基于多尺度特征融合与层次注意力的甲状腺超声图像三维可视化

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention.

作者信息

Mi Junyu, Wang Rui, Feng Qian, Han Lin, Zhuang Yan, Chen Ke, Chen Zhong, Hua Zhan, Luo Yan, Lin Jiangli

机构信息

College of Biomedical Engineering, Sichuan University, Chengdu, Sichuan, China.

Department of Ultrasound, General Hospital of Western Theater Command, Chengdu, Sichuan, China.

出版信息

Biomed Eng Online. 2024 Mar 11;23(1):31. doi: 10.1186/s12938-024-01215-1.

DOI:10.1186/s12938-024-01215-1

PMID:38468262

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10926618/

Abstract

BACKGROUND

Ultrasound three-dimensional visualization, a cutting-edge technology in medical imaging, enhances diagnostic accuracy by providing a more comprehensive and readable portrayal of anatomical structures compared to traditional two-dimensional ultrasound. Crucial to this visualization is the segmentation of multiple targets. However, challenges like noise interference, inaccurate boundaries, and difficulties in segmenting small structures exist in the multi-target segmentation of ultrasound images. This study, using neck ultrasound images, concentrates on researching multi-target segmentation methods for the thyroid and surrounding tissues.

METHOD

We improved the Unet++ to propose PA-Unet++ to enhance the multi-target segmentation accuracy of the thyroid and its surrounding tissues by addressing ultrasound noise interference. This involves integrating multi-scale feature information using a pyramid pooling module to facilitate segmentation of structures of various sizes. Additionally, an attention gate mechanism is applied to each decoding layer to progressively highlight target tissues and suppress the impact of background pixels.

RESULTS

Video data obtained from 2D ultrasound thyroid serial scans served as the dataset for this paper.4600 images containing 23,000 annotated regions were divided into training and test sets at a ratio of 9:1, the results showed that: compared with the results of U-net++, the Dice of our model increased from 78.78% to 81.88% (+ 3.10%), the mIOU increased from 73.44% to 80.35% (+ 6.91%), and the PA index increased from 92.95% to 94.79% (+ 1.84%).

CONCLUSIONS

Accurate segmentation is fundamental for various clinical applications, including disease diagnosis, treatment planning, and monitoring. This study will have a positive impact on the improvement of 3D visualization capabilities and clinical decision-making and research in the context of ultrasound image.

摘要

背景

超声三维可视化作为医学成像领域的一项前沿技术，与传统二维超声相比，它能够提供更全面、更具可读性的解剖结构描绘，从而提高诊断准确性。这种可视化的关键在于多个目标的分割。然而，超声图像的多目标分割存在噪声干扰、边界不准确以及小结构分割困难等挑战。本研究利用颈部超声图像，专注于研究甲状腺及其周围组织的多目标分割方法。

方法

我们改进了Unet++，提出了PA-Unet++，通过解决超声噪声干扰来提高甲状腺及其周围组织的多目标分割准确性。这包括使用金字塔池化模块集成多尺度特征信息，以促进各种大小结构的分割。此外，在每个解码层应用注意力门机制，逐步突出目标组织并抑制背景像素的影响。

结果

从二维超声甲状腺系列扫描获得的视频数据作为本文的数据集。4600张包含23000个标注区域的图像以9:1的比例分为训练集和测试集，结果表明：与U-net++的结果相比，我们模型的Dice从78.78%提高到81.88%（+3.10%），mIOU从73.44%提高到80.35%（+6.91%），PA指数从92.95%提高到94.79%（+1.84%）。