Table 2 Comparative predictive accuracy of our CNN-MLP and brainageR algorithms.

From: Brain age prediction using combined deep convolutional neural network and multi-layer perceptron algorithms

 

Algorithm

Input

Performance metrics

MAE (years)

RMSE (years)

R2

Proposed algorithm

Combined CNN-MLP

Minimally preprocessed whole brain T1-weighted image + sex information

4.910

6.148

0.891

Segmented GM & WM  + sex information

5.276

6.452

0.879

brainageR 15

GPR

Segmented GM & WM

5.360

6.923

0.861

  1. The performance of each algorithm was evaluated using the external validation dataset from the CamCAN set (n = 645).
  2. CamCAN Cambridge Centre for Ageing and Neuroscience, CNN convolutional neural network, GM gray matter, GPR Gaussian process regression, MAE mean absolute error, MLP multi-layer perceptron, RMSE root mean squared error, R2 coefficient of determination, WM white matter.
Back to article page