HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Xiaoqian, Huang, Zhen, Zhu, Heqin, Yao, Qingsong, Zhou, S. Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929632198000640
author Zhou, Xiaoqian
Huang, Zhen
Zhu, Heqin
Yao, Qingsong
Zhou, S. Kevin
author_facet Zhou, Xiaoqian
Huang, Zhen
Zhu, Heqin
Yao, Qingsong
Zhou, S. Kevin
contents Anatomical landmark detection (ALD) from a medical image is crucial for a wide array of clinical applications. While existing methods achieve quite some success in ALD, they often struggle to balance global context with computational efficiency, particularly with high-resolution images, thereby leading to the rise of a natural question: where is the performance limit of ALD? In this paper, we aim to forge performant ALD by proposing a {\bf HY}brid {\bf ATT}ention {\bf Net}work (HYATT-Net) with the following designs: (i) A novel hybrid architecture that integrates CNNs and Transformers. Its core is the BiFormer module, utilizing Bi-Level Routing Attention for efficient attention to relevant image regions. This, combined with Attention Residual Module(ARM), enables precise local feature refinement guided by the global context. (ii) A Feature Fusion Correction Module that aggregates multi-scale features and thus mitigates a resolution loss. Deep supervision with a mean-square error loss on multi-resolution heatmaps optimizes the model. Experiments on five diverse datasets demonstrate state-of-the-art performance, surpassing existing methods in accuracy, robustness, and efficiency. The HYATT-Net provides a promising solution for accurate and efficient ALD in complex medical images. Our codes and data are already released at: \url{https://github.com/ECNUACRush/HYATT-Net}.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06499
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark Detection
Zhou, Xiaoqian
Huang, Zhen
Zhu, Heqin
Yao, Qingsong
Zhou, S. Kevin
Computer Vision and Pattern Recognition
Anatomical landmark detection (ALD) from a medical image is crucial for a wide array of clinical applications. While existing methods achieve quite some success in ALD, they often struggle to balance global context with computational efficiency, particularly with high-resolution images, thereby leading to the rise of a natural question: where is the performance limit of ALD? In this paper, we aim to forge performant ALD by proposing a {\bf HY}brid {\bf ATT}ention {\bf Net}work (HYATT-Net) with the following designs: (i) A novel hybrid architecture that integrates CNNs and Transformers. Its core is the BiFormer module, utilizing Bi-Level Routing Attention for efficient attention to relevant image regions. This, combined with Attention Residual Module(ARM), enables precise local feature refinement guided by the global context. (ii) A Feature Fusion Correction Module that aggregates multi-scale features and thus mitigates a resolution loss. Deep supervision with a mean-square error loss on multi-resolution heatmaps optimizes the model. Experiments on five diverse datasets demonstrate state-of-the-art performance, surpassing existing methods in accuracy, robustness, and efficiency. The HYATT-Net provides a promising solution for accurate and efficient ALD in complex medical images. Our codes and data are already released at: \url{https://github.com/ECNUACRush/HYATT-Net}.
title HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.06499