• 대한금속재료학회지
• /
• 제50권5호
• /
• pp.401-406
• /
• 2012

When viewed using a magnetic resonance imaging (MRI) system, invasive materials inside the human body, in many cases, severely distort the MR image of human tissues. The degree of the MR image distortion increases in proportion not only to the difference in the susceptibility between the invasive material and the human tissue, but also to the intensity of the magnetic field induced by the MRI system. In this study, by blending paramagnetic Ti particles with diamagnetic graphite, we synthesized $Ti_{100-x}C_x$ composites that can reduce the artifact in the MR image under the high-strength magnetic field. Of the developed composites, $Ti_{70}C_{30}$ showed the magnetic susceptibility of ${\chi}=67.6{\times}10^{-6}$, which corresponds to 30% of those of commercially available Ti alloys, the lowest reported in the literature. The level of the MR image distortion in the vicinity of the $Ti_{70}C_{30}$ composite insert was nearly negligible even under the high magnetic field of 4.7 T. In this paper, we reported on a methodology of designing new structural materials for bio-applications, their synthesis, experimental confirmation and measurement of MR images.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권11호
• /
• pp.4487-4491
• /
• 2014

Objective: To explore the clinical manifestations and imaging characteristics of gliomatosis cerebri to raise the awareness and improve its diagnostic accuracy for patients. Materials and Methods: Clinical data, imaging characteristics and pathological examination of 12 patients with GC from Jan., 2008 to Jan., 2012 were analyzed retrospectively. Results: Patients with GC were clinically manifested with headache, vomiting, repeated seizures, fatigue and unstable walking, most of whom had more than 2 lesions involving in parietal lobe, followed by temporal lobe, frontal lobe, periventricular white matter and corpus callosum. Magnetic resonance imaging (MRI) showed diffuse distribution, T1-weighted images (T1WI) with equal and low signals and T2-weighted images (T2WI) with bilateral symmetrical high diffuse signals. There was no reinforcement by enhancement scanning and signals were different in diffusion-weighted images (DWI). The higher the tumor staging, the stronger the signals. Pathological examination showed neuroastrocytoma in which tumor tissues were manifested by infiltrative growth in blood vessels and around neurons. Conclusions: In clinical diagnosis of GC, much attention should be paid to the diffuse distribution of imaging characteristics, incomplete matching between clinical and imaging characteristics and confirmation by combining with histopathological examination.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• 한국임상수의학회지
• /
• 제31권4호
• /
• pp.337-340
• /
• 2014

An 11-year-old male Maltese dog was presented with sudden onset of convulsion and right sided circling. On neurological examination, left side proprioception and menace reflexes were delayed. Blood examinations indicated severe thrombocytopenia and increased hepatic enzymes. On brain magnetic resonance imaging, lesions were founded on the left lateral subarachnoid space area. Those lesions showed hyperintense on T1-weighted images, hyperintense on T2-weighted images and hyperintense on fluid attenuated inversion recovery images. Cerebrospinal fluid analysis revealed xanthochromia and erythrophagocytosis. Coagulation test results demonstrated that fibrin degradation product and D-dimer concentrations were higher than normal range. The patient expired few hours after presentation. This case report demonstrates intracranial hemorrhage with disseminated intravascular coagulation in a dog.

• 대한의용생체공학회:의공학회지
• /
• 제20권2호
• /
• pp.149-154
• /
• 1999

자기공명영상은 다른 의료영상에 비해서 보다 정확한 해부학적인 진단 정보를 제공해 주므로 널리 이용되고 있다. 본 논문에서는 이차원 축단면 뇌 자기총명영상을 분할하는 자동화 알고리즘과 병별에 의해서 손상된 슬라이스를 검출하는 알고리즘을 제안하였다. 영상분활 과정은 두단계로 구성되어 있는데, 첫 단계에서는 이진화와 형태학적 연산을 이용하여 대뇌영역을 추출하고, 둘째 단계에서는 FCM(Fuzzy C-means)알고리즘을 이용하여 추출된 대뇌 내부의 각 조직을 분할하였다. FCM알고리즘은 분할하는 조직의 수가 증가할수록 급격하게 많은 실행시간을 요구하므로 제안하는 두단계 영상분할 과정을 통하여 실행시간을 향상시켰다. 병변 인식은 해부학적지식과 패턴매칭을 이용하였다.

• 한국정보처리학회논문지
• /
• 제7권1호
• /
• pp.286-295
• /
• 2000

본 논문은 MR 영상의 비지도 분할을 위하여 MDL원리를 이용한 통계적 모델기반의 적응적 방법을 제안한다. 이 방법에서 조직 영역을 MRF로 모델링함으로써 잡음에 대응하고, 창으로 정의되는 국소영역 내의 밝기값을 가우스 혼합으로 모델링함으로써 영상의 비균일성을 흡수한다. 분할 알고리즘은 ICM을 기반으로 하며 MAP를 근사적으로 추정하고, 모델 파라미터를 국소영역으로부터 구한다. 파라미터 추정과 분할을 위한 창의 크기는 MDL원리를 이용하여 영상으로부터 추정한다. 실험에서 제안한 방법이 특히 비균일성이 있는 MR영상의 분할에서 국소영역의 영상특성을 잘 반영하였으며, 기존의 방법보다 더 좋은 결과를 보여주었다.

• Journal of Yeungnam Medical Science
• /
• 제19권2호
• /
• pp.136-143
• /
• 2002

저자들은 고령의 여성 당뇨 환자에서 비케톤성 고혈당과 동반되어 나타난 전신성 무도병과 그 특징적인 방사선학적 소견을 보이는 1예를 경험하였기에 문헌고찰과 함께 보고하는 바이다.

• Journal of International Society for Simulation Surgery
• /
• 제3권1호
• /
• pp.1-8
• /
• 2016

In the field of Radiology, the Computer Aided Diagnosis is the technology which gives valuable information for surgical purpose. For its importance, several computer vison methods are processed to obtain useful information of images acquired from the imaging devices such as X-ray, Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). These methods, called pattern recognition, extract features from images and feed them to some machine learning algorithm to find out meaningful patterns. Then the learned machine is then used for exploring patterns from unseen images. The radiologist can therefore easily find the information used for surgical planning or diagnosis of a patient through the Computer Aided Diagnosis. In this paper, we present a review on three widely-used methods applied to Computer Aided Diagnosis. The first one is the image processing methods which enhance meaningful information such as edge and remove the noise. Based on the improved image quality, we explain the second method called segmentation which separates the image into a set of regions. The separated regions such as bone, tissue, organs are then delivered to machine learning algorithms to extract representative information. We expect that this paper gives readers basic knowledges of the Computer Aided Diagnosis and intuition about computer vision methods applied in this area.

• 대한의용생체공학회:의공학회지
• /
• 제20권1호
• /
• pp.59-68
• /
• 1999

본 논문에서는 뇌량의 형태정보와 통계적 특성을 이용한 중앙시상 두뇌자기공명영상의 뇌량자동인식 알고리즘을 제안한다. 제안된 알고리즘에서는 우선 뇌량의 통계적 특성에 일치하는 영역들을 추출하고 형태정보와 일치하는 영역을 검출한다. 이러한 형태정합을 위해 기존의 윤곽정합알고리즘 대신에 통계적인 특성을 적응적으로 변화시켜 형태정보와 일치하는 영역을 검출하는 방향성 창영역확장 알고리즘을 제안하였다. 실험결과 제안된 알고리즘의 우수성을 확인할 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제15권2호
• /
• pp.175-182
• /
• 1994

The international standard for digital compression and coding of continuous-tone still image known as JPEG (Joint Photographic Experts Group) standard is investigated for medical image archiving and communication. The JPEG standard has widely been accepted in the areas of electronic image communication, computer graphics, and multimedia applications, however, due to the lossy character of the JPEG compression its application to the field of medical imaging has been limited. In this paper, the JPEG standard is investigated for medical image compression with a series of head sections of magnetic resonance (MR) images (256 and 4096 graylevels, $256 {\times}256$size). Two types of Huffman codes are employed, i. e., one is optimized to the image statistics to be encoded and the other is a predetermined code, and their coding efficiencies are examined. From experiments, compression ratios of higher than 15 were obtained for the MR images without noticeable distortion. Error signal in the reconstructed images by the JPEG standard appears close to random noise. Compared to existing full-frame bit-allocation technique used for radiological image compression, the JPEG standard achieves higher compression with less Gibb's artifact. Feature of the progressive image build-up of the JPEG progressive coding may be useful in remote diognosis when data is transmitted through slow public communication channel.