Scientists develop AI-based method to diagnose Alzheimer's or Parkinson's

February 17, 2017
Alzheimer's disease, which currently affects more than 40 million people, is the most common neurodegenerative disease in elder people. Credit: UGRdivulga

Alzheimer's disease, which currently affects more than 40 million people, is the most common neurodegenerative disease in elderly people. Early diagnosis is crucial both to treat the disease and to help the development of new medicines, as it hasn't been possible to find a cure so far. The development of Alzheimer's has been proven to be closely linked to both structural changes in gray matter and functional changes in the white matter connecting the regions of the brain. In the brain connectivity network, a significant loss of white matter fibers also causes functional alterations such as memory loss. However, diagnosis remains a challenge, and to date, it hasn't been possible to determine how functional cerebral activity contributes to the deterioration of structural activity and vice versa.

In this regard, computer-aided diagnosis (CAD) is an important tool that helps physicians to understand multimedia content obtained in tests carried out with patients, which allows simpler treatment. One such procedure is medical imaging, which provides high-resolution "live" information on the subject. The BioSip research team of the University of Malaga, in collaboration with a group of researchers from the University of Granada, has been studying biomedical images and signals for years.

Researchers Andrés Ortiz, Jorge Munilla, Juan Górriz and Javier Ramírez have recently published an article in the International Journal Of Neural Systems titled "Ensembles of architectures for the of the Alzheimer's ." The study presents a deep-learning technique for the diagnosis of Alzheimer's by the joint analysis of functional and structural images.

This artificial intelligence (AI) technique aims to model high-level data abstractions in order to enable computers to differentiate the brain of a healthy person from that of an ill person by automatically extracting the affected regions of interest. The researchers write, "The study uses deep learning techniques to calculate brain function predictors and magnetic resonance imaging to prevent Alzheimer's disease. To do this, we have used different neural networks with which to model each region of the brain to combine them afterwards."

The study explores the construction of classification methods based on deep learning architectures applied to brain regions defined by a digital atlas of the human brain called Automated Anatomical Labeling (AAL). To this end, images of the of each area of the brain have been divided according to the regions separated in different sectors by the AAL, which have been used to train deep-learning neural networks specialized in the different regions of the . The knowledge acquired by the networks is subsequently combined by different fusion techniques presented in this paper.

Classification architecture

The result of this work is a powerful classification architecture that combines supervised and unsupervised learning to automatically extract the most relevant features of a set of images. The proposed method has been evaluated using a large database from the Alzheimer's Disease Neuroimaging Initiative (ADNI).

The results of this work, which included patients with other cognitive deficits that can develop Alzheimer's within two years, show the potential of AI techniques to reveal patterns associated with the disease. The accuracy rates obtained for the diagnosis contribute to the knowledge of the neurodegenerative process involved in the development of the disease, and is also useful as a starting point for the development of more effective medical treatments.

Explore further: Artificial intelligence may aid in Alzheimer's diagnosis

More information: Andrés Ortiz et al, Ensembles of Deep Learning Architectures for the Early Diagnosis of the Alzheimer's Disease, International Journal of Neural Systems (2016). DOI: 10.1142/S0129065716500258

Related Stories

Artificial intelligence may aid in Alzheimer's diagnosis

July 6, 2016
Machine learning is a type of artificial intelligence that allows computer programs to learn when exposed to new data without being programmed. Now, researchers in The Netherlands have coupled machine learning methods with ...

A spherical brain mapping of MR images for the detection of Alzheimer's disease

May 20, 2016
Diagnosis, treatment and care of dementia is one of the major concerns in neurology research and associated healthcare programs. Dementia affects older age groups with a greater frequency, and as our population ages, the ...

Imaging links structural brain changes and cognitive decline in Parkinson's

December 7, 2016
People with Parkinson's disease and cognitive impairment have disruptions in their brain networks that can be seen on a type of MRI, according to a study appearing online in the journal Radiology.

What goes wrong in a brain affected by Alzheimer's disease?

August 22, 2013
The ability of different regions of the brain to communicate gradually breaks down with aging and in Alzheimer's disease, but there are key differences between these two processes. Some of these differences are reported in ...

New approaches to understanding Alzheimer's and Parkinson's disease

July 26, 2016
In a study presented today at the Alzheimer's Association International Conference 2016, researchers at the Douglas Mental Health University Institute have explored how some people may develop the hallmarks of Alzheimer's ...

Imaging test may identify biomarker of Alzheimer's disease

May 27, 2015
Degeneration of the white matter of the brain may be an early marker of specific types of Alzheimer's disease (AD), including early-onset AD, according to results of a new study published in the journal Radiology.

Recommended for you

Research redefines proteins' role in the development of spinal sensory cells

September 19, 2017
A recent study led by Samantha Butler at the Eli and Edythe Broad Center of Regenerative Medicine and Stem Cell Research at UCLA has overturned a common belief about how a certain class of proteins in the spinal cord regulate ...

The brain at work: Spotting half-hidden objects

September 19, 2017
How does a driver's brain realize that a stop sign is behind a bush when only a red edge is showing? Or how can a monkey suspect that the yellow sliver in the leaves is a round piece of fruit?

Team discovers how to train damaging inflammatory cells to promote repair after stroke

September 19, 2017
White blood cells called neutrophils are like soldiers in your body that form in the bone marrow and at the first sign of microbial attack, head for the site of injury just as fast as they can to neutralize invading bacteria ...

Epileptic seizures show long-distance effects

September 19, 2017
The area in which an epileptic seizure starts in the brain, may be small but it reaches other parts of the brain at distances of over ten centimeters. That distant activity, in turn, influences the epileptic core, according ...

Study uncovers markers for severe form of multiple sclerosis

September 18, 2017
Scientists have uncovered two closely related cytokines—molecules involved in cell communication and movement—that may explain why some people develop progressive multiple sclerosis (MS), the most severe form of the disease. ...

Genetically altered mice bear some hallmarks of human bipolar behavior

September 18, 2017
Johns Hopkins researchers report they have genetically engineered mice that display many of the behavioral hallmarks of human bipolar disorder, and that the abnormal behaviors the rodents show can be reversed using well-established ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.