Predicting dementia severity by merging anatomical and diffusion MRI with deep 3D convolutional neural networks

Abstract

Machine learning methods have been used for over a decade for staging and subtyping a variety of brain diseases, offering fast and objective methods to classify neurodegenerative diseases such as Alzheimer's disease (AD). Deep learning models based on convolutional neural networks (CNNs) have also been used to infer dementia severity and predict future clinical decline. Most CNN-based deep learning models use T1-weighted brain MRI scans to identify predictive features for these tasks. In contrast, we examine the added value of diffusion-weighted MRI (dMRI) -a variant of MRI, sensitive to microstructural tissue properties -as an additional input in CNN-based models of dementia severity. dMRI is sensitive to microstructural brain abnormalities not evident on standard anatomical MRI. By training CNNs on combined anatomical and diffusion MRI, we hypothesize that we could boost performance when predicting widely-used clinical assessments of dementia severity, such as individuals' scores on the ADAS11, ADAS13, and MMSE (mini-mental state exam) clinical scales. For benchmarking, we evaluate CNNs that use T1-weighted MRI and dMRI to estimate "brain age" -the task of predicting a person's chronological age from their neuroimaging data. To assess which dMRI-derived maps were most beneficial, we computed DWI-derived diffusion tensor imaging (DTI) maps of mean and radial diffusivity (MD/RD), axial diffusivity (AD) and fractional anisotropy (FA) for 1198 elderly subjects (age: 74.35 +/-7.74 yrs.; 600 F/598 M, with a distribution of 636 CN/421 MCI/141 AD) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We tested both 2D Slice CNN and 3D CNN neural network models for the above predictive tasks. Our results suggest that for at least some deep learning architectures, diffusion-weighted MRI may enhance performance for several AD-relevant deep learning tasks relative to using T1-weighted images alone.

Brain Age Analysis and Dementia Classification using Convolutional Neural Networks trained on Diffusion MRI: Tests in Indian and North American Cohorts

“…We also visualized saliency maps using Grad-CAM [28] for the best performing model in both experiments for Brain Age prediction and CN vs Alzheimer's Disease Classification. In Fig.…”

“…When smaller datasets are available for training, AD classification was more accurate when based on DWI-derived maps, compared to T1w images. DWI image modalities may complement T1w images for other prediction tasks [27,28]. A concatenated model with multiple image modality inputs also outperformed a model using only T1w MRIs.…”

“…dMRI were non-linearly registered to the T1w images. The dMRI processing pipeline is extensively detailed in [6,7,23].…”

“…With a few recent exceptions [4,5], most CNNs developed for detecting rely on T1-weighted brain MRI, the most commonly collected type of brain scan. Nevertheless, others [6,7] have found initial evidence that dMRI, which is more sensitive than T1-weighted MRI to subtle alterations in the brain's white matter microstructure, can provide metrics strongly correlated with age, dementia severity, and even levels of brain amyloid-a primary contributor to AD pathology not detectable on standard MRI. Here, we set out to investigate the potential advantages of dMRI for two common AD-related deep learning tasks: brain age estimation and AD classification.…”

Comparison of deep learning architectures for predicting amyloid positivity in Alzheimer’s disease, mild cognitive impairment, and healthy aging, from T1-weighted brain structural MRI

“…Classical machine learning models, including XGBoost, logistic regression, and ANNs, exhibited promising balanced accuracy and F1 scores: best scores reached around 0.77. There is potential for further improvement with larger training samples and additional data modalities like Diffusion Tensor Images, which have shown significant associations with amyloid ( Chattopadhyay and Singh, 2023a ; Nir et al, 2023 ). Deep learning models, such as the 3D CNN tested, showed slightly better performance than classical machine learning models.…”