MGA-Net:用于新生儿脑部精确成像的新型面具引导注意力神经网络。

IF 4.7 2区 医学 Q1 NEUROIMAGING NeuroImage Pub Date : 2024-09-28 DOI:10.1016/j.neuroimage.2024.120872
Bahram Jafrasteh , Simón Pedro Lubián-López , Emiliano Trimarco , Macarena Román Ruiz , Carmen Rodríguez Barrios , Yolanda Marín Almagro , Isabel Benavente-Fernández
{"title":"MGA-Net:用于新生儿脑部精确成像的新型面具引导注意力神经网络。","authors":"Bahram Jafrasteh ,&nbsp;Simón Pedro Lubián-López ,&nbsp;Emiliano Trimarco ,&nbsp;Macarena Román Ruiz ,&nbsp;Carmen Rodríguez Barrios ,&nbsp;Yolanda Marín Almagro ,&nbsp;Isabel Benavente-Fernández","doi":"10.1016/j.neuroimage.2024.120872","DOIUrl":null,"url":null,"abstract":"<div><div>In this study, we introduce MGA-Net, a novel mask-guided attention neural network, which extends the U-net model for precision neonatal brain imaging. MGA-Net is designed to extract the brain from other structures and reconstruct high-quality brain images. The network employs a common encoder and two decoders: one for brain mask extraction and the other for brain region reconstruction. A key feature of MGA-Net is its high-level mask-guided attention module, which leverages features from the brain mask decoder to enhance image reconstruction. To enable the same encoder and decoder to process both MRI and ultrasound (US) images, MGA-Net integrates sinusoidal positional encoding. This encoding assigns distinct positional values to MRI and US images, allowing the model to effectively learn from both modalities. Consequently, features learned from a single modality can aid in learning a modality with less available data, such as US. We extensively validated the proposed MGA-Net on diverse and independent datasets from varied clinical settings and neonatal age groups. The metrics used for assessment included the DICE similarity coefficient, recall, and accuracy for image segmentation; structural similarity for image reconstruction; and root mean squared error for total brain volume estimation from 3D ultrasound images. Our results demonstrate that MGA-Net significantly outperforms traditional methods, offering superior performance in brain extraction and segmentation while achieving high precision in image reconstruction and volumetric analysis. Thus, MGA-Net represents a robust and effective preprocessing tool for MRI and 3D ultrasound images, marking a significant advance in neuroimaging that enhances both research and clinical diagnostics in the neonatal period and beyond.</div></div>","PeriodicalId":19299,"journal":{"name":"NeuroImage","volume":"300 ","pages":"Article 120872"},"PeriodicalIF":4.7000,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MGA-Net: A novel mask-guided attention neural network for precision neonatal brain imaging\",\"authors\":\"Bahram Jafrasteh ,&nbsp;Simón Pedro Lubián-López ,&nbsp;Emiliano Trimarco ,&nbsp;Macarena Román Ruiz ,&nbsp;Carmen Rodríguez Barrios ,&nbsp;Yolanda Marín Almagro ,&nbsp;Isabel Benavente-Fernández\",\"doi\":\"10.1016/j.neuroimage.2024.120872\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>In this study, we introduce MGA-Net, a novel mask-guided attention neural network, which extends the U-net model for precision neonatal brain imaging. MGA-Net is designed to extract the brain from other structures and reconstruct high-quality brain images. The network employs a common encoder and two decoders: one for brain mask extraction and the other for brain region reconstruction. A key feature of MGA-Net is its high-level mask-guided attention module, which leverages features from the brain mask decoder to enhance image reconstruction. To enable the same encoder and decoder to process both MRI and ultrasound (US) images, MGA-Net integrates sinusoidal positional encoding. This encoding assigns distinct positional values to MRI and US images, allowing the model to effectively learn from both modalities. Consequently, features learned from a single modality can aid in learning a modality with less available data, such as US. We extensively validated the proposed MGA-Net on diverse and independent datasets from varied clinical settings and neonatal age groups. The metrics used for assessment included the DICE similarity coefficient, recall, and accuracy for image segmentation; structural similarity for image reconstruction; and root mean squared error for total brain volume estimation from 3D ultrasound images. Our results demonstrate that MGA-Net significantly outperforms traditional methods, offering superior performance in brain extraction and segmentation while achieving high precision in image reconstruction and volumetric analysis. Thus, MGA-Net represents a robust and effective preprocessing tool for MRI and 3D ultrasound images, marking a significant advance in neuroimaging that enhances both research and clinical diagnostics in the neonatal period and beyond.</div></div>\",\"PeriodicalId\":19299,\"journal\":{\"name\":\"NeuroImage\",\"volume\":\"300 \",\"pages\":\"Article 120872\"},\"PeriodicalIF\":4.7000,\"publicationDate\":\"2024-09-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"NeuroImage\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1053811924003690\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"NEUROIMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"NeuroImage","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1053811924003690","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NEUROIMAGING","Score":null,"Total":0}
引用次数: 0

摘要

在本研究中,我们介绍了 MGA-Net,这是一种新型的掩膜引导注意力神经网络,它扩展了 U-net 模型,可用于新生儿脑部精确成像。MGA-Net 设计用于从其他结构中提取大脑并重建高质量的大脑图像。该网络采用一个普通编码器和两个解码器:一个用于大脑掩膜提取,另一个用于大脑区域重建。MGA-Net 的一个主要特点是其高级掩膜引导注意模块,该模块利用脑掩膜解码器的特征来增强图像重建。为了让同一个编码器和解码器同时处理核磁共振成像和超声波(US)图像,MGA-Net 集成了正弦位置编码。这种编码为核磁共振成像和超声波图像分配了不同的位置值,使模型能有效地从两种模式中学习。因此,从单一模式中学习到的特征可以帮助学习可用数据较少的模式,如 US。我们在来自不同临床环境和新生儿年龄组的各种独立数据集上对所提出的 MGA-Net 进行了广泛验证。评估指标包括用于图像分割的 DICE 相似性系数、召回率和准确率;用于图像重建的结构相似性;以及用于从三维超声图像估算总脑容量的均方根误差。我们的研究结果表明,MGA-Net 明显优于传统方法,在大脑提取和分割方面表现出色,同时在图像重建和容积分析方面实现了高精度。因此,MGA-Net 是一种用于核磁共振成像和三维超声波图像的强大而有效的预处理工具,标志着神经成像技术的重大进步,可提高新生儿期及以后的研究和临床诊断水平。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
MGA-Net: A novel mask-guided attention neural network for precision neonatal brain imaging
In this study, we introduce MGA-Net, a novel mask-guided attention neural network, which extends the U-net model for precision neonatal brain imaging. MGA-Net is designed to extract the brain from other structures and reconstruct high-quality brain images. The network employs a common encoder and two decoders: one for brain mask extraction and the other for brain region reconstruction. A key feature of MGA-Net is its high-level mask-guided attention module, which leverages features from the brain mask decoder to enhance image reconstruction. To enable the same encoder and decoder to process both MRI and ultrasound (US) images, MGA-Net integrates sinusoidal positional encoding. This encoding assigns distinct positional values to MRI and US images, allowing the model to effectively learn from both modalities. Consequently, features learned from a single modality can aid in learning a modality with less available data, such as US. We extensively validated the proposed MGA-Net on diverse and independent datasets from varied clinical settings and neonatal age groups. The metrics used for assessment included the DICE similarity coefficient, recall, and accuracy for image segmentation; structural similarity for image reconstruction; and root mean squared error for total brain volume estimation from 3D ultrasound images. Our results demonstrate that MGA-Net significantly outperforms traditional methods, offering superior performance in brain extraction and segmentation while achieving high precision in image reconstruction and volumetric analysis. Thus, MGA-Net represents a robust and effective preprocessing tool for MRI and 3D ultrasound images, marking a significant advance in neuroimaging that enhances both research and clinical diagnostics in the neonatal period and beyond.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
NeuroImage
NeuroImage 医学-核医学
CiteScore
11.30
自引率
10.50%
发文量
809
审稿时长
63 days
期刊介绍: NeuroImage, a Journal of Brain Function provides a vehicle for communicating important advances in acquiring, analyzing, and modelling neuroimaging data and in applying these techniques to the study of structure-function and brain-behavior relationships. Though the emphasis is on the macroscopic level of human brain organization, meso-and microscopic neuroimaging across all species will be considered if informative for understanding the aforementioned relationships.
期刊最新文献
Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning Exploring the relationship between hallucination proneness and brain morphology Biological mechanism of sex differences in mental rotation: Evidence from multimodal MRI, transcriptomic and receptor/transporter data. Different oscillatory mechanisms of dementia-related diseases with cognitive impairment in closed-eye state. Generative Modeling of the Circle of Willis Using 3D-StyleGAN.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1