is improved by about 1.6 times compared to the existing deep learning-based interpolation method.

• The Journal of Korean Orthopaedic Ultrasound Society
• /
• v.1 no.1
• /
• pp.27-30
• /
• 2008

Snapping triceps syndrome is a rare condition in which a distal portion of triceps and ulnar nerve dislocate over the medial epicondyle as the elbow is flexed or extended from flexed position. Because it is frequently misdiagnosed as other elbow pathologies, accurate diagnosis is essential and imaging study is often needed to confirm the abnormal movement of ulnar nerve and triceps. Ultraonography is a convenient and effective method which is able to allow continual visualization of soft tissue movement compared to the other imaging modality including MRI. We reported one patient of snapping triceps syndrome who was diagnosed with the use of dynamic ultrasonography and treated with ulna nerve anterior transposition and repositioning of medial head of triceps. And we also provide the usefulness of musculoskeletal ultrasonography for the diagnosis of snapping triceps syndrome.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.271-273
• /
• 2023

불수의적인 혀 움직임과 떨림은 다른 신체 부위의 떨림증상이 없이 혀만 움직이는 증상을 말하며, 신경 정신과적 문제와 한의학의 기혈허약 등의 증상에 의해 발생할 수 있다. 혀 영상 촬영 장치로 정면과 측면의 혀를 연속을 촬영하여 혀의 움직임과 떨림을 탐색하려 한다. 혀의 표면은 코너와 같은 특징점을 구하기 어려운 모양이므로 혀의 움직임의 특성을 찾아내는 것은 매우 어려운 일이다. 움직임을 추적하는 방법 중에서 Farnebäck optical flow 방법은 모든 픽셀에 대해서 optical flow를 계산하여 혀의 움직임을 추적할 수 있었다. 이러한 움직임의 크기를 정면과 측면 영상에 대해서 구할 수 있었고, 움직임의 방향도 구할 수 있었다. 혀의 움직임과 떨림에 대한 위치별 정보와 세기 정보를 이용하여 건강상태를 진단할 수 있을 것으로 생각된다.

• The Journal of the Korean bone and joint tumor society
• /
• v.9 no.2
• /
• pp.200-205
• /
• 2003

Purpose: To report our experiences of clinical features, treatment method and results of giant cell tumor of 5 patients in proximal fibula. Materials and Methods: Five patients managed with an en bloc resection preserving common peroneal nerve and lateral collateral ligament reconstruction with biceps femoris tendon followed up between January 1997 and July 2001. Preoperative plain radiograph and MRI and bone scan were checked. The recurrence of the tumor was judged by plain radiograph and clinical signs. Lateral instability of knee joint was checked during the outpatient follow-up. Results: The mean age of the patients at the time of operation was twenty- three (21-29). There were one male and four female patients. Dull pain was main symptom and palpable mass was seen in two patients. Peroneal nerve palsy and local recurrence were not observed except one case of temporary peroneal nerve palsy. During the outpatient follow up, one among 5 patients showed slight lateral instability and the other 4 patients showed no instabililty. Conclusion: Giant cell tumor in proximal fibula managed with an en bloc resection preserving common peroneal nerve and lateral collateral ligament reconstruction with biceps femoris tendon showed favorable results.

• The Journal of Korean Orthopaedic Ultrasound Society
• /
• v.5 no.2
• /
• pp.102-105
• /
• 2012

Schwannoma is a common peripheral nerve tumor that mainly occur at head and neck, flexor muscle of upper, and lower extrimity. In posterior tibial nerve schwannoma, diagnosis is difficult, since physicians often consider achilles tendinitis, posterior impingement syndrome, retrocalcaneal bursitis, or injury of the flexor tendons, as the primary cause in patients with posterior ankle pain. Ultrasonogram may be a simple tool to differentiate such various diseases. The authors report a case of posterior tibial nerve schwannoma diagnosed with ultrasonogram, which was initially misunderstood as achilles tendinitis.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.2 s.16
• /
• pp.23-33
• /
• 2000

On this study, Among the classification methods of land cover using satellite imagery, we compared the classification accuracy of Neural Network Classifier and that of Maximum Likelihood Classifier which has the characteristics of parametric and non-parametric classification method. In the assessment of classification accuracy, we analyzed the classification accuracy about testing area as well as training area that many analysts use generally when assess the classification accuracy. As a result, Neural Network Classifier is superior to Maximum Likelihood Classifier as much as 3% in the classification of training data. When ground reference data is used, we could get poor result from both of classification methods, but we could reach conclusion that the classification result of Neural Network Classifier is superior to the classification result of Maximum Likelihood Classifier as much as 10%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2023

Convolutional neural networks have already been applied to various fields beyond human visual processing capabilities in the image processing area. However, they are exposed to a severe risk of deteriorating model performance due to the appearance of adversarial attacks. In addition, defense technology to respond to adversarial attacks is effective against the attack but is vulnerable to other types of attacks. Therefore, to respond to an adversarial attack, it is necessary to analyze how the performance of the adversarial attack deteriorates through the process inside the convolutional neural network. In this study, the adversarial attack of the Alexnet and VGG11 models was analyzed using the population sparseness index, a measure of neuronal activity in neurophysiology. Through the research, it was observed in each layer that the population sparsity index for adversarial examples showed differences from that of benign examples.