• Journal of Korean Neurosurgical Society
• /
• 제54권2호
• /
• pp.125-127
• /
• 2013

Here, we report a rare case of an anaplastic astrocytoma masquerading as a hypertensive basal ganglia hemorrhage. A 69-year-old woman who had been under medical management for hypertension during the past 3 years suddenly developed right hemiparesis with dysarthria. Brain computed tomography (CT) scans with contrast and CT angiograms revealed an intracerebral hemorrhage (ICH) in the left basal ganglia, without an underlying lesion. She was treated conservatively, but underwent a ventriculoperitoneal shunt operation 3 months after the initial attack due to deteriorated mental status and chronic hydrocephalus. Three months later, her mental status deteriorated further. Magnetic resonance imaging (MRI) with gadolinium demonstrated an irregular enhanced mass in which the previous hemorrhage occurred. The final histological diagnosis which made by stereotactic biopsy was an anaplastic astrocytoma. In the present case, the diagnosis of a high grade glioma was delayed due to tumor bleeding mimicking hypertensive ICH. Thus, a careful review of neuroradiological images including MRI with a suspicion of tumor bleeding is needed even in the patients with past medical history of hypertension.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4816-4834
• /
• 2020

This paper proposes transfer learning and fine-tuning techniques for a deep learning model to detect three distinct brain tumors from Magnetic Resonance Imaging (MRI) scans. In this work, the recent YOLOv4 model trained using a collection of 3064 T1-weighted Contrast-Enhanced (CE)-MRI scans that were pre-processed and labeled for the task. This work trained with the partial 29-layer YOLOv4-Tiny and fine-tuned to work optimally and run efficiently in most platforms with reliable performance. With the help of transfer learning, the model had initial leverage to train faster with pre-trained weights from the COCO dataset, generating a robust set of features required for brain tumor detection. The results yielded the highest mean average precision of 93.14%, a 90.34% precision, 88.58% recall, and 89.45% F1-Score outperforming other previous versions of the YOLO detection models and other studies that used bounding box detections for the same task like Faster R-CNN. As concluded, the YOLOv4-Tiny can work efficiently to detect brain tumors automatically at a rapid phase with the help of proper fine-tuning and transfer learning. This work contributes mainly to assist medical experts in the diagnostic process of brain tumors.

• Journal of Multimedia Information System
• /
• 제9권1호
• /
• pp.21-32
• /
• 2022

Early-stage diagnosis of Alzheimer's Disease (AD) from Cognitively Normal (CN) patients is crucial because treatment at an early stage of AD can prevent further progress in the AD's severity in the future. Recently, computer-aided diagnosis using magnetic resonance image (MRI) has shown better performance in the classification of AD. However, these methods use a traditional machine learning algorithm that requires supervision and uses a combination of many complicated processes. In recent research, the performance of deep neural networks has outperformed the traditional machine learning algorithms. The ability to learn from the data and extract features on its own makes the neural networks less prone to errors. In this paper, a dense neural network is designed for binary classification of Alzheimer's disease. To create a classifier with better results, we studied result of different activation functions in the prediction. We obtained results from 5-folds validations with combinations of different activation functions and compared with each other, and the one with the best validation score is used to classify the test data. In this experiment, features used to train the model are obtained from the ADNI database after processing them using FreeSurfer software. For 5-folds validation, two groups: AD and CN are classified. The proposed DNN obtained better accuracy than the traditional machine learning algorithms and the compared previous studies for AD vs. CN, AD vs. Mild Cognitive Impairment (MCI), and MCI vs. CN classifications, respectively. This neural network is robust and better.

• Investigative Magnetic Resonance Imaging
• /
• 제7권2호
• /
• pp.100-107
• /
• 2003

목적 : 급성심근경색을 진단하는데 있어 심장자기공명영상의 유용성을 알아보고, 생존심근을 평가하는데 있어 Tl-201 심근관류 SPECT와 비교하고자 하였다. 대상 및 방법 : 흉통 및 호흡곤란이 있는 환자 중 심장자기공명영상과 Tl-201 SPECT를 시행한 17명을 후향적으로 조사하였다. 심장자기공명영상에서는 T2강조영상에서 심벽의 고신호 강도 유무, 영화영상에서 심벽 운동, Gd-DTPA 조영 증강 후 좌심실 벽의 관류 결손 및 주입 15분 후의 지연조영증강 유무를 평가하였다. T1-201 SPECT에서는 아데노신 부하 영상과 휴식기 영상을 얻어 관류 결손 유무와 관류 결손시 가역성 여부를 평가하였다. 결과 심장자기공명영상과 T1-201 SPECT 모두 급성심근경색을 진단하는데 통계적으로 의미가 있었고, T2강조영상, T1-201 SPECT, 지연조영증강 및 심벽운동 순으로 연관성이 있는 것으로 나타났고, 관류 결손은 통계적 유의성이 없었다. 생존심근 평가에 있어서는 두 검사간 유의한 차이가 없었으며, T2강조영상과 관류영상에서 T1-201 SPECT와 높은 일치율, 지연조영증강 및 심벽운동은 낮은 일치율을 보였다. 결론 : 심장자기공명영상은 급성심근경색을 진단하는데 매우 유의한 진단율을 보였고, 생존 심근여부의 판단에 있어 SPECT와 높은 일치율을 보였다. 그러나 각 검사별 판독 기준과 방법에서 많은 연구가 필요할 것으로 생각된다.

• 수면정신생리
• /
• 제3권2호
• /
• pp.1-17
• /
• 1996

To demonstrate the clinical usefulness of electroencephalography (EEG) and factors increasing the usefulness of EEG, the authors evaluated each relationship between EEG related factors and clinical variables, and neuroimaging studies (CT and MRI)-related factors, and factors which are related with routine neurological examination for 207 patients who had been evaluated with both of EEG and neuroimaging study(CT or/and MRI). The results were as follows: 1) Abnormality of EEG findings had significant relationships with chief complaints, diagnosis, medication use, seizure attack, pathological reflex, and level of consciousness. However there were no significant correlations between abnormality of EEG findings and neuroimaging studies (CT and MRI)- related factors. 2) Laterality of EEG findings had significant relationships with abnormality, laterality, and focality of CT findings, and also with abnormality of MRI findings. But there were no significant correlations between laterality of EEG findings and clinical variables, and neurological examination-related factors. 3) Anterior-posterior distribution of EEG findings was significantly related with medication use. 4) Focality of EEG findings had significant relationships with sex, sensory dysfunction sign, and cerebellar dysfunction sign. But there were no significant correlations between focality of EEG findings and neuroimaging studies(CT and MRI) related factors. 5) Abnormal EEG pattern had significant correlations with various factors, such as age, chief complaints, duration from onset of symptom to taking MRI, seizure attack, abnormality and nature of lesion in CT findings, cortical atrophy in MRI findings, motor dysfunction sign, sensory dysfunction sign, and pathological reflex. 6) With abnormality on sleep activation, age, age of onset, seizure attack, ventricular enlargement in CT findings, and abnormality of MRI findings were significantly correlated. 7) With abnormality on hyperventilation activation, duration of illness and laterality of MRI findings were significantly correlated. Above results may suggest that abnormality of EEG findings is more closely related with functional change of the brain than structural changes of the brain and laterality of EEG findings is vice versa. And also that medication use has an influence on anterior versus posterior distribution of EEG findings and focality of EEG findings is not related with structural changes of the brain. Activation with sleep may be effective to show age differences and provocation of seizure activity and hyperventilation may be effective to detect the abnormal EEG findings by cerebrovascular insufficiency.

• 대한전자공학회논문지SP
• /
• 제37권3호
• /
• pp.70-78
• /
• 2000

본 연구에서는 촬상단면내의 평행이동에 기인한 MRI 아티팩트를 제거하는 새로운 방법을 제안한다 임상 진단에 있어서 종종 문제가 되고 있는 호흡에 따른 두뇌부분의 상하이동을 고려해서 위상 엔코드 축인 y 방향만의 강체의 평행이동을 취급한다 종래의 발견적인 반복위상탐색 처리법과는 달리, MRI 촬상과정과 화장 특성의 해석에 근거한 MRI 신호내의 체동성분과 화상성분을 단순한 대수연산에 의해 분리할 수 있는 새로운 구속조건을 도출한다 MRI 신호에 대해서 x 방향의 1차원 푸리에 변환을 행한 후의 y 방향 스펙트럼 위상값은 화상자신의 성분과 체동성분의 합이 되고 있다 한편 두뇌부위 등의 단층상에 있어서 주위의 피하지방 부분의 밀도는 거의 균일하다고 알려져 있어, 이 부위상에 있는 y 방향의 한 라인의 말도분포는 대칭모양으로 간주할 수 있다 밀도함수가 대칭인 경우 스펙트럼의 위상은 그 위치에 대하여 선형적으로 변화한다 따라서 이 선형함수로부터 벗어난 성분을 체동으로 분리할 수 있다. 이러한 구속조건에 기초를 둔 새로운 아티팩트의 제거방법이 본 연구에서 제안된다 최종적으로 phantom 화상을 사용한 시뮬레이션을 통해 본 방 법의 유효성을 나타낸다.

• Investigative Magnetic Resonance Imaging
• /
• 제23권3호
• /
• pp.179-201
• /
• 2019

Portable low-cost magnetic resonance imaging (MRI) systems have the potential to enable "point-of-care" and timely MRI diagnosis, and to make this imaging modality available to routine scans and to people in underdeveloped countries and areas. With simplicity, no maintenance, no power consumption, and low cost, permanent magnets/magnet arrays/magnet assemblies are attractive to be used as a source of static magnetic field to realize the portability and to lower the cost for an MRI scanner. However, when taking the canonical Fourier imaging approach and using linear gradient fields, homogeneous fields are required in a scanner, resulting in the facts that either a bulky magnet/magnet array is needed, or the imaging volume is too small to image an organ if the magnet/magnet array is scaled down to a portable size. Recently, with the progress on image reconstruction based on non-linear gradient field, static field patterns without spatial linearity can be used as spatial encoding magnetic fields (SEMs) to encode MRI signals for imaging. As a result, the requirements for the homogeneity of the static field can be relaxed, which allows permanent magnets/magnet arrays with reduced sizes, reduced weight to image a bigger volume covering organs such as a head. It offers opportunities of constructing a truly portable low-cost MRI scanner. For this exciting potential application, permanent magnets/magnet arrays have attracted increased attention recently. A magnet/magnet array is strongly associated with the imaging volume of an MRI scanner, image reconstruction methods, and RF excitation and RF coils, etc. through field patterns and field homogeneity. This paper offers a review of permanent magnets and magnet arrays of different kinds, especially those that can be used for spatial encoding towards the development of a portable and low-cost MRI system. It is aimed to familiarize the readers with relevant knowledge, literature, and the latest updates of the development on permanent magnets and magnet arrays for MRI. Perspectives on and challenges of using a permanent magnet/magnet array to supply a patterned static magnetic field, which does not have spatial linearity nor high field homogeneity, for image reconstruction in a portable setup are discussed.

• 한국융합학회논문지
• /
• 제7권4호
• /
• pp.1-7
• /
• 2016

구조적 MRI 영상은 여러 단 변량과 다변량 방법을 위해 그레이 메터 (GM), 화이트 메터 (WM), 뇌척수액 (CSF) 세션화 과정을 하고 난후 형태계측학적 특징을 추출하기 위해 사용한다. 새로운 접근 방법은 매우 가벼운 알츠하이머 병에서 가벼운 알츠하이머병의 진단을 위해 적용된다. 간이정신상태검사에 따른 형태계측학적 특징과 가우시안 복합 모델 파라미터를 결합하여 정상인으로부터 알츠하이머 병 환자로 분류하는 방법을 제안한다. 결합한 특징은 주성분 분석 기법을 이용한 고차원의 저주를 제거한 후 다중 커널 SVM 분류기에 공급한다. 제안한 진단 방법의 실험적 결과는 90%이상의 특성도와 고민감도에 따라 다중 커널 SVM을 가진 층화 정확도가 96%까지 최대 산출한다.

• Journal of Korean Neurosurgical Society
• /
• 제29권7호
• /
• pp.891-898
• /
• 2000

Objective : It is difficult to differentiate intramedullary spinal cord tumors preoperatively from non-neoplastic pathologies in patients presenting as non-compressive myelopathies in magnetic resonance imaging(MRI). In this report, the authors reviewed nonneoplastic intramedullary spinal cord lesions preoperatively diagnosed as tumors and discussed their clinical and radiological characteristics and usefulness of surgical intervention. Methods : From January, 1985 to January, 1999, authors experienced eight non-neoplastic pathologies mimicking intramedullary spinal cord tumors and analysed their medical records, radiological findings and histopathological specimens retrospectively. Results : There were five males and three females and the duration of symptoms were from two to 20 months(mean, 9.8 months). The location of lesions were four cervical, one cervicothoracic and three thoracic. All patients manifested sensory abnormality, seven motor weakness, and six bladder symptom. All cases had swollen spinal cords and increased signal intensities in spin-echo sequences. Six cases showed contrast enhancement : four cases were focal and two diffuse. Under the impression of intramedullary tumors, the patients were operated upon. Final diagnoses on the base of clinical and pathologic finding were : three subacute necrotizing myelopathies, two multiple scleroses, two myelopathy of unknown etiology. One case showed no gross abnormality in surgical field in spite of adequate exposure of the lesion, so biopsy was not performed. In that case, postoperative MRI revealed spontaneous resolution of the lesion. Conclusion : MRI is invaluable diagnostic tool in screening myelopathies. However, its high sensitivity and lack of specificity make difficulty in preoperative differential diagnosis of non-compressive myelopathies. Although no surgical morbidity occurred in our series, we sometimes failed to confirm definite diagnosis even with biopsy. In such a circumstance, long-term follow up is needed.

• Journal of Korean Neurosurgical Society
• /
• 제51권2호
• /
• pp.109-112
• /
• 2012

It is rare for low-grade gliomas to disseminate to the leptomeninges. However, low-grade gliomas with dissemination to the leptomeninges have been occasionally reported in children, and have generally been associated with local recurrence. A 16-year-old boy sought evaluation for diplopia and gait disturbance. A brain magnetic resonance imaging (MRI) revealed pontine mass, which was proved to be fibrillary astrocytoma on biopsy, later. Radiation therapy (5400 cGy) was given and the patient's symptoms were improved. He was followed-up radiologically for brain lesion. Seven months after diagnosis he complained of back pain and gait disturbance. A brain MRI showed a newly-developed lesion at the left cerebellopontine angle without an interval change in the primary lesion. A spinal MRI demonstrated leptomeningeal dissemination of the entire spine. Radiation therapy (3750 cGy) to the spine, and adjuvant chemotherapy with a carboplatin plus vincristine regimen were administered. However, he had a progressive course with tumoral hemorrhage and expired 13 months after diagnosis. We report an unusual case of a low-grade brainstem glioma with spinal dissemination, but without local recurrence, and a progressive course associated with hemorrhage.