For the first time, a group of researchers from Lithuania constructed what is believed to be a deep learning method with practically 100 percent accuracy of predicting the onset of cognitive diseases like Alzheimer’s disease.
The findings were presented online in the journal Diagnostics.
According to the study, researchers built the method by analyzing the fMRI scans of more than 130 participants.
“Although there has been an increase in research into the diagnosis of AD in its early levels of developments lately, brain changes, and their complexity for functional magnetic resonance imaging (fMRI), makes early detection of AD difficult,” the authors said in their study.
“This paper proposes a deep learning-based method that can predict MCI, early MCI (EMCI), late MCI (LMCI), and AD. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) fMRI dataset consisting of 138 subjects was used for evaluation.”
Researchers showed how the method they developed could efficiently identify the features of mild cognitive impairment (MCI) in the dataset, with an accuracy rate of 99.99 and 99.95 percent for early MCI vs AD, late MCI vs AD, and MCI vs early MCI.
The new algorithm, researchers say, would be able to analyze collected data from people with a history of pathology and notify of any anomalies that would identify early onset of Alzheimer’s disease.
“In this study, we have analyzed the effect of dropout on a fine-tuned pretrained model to classify fMR images from the ADNI database. This study’s findings revealed that fine-tuning the entire network gave high classification accuracy on all binary classification scenarios except AD vs. CN and CN vs. LMCI,” the authors explained in their journal article.
