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

The integration of machine learning in medicine has significantly improveddiagnostic precision, particularly in the interpretation of complex structureslike the human brain. Diagnosing challenging conditions such as Alzheimer'sdisease has prompted the development of brain age estimation techniques. Thesemethods often leverage three-dimensional Magnetic Resonance Imaging (MRI)scans, with recent studies emphasizing the efficacy of 3D convolutional neuralnetworks (CNNs) like 3D ResNet. However, the untapped potential of VisionTransformers (ViTs), known for their accuracy and interpretability, persists inthis domain due to limitations in their 3D versions. This paper introducesTriamese-ViT, an innovative adaptation of the ViT model for brain ageestimation. Our model uniquely combines ViTs from three different orientationsto capture 3D information, significantly enhancing accuracy andinterpretability. Tested on a dataset of 1351 MRI scans, Triamese-ViT achievesa Mean Absolute Error (MAE) of 3.84, a 0.9 Spearman correlation coefficientwith chronological age, and a -0.29 Spearman correlation coefficient betweenthe brain age gap (BAG) and chronological age, significantly better thanprevious methods for brian age estimation. A key innovation of Triamese-ViT isits capacity to generate a comprehensive 3D-like attention map, synthesizedfrom 2D attention maps of each orientation-specific ViT. This feature isparticularly beneficial for in-depth brain age analysis and disease diagnosis,offering deeper insights into brain health and the mechanisms of age-relatedneural changes.

Triamese-ViT: A 3D-Aware Method for Robust Brain Age Estimation from MRIs