Deep Relation Learning for Regression and Its Application to Brain Age Estimation

TL;DR

This paper introduces deep relation learning for regression tasks, specifically applied to brain age estimation, by modeling multiple relations between image pairs to improve accuracy over traditional single-input models.

Contribution

It proposes a novel deep relation learning framework that simultaneously learns four types of relations between image pairs using a combined CNN and Transformer architecture.

Findings

Achieved a mean absolute error of 2.38 years in brain age estimation.

Outperformed 8 state-of-the-art algorithms with statistically significant results.

Demonstrated effectiveness of relation learning in regression tasks.

Abstract

Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: "cumulative relation", "relative relation", "maximal relation" and "minimal relation". These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0-97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p$<$0.05) in paired T-test (two-side).