Benefits of Early Detection of Alzheimer’s Disease—A Machine Learning with Image Processing Approach

Nervous system, being the most critical part of the human body has attracted many neuro-surgeons to diagnose the neurological diseases which are of primary concern. It’s been a challenge since many years. The recent report of the World Health Organization’s declares that neurological syndrome, such as, Alzheimer’s disease, affects around one billion human beings. As a consequence of neurological disorder there have been around 6.8 million deaths globally. Along with being an irremediable Disease it is at the same time a progressive brain disease which gradually diminishes the cognitive ability and affects memory which in turn affects routine life. It is prevalent cause of dementia among the elderly. This paper presents the work which assesses the efficacy of classification using unsupervised learning along with the image processing employed on the images of Magnetic Resonance Imaging scans to calculate the probability of early detection of Alzheimer’s disease. The whole brain atrophy is considered as strong diagnostic test for Alzheimer’s disease. The paper expresses the image processing methods such as pixel thresholding and unsupervised learning methods like k-means clustering, and a tailored algorithm incorporated for this specific case. The algorithm has been implemented using platforms, OpenCV and R libraries (for k means clustering), which expedites the effectiveness of the developed prototype which can be used in the hospitals/clinics, reducing the need for any proprietary software. The final output of the prototype can assist the doctors to diagnose Alzheimer’s disease at an early stage. These results can be co-related with psychiatric results for better understanding and treatment required for Alzheimer’s disease.

Download Full-text

Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network

Applied Sciences ◽

10.3390/app11041574 ◽

2021 ◽

Vol 11 (4) ◽

pp. 1574

Author(s):

Shabana Urooj ◽

Satya P. Singh ◽

Areej Malibari ◽

Fadwa Alrowais ◽

Shaeen Kalathil

Keyword(s):

Neural Network ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Early Detection ◽

Differential Evolution ◽

Early Stage ◽

Selection Process ◽

Parameter Tuning ◽

Wavelet Neural Network ◽

Tuning Parameter

Effective and accurate diagnosis of Alzheimer’s disease (AD), as well as early-stage detection, has gained more and more attention in recent years. For AD classification, we propose a new hybrid method for early detection of Alzheimer’s disease (AD) using Polar Harmonic Transforms (PHT) and Self-adaptive Differential Evolution Wavelet Neural Network (SaDE-WNN). The orthogonal moments are used for feature extraction from the grey matter tissues of structural Magnetic Resonance Imaging (MRI) data. Irrelevant features are removed by the feature selection process through evaluating the in-class and among-class variance. In recent years, WNNs have gained attention in classification tasks; however, they suffer from the problem of initial parameter tuning, parameter setting. We proposed a WNN with the self-adaptation technique for controlling the Differential Evolution (DE) parameters, i.e., the mutation scale factor (F) and the cross-over rate (CR). Experimental results on the Alzheimer’s disease Neuroimaging Initiative (ADNI) database indicate that the proposed method yields the best overall classification results between AD and mild cognitive impairment (MCI) (93.7% accuracy, 86.0% sensitivity, 98.0% specificity, and 0.97 area under the curve (AUC)), MCI and healthy control (HC) (92.9% accuracy, 95.2% sensitivity, 88.9% specificity, and 0.98 AUC), and AD and HC (94.4% accuracy, 88.7% sensitivity, 98.9% specificity and 0.99 AUC).

Download Full-text

Astrocytic transporters in Alzheimer's disease

Biochemical Journal ◽

10.1042/bcj20160505 ◽

2017 ◽

Vol 474 (3) ◽

pp. 333-355 ◽

Cited By ~ 7

Author(s):

Chris Ugbode ◽

Yuhan Hu ◽

Benjamin Whalley ◽

Chris Peers ◽

Marcus Rattray ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Early Stage ◽

Neurological Diseases ◽

Current Evidence ◽

Specific Targeting ◽

Disease Modifying Therapies ◽

The Central Nervous System ◽

Disease Modifying ◽

And Function

Astrocytes play a fundamental role in maintaining the health and function of the central nervous system. Increasing evidence indicates that astrocytes undergo both cellular and molecular changes at an early stage in neurological diseases, including Alzheimer's disease (AD). These changes may reflect a change from a neuroprotective to a neurotoxic phenotype. Given the lack of current disease-modifying therapies for AD, astrocytes have become an interesting and viable target for therapeutic intervention. The astrocyte transport system covers a diverse array of proteins involved in metabolic support, neurotransmission and synaptic architecture. Therefore, specific targeting of individual transporter families has the potential to suppress neurodegeneration, a characteristic hallmark of AD. A small number of the 400 transporter superfamilies are expressed in astrocytes, with evidence highlighting a fraction of these are implicated in AD. Here, we review the current evidence for six astrocytic transporter subfamilies involved in AD, as reported in both animal and human studies. This review confirms that astrocytes are indeed a viable target, highlights the complexities of studying astrocytes and provides future directives to exploit the potential of astrocytes in tackling AD.

Download Full-text

Deep Learning Image Processing Technique for Early Detection of Alzheimer's Disease

International Journal of Advanced Science and Technology ◽

10.14257/ijast.2017.107.07 ◽

2017 ◽

Vol 107 ◽

pp. 85-104

Author(s):

Raju Anitha ◽

S. Jyothi ◽

Venkata Naresh Mandhala ◽

Debnath Bhattacharyya ◽

Tai-hoon Kim

Keyword(s):

Alzheimer’S Disease ◽

Image Processing ◽

Alzheimer's Disease ◽

Deep Learning ◽

Early Detection ◽

Processing Technique ◽

Image Processing Technique

Download Full-text

Exploring the methods on early detection of Alzheimer's disease

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.a2391.059120 ◽

2020 ◽

Vol 9 (1) ◽

pp. 1754-1758

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Neural Networks ◽

Alzheimer's Disease ◽

Early Detection ◽

Early Stage ◽

Optimization Techniques ◽

Maximum Information ◽

Daily Task ◽

Comparison Of Techniques

Alzheimer’s disease (AD) is a disorder which is said to be irreversible and affects the behavior and cognitive processes which will eventually affect the memory. This disease beget difficulty in performing the daily task of a patient. It is one of the most common form of dementia affecting people above the age 65 and the risk increases with age. The treatments currently available can only mitigate AD progression but there is no treatment to stop this progression. To bring down the progression of AD early detection becomes necessary. Researchers have found that many machine learning (ML) methods have been useful in detection of AD. Machine learning is a part of artificial intelligence involving probabilistic and optimization techniques such as neural networks that prepares pc's to gain a model from complex datasets. This paper Scrutinizes the developments taken in the field of ML for the possibly early diagnosis of AD. It discusses about various approaches used in recent times for the detection of AD at an early stage. Through this research we found several classification methods such as Recurrent neural networks(RNN), Convolution neural networks(CNN), many more binary and multiclass classifiers along with various methods of preprocessing steps involved in the detection of AD. This paper also throws light on the datasets being used and how these preprocessing steps and different classifiers attribute to increase of accuracy in prediction of AD. Finally, coming to the objective of this paper is to analyze and evaluate these different techniques of ML contributing for the detection AD as early as possible and also to help the researchers to get maximum information and comparison of techniques in one go.

Download Full-text

Fundus Image Analysis to Detect Abnormalities in Diabetic Retinopathy using Computer Aided Design Tools - A Review

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.c6366.089620 ◽

2020 ◽

Vol 9 (6) ◽

pp. 224-232

Keyword(s):

Image Processing ◽

Diabetic Retinopathy ◽

Early Detection ◽

Blood Vessels ◽

Computer Aided Design ◽

Vision Loss ◽

Early Stage ◽

Human Beings ◽

Fundus Image ◽

Detection Techniques

Diabetic retinopathy is becoming a major threat to visual loss in human beings. Many researchers are working to develop early detection techniques, which may reduce the risk of vision loss using image-processing techniques like image enhancement and segmentation. Improving the quality of medical images to detect the disease at an early stage is crucial for further medication. It is gaining more focus with automated techniques for machine learning. Filtering and morphological operators enhance image contrast and interested region can be extracted using segmentation techniques from the fundus image of the retina. For feature analysis the optical disk, localization of blood vessels and segmentation are very useful to observe the parameters like area, length and perimeter of blood vessels etc. Algorithms for this analysis include preprocessing, segmentation, feature extraction and classification. This paper tries to give a detailed review of various image-processing methods used in early detection of diabetic retinopathy and future insights to develop algorithms, which reduces clinician’s time for diagnosis and pathogenesis.

Download Full-text