Assessing Machine Learning Models for Predicting Age with Intracranial Vessel Tortuosity and Thickness Information

Abstract

This study aimed to develop and validate machine learning (ML) models that predict age using intracranial vessels' tortuosity and diameter features derived from magnetic resonance angiography (MRA) data. A total of 171 subjects' three-dimensional (3D) time-of-flight MRA image data were considered for analysis. After annotations of two endpoints in each arterial segment, tortuosity features such as the sum of the angle metrics, triangular index, relative length, and product of the angle distance, as well as the vessels' diameter features, were extracted and used to train and validate the ML models for age prediction. Features extracted from the right and left internal carotid arteries (ICA) and basilar arteries were considered as the inputs to train and validate six ML regression models with a four-fold cross validation. The random forest regression model resulted in the lowest root mean square error of 14.9 years and the highest average coefficient of determination of 0.186. The linear regression model showed the lowest average mean absolute percentage error (MAPE) and the highest average Pearson correlation coefficient (0.532). The mean diameter of the right ICA vessel segment was the most important feature contributing to prediction of age in two out of the four regression models considered. An ML of tortuosity descriptors and diameter features extracted from MRA data showed a modest correlation between real age and ML-predicted age. Further studies are warranted for the assessment of the model's age predictions in patients with intracranial vessel diseases.

Keywords: age prediction; feature extraction; intracranial artery; machine learning; magnetic resonance angiography; medical image analysis.

Figure 1

A flowchart of the overall process. The light green boxes are primarily related to the machine learning predictions of age.

Figure 2

An example of the annotated vessel segments. A1, anterior cerebral artery (ACA) A1; M1, middle cerebral artery (MCA) M1; ICA, internal carotid artery; PComm, posterior communicating artery; P1, posterior cerebral artery (PCA) P1; P2, PCA P2; BA, basilar artery; R, right; L, left.

Figure 3

The spline interpolation for smoothing the centerline in a basilar artery. The skeleton is discretized in the 3D coordinate space, and hence, when displayed, it shows a jagged appearance, as indicated by the blue line. A spline interpolation results in the smooth curve which is indicated by the red line.

Figure 4

Scatter plots of the age predictions of the (a) random forest regression, (b) linear regression, and (c) XGBoost regression models. The top plots are models’ predictions on the training data, and the bottom plots are the models’ predictions on the test data. The blue dots are samples, and the red line is the y = x line.

Figure 5

Lists of the ten most important features for the (a) random forest regression, (b) AdaBoost regression, (c) gradient boosting regression, and (d) XGBoost regression models.