# An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms

## TL;DR

This paper introduces an attention-guided deep learning framework using a 2-stage U-Net for accurate, robust landmark detection in cephalometric X-ray images, enhancing orthodontic diagnosis with minimal manual tuning.

## Contribution

It presents a novel 2-stage U-Net architecture with integrated attention mechanisms and an exploration strategy for improved landmark detection in cephalograms.

## Key findings

- Achieves state-of-the-art accuracy on public cephalometric datasets.
- Reduces manual tuning and computational complexity.
- Demonstrates robustness with expanded search scope.

## Abstract

Cephalometric tracing method is usually used in orthodontic diagnosis and treatment planning. In this paper, we propose a deep learning based framework to automatically detect anatomical landmarks in cephalometric X-ray images. We train the deep encoder-decoder for landmark detection, and combine global landmark configuration with local high-resolution feature responses. The proposed frame-work is based on 2-stage u-net, regressing the multi-channel heatmaps for land-mark detection. In this framework, we embed attention mechanism with global stage heatmaps, guiding the local stage inferring, to regress the local heatmap patches in a high resolution. Besides, the Expansive Exploration strategy improves robustness while inferring, expanding the searching scope without increasing model complexity. We have evaluated our framework in the most widely-used public dataset of landmark detection in cephalometric X-ray images. With less computation and manually tuning, our framework achieves state-of-the-art results.

---
Source: https://tomesphere.com/paper/1906.07549