Article
Biology
Amir Ebrahimi, Suhuai Luo, Raymond Chiong
Summary: The study examined the effectiveness of applying deep sequence-based network models for AD detection, addressing the classification accuracy issue of 2D and 3D CNNs in AD detection by handling the MRI feature sequences generated by CNNs.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Information Systems
Aya Gamal, Mustafa Elattar, Sahar Selim
Summary: This study proposes a new method for early detection of Alzheimer's disease using a computer-aided system. By processing MRI images and conducting multiple experiments, an ensemble learning approach is introduced, which outperforms previous studies in distinguishing different disease stages and multi-class tasks.
Article
Automation & Control Systems
Pakize Erdogmus, Abdullah Talha Kabakus
Summary: Alzheimer's Disease is a devastating neurologic disorder with no cure, and its symptoms eventually interfere with daily tasks. We propose a novel Convolutional Neural Network as a cheap, fast, yet accurate solution for early diagnosis, achieving an accuracy of 90.4% which outperforms existing classifiers.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Duaa AlSaeed, Samar Fouad Omar
Summary: Alzheimer's disease is the most common form of dementia and a leading cause of death among older adults. Early diagnosis of the disease can improve patient survival rates. This study proposes the use of deep learning, specifically a pre-trained CNN model called ResNet50, as an automatic feature extraction method for diagnosing Alzheimer's disease using MRI images. The performance of the proposed model is compared with other state-of-the-art models, achieving higher accuracy rates ranging from 85.7% to 99% on the MRI ADNI dataset.
Article
Engineering, Biomedical
Fangyu Liu, Shizhong Yuan, Weimin Li, Qun Xu, Bin Sheng
Summary: In this paper, a patch-based deep multi-modal learning framework is proposed for brain disease diagnosis. The method integrates multimodal imaging features and jointly learns local patches to improve diagnostic accuracy.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Plant Sciences
Ruoling Deng, Ming Tao, Hang Xing, Xiuli Yang, Chuang Liu, Kaifeng Liao, Long Qi
Summary: A new automatic diagnosis method based on deep learning was developed to diagnose six types of rice diseases, achieving an overall accuracy of 91% by integrating the three best submodels into an Ensemble Model, which effectively minimized confusion among different diseases and improved disease recognition accuracy in a smartphone app setting.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Neurosciences
Jingjing Hu, Zhao Qing, Renyuan Liu, Xin Zhang, Pin Lv, Maoxue Wang, Yang Wang, Kelei He, Yang Gao, Bing Zhang
Summary: The study utilized a deep learning network to classify FTD, AD, and corresponding NCs based on raw T1 images, achieving high accuracy without hypothesis-based preprocessing. The network demonstrated good performance and potential generalizability in solving the differential diagnosis problem of FTD and AD.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Engineering, Biomedical
Salim Lahmiri
Summary: Deep learning and machine learning techniques are gaining interest in the biomedical engineering community, particularly for diagnosing Alzheimer's disease. The proposed automatic system integrates convolutional neural networks (CNN) to extract deep traits from MRI, a filtering technique to reduce features, and a k-nearest neighbors (kNN) algorithm for classification. The results show that this integrative system improves accuracy compared to existing models, with an accuracy of 94.96%, sensitivity of 92.05%, and specificity of 96.62%.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Nitika Goenka, Shamik Tiwari
Summary: The study classified Alzheimer's disease using a deep learning method and achieved high accuracy. Different neuroimaging computational approaches impacted the classification accuracy, with the 3D subject-level method performing the best.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Neurosciences
Hao Guan, Chaoyue Wang, Jian Cheng, Jing Jing, Tao Liu
Summary: The proposed deep learning framework for AD diagnosis learns global and local features directly from sMRI scans without prior knowledge, achieving competitive results on public datasets. The framework is lightweight, suitable for end-to-end training, and effective when medical priors are unavailable or computing resources are limited.
HUMAN BRAIN MAPPING
(2022)
Article
Computer Science, Artificial Intelligence
Regina Esi Turkson, Hong Qu, Cobbinah Bernard Mawuli, Moses J. Eghan
Summary: Using deep learning techniques, a novel spiking deep convolutional neural network-based pipeline was developed for classifying Alzheimer's Disease through MRI scans. Experimental results demonstrated the effectiveness of pre-training the spiking neural networks in improving classification accuracy, showcasing the robust discriminative capability of the proposed method.
NEURAL PROCESSING LETTERS
(2021)
Article
Computer Science, Information Systems
Yori Pusparani, Chih-Yang Lin, Yih-Kuen Jan, Fu-Yu Lin, Ben-Yi Liau, Peter Ardhianto, Isack Farady, John Sahaya Rani Alex, Jeetashree Aparajeeta, Wen-Hung Chao, Chi-Wen Lung
Summary: Alzheimer's disease is a significant public health concern. We improved the accuracy of machine learning for diagnosing AD by selecting key slices in the hippocampus region of MRI images.
Article
Multidisciplinary Sciences
Ellen Xu, Shamim Nemati, Adriana H. Tremoulet
Summary: This study aimed to develop a deep convolutional neural network, KD-CNN, to differentiate photographs of Kawasaki disease clinical signs from those of other pediatric illnesses. The study showed that KD-CNN can accurately distinguish between children with and without clinical manifestations of Kawasaki disease, potentially assisting clinicians in reducing morbidity and mortality rates.
SCIENTIFIC REPORTS
(2022)
Article
Oncology
Mubashar Mehmood, Sadam Hussain Abbasi, Khursheed Aurangzeb, Muhammad Faran Majeed, Muhammad Shahid Anwar, Musaed Alhussein
Summary: This study proposes a methodology combining deep learning and transfer learning for identifying prostate cancer using MRI images. By utilizing the EfficientNet architecture and three branches for feature extraction, the model achieves remarkable accuracy of 88.89% in classifying prostate cancer.
FRONTIERS IN ONCOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Lin Zhang, Lei Ren, Tian Bai, Mingyu Du, Li Ruan, Yuan Yang, Guanghao Qian, Zihao Meng, Li Zhao, M. Jamal Deen
Summary: The paper proposes a novel AD detection method based on an adversarial network, which combines generative adversarial network (GAN) and convolutional neural network (CNN) to extract high-level brain features for AD diagnosis. Experimental results demonstrate that this method extracts more representative brain features and achieves a significant improvement in diagnosis performance.