A review of the application of deep learning in the detection of Alzheimer's disease

Gao, Shuangshuang; Lima, Dimas

doi:10.1016/j.ijcce.2021.12.002

Cited by 46 publications

(27 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The segmented regions are validated against Ground Truth (GT) images. Segmented images are evaluated by using statistic indices like accuracy, sensitivity, specificity, precision and f1 score [1]. Three cross-validation techniques namely, split validation, K-fold validation and LooCV has be explored.…”

Section: Loss Functionmentioning

confidence: 99%

“…Alzheimer's disease (AD) is the most common form of dementia that impairs memory and cognitive behavior. Treatment strategies for AD have proven more successful when they are administrated during the early stages of the disease [1]. Thus, the early diagnosis of the disease is highly desirable.…”

Section: Introductionmentioning

confidence: 99%

“…The lateral ventricles (LV) are in the center of the brain, surrounded by gray and white matter structures that are often affected by dementia diseases. Existing studies report the use of morphometric features of LV to differentiate AD stages [1].…”

Section: Introductionmentioning

confidence: 99%

“…The analysis of the neuroimaging data such as functional magnetic resonance imaging (fMRI), magnetic resonance imaging (MRI), positron emission tomography (PET), and computed tomography (CT) has achieved much attraction in recent years for AD diagnosis. Among all these modalities MRI images are generally available in a standardized form for clinical practice [1].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated Segmentation of Lateral Ventricles in Alzheimer’s Conditions Using UNET++ Model

Shaikh

Ganapathy

Swaminathan

2022

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

Accurate diagnosis of Alzheimer’s disease (AD) in early stage can control the disease progression. Enlargement of Lateral Ventricles (LV) is one of the significant imaging biomarkers for the differentiation of Alzheimer’s conditions. However, segmentation of accurate LV for analysis is still challenging. In this work, an attempt is made to segment LV regions from brain MR images using the UNet++ model. For this, axial scans of the MR images are taken from the publicly available Open Access Series of Imaging Studies (OASIS) Brain dataset. LV-based region of interest is segmented using the UNet++ network. Results show that the proposed approach is able to segment brain regions in Alzheimer’s conditions. The UNet++ network model yields the highest dice score of 99.4% and sensitivity of 99.3% in segmenting the LV brain region. Thus, the proposed method could be useful for characterizing Alzheimer’s condition.

show abstract

Section: Loss Functionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Segmentation of Lateral Ventricles in Alzheimer’s Conditions Using UNET++ Model

Shaikh

Ganapathy

Swaminathan

2022

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

show abstract

“…Supervised learning is more widely used than unsupervised learning. The most well-known supervised network methods are Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Deep Neural Network (DNN) [28]. The most successful method among them is the convolutional neural network.…”

Section: Supervised Learningmentioning

confidence: 99%

Derin Öğrenme ile Alzheimer Hastalığı Teşhisi İçin Model Önerisi

ÖZKAYA

Cebeci

2022

EJOSAT

View full text Add to dashboard Cite

Alzheimer's disease is one of the greatest health problems of our time. Since there is no cure, it is necessary to diagnose the disease in the early stages and to apply preventive treatments. However, early diagnosis of the disease is very difficult, so most people can be diagnosed after significant and irreversible effects occur. Various studies are carried out by researchers around the world for the early diagnosis of the disease. Deep learning has recently gained importance in the early diagnosis of Alzheimer's disease. With the use of models created using deep learning, the success of early diagnosis has reached high levels. In this study, the stages of Alzheimer's disease and the changes that occur were examined. A literature review was conducted for various techniques used in the diagnosis of Alzheimer's and the use of imaging techniques in the early diagnosis of Alzheimer's was investigated. Due to its widespread use, the MRI technique has been emphasized, and mostly studies using MRI have been examined. Concepts used in deep learning are explained, innovations and results are presented. The architectures used in deep learning and the innovations they bring to this field are revealed, and deep learning models that have been created and tested in current studies are examined. The innovations and success rates brought by various studies have been revealed. Efforts have been made to develop a fast, efficient and successful model that provides ease of use. For this, the scheduler structure, MONAI framework, Data loader structure and various techniques are presented with simple use. Also, the model is optimized to run smoothly on Google Colab. In addition, the tools in the FSL library, which are very important in preprocessing, were studied and optimal parameters were found for the "Bias field and Neck Clean Up", "Standard Brain Extraction Using BET2" and "Robust Brain Center Estimation" tools. By using this library, optimal brain images can be obtained for any model. The DenseNet121 model was used as a basis in the model and it was presented in a structure that can be easily changed. The model can directly use 3D MR images, thus preventing the loss of various spatial information.

show abstract