• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.285-288
• /
• 2002

Compression of magnetic resonance images (MRI) has proved to be more difficult than other medical imaging modalities. In an average sized hospital, many tora bytes of digital imaging data (MRI) are generated every year, almost all of which has to be kept. The medical image compression is currently being performed by using different algorithms. In this paper, Fuzzy C-Means (FCM) algorithm is used for the Vector Quantization (VQ). First, a digital image is divided into subblocks of fixed size, which consists of 4${\times}$4 blocks of pixels. By performing 2-D Discrete Cosine Transform (DCT), we select six DCT coefficients to form the feature vector. And using FCM algorithm in constructing the VQ codebook. By doing so, the algorithm can make good time quality, and reduce the processing time while constructing the VQ codebook.

• 동의생리병리학회지
• /
• 제19권3호
• /
• pp.830-833
• /
• 2005

Intracranial lipomas are rare lesions, which are believed to be congenital malformations. They are usually asymptomatic incidental findings and localized in the midline. However, they may occasionally produce neurological symptoms such as seizure, headache, mental changes, paresis. Currently, diagnosis of intracranial lipomas is made on based of imaging modalities, particularly Magnetic resonance imaging(MRI). Because Lipomas are strongly adherent to the surroundings and typically enclose both vessels and nerves, Surgical approach is rarely indicated.

• ETRI Journal
• /
• 제28권2호
• /
• pp.162-174
• /
• 2006

Several photogrammetric and geographic information system applications such as surface matching, object recognition, city modeling, environmental monitoring, and change detection deal with multiple versions of the same surface that have been derived from different sources and/or at different times. Surface registration is a necessary procedure prior to the manipulation of these 3D datasets. This need is also applicable in the field of medical imaging, where imaging modalities such as magnetic resonance imaging (MRI) can provide temporal 3D imagery for monitoring disease progression. This paper will present a general automated surface registration procedure that can establish correspondences between conjugate surface elements. Experimental results using light detection and ranging (LIDAR) and MRI data will verify the feasibility, robustness, and accuracy of this approach.

• Journal of information and communication convergence engineering
• /
• 제2권3호
• /
• pp.167-171
• /
• 2004

The evolution of modern imaging modalities, followed by the rapid development of computer technology has introduced many new features in the communication networks used in medical facilities. Since it is very important to keep patient's record accurately, the ability to exchange medical data securely over the communication network is essential for any medical information. In this paper, therefore, we introduce some problems which occur from digitizing medical images such as MRI (Magnetic Resonance Imaging), CT (Computed Tomography), CR(Computed Radiography), etc., and then we propose a authentication mechanism for medical image verification using secret watermark images.

• 대한정형외과 초음파학회지
• /
• 제1권2호
• /
• pp.94-111
• /
• 2008

전통적으로 슬관절 질병은 주로 방사선 촬영과 자기 공명 영상에 근거하여 진단과 치료를 하고 있다. 그러나 방사선 진단은 골 내부의 변화에는 좋은 영상을 가져다 주지만 연부 조직의 영상은 잘 볼 수 없는 단점이 있고 외래 진료실에서 실시간으로 할 수 없는 단점이 있다. 또 자기 공명 영상은 고가이고 역시 실시간으로 볼 수 없으며 정적인 정보만 제공한다. 초음파는 동적인 영상을 실시간으로 외래 진료실에서 즉시 볼 수 있고 비용이 저렴하며 동적 영상을 제공하고 연조직 영상을 잘 보여준다. 슬관절에서는 연조직 및 골 표면의 변화까지 관찰이 가능하므로 진단에 중요한 역할을 한다. 이 글에서는 정상적인 구조물의 초음파 영상과 병적 소견을 방사선 또는 자기 공명 영상 소견과 연계하여 소개하고 그 용도의 개략적인 것들을 설명하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.105-125
• /
• 2024

Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.

• 대한족부족관절학회지
• /
• 제10권1호
• /
• pp.31-36
• /
• 2006

Purpose: To evaluate the usefulness of ultrasound and MRI in diagnosing Morton's Neuroma, and the effect and significance of stepwise treatment. Materials and Methods: Out of all patients suspected of Morton's neuroma through history taking and physical examination, 77 patients (84 feet, 95 lesions) in whom Morton's neuroma was confirmed by ultrasound or MR imaging study or was clinically suspected with negative imaging studies, and followed up for over 3 months were included. In all cases, history taking and imaging study were done, and by comparison with operative findings of the patients, the sensitivity of ultrasound and MRI was checked. Postoperative evaluation was done using the AOFAS scale. The patient's satisfaction was also examined. Results: Morton's neuroma occurred most frequently at the $3^{rd}$ web space of the foot (56%), followed by the $2^{nd}$ web space (44%). Out of 15 cases suspected of morton's neuroma through ultrasound study, 13 were pathologically positive showing a sensitivity of 85.7%. Out of 16 cases suspected of morton's neuroma through MRI, 14 were pathologically positive showing a sensitivity of 83.3%. There was no significant difference in sensitivity between the two imaging modalities. Conclusion: In diagnosing Morton's neuroma, ultrasound examination had a similar sensitivity with MRI, therefore can be used as a screening study.

• Investigative Magnetic Resonance Imaging
• /
• 제11권2호
• /
• pp.119-126
• /
• 2007

상완신경총의 영상 진단은 복잡한 해부학적인 구조와 다양하게 침범하는 병들로 인해 어렵고 도전적이다. 상완신경총 영상 진단의 일차적인 목표는 외상성 손상과 비외상성 손상의 구별이다. MRI의 급속경사와 전용표면코일을 이용한 적절한 공간분해능을 가진 영상기기의 발전과 이를 이용한 다양한 펄스열의 개발이 상완신경총의 외상성 손상과 비외상성 손상에 대한 구별에 많은 도움을 주어 정확한 진단으로 수술 여부의 결정에 이용된다. MRI는 비외상성 상완신경총 병변의 진단에 가장 좋은 영상진단이며, CT 척수강조영술은 상완신경총을 침범하는 신경근견열 병변의 검사에 많이 이용된다. 그리고 일반적으로 고화질, 고해상력의 MRI 가 상완신경총 비외상성병변의 진단에 일차적인 영상검사로 중요한 역할을 하고 있다.

• 한국콘텐츠학회논문지
• /
• 제3권3호
• /
• pp.85-97
• /
• 2003

MRI, CT, MRI, PET, SPECT, fMRI 등과 같은 단층의료영상은 병원에서 환자의 진단 및 치료 임상적 연구에서 폭넓게 사용되고 있다. 동일한 대상에 대하여 서로 다른 정보를 얻거나 비교를 하기 위하여 서로 다른 영상양식으로 촬영하거나 시간적 간격을 두고 단층영상을 획득하는 경우가 많다. 3차원 영상정합은 비교하고자 하는 두 영상을 하나의 3차원 좌표 공간으로 지도화하는 것이며, 크게 마커기반 정합과 특징기반 정합으로 분류된다. 뇌 영상의 3차원 정합은 뇌 수술부위 선정, 뇌 기능 연구, 뇌 지도화 연구 등에서 시각적 분석과 정량적 분석에서 중요한 위치를 차지한다. 본 논문에서는 뇌의 단층영상에 대하여 흔히 사용되고 있는 3차원 정합인 마커기반 정합법과 특징기반 정합법에 대하여 소개하고 이에 대한 비교 고찰을 행하고자 한다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권7호
• /
• pp.3569-3573
• /
• 2016

Purpose: The aim of this study was to compare C-11 choline and F-18 FDG PET/CT, gadoxetic-enhanced 3-T MRI and contrast-enhanced CT for diagnosis of hepatocellular carcinoma (HCC). Materials and Methods: Twelve chronic hepatitis B patients suspected of having HCC by abdominal ultrasonography received all diagnostic modalities performed within a one-week timeslot. PET/CT results were analyzed visually by two independent nuclear medicine physicians and quantitatively by tumor to background ratio (T/B). Nine patients then had histopathological confirmation. Results: Six patients had well differentiated HCC, while two and one patient(s) were noted with moderately and poorly differentiated HCC, respectively. All were detected by both CT and MRI with an average tumor size of $5.7{\pm}3.8cm$. Five patients had positive C-11 choline and F-18 FDG uptake. Of the remaining four patients, three with well differentiated HCC showed negative F-FDG uptake (one of which showed negative results by both tracers) and one patient with moderately differentiated HCC demonstrated no C-11 choline uptake despite intense F-18 FDG avidity. The overall HCC detection rates with C-11 choline and F-18 FDG were 78% and 67%, respectively, while the sensitivity of F-18 FDG for non-well differentiated HCC was 100%, compared with 83% of C-11 choline. The average T/B of C-11 choline in well-differentiated HCC patients was higher than in moderately and poorly differentiated cases (p=0.5) and vice versa with statistical significance for T/B of F-18 FDG (p = 0.02). Conclusions: Our results suggested better detection rate in C-11 choline for well differentiated HCC than F-18 FDG PET. However, the overall detection rate of PET/CT with both tracers could not compare with contrast-enhanced CT and MRI.