Cephalometric Landmark Detection by AttentiveFeature Pyramid Fusion and Regression-Voting

TL;DR

This paper introduces an attentive feature pyramid fusion module and a regression-voting approach to enhance the accuracy of automatic cephalometric landmark detection in radiographs, outperforming existing methods.

Contribution

The paper proposes a novel AFPF module and a pixel-wise regression-voting method, significantly improving landmark detection accuracy in cephalometric analysis.

Findings

Achieved 7-11% higher accuracy over state-of-the-art methods

Demonstrated robustness across diverse datasets and devices

Provided ablation studies for component analysis

Abstract

Marking anatomical landmarks in cephalometric radiography is a critical operation in cephalometric analysis. Automatically and accurately locating these landmarks is a challenging issue because different landmarks require different levels of resolution and semantics. Based on this observation, we propose a novel attentive feature pyramid fusion module (AFPF) to explicitly shape high-resolution and semantically enhanced fusion features to achieve significantly higher accuracy than existing deep learning-based methods. We also combine heat maps and offset maps to perform pixel-wise regression-voting to improve detection accuracy. By incorporating the AFPF and regression-voting, we develop an end-to-end deep learning framework that improves detection accuracy by 7%~11% for all the evaluation metrics over the state-of-the-art method. We present ablation studies to give more insights into different components of our method and demonstrate its generalization capability and stability for unseen data from diverse devices.