Multi-Resolution Fusion for Fully Automatic Cephalometric Landmark Detection

TL;DR

This paper introduces a multi-resolution fusion approach using an image pyramid to improve automatic cephalometric landmark detection on lateral skull X-ray images, achieving high accuracy and robustness.

Contribution

It proposes a novel multi-resolution fusion method employing an image pyramid and multiple receptive fields for improved landmark detection accuracy.

Findings

Achieved a Mean Radial Error of 1.62 mm

Attained a Success Detection Rate of 74.18% at 2.0mm

Enhanced robustness with data augmentation techniques

Abstract

Cephalometric landmark detection on lateral skull X-ray images plays a crucial role in the diagnosis of certain dental diseases. Accurate and effective identification of these landmarks presents a significant challenge. Based on extensive data observations and quantitative analyses, we discovered that visual features from different receptive fields affect the detection accuracy of various landmarks differently. As a result, we employed an image pyramid structure, integrating multiple resolutions as input to train a series of models with different receptive fields, aiming to achieve the optimal feature combination for each landmark. Moreover, we applied several data augmentation techniques during training to enhance the model's robustness across various devices and measurement alternatives. We implemented this method in the Cephalometric Landmark Detection in Lateral X-ray Images 2023 Challenge and achieved a Mean Radial Error (MRE) of 1.62 mm and a Success Detection Rate (SDR) 2.0mm of 74.18% in the final testing phase.