Residual Attention based Network for Hand Bone Age Assessment

TL;DR

This paper introduces a novel deep learning framework combining hand segmentation and residual attention mechanisms to improve accuracy and interpretability in automated hand bone age assessment from X-ray images.

Contribution

It proposes a two-component framework with hand segmentation and residual attention networks, inspired by clinical workflows, to enhance focus on key hand features for bone age prediction.

Findings

Outperforms previous methods on RSNA dataset

Effectively isolates hand regions from X-ray images

Provides visual explanations similar to clinical assessment

Abstract

Computerized automatic methods have been employed to boost the productivity as well as objectiveness of hand bone age assessment. These approaches make predictions according to the whole X-ray images, which include other objects that may introduce distractions. Instead, our framework is inspired by the clinical workflow (Tanner-Whitehouse) of hand bone age assessment, which focuses on the key components of the hand. The proposed framework is composed of two components: a Mask R-CNN subnet of pixelwise hand segmentation and a residual attention network for hand bone age assessment. The Mask R-CNN subnet segments the hands from X-ray images to avoid the distractions of other objects (e.g., X-ray tags). The hierarchical attention components of the residual attention subnet force our network to focus on the key components of the X-ray images and generate the final predictions as well as the associated visual supports, which is similar to the assessment procedure of clinicians. We evaluate the performance of the proposed pipeline on the RSNA pediatric bone age dataset and the results demonstrate its superiority over the previous methods.