PRSNet: Part Relation and Selection Network for Bone Age Assessment

TL;DR

PRSNet introduces a novel deep learning framework that models part relations and selects key hand bones to improve bone age assessment accuracy from X-ray images, achieving state-of-the-art results.

Contribution

The paper proposes a new part relation module and a part selection module, jointly trained end-to-end, to enhance bone age assessment accuracy by effectively modeling anatomical part relationships.

Findings

Achieves state-of-the-art performance on RSNA 2017 dataset.

Outperforms existing methods significantly.

Effectively models part relationships and importance for BAA.

Abstract

Bone age is one of the most important indicators for assessing bone's maturity, which can help to interpret human's growth development level and potential progress. In the clinical practice, bone age assessment (BAA) of X-ray images requires the joint consideration of the appearance and location information of hand bones. These kinds of information can be effectively captured by the relation of different anatomical parts of hand bone. Recently developed methods differ mostly in how they model the part relation and choose useful parts for BAA. However, these methods neglect the mining of relationship among different parts, which can help to improve the assessment accuracy. In this paper, we propose a novel part relation module, which accurately discovers the underlying concurrency of parts by using multi-scale context information of deep learning feature representation. Furthermore, based on the part relation, we explore a new part selection module, which comprehensively measures the importance of parts and select the top ranking parts for assisting BAA. We jointly train our part relation and selection modules in an end-to-end way, achieving state-of-the-art performance on the public RSNA 2017 Pediatric Bone Age benchmark dataset and outperforming other competitive methods by a significant margin.