English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Alzheimer's disease and Frontotemporal dementia are common forms ofneurodegenerative dementia. Behavioral alterations and cognitive impairmentsare found in the clinical courses of both diseases and their differentialdiagnosis is sometimes difficult for physicians. Therefore, an accurate tooldedicated to this diagnostic challenge can be valuable in clinical practice.However, current structural imaging methods mainly focus on the detection ofeach disease but rarely on their differential diagnosis. In this paper, wepropose a deep learning based approach for both problems of disease detectionand differential diagnosis. We suggest utilizing two types of biomarkers forthis application: structure grading and structure atrophy. First, we propose totrain a large ensemble of 3D U-Nets to locally determine the anatomicalpatterns of healthy people, patients with Alzheimer's disease and patients withFrontotemporal dementia using structural MRI as input. The output of theensemble is a 2-channel disease's coordinate map able to be transformed into a3D grading map which is easy to interpret for clinicians. This 2-channel map iscoupled with a multi-layer perceptron classifier for different classificationtasks. Second, we propose to combine our deep learning framework with atraditional machine learning strategy based on volume to improve the modeldiscriminative capacity and robustness. After both cross-validation andexternal validation, our experiments based on 3319 MRI demonstrated competitiveresults of our method compared to the state-of-the-art methods for both diseasedetection and differential diagnosis.

Deep grading for MRI-based differential diagnosis of Alzheimer's disease and Frontotemporal dementia