Objective: To establish a multi-dimensional representation solely on structural MRI (sMRI) for early diagnosis of AD.
Methods: A total of 3377 participants' sMRI from four independent databases were retrospectively identified to construct an interpretable deep learning model that integrated multi-dimensional representations of AD solely on sMRI (called s2MRI-ADNet) by a dual-channel learning strategy of gray matter volume (GMV) from Euclidean space and the regional radiomics similarity network (R2SN) from graph space. Specifically, the GMV feature map learning channel (called GMV-Channel) was to take into consideration spatial information of both long-range spatial relations and detailed localization information, while the node feature and connectivity strength learning channel (called NFCS-Channel) was to characterize the graph-structured R2SN network by a separable learning strategy.
Results: The s2MRI-ADNet achieved a superior classification accuracy of 92.1% and 91.4% under intra-database and inter-database cross-validation. The GMV-Channel and NFCS-Channel captured complementary group-discriminative brain regions, revealing a complementary interpretation of the multi-dimensional representation of brain structure in Euclidean and graph spaces respectively. Besides, the generalizable and reproducible interpretation of the multi-dimensional representation in capturing complementary group-discriminative brain regions revealed a significant correlation between the four independent databases (p < 0.05). Significant associations (p < 0.05) between attention scores and brain abnormality, between classification scores and clinical measure of cognitive ability, CSF biomarker, metabolism, and genetic risk score also provided solid neurobiological interpretation.
Conclusion: The s2MRI-ADNet solely on sMRI could leverage the complementary multi-dimensional representations of AD in Euclidean and graph spaces, and achieved superior performance in the early diagnosis of AD, facilitating its potential in both clinical translation and popularization.
目的方法:从四个独立的数据库中回顾性地识别了3377名参与者的sMRI,并构建了一个可解释的深度学习模型,该模型仅在结构性磁共振成像(sMRI)上整合了AD的多维表征,用于早期诊断AD:方法:回顾性鉴定了四个独立数据库中3377名参与者的sMRI,通过欧几里得空间的灰质体积(GMV)和图空间的区域放射组学相似性网络(R2SN)的双通道学习策略,构建了一个可解释的深度学习模型,该模型仅在sMRI上整合了AD的多维表征(称为s2MRI-ADNet)。具体来说,GMV特征图学习通道(称为GMV通道)考虑了长程空间关系的空间信息和详细的定位信息,而节点特征和连接强度学习通道(称为NFCS通道)则通过可分离的学习策略来表征图结构的R2SN网络:结果:s2MRI-ADNet 在数据库内和数据库间交叉验证中的分类准确率分别达到 92.1% 和 91.4%。GMV通道和NFCS通道捕捉到了互补的分组区分脑区,分别揭示了欧几里得空间和图空间中脑结构多维表征的互补性解释。此外,在捕捉互补性组别区分脑区方面,对多维表征的解释具有普遍性和可重复性,这揭示了四个独立数据库之间的显著相关性(p 结论):仅基于 sMRI 的 s2MRI-ADNet 可利用欧几里得空间和图空间中互补的 AD 多维表征,在 AD 早期诊断方面取得了优异的表现,促进了其在临床转化和推广方面的潜力。
{"title":"s<sup>2</sup>MRI-ADNet: an interpretable deep learning framework integrating Euclidean-graph representations of Alzheimer's disease solely from structural MRI.","authors":"Zhiwei Song, Honglun Li, Yiyu Zhang, Chuanzhen Zhu, Minbo Jiang, Limei Song, Yi Wang, Minhui Ouyang, Fang Hu, Qiang Zheng","doi":"10.1007/s10334-024-01178-3","DOIUrl":"10.1007/s10334-024-01178-3","url":null,"abstract":"<p><strong>Objective: </strong>To establish a multi-dimensional representation solely on structural MRI (sMRI) for early diagnosis of AD.</p><p><strong>Methods: </strong>A total of 3377 participants' sMRI from four independent databases were retrospectively identified to construct an interpretable deep learning model that integrated multi-dimensional representations of AD solely on sMRI (called s<sup>2</sup>MRI-ADNet) by a dual-channel learning strategy of gray matter volume (GMV) from Euclidean space and the regional radiomics similarity network (R2SN) from graph space. Specifically, the GMV feature map learning channel (called GMV-Channel) was to take into consideration spatial information of both long-range spatial relations and detailed localization information, while the node feature and connectivity strength learning channel (called NFCS-Channel) was to characterize the graph-structured R2SN network by a separable learning strategy.</p><p><strong>Results: </strong>The s<sup>2</sup>MRI-ADNet achieved a superior classification accuracy of 92.1% and 91.4% under intra-database and inter-database cross-validation. The GMV-Channel and NFCS-Channel captured complementary group-discriminative brain regions, revealing a complementary interpretation of the multi-dimensional representation of brain structure in Euclidean and graph spaces respectively. Besides, the generalizable and reproducible interpretation of the multi-dimensional representation in capturing complementary group-discriminative brain regions revealed a significant correlation between the four independent databases (p < 0.05). Significant associations (p < 0.05) between attention scores and brain abnormality, between classification scores and clinical measure of cognitive ability, CSF biomarker, metabolism, and genetic risk score also provided solid neurobiological interpretation.</p><p><strong>Conclusion: </strong>The s<sup>2</sup>MRI-ADNet solely on sMRI could leverage the complementary multi-dimensional representations of AD in Euclidean and graph spaces, and achieved superior performance in the early diagnosis of AD, facilitating its potential in both clinical translation and popularization.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141310994","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}
Pub Date : 2024-10-01Epub Date: 2024-05-13DOI: 10.1007/s10334-024-01164-9
Alexander Dunn, Sophie Wagner, Dafna Sussman
To review and analyze the currently available MRI motion phantoms. Publications were collected from the Toronto Metropolitan University Library, PubMed, and IEEE Xplore. Phantoms were categorized based on the motions they generated: linear/cartesian, cardiac-dilative, lung-dilative, rotational, deformation or rolling. Metrics were extracted from each publication to assess the motion mechanisms, construction methods, as well as phantom validation. A total of 60 publications were reviewed, identifying 48 unique motion phantoms. Translational movement was the most common movement (used in 38% of phantoms), followed by cardiac-dilative (27%) movement and rotational movement (23%). The average degrees of freedom for all phantoms were determined to be 1.42. Motion phantom publications lack quantification of their impact on signal-to-noise ratio through standardized testing. At present, there is a lack of phantoms that are designed for multi-role as many currently have few degrees of freedom.
{"title":"Scoping review of magnetic resonance motion imaging phantoms.","authors":"Alexander Dunn, Sophie Wagner, Dafna Sussman","doi":"10.1007/s10334-024-01164-9","DOIUrl":"10.1007/s10334-024-01164-9","url":null,"abstract":"<p><p>To review and analyze the currently available MRI motion phantoms. Publications were collected from the Toronto Metropolitan University Library, PubMed, and IEEE Xplore. Phantoms were categorized based on the motions they generated: linear/cartesian, cardiac-dilative, lung-dilative, rotational, deformation or rolling. Metrics were extracted from each publication to assess the motion mechanisms, construction methods, as well as phantom validation. A total of 60 publications were reviewed, identifying 48 unique motion phantoms. Translational movement was the most common movement (used in 38% of phantoms), followed by cardiac-dilative (27%) movement and rotational movement (23%). The average degrees of freedom for all phantoms were determined to be 1.42. Motion phantom publications lack quantification of their impact on signal-to-noise ratio through standardized testing. At present, there is a lack of phantoms that are designed for multi-role as many currently have few degrees of freedom.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140912227","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}
Pub Date : 2024-09-11DOI: 10.1007/s10334-024-01204-4
Octavia Bane,Durgesh Kumar Dwivedi,Susan T Francis,Dimitrios Karampinos,Holden H Wu,Takeshi Yokoo
{"title":"Quantitative body magnetic resonance imaging: how to make it work.","authors":"Octavia Bane,Durgesh Kumar Dwivedi,Susan T Francis,Dimitrios Karampinos,Holden H Wu,Takeshi Yokoo","doi":"10.1007/s10334-024-01204-4","DOIUrl":"https://doi.org/10.1007/s10334-024-01204-4","url":null,"abstract":"","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215249","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}
Objectives: Brain tumor detection, classification and segmentation are challenging due to the heterogeneous nature of brain tumors. Different deep learning-based algorithms are available for object detection; however, the performance of detection algorithms on brain tumor data has not been widely explored. Therefore, we aim to compare different object detection algorithms (Faster R-CNN, YOLO & SSD) for brain tumor detection on MRI data. Furthermore, the best-performing detection network is paired with a 2D U-Net for pixel-wise segmentation of abnormal tumor cells.
Materials and methods: The proposed model was evaluated on the Brain Tumor Figshare (BTF) dataset, and the best-performing detection network cascaded with 2D U-Net for pixel-wise segmentation of tumors. The best-performing detection network was also fine-tuned on BRATS 2018 data to detect and classify the glioma tumor.
Results: For the detection of three tumor types, YOLOv5 achieved the highest mAP of 89.5% on test data compared to other networks. For segmentation, YOLOv5 combined with 2D U-Net achieved a higher DSC compared to the 2D U-Net alone (DSC: YOLOv5 + 2D U-Net = 88.1%; 2D U-Net = 80.5%). The proposed method was compared with the existing detection and segmentation network i.e. Mask R-CNN and achieved a higher mAP (YOLOv5 + 2D U-Net = 89.5%; Mask R-CNN = 67%) and DSC (YOLOv5 + 2D U-Net = 88.1%; Mask R-CNN = 44.2%).
Conclusion: In this work, we propose a deep-learning-based method for multi-class tumor detection, classification and segmentation that combines YOLOv5 with 2D U-Net. The results show that the proposed method not only detects different types of brain tumors accurately but also delineates the tumor region precisely within the detected bounding box.
{"title":"Brain tumor detection and segmentation using deep learning.","authors":"Rafia Ahsan, Iram Shahzadi, Faisal Najeeb, Hammad Omer","doi":"10.1007/s10334-024-01203-5","DOIUrl":"https://doi.org/10.1007/s10334-024-01203-5","url":null,"abstract":"<p><strong>Objectives: </strong>Brain tumor detection, classification and segmentation are challenging due to the heterogeneous nature of brain tumors. Different deep learning-based algorithms are available for object detection; however, the performance of detection algorithms on brain tumor data has not been widely explored. Therefore, we aim to compare different object detection algorithms (Faster R-CNN, YOLO & SSD) for brain tumor detection on MRI data. Furthermore, the best-performing detection network is paired with a 2D U-Net for pixel-wise segmentation of abnormal tumor cells.</p><p><strong>Materials and methods: </strong>The proposed model was evaluated on the Brain Tumor Figshare (BTF) dataset, and the best-performing detection network cascaded with 2D U-Net for pixel-wise segmentation of tumors. The best-performing detection network was also fine-tuned on BRATS 2018 data to detect and classify the glioma tumor.</p><p><strong>Results: </strong>For the detection of three tumor types, YOLOv5 achieved the highest mAP of 89.5% on test data compared to other networks. For segmentation, YOLOv5 combined with 2D U-Net achieved a higher DSC compared to the 2D U-Net alone (DSC: YOLOv5 + 2D U-Net = 88.1%; 2D U-Net = 80.5%). The proposed method was compared with the existing detection and segmentation network i.e. Mask R-CNN and achieved a higher mAP (YOLOv5 + 2D U-Net = 89.5%; Mask R-CNN = 67%) and DSC (YOLOv5 + 2D U-Net = 88.1%; Mask R-CNN = 44.2%).</p><p><strong>Conclusion: </strong>In this work, we propose a deep-learning-based method for multi-class tumor detection, classification and segmentation that combines YOLOv5 with 2D U-Net. The results show that the proposed method not only detects different types of brain tumors accurately but also delineates the tumor region precisely within the detected bounding box.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142133157","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}
Pub Date : 2024-08-30DOI: 10.1007/s10334-024-01200-8
Luka C Liebrand, Dimitrios Karkalousos, Émilie Poirion, Bart J Emmer, Stefan D Roosendaal, Henk A Marquering, Charles B L M Majoie, Julien Savatovsky, Matthan W A Caan
Objective: To compare compressed sensing (CS) and the Cascades of Independently Recurrent Inference Machines (CIRIM) with respect to image quality and reconstruction times when 12-fold accelerated scans of patients with neurological deficits are reconstructed.
Materials and methods: Twelve-fold accelerated 3D T2-FLAIR images were obtained from a cohort of 62 patients with neurological deficits on 3 T MRI. Images were reconstructed offline via CS and the CIRIM. Image quality was assessed in a blinded and randomized manner by two experienced interventional neuroradiologists and one experienced pediatric neuroradiologist on imaging artifacts, perceived spatial resolution (sharpness), anatomic conspicuity, diagnostic confidence, and contrast. The methods were also compared in terms of self-referenced quality metrics, image resolution, patient groups and reconstruction time. In ten scans, the contrast ratio (CR) was determined between lesions and white matter. The effect of acceleration factor was assessed in a publicly available fully sampled dataset, since ground truth data are not available in prospectively accelerated clinical scans. Specifically, 451 FLAIR scans, including scans with white matter lesions, were adopted from the FastMRI database to evaluate structural similarity (SSIM) and the CR of lesions and white matter on ranging acceleration factors from four-fold up to 12-fold.
Results: Interventional neuroradiologists significantly preferred the CIRIM for imaging artifacts, anatomic conspicuity, and contrast. One rater significantly preferred the CIRIM in terms of sharpness and diagnostic confidence. The pediatric neuroradiologist preferred CS for imaging artifacts and sharpness. Compared to CS, the CIRIM reconstructions significantly improved in terms of imaging artifacts and anatomic conspicuity (p < 0.01) for higher resolution scans while yielding a 28% higher SNR (p = 0.001) and a 5.8% lower CR (p = 0.04). There were no differences between patient groups. Additionally, CIRIM was five times faster than CS was. An increasing acceleration factor did not lead to changes in CR (p = 0.92), but led to lower SSIM (p = 0.002).
Discussion: Patients with neurological deficits can undergo MRI at a range of moderate to high acceleration. DL reconstruction outperforms CS in terms of image resolution, efficient denoising with a modest reduction in contrast and reduced reconstruction times.
{"title":"Deep learning for efficient reconstruction of highly accelerated 3D FLAIR MRI in neurological deficits.","authors":"Luka C Liebrand, Dimitrios Karkalousos, Émilie Poirion, Bart J Emmer, Stefan D Roosendaal, Henk A Marquering, Charles B L M Majoie, Julien Savatovsky, Matthan W A Caan","doi":"10.1007/s10334-024-01200-8","DOIUrl":"https://doi.org/10.1007/s10334-024-01200-8","url":null,"abstract":"<p><strong>Objective: </strong>To compare compressed sensing (CS) and the Cascades of Independently Recurrent Inference Machines (CIRIM) with respect to image quality and reconstruction times when 12-fold accelerated scans of patients with neurological deficits are reconstructed.</p><p><strong>Materials and methods: </strong>Twelve-fold accelerated 3D T2-FLAIR images were obtained from a cohort of 62 patients with neurological deficits on 3 T MRI. Images were reconstructed offline via CS and the CIRIM. Image quality was assessed in a blinded and randomized manner by two experienced interventional neuroradiologists and one experienced pediatric neuroradiologist on imaging artifacts, perceived spatial resolution (sharpness), anatomic conspicuity, diagnostic confidence, and contrast. The methods were also compared in terms of self-referenced quality metrics, image resolution, patient groups and reconstruction time. In ten scans, the contrast ratio (CR) was determined between lesions and white matter. The effect of acceleration factor was assessed in a publicly available fully sampled dataset, since ground truth data are not available in prospectively accelerated clinical scans. Specifically, 451 FLAIR scans, including scans with white matter lesions, were adopted from the FastMRI database to evaluate structural similarity (SSIM) and the CR of lesions and white matter on ranging acceleration factors from four-fold up to 12-fold.</p><p><strong>Results: </strong>Interventional neuroradiologists significantly preferred the CIRIM for imaging artifacts, anatomic conspicuity, and contrast. One rater significantly preferred the CIRIM in terms of sharpness and diagnostic confidence. The pediatric neuroradiologist preferred CS for imaging artifacts and sharpness. Compared to CS, the CIRIM reconstructions significantly improved in terms of imaging artifacts and anatomic conspicuity (p < 0.01) for higher resolution scans while yielding a 28% higher SNR (p = 0.001) and a 5.8% lower CR (p = 0.04). There were no differences between patient groups. Additionally, CIRIM was five times faster than CS was. An increasing acceleration factor did not lead to changes in CR (p = 0.92), but led to lower SSIM (p = 0.002).</p><p><strong>Discussion: </strong>Patients with neurological deficits can undergo MRI at a range of moderate to high acceleration. DL reconstruction outperforms CS in terms of image resolution, efficient denoising with a modest reduction in contrast and reduced reconstruction times.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142108914","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}
Pub Date : 2024-08-29DOI: 10.1007/s10334-024-01193-4
Frank Zijlstra, Peter Thomas While
Object: Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality.
Materials and methods: An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data.
Results: Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%.
Discussion: Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets.
{"title":"Deep-learning-based image reconstruction with limited data: generating synthetic raw data using deep learning.","authors":"Frank Zijlstra, Peter Thomas While","doi":"10.1007/s10334-024-01193-4","DOIUrl":"https://doi.org/10.1007/s10334-024-01193-4","url":null,"abstract":"<p><strong>Object: </strong>Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality.</p><p><strong>Materials and methods: </strong>An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data.</p><p><strong>Results: </strong>Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%.</p><p><strong>Discussion: </strong>Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142108915","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}
Pub Date : 2024-08-29DOI: 10.1007/s10334-024-01197-0
Tim Schmidt, Zoltán Nagy
Objective: Despite the prevalent use of the general linear model (GLM) in fMRI data analysis, assuming a pre-defined hemodynamic response function (HRF) for all voxels can lead to reduced reliability and may distort the inferences derived from it. To overcome the necessity of presuming a specific model for the hemodynamic response, we introduce a semi-supervised automatic detection (SAD) method.
Materials and methods: The proposed SAD method employs a Bi-LSTM neural network to classify high temporal resolution fMRI data. Network training utilized an fMRI dataset with 75-ms temporal resolution in an iterative scheme. Classification performance was evaluated on a second fMRI dataset from the same participant, collected on a different day. Comparative analysis with the standard GLM approach was conducted to evaluate the cooperative effectiveness of the SAD method.
Results: The SAD method performed well based on the classification scores: true-positive rate = 0.961, area under the receiver operating curve = 0.998, true-negative rate = 0.99, F1-score = 0.979, False-negative rate = 0.038, false-discovery rate = 0.002, false-positive rate = 0.002 at 75-ms temporal resolution.
Conclusion: SAD can detect hemodynamic responses at 75-ms temporal resolution without relying on a specific shape of an HRF. Future work could expand the use cases to include more participants and different fMRI paradigms.
{"title":"SAD: semi-supervised automatic detection of BOLD activations in high temporal resolution fMRI data.","authors":"Tim Schmidt, Zoltán Nagy","doi":"10.1007/s10334-024-01197-0","DOIUrl":"https://doi.org/10.1007/s10334-024-01197-0","url":null,"abstract":"<p><strong>Objective: </strong>Despite the prevalent use of the general linear model (GLM) in fMRI data analysis, assuming a pre-defined hemodynamic response function (HRF) for all voxels can lead to reduced reliability and may distort the inferences derived from it. To overcome the necessity of presuming a specific model for the hemodynamic response, we introduce a semi-supervised automatic detection (SAD) method.</p><p><strong>Materials and methods: </strong>The proposed SAD method employs a Bi-LSTM neural network to classify high temporal resolution fMRI data. Network training utilized an fMRI dataset with 75-ms temporal resolution in an iterative scheme. Classification performance was evaluated on a second fMRI dataset from the same participant, collected on a different day. Comparative analysis with the standard GLM approach was conducted to evaluate the cooperative effectiveness of the SAD method.</p><p><strong>Results: </strong>The SAD method performed well based on the classification scores: true-positive rate = 0.961, area under the receiver operating curve = 0.998, true-negative rate = 0.99, F1-score = 0.979, False-negative rate = 0.038, false-discovery rate = 0.002, false-positive rate = 0.002 at 75-ms temporal resolution.</p><p><strong>Conclusion: </strong>SAD can detect hemodynamic responses at 75-ms temporal resolution without relying on a specific shape of an HRF. Future work could expand the use cases to include more participants and different fMRI paradigms.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142108916","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}
Pub Date : 2024-08-24DOI: 10.1007/s10334-024-01198-z
Fei Xu, Stefano Mandija, Jordi P D Kleinloog, Hongyan Liu, Oscar van der Heide, Anja G van der Kolk, Jan Willem Dankbaar, Cornelis A T van den Berg, Alessandro Sbrizzi
Objective: The image quality of synthetized FLAIR (fluid attenuated inversion recovery) images is generally inferior to its conventional counterpart, especially regarding the lesion contrast mismatch. This work aimed to improve the lesion appearance through a hybrid methodology.
Materials and methods: We combined a full brain 5-min MR-STAT acquisition followed by FLAIR synthetization step with an ultra-under sampled conventional FLAIR sequence and performed the retrospective and prospective analysis of the proposed method on the patient datasets and a healthy volunteer.
Results: All performance metrics of the proposed hybrid FLAIR images on patient datasets were significantly higher than those of the physics-based FLAIR images (p < 0.005), and comparable to those of conventional FLAIR images. The small difference between prospective and retrospective analysis on a healthy volunteer demonstrated the validity of the retrospective analysis of the hybrid method as presented for the patient datasets.
Discussion: The proposed hybrid FLAIR achieved an improved lesion appearance in the clinical cases with neurological diseases compared to the physics-based FLAIR images, Future prospective work on patient data will address the validation of the method from a diagnostic perspective by radiological inspection of the new images over a larger patient cohort.
{"title":"Improving the lesion appearance on FLAIR images synthetized from quantitative MRI: a fast, hybrid approach.","authors":"Fei Xu, Stefano Mandija, Jordi P D Kleinloog, Hongyan Liu, Oscar van der Heide, Anja G van der Kolk, Jan Willem Dankbaar, Cornelis A T van den Berg, Alessandro Sbrizzi","doi":"10.1007/s10334-024-01198-z","DOIUrl":"https://doi.org/10.1007/s10334-024-01198-z","url":null,"abstract":"<p><strong>Objective: </strong>The image quality of synthetized FLAIR (fluid attenuated inversion recovery) images is generally inferior to its conventional counterpart, especially regarding the lesion contrast mismatch. This work aimed to improve the lesion appearance through a hybrid methodology.</p><p><strong>Materials and methods: </strong>We combined a full brain 5-min MR-STAT acquisition followed by FLAIR synthetization step with an ultra-under sampled conventional FLAIR sequence and performed the retrospective and prospective analysis of the proposed method on the patient datasets and a healthy volunteer.</p><p><strong>Results: </strong>All performance metrics of the proposed hybrid FLAIR images on patient datasets were significantly higher than those of the physics-based FLAIR images (p < 0.005), and comparable to those of conventional FLAIR images. The small difference between prospective and retrospective analysis on a healthy volunteer demonstrated the validity of the retrospective analysis of the hybrid method as presented for the patient datasets.</p><p><strong>Discussion: </strong>The proposed hybrid FLAIR achieved an improved lesion appearance in the clinical cases with neurological diseases compared to the physics-based FLAIR images, Future prospective work on patient data will address the validation of the method from a diagnostic perspective by radiological inspection of the new images over a larger patient cohort.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142046858","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}
Pub Date : 2024-08-10DOI: 10.1007/s10334-024-01190-7
Soo Hyun Shin, Dina Moazamian, Qingbo Tang, Saeed Jerban, Yajun Ma, Jiang Du, Eric Y Chang
Objective: To assess and improve the reliability of the ultrashort echo time quantitative magnetization transfer (UTE-qMT) modeling of the cortical bone.
Materials and methods: Simulation-based digital phantoms were created that mimic the UTE-qMT properties of cortical bones. A wide range of SNR from 25 to 200 was simulated by adding different levels of noise to the synthesized MT-weighted images to assess the effect of SNR on UTE-qMT fitting results. Tensor-based denoising algorithm was applied to improve the fitting results. These results from digital phantom studies were validated via ex vivo rat leg bone scans.
Results: The selection of initial points for nonlinear fitting and the number of data points tested for qMT analysis have minimal effect on the fitting result. Magnetization exchange rate measurements are highly dependent on the SNR of raw images, which can be substantially improved with an appropriate denoising algorithm that gives similar fitting results from the raw images with an 8-fold higher SNR.
Discussion: The digital phantom approach enables the assessment of the reliability of bone UTE-qMT fitting by providing the known ground truth. These findings can be utilized for optimizing the data acquisition and analysis pipeline for UTE-qMT imaging of cortical bones.
{"title":"Towards assessing and improving the reliability of ultrashort echo time quantitative magnetization transfer (UTE-qMT) MRI of cortical bone: In silico and ex vivo study.","authors":"Soo Hyun Shin, Dina Moazamian, Qingbo Tang, Saeed Jerban, Yajun Ma, Jiang Du, Eric Y Chang","doi":"10.1007/s10334-024-01190-7","DOIUrl":"10.1007/s10334-024-01190-7","url":null,"abstract":"<p><strong>Objective: </strong>To assess and improve the reliability of the ultrashort echo time quantitative magnetization transfer (UTE-qMT) modeling of the cortical bone.</p><p><strong>Materials and methods: </strong>Simulation-based digital phantoms were created that mimic the UTE-qMT properties of cortical bones. A wide range of SNR from 25 to 200 was simulated by adding different levels of noise to the synthesized MT-weighted images to assess the effect of SNR on UTE-qMT fitting results. Tensor-based denoising algorithm was applied to improve the fitting results. These results from digital phantom studies were validated via ex vivo rat leg bone scans.</p><p><strong>Results: </strong>The selection of initial points for nonlinear fitting and the number of data points tested for qMT analysis have minimal effect on the fitting result. Magnetization exchange rate measurements are highly dependent on the SNR of raw images, which can be substantially improved with an appropriate denoising algorithm that gives similar fitting results from the raw images with an 8-fold higher SNR.</p><p><strong>Discussion: </strong>The digital phantom approach enables the assessment of the reliability of bone UTE-qMT fitting by providing the known ground truth. These findings can be utilized for optimizing the data acquisition and analysis pipeline for UTE-qMT imaging of cortical bones.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141913158","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}