Adversarial Regression Learning for Bone Age Estimation

TL;DR

This paper introduces ARLNet, an adversarial regression network that improves bone age estimation accuracy by reducing training-test data discrepancy through adversarial and feature reconstruction losses.

Contribution

The paper presents a novel adversarial regression learning framework with specific loss functions to enhance generalization in bone age estimation.

Findings

ARLNet outperforms existing methods on benchmark datasets.

The model effectively reduces training-test discrepancy.

Invariant feature preservation improves estimation accuracy.

Abstract

Estimation of bone age from hand radiographs is essential to determine skeletal age in diagnosing endocrine disorders and depicting the growth status of children. However, existing automatic methods only apply their models to test images without considering the discrepancy between training samples and test samples, which will lead to a lower generalization ability. In this paper, we propose an adversarial regression learning network (ARLNet) for bone age estimation. Specifically, we first extract bone features from a fine-tuned Inception V3 neural network and propose regression percentage loss for training. To reduce the discrepancy between training and test data, we then propose adversarial regression loss and feature reconstruction loss to guarantee the transition from training data to test data and vice versa, preserving invariant features from both training and test data. Experimental results show that the proposed model outperforms state-of-the-art methods.