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

TL;DR

This paper introduces a deep learning framework utilizing 3D U-Nets and traditional machine learning to improve the accuracy of diagnosing Alzheimer's disease and Frontotemporal dementia from MRI scans, aiding clinical decision-making.

Contribution

The study presents a novel deep learning approach combining structure grading, atrophy analysis, and ensemble models for differential diagnosis of neurodegenerative diseases from MRI.

Findings

Achieved competitive accuracy in disease detection and differentiation.

Validated model robustness through cross-validation and external testing.

Demonstrated effectiveness on a large dataset of 3319 MRI scans.

Abstract

Alzheimer's disease and Frontotemporal dementia are common forms of neurodegenerative dementia. Behavioral alterations and cognitive impairments are found in the clinical courses of both diseases and their differential diagnosis is sometimes difficult for physicians. Therefore, an accurate tool dedicated to this diagnostic challenge can be valuable in clinical practice. However, current structural imaging methods mainly focus on the detection of each disease but rarely on their differential diagnosis. In this paper, we propose a deep learning based approach for both problems of disease detection and differential diagnosis. We suggest utilizing two types of biomarkers for this application: structure grading and structure atrophy. First, we propose to train a large ensemble of 3D U-Nets to locally determine the anatomical patterns of healthy people, patients with Alzheimer's disease and patients with Frontotemporal dementia using structural MRI as input. The output of the ensemble is a 2-channel disease's coordinate map able to be transformed into a 3D grading map which is easy to interpret for clinicians. This 2-channel map is coupled with a multi-layer perceptron classifier for different classification tasks. Second, we propose to combine our deep learning framework with a traditional machine learning strategy based on volume to improve the model discriminative capacity and robustness. After both cross-validation and external validation, our experiments based on 3319 MRI demonstrated competitive results of our method compared to the state-of-the-art methods for both disease detection and differential diagnosis.