• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1233-1241
• /
• 2022

Tumors of the brain are the deadliest, with a life expectancy of only a few years for those with the most advanced forms. Diagnosing a brain tumor is critical to developing a treatment plan to help patients with the disease live longer. A misdiagnosis of brain tumors will lead to incorrect medical treatment, decreasing a patient's chance of survival. Radiologists classify brain tumors via biopsy, which takes a long time. As a result, the doctor will need an automatic classification system to identify brain tumors. Image classification is one application of the deep learning method in computer vision. One of the deep learning's most powerful algorithms is the convolutional neural network (CNN). This paper will introduce a novel deep learning structure and image gradient to classify brain tumors. Meningioma, glioma, and pituitary tumors are the three most popular forms of brain cancer represented in the Figshare dataset, which contains 3,064 T1-weighted brain images from 233 patients. According to the numerical results, our method is more accurate than other approaches.

• International Journal of Computer Science & Network Security
• /
• 제22권8호
• /
• pp.343-351
• /
• 2022

A brain tumor forms when some tissue becomes old or damaged but does not die when it must, preventing new tissue from being born. Manually finding such masses in the brain by analyzing MRI images is challenging and time-consuming for experts. In this study, our main objective is to detect the brain's tumorous part, allowing rapid diagnosis to treat the primary disease instantly. With image processing techniques and deep learning prediction algorithms, our research makes a system capable of finding a tumor in MRI images of a brain automatically and accurately. Our tumor segmentation adopts the U-Net deep learning segmentation on the standard MICCAI BRATS 2018 dataset, which has MRI images with different modalities. The proposed approach was evaluated and achieved Dice Coefficients of 0.9795, 0.9855, 0.9793, and 0.9950 across several test datasets. These results show that the proposed system achieves excellent segmentation of tumors in MRIs using deep learning techniques such as the U-Net algorithm.

• 한국컴퓨터정보학회논문지
• /
• 제26권7호
• /
• pp.37-44
• /
• 2021

뇌 MRI 영상의 자동 분류는 뇌종양의 조기 진단을 하는 데 있어 중요한 역할을 한다. 본 연구에서 우리는 심층 특징 앙상블을 사용한 MRI 영상에서의 딥 러닝 기반 뇌종양 분류 모델을 제안한다. 우선 사전 학습된 3개의 합성 곱 신경망을 사용하여 입력 MRI 영상에 대한 심층 특징들을 추출한다. 그 이후 추출된 심층 특징들은 완전 연결 계층들로 구성된 분류 모듈의 입력 값으로 들어간다. 분류 모듈에서는 우선 3개의 서로 다른 심층 특징들 각각에 대해 먼저 완전 연결 계층을 거쳐 특징 차원을 줄인다. 그 이후 3개의 차원이 준 특징들을 결합하여 하나의 특징 벡터를 생성한 뒤 다시 완전 연결 계층의 입력값으로 들어가서 최종적인 분류 결과를 예측한다. 우리가 제안한 모델을 평가하기 위해 웹상에 공개된 뇌 MRI 데이터 셋을 사용하였다. 실험 결과 우리가 제안한 모델이 다른 기계학습 기반 모델보다 더 좋은 성능을 나타냄을 확인하였다.

• ETRI Journal
• /
• 제46권2호
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• 한국전자통신학회논문지
• /
• 제19권1호
• /
• pp.137-142
• /
• 2024

최근, 의료 데이터 표현 분야에서 딥러닝 방법들이 사실상의 표준으로 자리잡고 있다. 하지만, 딥러닝 기술은 내재적으로 많은 양의 학습 데이터를 필요로 하므로 대규모의 데이터를 확보하기 쉽지 않은 의료 분야에서는 직접적인 적용이 어려운 실정이다. 특히 뇌신호 모달리티의 경우, 변동성이 크기 때문에 여전히 데이터 부족 문제를 가진다. 이에, 최근 연구에서는 뇌신호의 시간-공간-주파수 특징을 적절하게 추출할 수 있는 딥 뉴럴 네트워크 구조를 설계하거나, 혹은 자가-지도 학습 방법을 도입하여 뇌신호의 신경생리학적 특징을 미리 학습하도록 한다. 본 논문에서는, 최근 각광받는 기술인 뇌-컴퓨터 인터페이스 및 피험자 상태 예측 등의 관점에서 소규모데이터를 다루기 위해 적용되는 방법론에 대한 분석 및 향후 기술 방향성을 제시한다. 먼저 현재 제안되고 있는 뇌신호 표현을 위한 딥 뉴럴 네트워크 구조에 대해 분석한다. 또한 뇌신호의 특성을 잘 학습하기 위한 자가-지도 학습 방법론을 분석한다. 끝으로, 딥러닝 기반 뇌신호 분석을 위한 중요 시사점 및 방향성에 관하여 논한다.

• Journal of Multimedia Information System
• /
• 제8권2호
• /
• pp.79-84
• /
• 2021

Detecting brain tumors of different sizes is a challenging task. This study aimed to identify brain tumors using detection algorithms. Most studies in this area use segmentation; however, we utilized detection owing to its advantages. Data were obtained from 64 patients and 11,200 MR images. The deep learning model used was RetinaNet, which is based on ResNet152. The model learned three different types of pre-processing images: normal, general histogram equalization, and contrast-limited adaptive histogram equalization (CLAHE). The three types of images were compared to determine the pre-processing technique that exhibits the best performance in the deep learning algorithms. During pre-processing, we converted the MR images from DICOM to JPG format. Additionally, we regulated the window level and width. The model compared the pre-processed images to determine which images showed adequate performance; CLAHE showed the best performance, with a sensitivity of 81.79%. The RetinaNet model for detecting brain tumors through deep learning algorithms demonstrated satisfactory performance in finding lesions. In future, we plan to develop a new model for improving the detection performance using well-processed data. This study lays the groundwork for future detection technologies that can help doctors find lesions more easily in clinical tasks.

• Investigative Magnetic Resonance Imaging
• /
• 제25권4호
• /
• pp.266-280
• /
• 2021

Advances in radiomics and deep learning (DL) hold great potential to be at the forefront of precision medicine for the treatment of patients with brain metastases. Radiomics and DL can aid clinical decision-making by enabling accurate diagnosis, facilitating the identification of molecular markers, providing accurate prognoses, and monitoring treatment response. In this review, we summarize the clinical background, unmet needs, and current state of research of radiomics and DL for the treatment of brain metastases. The promises, pitfalls, and future roadmap of radiomics and DL in brain metastases are addressed as well.

• Clinical Psychopharmacology and Neuroscience
• /
• 제16권4호
• /
• pp.494-496
• /
• 2018

No previous reports have described a case in which deep brain stimulation elicited an acute mood swing from a depressive to manic state simply by switching one side of the bilateral deep brain stimulation electrode on and off. The patient was a 68-year-old woman with a 10-year history of Parkinson's disease. She underwent bilateral subthalamic deep brain stimulation surgery. After undergoing surgery, the patient exhibited hyperthymia. She was scheduled for admission. On the first day of admission, it was clear that resting tremors in the right limbs had relapsed and her hyperthymia had reverted to depression. It was discovered that the left-side electrode of the deep brain stimulation device was found to be accidentally turned off. As soon as the electrode was turned on, motor impairment improved and her mood switched from depression to mania. The authors speculate that the lateral balance of stimulation plays an important role in mood regulation. The current report provides an intriguing insight into possible mechanisms of mood swing in mood disorders.

• Journal of Korean Neurosurgical Society
• /
• 제54권2호
• /
• pp.118-124
• /
• 2013

Objective : Subthalamic nucleus (STN) deep brain stimulation (DBS) is an effective treatment of choice for patients with advanced idiopathic Parkinson's disease (PD) who have motor complication with medication. The objectives of this study are to analyze long-term follow-up data of STN DBS cases and to identify the factors related to outcomes. Methods : Fifty-two PD patients who underwent STN DBS were followed-up for more than 3 years. The Unified Parkinson's Disease Rating Scale (UPDRS) and other clinical profiles were assessed preoperatively and during follow-up. A linear regression model was used to analyze whether factors predict the results of STN DBS. We divided the study individuals into subgroups according to several factors and compared subgroups. Results : Preoperative activity of daily living (ADL) and the magnitude of preoperative levodopa response were shown to predict the improvement in UPDRS part II without medication, and preoperative ADL and levodopa equivalent dose (LED) were shown to predict the improvement in UPDRS part II with medication. In UPDRS part III with medication, the magnitude of preoperative levodopa response was a predicting factor. Conclusion : The intensity of preoperative levodopa response was a strong factor for motor outcome. And preoperative ADL and LED were strong factors for ADL improvement. More vigorous studies should be conducted to elucidate how levodopa-induced motor complications are ameliorated after STN DBS.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2013년도 춘계학술대회 논문집
• /
• pp.1497-1498
• /
• 2013