Magnetic resonance imaging最新文献_第3页

Radiomic features of dynamic contrast-enhanced MRI can predict Ki-67 status in head and neck squamous cell carcinoma 动态对比增强磁共振成像的放射学特征可预测头颈部鳞状细胞癌的 Ki-67 状态。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-19 DOI: 10.1016/j.mri.2024.110276

Lu Yang , Longwu Yu , Guangzi Shi , Lingjie Yang , Yu Wang , Riyu Han , Fengqiong Huang , Yinfeng Qian , Xiaohui Duan

Purpose

This study aimed to investigate the potential of radiomic features derived from dynamic contrast-enhanced MRI (DCE-MRI) in predicting Ki-67 and p16 status in head and neck squamous cell carcinoma (HNSCC).

Materials and methods

A cohort of 124 HNSCC patients who underwent pre-surgery DCE-MRI were included and divided into training and test set (7:3), further subgroup analysis was performed for 104 cases with oral squamous cell carcinoma (OSCC). Radiomics features were extracted from DCE images. The least absolute shrinkage and selection operator (LASSO) was used for radiomics features selection, and receiver operating characteristics analysis for predictive performance assessment. The nomogram's performance was evaluated using decision curve analysis (DCA).

Results

Ten DCE-MRI features were identified to build the predictive model of HNSCC, demonstrating excellent predictive value for Ki-67 status in both the training set (AUC of 0.943) and test set (AUC of 0.801). The nomograms based on the predictive model showed good fit in the calibration curves (p > 0.05), and DCA indicated its high clinical usefulness. In subgroup analysis of OSCC, fourteen features were selected to build the predictive model for Ki-67 status with an AUC of 0.960 in training set and 0.817 in test set. No features could be included to establish a model to predict p16 status.

Conclusion

The radiomics model utilizing DCE-MRI features could effectively predict Ki-67 status in HNSCC patients, offering potential for noninvasive preoperative prediction of Ki-67 status.

目的：本研究旨在探讨动态对比增强磁共振成像（DCE-MRI）得出的放射学特征在预测头颈部鳞状细胞癌（HNSCC）Ki-67和p16状态方面的潜力：纳入124例接受术前DCE-MRI检查的HNSCC患者，将其分为训练集和测试集（7:3），并对104例口腔鳞状细胞癌（OSCC）患者进行了进一步的亚组分析。从 DCE 图像中提取放射组学特征。使用最小绝对收缩和选择算子（LASSO）选择放射组学特征，并使用接收者操作特征分析评估预测性能。使用决策曲线分析法（DCA）评估了提名图的性能：在训练集（AUC 为 0.943）和测试集（AUC 为 0.801）中，Ki-67 状态均显示出极佳的预测价值。基于预测模型的提名图在校准曲线上显示出良好的拟合度（P > 0.05），DCA 表明其临床实用性很高。在 OSCC 亚组分析中，选择了 14 个特征来建立 Ki-67 状态预测模型，训练集的 AUC 为 0.960，测试集的 AUC 为 0.817。结论：利用DC-MR技术建立的放射组学模型可以预测P16状态：结论：利用DCE-MRI特征的放射组学模型可有效预测HNSCC患者的Ki-67状态，为Ki-67状态的术前无创预测提供了可能。

{"title":"Radiomic features of dynamic contrast-enhanced MRI can predict Ki-67 status in head and neck squamous cell carcinoma","authors":"Lu Yang , Longwu Yu , Guangzi Shi , Lingjie Yang , Yu Wang , Riyu Han , Fengqiong Huang , Yinfeng Qian , Xiaohui Duan","doi":"10.1016/j.mri.2024.110276","DOIUrl":"10.1016/j.mri.2024.110276","url":null,"abstract":"<div><h3>Purpose</h3><div>This study aimed to investigate the potential of radiomic features derived from dynamic contrast-enhanced MRI (DCE-MRI) in predicting Ki-67 and p16 status in head and neck squamous cell carcinoma (HNSCC).</div></div><div><h3>Materials and methods</h3><div>A cohort of 124 HNSCC patients who underwent pre-surgery DCE-MRI were included and divided into training and test set (7:3), further subgroup analysis was performed for 104 cases with oral squamous cell carcinoma (OSCC). Radiomics features were extracted from DCE images. The least absolute shrinkage and selection operator (LASSO) was used for radiomics features selection, and receiver operating characteristics analysis for predictive performance assessment. The nomogram's performance was evaluated using decision curve analysis (DCA).</div></div><div><h3>Results</h3><div>Ten DCE-MRI features were identified to build the predictive model of HNSCC, demonstrating excellent predictive value for Ki-67 status in both the training set (AUC of 0.943) and test set (AUC of 0.801). The nomograms based on the predictive model showed good fit in the calibration curves (<em>p</em> > 0.05), and DCA indicated its high clinical usefulness. In subgroup analysis of OSCC, fourteen features were selected to build the predictive model for Ki-67 status with an AUC of 0.960 in training set and 0.817 in test set. No features could be included to establish a model to predict p16 status.</div></div><div><h3>Conclusion</h3><div>The radiomics model utilizing DCE-MRI features could effectively predict Ki-67 status in HNSCC patients, offering potential for noninvasive preoperative prediction of Ki-67 status.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"116 ","pages":"Article 110276"},"PeriodicalIF":2.1,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142687383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GraFMRI: A graph-based fusion framework for robust multi-modal MRI reconstruction GraFMRI：基于图形的鲁棒性多模态磁共振成像重建融合框架。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-17 DOI: 10.1016/j.mri.2024.110279

Shahzad Ahmed , Feng Jinchao , Javed Ferzund , Muhammad Usman Ali , Muhammad Yaqub , Malik Abdul Manan , Atif Mehmood

Purpose

This study introduces GraFMRI, a novel framework designed to address the challenges of reconstructing high-quality MRI images from undersampled k-space data. Traditional methods often suffer from noise amplification and loss of structural detail, leading to suboptimal image quality. GraFMRI leverages Graph Neural Networks (GNNs) to transform multi-modal MRI data (T1, T2, PD) into a graph-based representation, enabling the model to capture intricate spatial relationships and inter-modality dependencies.

Methods

The framework integrates Graph-Based Non-Local Means (NLM) Filtering for effective noise suppression and Adversarial Training to reduce artifacts. A dynamic attention mechanism enables the model to focus on key anatomical regions, even when fully-sampled reference images are unavailable. GraFMRI was evaluated on the IXI and fastMRI datasets using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) as metrics for reconstruction quality.

Results

GraFMRI consistently outperforms traditional and self-supervised reconstruction techniques. Significant improvements in multi-modal fusion were observed, with better preservation of information across modalities. Noise suppression through NLM filtering and artifact reduction via adversarial training led to higher PSNR and SSIM scores across both datasets. The dynamic attention mechanism further enhanced the accuracy of the reconstructions by focusing on critical anatomical regions.

Conclusion

GraFMRI provides a scalable, robust solution for multi-modal MRI reconstruction, addressing noise and artifact challenges while enhancing diagnostic accuracy. Its ability to fuse information from different MRI modalities makes it adaptable to various clinical applications, improving the quality and reliability of reconstructed images.

目的：本研究介绍了 GraFMRI，这是一个新颖的框架，旨在解决从采样不足的 k 空间数据重建高质量 MRI 图像的难题。传统方法经常会出现噪声放大和结构细节丢失的问题，导致图像质量不理想。GraFMRI 利用图神经网络（GNN）将多模态 MRI 数据（T1、T2、PD）转换为基于图的表示，使模型能够捕捉复杂的空间关系和模态间的依赖关系：该框架整合了基于图的非局部均值（NLM）滤波技术和对抗训练技术，前者可有效抑制噪音，后者可减少伪影。动态关注机制使模型能够关注关键解剖区域，即使在无法获得全采样参考图像的情况下也是如此。使用峰值信噪比（PSNR）和结构相似性指数（SSIM）作为重建质量指标，在 IXI 和 fastMRI 数据集上对 GraFMRI 进行了评估：结果：GraFMRI 始终优于传统和自我监督重建技术。多模态融合有了显著改善，各模态的信息得到了更好的保存。通过 NLM 滤波抑制噪音，以及通过对抗训练减少伪影，使两个数据集的 PSNR 和 SSIM 得分更高。动态关注机制通过聚焦关键解剖区域，进一步提高了重建的准确性：GraFMRI为多模态磁共振成像重建提供了可扩展的稳健解决方案，在提高诊断准确性的同时解决了噪音和伪影难题。它能融合不同磁共振成像模式的信息，因此能适应各种临床应用，提高重建图像的质量和可靠性。

{"title":"GraFMRI: A graph-based fusion framework for robust multi-modal MRI reconstruction","authors":"Shahzad Ahmed , Feng Jinchao , Javed Ferzund , Muhammad Usman Ali , Muhammad Yaqub , Malik Abdul Manan , Atif Mehmood","doi":"10.1016/j.mri.2024.110279","DOIUrl":"10.1016/j.mri.2024.110279","url":null,"abstract":"<div><h3>Purpose</h3><div>This study introduces GraFMRI, a novel framework designed to address the challenges of reconstructing high-quality MRI images from undersampled k-space data. Traditional methods often suffer from noise amplification and loss of structural detail, leading to suboptimal image quality. GraFMRI leverages Graph Neural Networks (GNNs) to transform multi-modal MRI data (T1, T2, PD) into a graph-based representation, enabling the model to capture intricate spatial relationships and inter-modality dependencies.</div></div><div><h3>Methods</h3><div>The framework integrates Graph-Based Non-Local Means (NLM) Filtering for effective noise suppression and Adversarial Training to reduce artifacts. A dynamic attention mechanism enables the model to focus on key anatomical regions, even when fully-sampled reference images are unavailable. GraFMRI was evaluated on the IXI and fastMRI datasets using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) as metrics for reconstruction quality.</div></div><div><h3>Results</h3><div>GraFMRI consistently outperforms traditional and self-supervised reconstruction techniques. Significant improvements in multi-modal fusion were observed, with better preservation of information across modalities. Noise suppression through NLM filtering and artifact reduction via adversarial training led to higher PSNR and SSIM scores across both datasets. The dynamic attention mechanism further enhanced the accuracy of the reconstructions by focusing on critical anatomical regions.</div></div><div><h3>Conclusion</h3><div>GraFMRI provides a scalable, robust solution for multi-modal MRI reconstruction, addressing noise and artifact challenges while enhancing diagnostic accuracy. Its ability to fuse information from different MRI modalities makes it adaptable to various clinical applications, improving the quality and reliability of reconstructed images.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"116 ","pages":"Article 110279"},"PeriodicalIF":2.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142676371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Progress in MRI is NOT ubiquitous 磁共振成像技术的进步并非无处不在。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-17 DOI: 10.1016/j.mri.2024.110273

John C. Gore

There has been tremendous progress in MRI over the past 40+ years, driven by advances in technology as well as human ingenuity, with considerable impact in medicine. However, our understanding of how to account for, and interpret, MRI properties quantitatively lags behind these technical advances. This lack of understanding will limit our ability to make full use of quantitative metrics in the future, and much more work is needed to bridge this knowledge gap.

过去 40 多年来，在技术进步和人类智慧的推动下，核磁共振成像技术取得了巨大进步，对医学产生了重大影响。然而，我们对如何定量解释 MRI 特性的理解却落后于这些技术进步。这种认识上的不足将限制我们在未来充分利用定量指标的能力，我们需要做更多的工作来弥补这一知识差距。

引用次数: 0

Manual data labeling, radiology, and artificial intelligence: It is a dirty job, but someone has to do it 人工数据标注、放射学和人工智能：这是一项肮脏的工作，但必须有人去做。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-16 DOI: 10.1016/j.mri.2024.110280

Teodoro Martín-Noguerol , Pilar López-Úbeda , Félix Paulano-Godino , Antonio Luna

In this letter to the editor, authors highlight the key role of data labeling in training AI models for medical imaging, discussing the complexities, resource demands, costs, and the relevance of quality control in the labeling process including the potential and limitations of AI tools for automated labeling. The article underlines that labeling quality is essential for the accuracy of AI models and the safety of their clinical applications, highlighting the legal responsibilities of labelers in cases where improper labeling leads to AI errors.

在这封致编辑的信中，作者强调了数据标注在医学影像人工智能模型训练中的关键作用，讨论了标注过程中的复杂性、资源需求、成本和质量控制的相关性，包括自动标注人工智能工具的潜力和局限性。文章强调，标注质量对人工智能模型的准确性及其临床应用的安全性至关重要，并强调了在标注不当导致人工智能错误的情况下标注者的法律责任。

引用次数: 0

The effects of reference selection methods on PROPELLER MRI 参照物选择方法对 PROPELLER MRI 的影响。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-16 DOI: 10.1016/j.mri.2024.110275

Yilong Liu , Bing Zhang , Jintang Ye , Zhe Zhang , Renyuan Liu , Ming Li , Xiaodong Chen , Taihui Yu , Biling Liang , Xiaoying Wang , Rui Li , Chun Yuan , Hua Guo

PROPELLER MRI has been shown effective for rigid motion compensation, while the performance of existing PROPELLER reconstruction methods critically depend on selecting a proper reference blade.

In this work, we proposed a robust implementation for PROPELLER reconstruction, which was incorporated with different reference selection methods, including single blade reference (SBR), combined blades reference (CBR), grouped blades reference (GBR) and Pipe et al.'s revised method, which requires no blade reference (NBR).

Both simulation and in vivo studies were performed to evaluate the precision and robustness of motion estimation for reference selection methods. In vivo data sets from 10 volunteers with instructed motion and 11 patients with random motion were collected and images were scored independently and blindly by two experienced radiologists.

Both simulation and in vivo studies demonstrate that the four reference selection methods have similar performances according to visual inspection. In our tests, one iteration for the motion estimation can be sufficient for SBR, CBR, or GBR, and comparable to NBR in terms of image quality for clinical diagnosis. With two iterations, SBR, CBR, and GBR are comparable to NBR in terms of motion estimation precision. With our proposed PROPELLER reconstruction, reference selection is not critical for robust motion correction. NBR with no iterations and SBR, CBR, and GBR with two iterations are recommended for accurate motion correction.

PROPELLER磁共振成像已被证明对刚性运动补偿有效，而现有PROPELLER重建方法的性能关键取决于选择合适的参考叶片。在这项工作中，我们提出了 PROPELLER 重建的稳健实现方法，并将其与不同的参考选择方法相结合，包括单刀片参考（SBR）、组合刀片参考（CBR）、分组刀片参考（GBR）和 Pipe 等人的修订方法（不需要刀片参考（NBR））。为了评估参照物选择方法的运动估计精度和稳健性，我们进行了模拟和活体研究。我们收集了 10 名志愿者的指示运动和 11 名患者的随机运动的活体数据集，并由两名经验丰富的放射科医生对图像进行独立、盲法评分。模拟和活体研究都表明，根据目测，四种参考选择方法具有相似的性能。在我们的测试中，对 SBR、CBR 或 GBR 来说，运动估计迭代一次就足够了，在临床诊断的图像质量方面与 NBR 相当。迭代两次后，SBR、CBR 和 GBR 的运动估计精度与 NBR 相当。在我们提出的 PROPELLER 重建中，参照物的选择对于稳健的运动校正并不重要。建议采用不迭代的 NBR 和迭代两次的 SBR、CBR 和 GBR 来进行精确的运动校正。

{"title":"The effects of reference selection methods on PROPELLER MRI","authors":"Yilong Liu , Bing Zhang , Jintang Ye , Zhe Zhang , Renyuan Liu , Ming Li , Xiaodong Chen , Taihui Yu , Biling Liang , Xiaoying Wang , Rui Li , Chun Yuan , Hua Guo","doi":"10.1016/j.mri.2024.110275","DOIUrl":"10.1016/j.mri.2024.110275","url":null,"abstract":"<div><div>PROPELLER MRI has been shown effective for rigid motion compensation, while the performance of existing PROPELLER reconstruction methods critically depend on selecting a proper reference blade.</div><div>In this work, we proposed a robust implementation for PROPELLER reconstruction, which was incorporated with different reference selection methods, including single blade reference (SBR), combined blades reference (CBR), grouped blades reference (GBR) and Pipe et al.'s revised method, which requires no blade reference (NBR).</div><div>Both simulation and <em>in vivo</em> studies were performed to evaluate the precision and robustness of motion estimation for reference selection methods. <em>In vivo</em> data sets from 10 volunteers with instructed motion and 11 patients with random motion were collected and images were scored independently and blindly by two experienced radiologists.</div><div>Both simulation and <em>in vivo</em> studies demonstrate that the four reference selection methods have similar performances according to visual inspection. In our tests, one iteration for the motion estimation can be sufficient for SBR, CBR, or GBR, and comparable to NBR in terms of image quality for clinical diagnosis. With two iterations, SBR, CBR, and GBR are comparable to NBR in terms of motion estimation precision. With our proposed PROPELLER reconstruction, reference selection is not critical for robust motion correction. NBR with no iterations and SBR, CBR, and GBR with two iterations are recommended for accurate motion correction.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"116 ","pages":"Article 110275"},"PeriodicalIF":2.1,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142667770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Detection challenges of temporal encephaloceles in epilepsy: A retrospective analysis 癫痫颞叶脑瘤的检测难题：回顾性分析

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-10 DOI: 10.1016/j.mri.2024.110272

Alexander V. Ortiz , Jarrod J. Eisma , Dann Martin , Andre H. Lagrange , Cari Motuzas , William Nobis , Bassel W. Abou-Khalil , Victoria L. Morgan , Jonah Fox

Temporal encephaloceles (TEs) are herniations of cerebral parenchyma through structural defects in the floor of the middle cranial fossa. They are a relatively common, but only relatively recently identified potential cause of drug-resistant epilepsy. Uncontrolled epilepsy is associated with many negative long term health consequences including a heightened risk of death. The most effective treatment for drug-resistant epilepsy is surgery. One of the most predictive factors associated with successful surgery is identification of an abnormality on imaging. However, TEs can be difficult to detect and are often overlooked on neuroimaging studies. Improving our ability to accurately detect TEs by MRI is an important step in improving surgical outcomes in patients with drug-resistant epilepsy. We performed a review on existing imaging modalities for detecting TEs and report on our attempt to use a voxel-based morphometry (VBM) algorithm to detect TEs in T1-weighted MRIs of 81 patients from a database comprised of 25 patients with confirmed encephaloceles and 56 controls. Our program's sensitivity and specificity were compared to those of two neuroradiologists and two epileptologists using visualization during surgery as the gold standard. On average, the neuroradiologists and epileptologists had sensitivities of 41 % and 58 % and specificities of 81 % and 60 % while our VBM-based approach had sensitivities and specificities ranging from 11 % to 50 % and 0.2 % to 17 %, respectively. This work provides an overview of the different imaging modalities utilized in the detection of TEs and highlights the difficulties associated with their detection for both experienced physicians and cutting-edge computational methods. Our findings suggest that VBM-based methods could potentially be used to enhance clinicians' ability to detect TEs thereby facilitating surgical planning, improving surgical outcomes by allowing for more specific targeting, and bettering the long-term health and well-being of patients with drug-resistant epilepsy secondary to TEs.

颞叶脑瘤（TEs）是大脑实质通过中颅窝底的结构性缺损疝出。颞叶脑疝是一种比较常见的、但最近才发现的导致耐药性癫痫的潜在原因。不受控制的癫痫会对长期健康造成许多负面影响，包括增加死亡风险。手术是治疗耐药性癫痫的最有效方法。预测手术成功的最重要因素之一是在成像中发现异常。然而，TE 难以检测，在神经影像学研究中经常被忽视。提高磁共振成像准确检测 TE 的能力是改善耐药癫痫患者手术效果的重要一步。我们对现有的检测 TE 的成像模式进行了回顾，并报告了我们尝试使用基于体素形态测量（VBM）算法检测 T1 加权 MRI 中 81 例患者的 TE 的结果，该数据库由 25 例确诊脑瘤患者和 56 例对照患者组成。我们将程序的灵敏度和特异性与两位神经放射科医生和两位癫痫科医生的灵敏度和特异性进行了比较，前者使用手术中的可视化作为金标准。平均而言，神经放射学专家和癫痫专家的灵敏度分别为 41 % 和 58 %，特异性分别为 81 % 和 60 %，而我们基于 VBM 的方法的灵敏度和特异性分别为 11 % 至 50 % 和 0.2 % 至 17 %。这项研究概述了用于检测 TE 的不同成像模式，并强调了经验丰富的医生和尖端计算方法在检测 TE 方面遇到的困难。我们的研究结果表明，基于 VBM 的方法有可能用于提高临床医生检测 TE 的能力，从而促进手术规划，通过更有针对性的定位来改善手术效果，并改善继发于 TE 的耐药性癫痫患者的长期健康和福祉。

{"title":"Detection challenges of temporal encephaloceles in epilepsy: A retrospective analysis","authors":"Alexander V. Ortiz , Jarrod J. Eisma , Dann Martin , Andre H. Lagrange , Cari Motuzas , William Nobis , Bassel W. Abou-Khalil , Victoria L. Morgan , Jonah Fox","doi":"10.1016/j.mri.2024.110272","DOIUrl":"10.1016/j.mri.2024.110272","url":null,"abstract":"<div><div>Temporal encephaloceles (TEs) are herniations of cerebral parenchyma through structural defects in the floor of the middle cranial fossa. They are a relatively common, but only relatively recently identified potential cause of drug-resistant epilepsy. Uncontrolled epilepsy is associated with many negative long term health consequences including a heightened risk of death. The most effective treatment for drug-resistant epilepsy is surgery. One of the most predictive factors associated with successful surgery is identification of an abnormality on imaging. However, TEs can be difficult to detect and are often overlooked on neuroimaging studies. Improving our ability to accurately detect TEs by MRI is an important step in improving surgical outcomes in patients with drug-resistant epilepsy. We performed a review on existing imaging modalities for detecting TEs and report on our attempt to use a voxel-based morphometry (VBM) algorithm to detect TEs in T1-weighted MRIs of 81 patients from a database comprised of 25 patients with confirmed encephaloceles and 56 controls. Our program's sensitivity and specificity were compared to those of two neuroradiologists and two epileptologists using visualization during surgery as the gold standard. On average, the neuroradiologists and epileptologists had sensitivities of 41 % and 58 % and specificities of 81 % and 60 % while our VBM-based approach had sensitivities and specificities ranging from 11 % to 50 % and 0.2 % to 17 %, respectively. This work provides an overview of the different imaging modalities utilized in the detection of TEs and highlights the difficulties associated with their detection for both experienced physicians and cutting-edge computational methods. Our findings suggest that VBM-based methods could potentially be used to enhance clinicians' ability to detect TEs thereby facilitating surgical planning, improving surgical outcomes by allowing for more specific targeting, and bettering the long-term health and well-being of patients with drug-resistant epilepsy secondary to TEs.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"115 ","pages":"Article 110272"},"PeriodicalIF":2.1,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142622520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cystic Fibrosis or asthma? Discerning dyspnea with hyperpolarizaed xenon gas magnetic resonance imaging 囊性纤维化还是哮喘？用超极化氙气磁共振成像鉴别呼吸困难。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-02 DOI: 10.1016/j.mri.2024.110271

David Wang , Cody Thornburgh , Harjeet Singh , Zach Holliday

Hyperpolarized Xenon MRI (HPG MRI) has been studied for its potential use in assessing lung function in patients with cystic fibrosis (CF) and in patients with asthma. We present a case of a man with overlapping cystic fibrosis and allergic asthma with severe obstructive lung disease in which spirometry and computed topography (CT) imaging was unable to determine the primary cause for his uncontrolled symptoms. HPG MRI was used to guide a tissue biopsy and determine the primary driver to be allergic asthma. After starting targeted therapy for severe asthma, his symptoms have greatly improved.

超极化氙磁共振成像（HPG MRI）已被研究用于评估囊性纤维化（CF）患者和哮喘患者的肺功能。我们介绍了一例患有重叠性囊性纤维化和过敏性哮喘并伴有严重阻塞性肺部疾病的男性病例，在该病例中，肺活量测定和计算机地形图（CT）成像无法确定导致其症状失控的主要原因。HPG MRI 被用来指导组织活检，并确定主要病因是过敏性哮喘。在开始接受重症哮喘的靶向治疗后，他的症状大有好转。

引用次数: 0

Intravascular enhancement sign at 3D T1-weighted turbo spin echo sequence is associated with cerebral atherosclerotic stenosis 三维 T1 加权涡轮自旋回波序列的血管内强化征象与脑动脉粥样硬化性狭窄有关。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-02 DOI: 10.1016/j.mri.2024.110270

Bo Wang , Feng Ouyang , Qin Wu , Jingting Chen , Jie Liu , Zihe Xu , Lianjiang Lv , Nianzu Yu , Xianjun Zeng

Objective

Intravascular enhancement sign (IVES) at three-dimensional T1-weighted turbo spin echo (3D T1W TSE) sequence may be a simple hemodynamic maker. This study aims to investigate the association between IVES and features of intracranial atherosclerotic stenosis (ICAS).

Method

Retrospective analysis of clinical and imaging data of patients who underwent high resolution-vessel wall imaging (HR-VWI) examination from May 2021 to May 2023. The number of IVES vessels and ICAS features at HR-VWI were extracted by two neuroradiologists. Paired comparisons and correlation analysis on these indicators were performed.

Results

A total of 118 patients with ICAS in the first segment of the middle cerebral artery and accompanied by unilateral IVES were enrolled. Compared to the non-IVES side, a higher incidence of ischemic events and intraplaque hemorrhage (IPH), higher degree of vascular stenosis and enhancement, lower remodeling index, and lower signal intensity ratio (SIR) were found in subjects with IVES. In the ICAS with IVES, 79.66 % showed severe stenosis and occlusion; in the ICAS with severe stenosis and occlusion, 89.5 % showed IVES in the distal. A multivariable logistic regression model identified the vascular stenosis degree (OR = 1.922; 95 %CI [1.37–2.692]; P < 0.001), enhanced-degree (OR = 2.486; 95 %CI [1.315–4.698]; P = 0.005), position (OR = 2.869; 95 %CI [1.255–6.560]; P = 0.012), and SIR (OR = 0.032; 95 %CI [0.004–0.275]; P = 0.002) were independent association with the presence of IVES. The area under the curve was 0.911 for the use of IVES vessel quantities to identify severe stenosis and occlusion of arterial lumen.

Conclusion

The number of IVES vessels was associated with the local features of ICAS, which may indicate severe stenosis and occlusion in the major branches of the proximal artery.

目的三维T1加权涡轮自旋回波（3D T1W TSE）序列的血管内强化征（IVES）可能是一种简单的血液动力学指标。本研究旨在探讨 IVES 与颅内动脉粥样硬化性狭窄（ICAS）特征之间的关联：方法：回顾性分析2021年5月至2023年5月期间接受高分辨率血管壁成像（HR-VWI）检查的患者的临床和成像数据。由两名神经放射学专家提取高分辨率血管壁成像（HR-VWI）的 IVES 血管数量和 ICAS 特征。对这些指标进行配对比较和相关分析：共有 118 名大脑中动脉第一段伴有单侧 IVES 的 ICAS 患者入选。与非IVES侧相比，IVES侧缺血事件和斑块内出血（IPH）发生率更高，血管狭窄和增强程度更高，重塑指数更低，信号强度比（SIR）更低。在有 IVES 的 ICAS 中，79.66% 表现为严重狭窄和闭塞；在有严重狭窄和闭塞的 ICAS 中，89.5% 在远端表现为 IVES。多变量逻辑回归模型确定了血管狭窄程度（OR = 1.922；95 %CI [1.37-2.692]；P 结论：IVES血管的数量与ICAS的局部特征有关，这可能表明近端动脉的主要分支存在严重狭窄和闭塞。

{"title":"Intravascular enhancement sign at 3D T1-weighted turbo spin echo sequence is associated with cerebral atherosclerotic stenosis","authors":"Bo Wang , Feng Ouyang , Qin Wu , Jingting Chen , Jie Liu , Zihe Xu , Lianjiang Lv , Nianzu Yu , Xianjun Zeng","doi":"10.1016/j.mri.2024.110270","DOIUrl":"10.1016/j.mri.2024.110270","url":null,"abstract":"<div><h3>Objective</h3><div>Intravascular enhancement sign (IVES) at three-dimensional T1-weighted turbo spin echo (3D T1W TSE) sequence may be a simple hemodynamic maker. This study aims to investigate the association between IVES and features of intracranial atherosclerotic stenosis (ICAS).</div></div><div><h3>Method</h3><div>Retrospective analysis of clinical and imaging data of patients who underwent high resolution-vessel wall imaging (HR-VWI) examination from May 2021 to May 2023. The number of IVES vessels and ICAS features at HR-VWI were extracted by two neuroradiologists. Paired comparisons and correlation analysis on these indicators were performed.</div></div><div><h3>Results</h3><div>A total of 118 patients with ICAS in the first segment of the middle cerebral artery and accompanied by unilateral IVES were enrolled. Compared to the non-IVES side, a higher incidence of ischemic events and intraplaque hemorrhage (IPH), higher degree of vascular stenosis and enhancement, lower remodeling index, and lower signal intensity ratio (SIR) were found in subjects with IVES. In the ICAS with IVES, 79.66 % showed severe stenosis and occlusion; in the ICAS with severe stenosis and occlusion, 89.5 % showed IVES in the distal. A multivariable logistic regression model identified the vascular stenosis degree (OR = 1.922; 95 %CI [1.37–2.692]; <em>P</em> < 0.001), enhanced-degree (OR = 2.486; 95 %CI [1.315–4.698]; <em>P</em> = 0.005), position (OR = 2.869; 95 %CI [1.255–6.560]; <em>P</em> = 0.012), and SIR (OR = 0.032; 95 %CI [0.004–0.275]; <em>P</em> = 0.002) were independent association with the presence of IVES. The area under the curve was 0.911 for the use of IVES vessel quantities to identify severe stenosis and occlusion of arterial lumen.</div></div><div><h3>Conclusion</h3><div>The number of IVES vessels was associated with the local features of ICAS, which may indicate severe stenosis and occlusion in the major branches of the proximal artery.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"115 ","pages":"Article 110270"},"PeriodicalIF":2.1,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142568699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Monitoring of lung stiffness for long-COVID patients using magnetic resonance elastography (MRE) 使用磁共振弹性成像技术（MRE）监测长COVID患者的肺部僵硬度。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-11-02 DOI: 10.1016/j.mri.2024.110269

Sabine F. Bensamoun , Kiaran P. McGee , Mashhour Chakouch , Philippe Pouletaut , Fabrice Charleux

Purpose

Transaxial CT imaging is the main clinical imaging modality for the assessment of COVID-induced lung damage. However, this type of data does not quantify the functional properties of the lung. The objective is to provide non-invasive personalized cartographies of lung stiffness for long-COVID patients using MR elastography (MRE) and follow-up the evolution of this quantitative mapping over time.

Methods

Seven healthy and seven long-COVID participants underwent CT and MRE imaging at total lung capacity. After CT test, a senior radiologist visually analyzed the lung structure. Less than one month later, a first MRI (1.5 T, GRE sequence) lung density test followed by a first MRE (SE-EPI sequence) test were performed. Gadolinium-doped water phantom and a pneumatic driver (vibration frequency: 50 Hz), placed on the sternum, were used for MRI and MRE tests, respectively. Personalized cartographies of the stiffness were obtained, by two medical imaging engineers, using a specific post processing (MMDI algorithm). The monitoring (lung density, stiffness) was carried out no later than 11 months for each COVID patient. Wilcoxon's tests and an intra-class correlation coefficient (ICC) were used for statistical analysis.

Results

The density for long-COVID patients was significantly (P = 0.047) greater (170 kg.m⁻³) compared to healthy (125 kg.m⁻³) subjects. After the first MRE test, the stiffness measured for the healthy subjects was in the same range (median value (interquartile range, IQR): 0.93 (0.09) kPa), while the long-COVID patients showed a larger stiffness range (from 1.39 kPa to 2.05 kPa). After a minimum delay of 5 months, the second MRE test showed a decrease of stiffness (from 22 % to 40 %) for every long-COVID patient. The inter-operator agreement was excellent (intra-class correlation coefficient: 0.93 [0.78–0.97]).

Conclusion

The MRE test is sensitive enough to monitor disease-induced change in lung stiffness (increase with COVID symptoms and decrease with recovery). This non-invasive modality could yield complementary information as a new imaging biomarker to follow up long-COVID patients.

目的：横轴 CT 成像是评估 COVID 引起的肺损伤的主要临床成像模式。然而，这类数据并不能量化肺的功能特性。我们的目标是利用磁共振弹性成像（MRE）为长期 COVID 患者提供非侵入性的肺部僵硬度个性化图谱，并跟踪这种定量图谱随时间的变化情况：方法：七名健康人和七名长期慢性阻塞性肺气肿患者分别接受了 CT 和总肺活量下的磁共振弹性成像检查。CT 测试后，一位资深放射科医生对肺部结构进行了目测分析。不到一个月后，进行了首次核磁共振成像（1.5 T，GRE 序列）肺密度测试和首次 MRE（SE-EPI 序列）测试。核磁共振成像和 MRE 测试分别使用了掺钆水模型和放置在胸骨上的气动驱动器（振动频率：50 赫兹）。两名医学影像工程师通过特定的后处理（MMDI 算法）获得了个性化的僵硬度绘图。对每位 COVID 患者的监测（肺密度、肺硬度）在 11 个月内完成。统计分析采用 Wilcoxon 检验和类内相关系数（ICC）：结果：与健康人（125 kg.m-3）相比，COVID 长期患者的密度（170 kg.m-3）明显更高（P = 0.047）。首次 MRE 测试后，健康受试者测得的僵硬度范围相同（中位值（四分位数间距，IQR）：0.93 (0.09) kPa），而长期 COVID 患者测得的僵硬度范围更大（从 1.39 kPa 到 2.05 kPa）。至少延迟 5 个月后，第二次 MRE 测试显示，每位长 COVID 患者的僵硬度都有所下降（从 22% 降至 40%）。操作者之间的一致性非常好（类内相关系数：0.93 [0.78-0.97]）：MRE测试的灵敏度足以监测疾病引起的肺部僵硬度变化（随COVID症状增加而增加，随恢复而减少）。作为一种新的成像生物标志物，这种无创模式可为长期随访 COVID 患者提供补充信息。

{"title":"Monitoring of lung stiffness for long-COVID patients using magnetic resonance elastography (MRE)","authors":"Sabine F. Bensamoun , Kiaran P. McGee , Mashhour Chakouch , Philippe Pouletaut , Fabrice Charleux","doi":"10.1016/j.mri.2024.110269","DOIUrl":"10.1016/j.mri.2024.110269","url":null,"abstract":"<div><h3>Purpose</h3><div>Transaxial CT imaging is the main clinical imaging modality for the assessment of COVID-induced lung damage. However, this type of data does not quantify the functional properties of the lung. The objective is to provide non-invasive personalized cartographies of lung stiffness for long-COVID patients using MR elastography (MRE) and follow-up the evolution of this quantitative mapping over time.</div></div><div><h3>Methods</h3><div>Seven healthy and seven long-COVID participants underwent CT and MRE imaging at total lung capacity. After CT test, a senior radiologist visually analyzed the lung structure. Less than one month later, a first MRI (1.5 T, GRE sequence) lung density test followed by a first MRE (SE-EPI sequence) test were performed. Gadolinium-doped water phantom and a pneumatic driver (vibration frequency: 50 Hz), placed on the sternum, were used for MRI and MRE tests, respectively. Personalized cartographies of the stiffness were obtained, by two medical imaging engineers, using a specific post processing (MMDI algorithm). The monitoring (lung density, stiffness) was carried out no later than 11 months for each COVID patient. Wilcoxon's tests and an intra-class correlation coefficient (ICC) were used for statistical analysis.</div></div><div><h3>Results</h3><div>The density for long-COVID patients was significantly (<em>P</em> = 0.047) greater (170 kg.m<sup>−3</sup>) compared to healthy (125 kg.m<sup>−3</sup>) subjects. After the first MRE test, the stiffness measured for the healthy subjects was in the same range (median value (interquartile range, IQR): 0.93 (0.09) kPa), while the long-COVID patients showed a larger stiffness range (from 1.39 kPa to 2.05 kPa). After a minimum delay of 5 months, the second MRE test showed a decrease of stiffness (from 22 % to 40 %) for every long-COVID patient. The inter-operator agreement was excellent (intra-class correlation coefficient: 0.93 [0.78–0.97]).</div></div><div><h3>Conclusion</h3><div>The MRE test is sensitive enough to monitor disease-induced change in lung stiffness (increase with COVID symptoms and decrease with recovery). This non-invasive modality could yield complementary information as a new imaging biomarker to follow up long-COVID patients.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"115 ","pages":"Article 110269"},"PeriodicalIF":2.1,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142568720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

vSHARP: Variable Splitting Half-quadratic ADMM algorithm for reconstruction of inverse-problems vSHARP：用于重建逆问题的变量分割半二次 ADMM 算法。

IF 2.1 4区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Magnetic resonance imaging

Pub Date : 2024-10-24 DOI: 10.1016/j.mri.2024.110266

George Yiasemis , Nikita Moriakov , Jan-Jakob Sonke , Jonas Teuwen

Medical Imaging (MI) tasks, such as accelerated parallel Magnetic Resonance Imaging (MRI), often involve reconstructing an image from noisy or incomplete measurements. This amounts to solving ill-posed inverse problems, where a satisfactory closed-form analytical solution is not available. Traditional methods such as Compressed Sensing (CS) in MRI reconstruction can be time-consuming or prone to obtaining low-fidelity images. Recently, a plethora of Deep Learning (DL) approaches have demonstrated superior performance in inverse-problem solving, surpassing conventional methods. In this study, we propose vSHARP (variable Splitting Half-quadratic ADMM algorithm for Reconstruction of inverse Problems), a novel DL-based method for solving ill-posed inverse problems arising in MI. vSHARP utilizes the Half-Quadratic Variable Splitting method and employs the Alternating Direction Method of Multipliers (ADMM) to unroll the optimization process. For data consistency, vSHARP unrolls a differentiable gradient descent process in the image domain, while a DL-based denoiser, such as a U-Net architecture, is applied to enhance image quality. vSHARP also employs a dilated-convolution DL-based model to predict the Lagrange multipliers for the ADMM initialization. We evaluate vSHARP on tasks of accelerated parallel MRI Reconstruction using two distinct datasets and on accelerated parallel dynamic MRI Reconstruction using another dataset. Our comparative analysis with state-of-the-art methods demonstrates the superior performance of vSHARP in these applications.

医学成像（MI）任务，如加速并行磁共振成像（MRI），通常涉及从嘈杂或不完整的测量结果中重建图像。这就相当于在求解不确定的逆问题，在这种情况下，无法获得令人满意的闭式解析解。磁共振成像重建中的压缩传感（CS）等传统方法可能会耗费大量时间，或容易获得低保真图像。最近，大量深度学习（DL）方法在逆问题求解中表现出了超越传统方法的卓越性能。在本研究中，我们提出了 vSHARP（用于逆问题重构的半二次方变量分割 ADMM 算法），这是一种基于深度学习的新方法，用于解决 MI 中出现的难以解决的逆问题。为了保证数据的一致性，vSHARP 在图像域中展开可变梯度下降过程，同时应用基于 DL 的去噪器（如 U-Net 架构）来提高图像质量。vSHARP 还采用基于 DL 的扩张卷积模型来预测 ADMM 初始化的拉格朗日乘数。我们利用两个不同的数据集对 vSHARP 的加速并行 MRI 重建任务进行了评估，并利用另一个数据集对加速并行动态 MRI 重建任务进行了评估。我们与最先进方法的对比分析表明，vSHARP 在这些应用中表现出色。

{"title":"vSHARP: Variable Splitting Half-quadratic ADMM algorithm for reconstruction of inverse-problems","authors":"George Yiasemis , Nikita Moriakov , Jan-Jakob Sonke , Jonas Teuwen","doi":"10.1016/j.mri.2024.110266","DOIUrl":"10.1016/j.mri.2024.110266","url":null,"abstract":"<div><div>Medical Imaging (MI) tasks, such as accelerated parallel Magnetic Resonance Imaging (MRI), often involve reconstructing an image from noisy or incomplete measurements. This amounts to solving ill-posed inverse problems, where a satisfactory closed-form analytical solution is not available. Traditional methods such as Compressed Sensing (CS) in MRI reconstruction can be time-consuming or prone to obtaining low-fidelity images. Recently, a plethora of Deep Learning (DL) approaches have demonstrated superior performance in inverse-problem solving, surpassing conventional methods. In this study, we propose vSHARP (variable Splitting Half-quadratic ADMM algorithm for Reconstruction of inverse Problems), a novel DL-based method for solving ill-posed inverse problems arising in MI. vSHARP utilizes the Half-Quadratic Variable Splitting method and employs the Alternating Direction Method of Multipliers (ADMM) to unroll the optimization process. For data consistency, vSHARP unrolls a differentiable gradient descent process in the image domain, while a DL-based denoiser, such as a U-Net architecture, is applied to enhance image quality. vSHARP also employs a dilated-convolution DL-based model to predict the Lagrange multipliers for the ADMM initialization. We evaluate vSHARP on tasks of accelerated parallel MRI Reconstruction using two distinct datasets and on accelerated parallel dynamic MRI Reconstruction using another dataset. Our comparative analysis with state-of-the-art methods demonstrates the superior performance of vSHARP in these applications.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"115 ","pages":"Article 110266"},"PeriodicalIF":2.1,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142503198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0