H3DE-Net: Efficient and Accurate 3D Landmark Detection in Medical Imaging

TL;DR

H3DE-Net is a novel hybrid deep learning framework that combines CNNs with a lightweight attention mechanism for efficient and accurate 3D landmark detection in medical imaging, addressing the challenge of capturing local details and global context.

Contribution

This work introduces the first 3D landmark detection model integrating a lightweight attention mechanism with CNNs, enhancing accuracy and efficiency in complex anatomical scenarios.

Findings

Achieves state-of-the-art accuracy on a public CT dataset.

Improves robustness in cases with missing landmarks.

Reduces computational cost while maintaining global context modeling.

Abstract

3D landmark detection is a critical task in medical image analysis, and accurately detecting anatomical landmarks is essential for subsequent medical imaging tasks. However, mainstream deep learning methods in this field struggle to simultaneously capture fine-grained local features and model global spatial relationships, while maintaining a balance between accuracy and computational efficiency. Local feature extraction requires capturing fine-grained anatomical details, while global modeling requires understanding the spatial relationships within complex anatomical structures. The high-dimensional nature of 3D volume further exacerbates these challenges, as landmarks are sparsely distributed, leading to significant computational costs. Therefore, achieving efficient and precise 3D landmark detection remains a pressing challenge in medical image analysis. In this work, We propose a \textbf{H}ybrid \textbf{3}D \textbf{DE}tection \textbf{Net}(H3DE-Net), a novel framework that combines CNNs for local feature extraction with a lightweight attention mechanism designed to efficiently capture global dependencies in 3D volumetric data. This mechanism employs a hierarchical routing strategy to reduce computational cost while maintaining global context modeling. To our knowledge, H3DE-Net is the first 3D landmark detection model that integrates such a lightweight attention mechanism with CNNs. Additionally, integrating multi-scale feature fusion further enhances detection accuracy and robustness. Experimental results on a public CT dataset demonstrate that H3DE-Net achieves state-of-the-art(SOTA) performance, significantly improving accuracy and robustness, particularly in scenarios with missing landmarks or complex anatomical variations. We aready open-source our project, including code, data and model weights.