http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Classification of Alzheimer’s Disease with Stacked Convolutional Autoencoder
Husnu Baris Baydargil,Jang Sik Park,강도영 한국멀티미디어학회 2020 멀티미디어학회논문지 Vol.23 No.2
In this paper, a stacked convolutional autoencoder model is proposed in order to classify Alzheimer’s disease with high accuracy in PET/CT images. The proposed model makes use of the latent space representation - which is also called the bottleneck, of the encoder-decoder architecture: The input image is sent through the pipeline and the encoder part, using stacked convolutional filters, extracts the most useful information. This information is in the bottleneck, which then uses Softmax classification operation to classify between Alzheimer’s disease, Mild Cognitive Impairment, and Normal Control. Using the data from Dong-A University, the model performs classification in detecting Alzheimer’s disease up to 98.54% accuracy.
Classification of Alzheimer’s Disease Using Stacked Sparse Convolutional Autoencoder
Husnu Baris Baydargil,Jang-Sik Park,Do-Young Kang 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10
Alzheimer’s disease is a neurodegenerative disease that affects the brain structure and its functions. Early and accurate detection of AD through medical imaging may improve lifespan and overall quality of life for patients and their caretakers. In this paper, a specially developed sparse autoencoder is used to accurately detect AD in PET/CT (Positron Emission Tomography/ Computerized Tomography) brain images. Sagittal and coronal images were created from axial images, and those were trained separately to compare classification results. Two-stage training is utilized; first stage, a supervised training to train the classifier to identify the AD, and an unsupervised learning in order to produce an image output. In the created dataset, state-of-the-art classification models are trained and compared to the developed model. A 98.67% accuracy is reached for sagittal images. Detailed information is provided in chapters three and four.
Classification of Alzheimer's Disease with Stacked Convolutional Autoencoder
Baydargil, Husnu Baris,Park, Jang Sik,Kang, Do Young Korea Multimedia Society 2020 멀티미디어학회논문지 Vol.23 No.2
In this paper, a stacked convolutional autoencoder model is proposed in order to classify Alzheimer's disease with high accuracy in PET/CT images. The proposed model makes use of the latent space representation - which is also called the bottleneck, of the encoder-decoder architecture: The input image is sent through the pipeline and the encoder part, using stacked convolutional filters, extracts the most useful information. This information is in the bottleneck, which then uses Softmax classification operation to classify between Alzheimer's disease, Mild Cognitive Impairment, and Normal Control. Using the data from Dong-A University, the model performs classification in detecting Alzheimer's disease up to 98.54% accuracy.
( Husnu Baris Baydargil ),( Jangsik Park ),( Do-young Kang ),( Hyun Kang ),( Kook Cho ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.9
In this paper, a parallel deep learning model using a convolutional neural network and a dilated convolutional neural network is proposed to classify Alzheimer’s disease with high accuracy in PET/CT images. The developed model consists of two pipelines, a conventional CNN pipeline, and a dilated convolution pipeline. An input image is sent through both pipelines, and at the end of both pipelines, extracted features are concatenated and used for classifying Alzheimer’s disease. Complimentary abilities of both networks provide better overall accuracy than single conventional CNNs in the dataset. Moreover, instead of performing binary classification, the proposed model performs three-class classification being Alzheimer’s disease, mild cognitive impairment, and normal control. Using the data received from Dong-a University, the model performs classification detecting Alzheimer’s disease with an accuracy of up to 95.51%.