Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images

TL;DR

This paper introduces a novel topological graph convolutional network integrated with an improved conformer for more accurate hip landmark detection in ultrasound images, addressing noise challenges in medical diagnosis.

Contribution

The work presents a new TGCN-ICF model combining topological GCN and conformer architectures with a fusion module, enhancing detection accuracy over existing methods.

Findings

TGCN-ICF outperforms existing algorithms on real DDH dataset.

The integrated model improves landmark detection accuracy in noisy ultrasound images.

Fusion of features from U-Net and Transformer enhances performance.

Abstract

The B-mode ultrasound based computer-aided diagnosis (CAD) has demonstrated its effectiveness for diagnosis of Developmental Dysplasia of the Hip (DDH) in infants. However, due to effect of speckle noise in ultrasound im-ages, it is still a challenge task to accurately detect hip landmarks. In this work, we propose a novel hip landmark detection model by integrating the Topological GCN (TGCN) with an Improved Conformer (TGCN-ICF) into a unified frame-work to improve detection performance. The TGCN-ICF includes two subnet-works: an Improved Conformer (ICF) subnetwork to generate heatmaps and a TGCN subnetwork to additionally refine landmark detection. This TGCN can effectively improve detection accuracy with the guidance of class labels. Moreo-ver, a Mutual Modulation Fusion (MMF) module is developed for deeply ex-changing and fusing the features extracted from the U-Net and Transformer branches in ICF. The experimental results on the real DDH dataset demonstrate that the proposed TGCN-ICF outperforms all the compared algorithms.