• Investigative Magnetic Resonance Imaging
• /
• 제17권4호
• /
• pp.308-311
• /
• 2013

심부실비우스열뇌수막종은 뇌수막종의 드문 형태이다. 본 증례를 합하여 한국에서 총 4증례가 보고 되었다. 이전 병력이 없던 43세 남자가 경련발작을 주소로 본원에 내원하였다. 자기공명영상에서 오른 심부실비우스열에 테두리가 조영증강되는 종괴가 발견되었고 경막과의 연결성은 없었다. 수술적 제거 후 심부실비우스뇌수막종으로 진단되었다.

• Journal of Korean Neurosurgical Society
• /
• 제30권2호
• /
• pp.168-172
• /
• 2001

Objective : The authors have studied the clinical outcome of patients with diffuse axonal injuries(DAI) to evaluate the prognostic value of gradient-echo MR imaging findings. Materials and Methods : From March 1995 to March 1998, there were nineteen patients with DAI whose initial Glasgow coma scales were eight or less. Authors divided them into two groups according to Glasgow outcome scales ; those patients with GOS 3 or less(group A ; 9) and those with 4 or more(group B ; 10). We subdivided the lesions as superficial and deep lesion, and analyzed the numbers, anatomical loci of the lesions on the gradient echo images of each group. Results : Mean numbers of the lesions were 15 per case in group A(135/9) and 10 in group B(100/10). The common loci involved in DAI were cerebral cortex, brain stem, and corpus callosum. Cortical lesions were 31.1% in group A(42/135) and 47% in group B(47/100). Brain stem lesions were 25.9%(35/135) and 15%(15/100) each. Callosal lesions were 31.1%(26/135) and 13%(13/100) each. The frequency of callosal and brain stem lesions was significantly different between two groups(p<0.05). We divided callosal lesions as genu, body, and splenium and body lesions as anterior, middle, posterior, but no significant topographical difference of lesions was observed between two groups. Deep lesions were observed more frequently in group A(58.5%, 79/135) than group B(36%, 36/100). Conclusion : The poor outcome group showed more numbers of lesion and more frequent involvement of brain stem and corpus callosum than favorable outcome group. Gradient-echo MR imaging seems to have predictive value for clinical outcome in patients with DAI.

• 한국차세대컴퓨팅학회논문지
• /
• 제15권5호
• /
• pp.64-74
• /
• 2019

비강체 정합은 임상적 필요성은 높으나 계산 복잡도가 높고, 정합의 정확성 및 강건성을 확보하기 어려운 분야이다. 본 논문은 비지도 학습 환경에서 3차원 뇌 자기공명 영상 데이터에 딥러닝 네트워크를 이용한 비강체 정합 기법을 제안한다. 서로 다른 환자의 두 영상을 입력받아 네트워크를 통하여 두 영상 간의 특징 벡터를 생성하고, 변위 벡터장을 만들어 기준 영상에 맞추어 다른 쪽 영상을 변형시킨다. 네트워크는 U-Net 형태를 기반으로 설계하여 정합 시 두 영상의 전역적, 지역적인 차이를 모두 고려한 특징 벡터를 만들 수 있고, 손실함수에 균일화 항을 추가하여 3차원 선형보간법 적용 후에 실제 뇌의 움직임과 유사한 변형 결과를 얻을 수 있다. 본 방법은 비지도 학습을 통해 임의의 두 영상만을 입력으로 받아 단일 패스 변형으로 비강체 정합을 수행한다. 이는 반복적인 최적화 과정을 거치는 비학습 기반의 정합 방법들보다 빠르게 수행할 수 있다. 실험은 50명의 뇌를 촬영한 3차원 자기공명 영상을 가지고 수행하였고, 정합 전·후의 Dice Similarity Coefficient 측정 결과 평균 0.690으로 정합 전과 비교하여 약 16% 정도의 유사도 향상을 확인하였다. 또한, 비학습 기반 방법과 비교하여 유사한 성능을 보여주면서 약 10,000배 정도의 속도 향상을 보여주었다. 제안 기법은 다양한 종류의 의료 영상 데이터의 비강체 정합에 활용이 가능하다.

• 제어로봇시스템학회논문지
• /
• 제21권1호
• /
• pp.59-64
• /
• 2015

In this paper, we found the usefulness of the deep belief network (DBN) in the fields of brain-computer interface (BCI), especially in relation to imagined speech. In recent years, the growth of interest in the BCI field has led to the development of a number of useful applications, such as robot control, game interfaces, exoskeleton limbs, and so on. However, while imagined speech, which could be used for communication or military purpose devices, is one of the most exciting BCI applications, there are some problems in implementing the system. In the previous paper, we already handled some of the issues of imagined speech when using the International Phonetic Alphabet (IPA), although it required complementation for multi class classification problems. In view of this point, this paper could provide a suitable solution for vowel classification for imagined speech. We used the DBN algorithm, which is known as a deep learning algorithm for multi-class vowel classification, and selected four vowel pronunciations:, /a/, /i/, /o/, /u/ from IPA. For the experiment, we obtained the required 32 channel raw electroencephalogram (EEG) data from three male subjects, and electrodes were placed on the scalp of the frontal lobe and both temporal lobes which are related to thinking and verbal function. Eigenvalues of the covariance matrix of the EEG data were used as the feature vector of each vowel. In the analysis, we provided the classification results of the back propagation artificial neural network (BP-ANN) for making a comparison with DBN. As a result, the classification results from the BP-ANN were 52.04%, and the DBN was 87.96%. This means the DBN showed 35.92% better classification results in multi class imagined speech classification. In addition, the DBN spent much less time in whole computation time. In conclusion, the DBN algorithm is efficient in BCI system implementation.

• 방송공학회논문지
• /
• 제28권3호
• /
• pp.293-301
• /
• 2023

표준화되지 않은 의료 데이터 수집 및 관리는 여전히 수동으로 진행되고 있어, 이 문제를 해결하기 위해 딥 러닝을 사용해 CT 데이터를 분류하는 연구들이 진행되고 있다. 하지만 대부분 연구에서는 기본적인 CT slice인 axial 평면만을 기반으로 모델을 개발하고 있다. CT 영상은 일반 이미지와 다르게 인체 구조만 묘사하기 때문에 CT scan을 재구성하는 것만으로도 더 풍부한 신체적 특징을 나타낼 수 있다. 이 연구는 axial 평면뿐만 아니라 CT 데이터를 2D로 변환하는 여러가지 방법들을 통해 보다 높은 성능을 달성할 수 있는 방법을 찾고자 한다. 훈련은 5가지 부위의 CT 스캔 1042개를 사용했고, 모델 평가를 위해 테스트셋 179개, 외부 데이터셋으로 448개를 수집했다. 딥러닝 모델 개발을 위해 ImageNet으로 사전 학습된 InceptionResNetV2를 백본으로 사용하였으며, 모델의 전체 레이어를 재 학습했다. 실험결과 신체 부위 분류에서는 재구성 데이터 모델이 99.33%를 달성하며 axial 모델보다 1.12% 더 높았고, 조영제 분류에서는 brain과 neck에서만 axial모델이 높았다. 결론적으로 axial slice로만 훈련했을 때 보다 해부학적 특징이 잘 나타나는 데이터로 학습했을 때 더 정확한 성능 달성이 가능했다.

• Journal of Korean Neurosurgical Society
• /
• 제52권4호
• /
• pp.377-383
• /
• 2012

Objective : Detection of focal non-hemorrhagic lesion (NHL) has become more efficient in diffuse axonal injury (DAI) patients using an MRI. The aims of this study are to find out the radiological distribution, progress of NHL and its clinical significance. Methods : Between September 2005 and October 2011, 32 individuals with NHLs on brain MRI were enrolled. NHLs were classified by brain location into 4 major districts and 13 detailed locations including cortical and subcortical, corpus callosum, deep nuclei and adjacent area, and brainstem. The severity of NHL was scored from grades 1 to 4, according to the number of districts involved. Fourteen patients with NHL were available for MRI follow-up and an investigation of the changes was conducted. Results : Thirty-two patients had 59 NHLs. The most common district of NHL was cortical and subcortical area; 15 patients had 20 NHSs. However the most common specific location was the splenium of the corpus callosum; 14 patients had 14 lesions. The more lesions patients had, the lower the GCS, however, this was not a statistically meaningful difference. On follow-up MRI in 14 patients, out of 24 lesions, 13 NHLs resolved, 5 showed cystic change, and 6 showed atrophic changes. Conclusion : NHLs were located most commonly in the splenium and occur frequently in the thalamus and the mesial temporal lobe. Because most NHS occur concomitantly with hemorrhagic lesions, it was difficult to determine their effects on prognosis. Since most NHLs resolve completely, they are probably less significant to prognosis than hemorrhagic lesions.

• Investigative Magnetic Resonance Imaging
• /
• 제19권3호
• /
• pp.186-190
• /
• 2015

Acute disseminated encephalomyelitis (ADEM) is a demyelinating and inflammatory condition of the central nervous system, occurring predominantly in white matter. ADEM involving the rhombencephalon without affecting the white matter is very rare. Here, we present an unusual case of ADEM involving only the rhombencephalon in a 4-year-old Asian girl. The patient complained of pain in the right lower extremities, general weakness, ataxia, and dysarthria. The initial brain CT showed subtle ill-defined low-density lesions in the pons and medulla. On brain MRI, T2 high signal intensity (T2-HSI) lesions with mild swelling were present in the pons, both middle cerebellar peduncles, and the anterior medulla. The initial diagnosis was viral encephalitis involving the rhombencephalon. Curiously, a cerebrospinal fluid (CSF) study revealed no cellularity, and negative viral marker findings. Three weeks later, follow up brain MRI showed that the extent of the T2-HSI lesions in the brain stem had decreased. After reinvestigation, it was found that she had a prior history of upper respiratory infection. In this case, we report the very rare case of a patient showing isolated involvement of the rhombencephalon in ADEM, mimicking viral rhombencephalitis on CT and MR imaging. ADEM can involve unusual sites such as the rhombencephalon in isolation, without involvement of the white matter or deep gray matter and, therefore, should be considered even when it appears in unusual anatomical areas. Thorough history taking is important for making a correct diagnosis.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.43-52
• /
• 2024

Medical imaginings assume a important part in the analysis of tumors and cerebrospinal fluid (CSF) leak. Magnetic resonance imaging (MRI) is an image segmentation technology, which shows an angular sectional perspective of the body which provides convenience to medical specialists to examine the patients. The images generated by MRI are detailed, which enable medical specialists to identify affected areas to help them diagnose disease. MRI imaging is usually a basic part of diagnostic and treatment. In this research, we propose new techniques using the 4D-MRI image segmentation process to detect the brain tumor in the skull. We identify the issues related to the quality of cerebrum disease images or CSF leakage (discover fluid inside the brain). The aim of this research is to construct a framework that can identify cancer-damaged areas to be isolated from non-tumor. We use 4D image light field segmentation, which is followed by MATLAB modeling techniques, and measure the size of brain-damaged cells deep inside CSF. Data is usually collected from the support vector machine (SVM) tool using MATLAB's included K-Nearest Neighbor (KNN) algorithm. We propose a 4D light field tool (LFT) modulation method that can be used for the light editing field application. Depending on the input of the user, an objective evaluation of each ray is evaluated using the KNN to maintain the 4D frequency (redundancy). These light fields' approaches can help increase the efficiency of device segmentation and light field composite pipeline editing, as they minimize boundary artefacts.

• Korean Journal of Radiology
• /
• 제1권1호
• /
• pp.5-10
• /
• 2000

Objective: To describe the neuroradiologic findings of primary antiphospholipid antibody syndrome (PAPS). Materials and Methods: During a recent two-year period, abnormally elevated antiphospholipid antibodies were detected in a total of 751 patients. In any cases in which risk factors for stroke were detected - hypertension, diabetes mellitus, hyperlipidemia, smoking, and the presence of SLE or other connective tissue diseases - PAPS was not diagnosed. Neuroradiologic studies were performed in 11 of 32 patients with PAPS. We retrospectively reviewed brain CT (n = 7), MR (n = 8), and cerebral angiography (n = 8) in 11 patients with special attention to the presence of brain parenchymal lesions and cerebral arterial or venous abnormalities. Results: CT or MR findings of PAPS included nonspecific multiple hyper-intensity foci in deep white matter on T2-weighted images (5/11), a large infarct in the territory of the middle cerebral artery (4/11), diffuse cortical atrophy (2/11), focal hemorrhage (2/11), and dural sinus thrombosis (1/11). Angiographic findings were normal (5/8) or reflected either occlusion of a large cerebral artery (2/8) or dural sinus thrombosis (1/8). Conclusion: Neuroradiologic findings of PAPS are nonspecific but in young or middle- aged adults who show the above mentioned CT or MR findings, and in whom risk factors for stroke are not present, the condition should be suspected.

• 한국정밀공학회지
• /
• 제30권5호
• /
• pp.559-563
• /
• 2013

This study aims to quantify the effects of medication (Med) and deep brain stimulation (DBS) on resting rigidity in patients with Parkinson's disease. We tested 10 limbs of five patients under each of four treatment conditions: 1) baseline, 2) DBS, 3) Med, 4) DBS + Med. Rigidity at the wrist joint was assessed using the Unified Parkinson's Disease Rating Scale (UPDRS). The examiner randomly imposed flexion and extension movement on patient's wrist joint. Resistance to passive movement was quantified by viscoelastic properties. Not only rigidity score but also damping constant showed improvements in rigidity by DBS and Med treatments (p<0.05). This indicates that the viscosity can represent the change in rigidity due to DBS as well as Med, which was manifested by UPDRS score.