• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2788-2808
• /
• 2023

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.

• 대한의생명과학회지
• /
• 제14권2호
• /
• pp.77-81
• /
• 2008

Testis brain RNA-binding protein (TB-RBP) is a DNA/RNA binding protein. TB-RBP is mainly expressed in testis and brain and highly conserved protein with several functions, including chromosomal translocations, DNA repair, mitotic cell division, and mRNA transport, stabilization, and storage. In our previous study, we identified TB-RBP as an interacting partner for the catalytic subunit $(C{\alpha})$ of protein kinase A(PKA) and verified their interaction with several biochemical analyses. Here, we confirmed interaction between $C{\alpha}$. and TB-RBP in mammalian cells and determined the effect of $C{\alpha}$. on the function of TB-RBP. The activation of $C{\alpha}$. increased the TB-RBP function as a DNA-binding protein. These results suggest that the function of TB-RBP can be modulated by PKA and provide insights into the diverse role of PKA.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(5)
• /
• pp.203-206
• /
• 2001

The fMRI which can express the function of brain as MR image is now being studied. The study on the functional image has usually been performed with the MRI in 4 tesla class in goneral, but if gradient echo imaging method could be used, it might make the most of what it has with the MRI in 1.5 tesla class. However, the lack of adequate image post-processing software prevents it from being used as widely as it could be. For the image post-processing algorithm of the functional image, subtraction method and several statistical methods are used with continuous introduction of new method recently. In this paper, we suggest adaptation of wavelet algorithm for obtaining a more reliable brain function map.

• The Korean Journal of Physiology and Pharmacology
• /
• 제11권3호
• /
• pp.113-119
• /
• 2007

Developmental disability shows life-long behavioral abnormality with no significant physical malformation. This study was undertaken to develop an animal model for developmental disability by using two-factor approach. Lipopolysaccharide (LPS), a bacterial toxin, and NAN-190, a $5-HT_{1A}$ receptor antagonist, were administered to Sprague-Dawley rats on postnatal day (PND) 5 to induce inflammation and an altered 5-HT system, respectively. Long-term alteration of behavior occurred in the drug-treated groups. The LPS-treated group showed impaired motor coordination in the Rota-rod test. The LPS- treated or both LPS and NAN-190-treated groups showed impaired fore-paw muscle power in the wire maneuver test. These groups also showed decreased white matter volume and increased serotonergic fibers. The LPS and NAN-190-treated group also exhibited neurologic deficit in the placing reaction test and impaired equilibrium function in the tilt table test. The results showed that a variety of altered behaviors can be generated by two factor model, and suggested that combination of important etiologic factors and possible underlying defects is a promising strategy of establishing an animal model for developmental disabilities.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(C)
• /
• pp.393-396
• /
• 2011

In this paper, we propose a constrained alternating least squares nonnegative matrix factorization algorithm (cALSNMF) to detect active brain regions from single subject's task-related fMRI data. In cALSNMF, we define a new cost function which considers the uncorrelation and noisy problems of fMRI data by adding decorrelation and smoothing constraints in original Euclidean distance cost function. We also generate a novel training procedure by modifying the update rules and combining with optimal brain surgeon (OBS) algorithm. The experimental results on visuomotor task fMRI data show that our cALSNMF fits fMRI data better than original ALSNMF in detecting task-related brain activation from single subject's fMRI data.

• Journal of Korean Neurosurgical Society
• /
• 제29권1호
• /
• pp.5-14
• /
• 2000

Objective : Somatosensory evoked potential(SSEP) has been known to be a good method for evaluating brain stem function, but it is not sufficient to check the fine changes of cortical functions. A fine change of cortical function can be expressed with somatosensory evoked cortical field potential(SSEFP) rather than general SSEP. To confirm the usefulness of SSEFP for evaluating the cortical function, the authors simultaneously measured SSEFP and the intracranial pressure-volume index(PVI) in kaolin-induced hydrocephalic rats. Method : Hydrocephalus was induced with injection of 0.1ml kaolin-suspended solution into the cisterna magna in 60 Sprague-Dawley rats. The authors measured PVI and SSEFP 1 week after injection of kaolin-suspended solution. To evaluate the severity of induced hydrocephalus, we measured the transverse diameter of the lateral ventricle on the coronal slice of the rat brain 0.40mm posterior to the bregma. Result : The typical wave form of SSEFP in control rats showed a negative-positive complex wave at early latency. In SSEFP of normal rats, N0 is 10.0 msec, N1 15.3 msec, P1 31.2 msec and N1-P1 amplitude $15.4{\mu}V$. As hydrocephalus progressed, the peak latency of N1 and P1 were delayed. In mild hydrocephalus, negative peak waves were split. The N1-P1 amplitude was decreased only in severe hydrocephalus. The changes of the characteristics of SSEFP according to the severity of hydrocephalus were well correlated with the changes of PVI. Shunting normalized the characteristics of SSEFP in relation to ventricular sizes and PVI in hydrocephalic rats. Conclusion : SSEFP may be useful for evaluating the impairment of cortical function in hydrocephalus.

• 한국방사선학회논문지
• /
• 제16권1호
• /
• pp.25-34
• /
• 2022

뇌 전산화단층촬영은 비침습성, 3차원 영상 제공, 저방사선량 등의 장점 때문에 뇌출혈과 같은 질병 진단을 위해 시행된다. 하지만 뇌 전산화단층영상 판독을 위한 전문의의 인력 공급 부족 및 막대한 업무량으로 인해 수많은 판독 오류 및 오진이 발생하고 있다. 이와 같은 문제를 해결하기 위해 객체 검출을 위한 다양한 인공지능 기술이 개발되고 있다. 본 연구에서는 뇌 전산화단층영상으로부터 뇌출혈 검출을 위한 딥러닝 기반 YOLOv5s 모델의 적용 가능성을 확인하였다. 또한 YOLOv5s 모델 학습 시 초매개변수를 변화시켜 학습된 모델의 성능을 평가하였다. YOLOv5s 모델은 backbone, neck 및 output 모듈로 구성하였고, 입력 CT 영상 내 뇌출혈로 의심되는 부위를 검출하여 출력할 수 있도록 하였다. YOLOv5s 모델 학습 시 활성화함수, 최적화함수, 손실함수 및 학습 횟수를 변화시켰고, 학습된 모델의 뇌출혈 검출 정확도 및 학습 시간을 측정하였다. 연구결과 학습된 YOLOv5s 모델은 뇌출혈로 의심되는 부위에 대한 경계 박스 및 해당 경계박스에 대한 정확도를 출력할 수 있음을 확인하였다. Mish 활성화함수, stochastic gradient descent 최적화함수 및 completed intersection over union 손실함수 적용 시 YOLOv5s 모델의 뇌출혈 검출 정확도 향상 및 학습 시간이 단축되는 결과를 확인하였다. 또한 YOLOv5s 모델의 뇌출혈 검출 정확도 및 학습 시간은 학습 횟수에 비례하여 증가하는 결과를 확인하였다. 따라서 YOLOv5s 모델은 뇌 전산화단층영상을 이용한 뇌출혈 검출을 위해 활용할 수 있으며, 최적의 초매개변수 적용을 통해 성능을 향상 시킬 수 있다.

• 디지털융복합연구
• /
• 제13권8호
• /
• pp.289-294
• /
• 2015

본 연구는 비교사학습의 대표적인 방법 중 하나인 코호넨의 자기조직화 방법을 기반으로 BCI(Brain-Computer Interface)에 적용 가능한 자율적 기계학습방법을 제안한다. 이를 위해 상호작용 함수를 이용한 학습영역조정방법과 자율적 기계학습규칙을 제안하였다. 학습영역조정과 기계학습은 코호넨의 자기조직화 방법을 기반으로 한 상호작용 함수에 의한 측면제어효과를 이용하였다. 승자 뉴런을 결정하고 난 후 학습 규칙에 따라 뉴런의 연결강도를 조정하고 학습 횟수가 증가함에 따라 학습영역이 점차 감소하여 출력층 뉴런 가중치들의 입력을 향한 유동을 완화시켜 네트워크가 평형 상태(equilibrium state)에 도달하여 학습을 마칠 수 있는 자율적 기계학습을 제안하였다.

• 한국콘텐츠학회논문지
• /
• 제9권12호
• /
• pp.656-664
• /
• 2009

본 논문은 산업화와 교통 환경의 발달로 인해 최근 들어 발생빈도가 크게 증가되고 있는 외상성 뇌손상을 대상으로 하여, 치료적 운동의 적용에 있어 수중운동의 뇌신경 가소성에 미치는 영향과 전정-운동에 대한 영향에 대해 알아보고자 한 연구이다. 수중운동이라는 운동학적 특성을 통해 기능적 독립을 위해선 반드시 전제되어야 하는 뇌신경 가소성과 전정-운동 기능의 회복에 어떠한 영향을 주는지를 알아보기 위하여 80마리의 백서를 대상으로 4군으로 나누고, 3주간 서로 다른 방식의 운동 훈련(실험군 I: 대조군, II: 수중운동군, III: 속도 및 경사 조절 트레드밀 운동군, IV: 단순 트레드밀 운동군)을 적용하여 전정-운동 기능에 미치는 영향을 Rota-Rod 검사를 통해 알아보고, 신경가소성에 대한 영향성에 대해서는 대뇌피질에서의 GAP-43 인자를 조직면역화학적 방법으로 검사해 보았다. 연구결과, 수중운동을 적용한 군에서, 다른 군들에 비해 뇌신경 가소성에 긍정적이고도 유의한 영향을 미칠 수 있음을 확인할 수 있었으며, 전정-운동 기능 향상에 있어서도 다른 군들에 비해 유의한 향상 효과를 나타내었다. 이는 물이 가지고 있는 다양한 감각적 특성과 환경적 상황이 뇌손상으로 인해 불안정한 신체의 운동에 긍정적인 영향을 미치기 때문인 것으로 사료된다.

• 대한한방내과학회지
• /
• 제32권1호
• /
• pp.43-55
• /
• 2011

Objectives : Sokmyeung-tang(SMT) has been used for treatment of CVA in traditional oriental medicine, so this study was designed to evaluate the effect of SMT's protection on brain cell damage against the oxidative stress that was affected by CVA, We also investigated the effect of motor function improvement and neurotrophic factor in ischemic cerebral damaged rats. Methods : We measured cell viability after administrating SMT, chemicals(Paraquat, SNP, rotenone, and $H_2O_2$) which cause oxidative stress, and both SMT and chemicals. We carried out neurobehavioral evaluation(Rotarod test, Beam-walking test, postural reflex test) and observed BDNF (brain-derived neurotrophic factor) expression by injecting SMT into ischemic cerebral damaged rat. Results : Through this study, we observed the following three results. First, brain cell death caused by paraquat, rotenone, and $H_2O_2$ significantly decreased with the treatment of SMT. Second, neuronal movement function in ischemic cerebral damaged rats was significantly improved by the treatment of SMT. Third, BDNF in ischemic cerebral damaged rats increased with the treatment of SMT. Conclusions : SMT protects brain cells from damage induced by oxidative stress (Paraquat, rotenone, $H_2O_2$). SMT also improves neuronal movement function and increases BDNF in ischemic cerebral damaged rats.