Arterial Spin Labeling Aids MRI in Alzheimer’s Classification

July 25, 2016

Adding arterial spin labeling to MRI may help classify and predict Alzheimer’s diagnosis and progression from subjective cognitive decline.

Automated methods, age- and sex-adjusted arterial spin labeling perfusion maps may aid in classifying and predicting Alzheimer’s disease (AD) diagnosis, as well as conversion of mild cognitive impairment (MCI), according to a study published in Radiology.

Researchers from the Netherlands sought to determine if multivariate pattern recognition analysis of arterial spin labeling (ASL) magnetic resonance images can be used to classify and predict progression of AD and MCI, and subjective cognitive decline (SCD) after using the W score method to remove confounding effects of sex and age.

The study included the pseudocontinuous 3.0-T ASL images of 260 patients:

100 with probable AD

60 with MCI (12 remained stable, 12 converted to a diagnosis of AD, and 36 with no follow-up)

100 with SCD

26 healthy controls.

The AD, MCI, and SCD groups were divided into a sex- and age-matched training set (130 subjects) and an independent prediction set (130 subjects). Standardized perfusion scores adjusted for age and sex (W scores) were computed per voxel for each participant. Training of a support vector machine classifier was performed with diagnostic status and perfusion maps. Discrimination maps were extracted and used for single-subject classification in the prediction set. Prediction performance was assessed with receiver operating characteristic (ROC) analysis to generate an area under the ROC curve (AUC) and sensitivity and specificity distribution.

The results showed that the discrimination maps yielded excellent performance for AD versus SCD, good performance for AD versus MCI, and poor performance for MCI versus SCD. “Application of the AD versus SCD discrimination map for prediction of MCI subgroups resulted in good performance for patients with MCI diagnosis converted to AD versus subjects with SCD and fair performance for patients with MCI diagnosis converted to AD versus those with stable MCI,” the authors wrote.[[{"type":"media","view_mode":"media_crop","fid":"50440","attributes":{"alt":"©RSNA 2016","class":"media-image","id":"media_crop_218847514910","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"6158","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 389px; width: 400px;","title":"Discrimination maps for training analysis with the main diagnostic groups. A, For AD versus SCD: In the parietal lobe and hippocampus, AUC was 0.93, and accuracy was 89.0%. B, For AD versus MCI: In the parietal and occipital lobe, AUC was 0.88, and accuracy was 83.8%. C, For MCI versus SCD: In the whole brain, AUC was 0.49, and accuracy was 57.5%. MNI coordinates are as follows: x = 26, y = −20, z = 0. Image courtesy of Radiology. ©RSNA 2016","typeof":"foaf:Image"}}]]