Pub Date : 2024-07-05DOI: 10.1007/s10334-024-01184-5
Lei Li, Qingyuan He, Shufeng Wei, Huixian Wang, Zheng Wang, Zhao Wei, Hongyan He, Ce Xiang, Wenhui Yang
Objective: To propose a deep learning-based low-field mobile MRI strategy for fast, high-quality, unshielded imaging using minimal hardware resources.
Methods: Firstly, we analyze the correlation of EMI signals between the sensing coil and the MRI coil to preliminarily verify the feasibility of active EMI shielding using a single sensing coil. Then, a powerful deep learning EMI elimination model is proposed, which can accurately predict the EMI components in the MRI coil signals using EMI signals from at least one sensing coil. Further, deep learning models with different task objectives (super-resolution and denoising) are strategically stacked for multi-level post-processing to enable fast and high-quality low-field MRI. Finally, extensive phantom and brain experiments were conducted on a home-built 0.2 T mobile brain scanner for the evaluation of the proposed strategy.
Results: 20 healthy volunteers were recruited to participate in the experiment. The results show that the proposed strategy enables the 0.2 T scanner to generate images with sufficient anatomical information and diagnostic value under unshielded conditions using a single sensing coil. In particular, the EMI elimination outperforms the state-of-the-art deep learning methods and numerical computation methods. In addition, 2 × super-resolution (DDSRNet) and denoising (SwinIR) techniques enable further improvements in imaging speed and quality.
Discussion: The proposed strategy enables low-field mobile MRI scanners to achieve fast, high-quality imaging under unshielded conditions using minimal hardware resources, which has great significance for the widespread deployment of low-field mobile MRI scanners.
目的提出一种基于深度学习的低场移动磁共振成像策略,利用最少的硬件资源实现快速、高质量、无屏蔽成像:首先,我们分析了传感线圈和磁共振成像线圈之间的电磁干扰信号的相关性,初步验证了使用单传感线圈进行主动电磁干扰屏蔽的可行性。然后,提出了一个功能强大的深度学习 EMI 消除模型,该模型可以利用至少一个传感线圈的 EMI 信号准确预测 MRI 线圈信号中的 EMI 成分。此外,具有不同任务目标(超分辨率和去噪)的深度学习模型被策略性地堆叠起来进行多级后处理,以实现快速、高质量的低场磁共振成像。最后,在自制的 0.2 T 移动脑部扫描仪上进行了大量的模型和脑部实验,以评估所提出的策略。结果表明,所提出的策略能使 0.2 T 扫描仪在无屏蔽条件下使用单传感线圈生成具有足够解剖信息和诊断价值的图像。特别是,EMI 消除效果优于最先进的深度学习方法和数值计算方法。此外,2 × 超分辨率(DDSRNet)和去噪(SwinIR)技术还能进一步提高成像速度和质量:所提出的策略可使低场移动磁共振成像扫描仪在无屏蔽条件下使用最少的硬件资源实现快速、高质量成像,这对低场移动磁共振成像扫描仪的广泛部署具有重要意义。
{"title":"Fast, high-quality, and unshielded 0.2 T low-field mobile MRI using minimal hardware resources.","authors":"Lei Li, Qingyuan He, Shufeng Wei, Huixian Wang, Zheng Wang, Zhao Wei, Hongyan He, Ce Xiang, Wenhui Yang","doi":"10.1007/s10334-024-01184-5","DOIUrl":"https://doi.org/10.1007/s10334-024-01184-5","url":null,"abstract":"<p><strong>Objective: </strong>To propose a deep learning-based low-field mobile MRI strategy for fast, high-quality, unshielded imaging using minimal hardware resources.</p><p><strong>Methods: </strong>Firstly, we analyze the correlation of EMI signals between the sensing coil and the MRI coil to preliminarily verify the feasibility of active EMI shielding using a single sensing coil. Then, a powerful deep learning EMI elimination model is proposed, which can accurately predict the EMI components in the MRI coil signals using EMI signals from at least one sensing coil. Further, deep learning models with different task objectives (super-resolution and denoising) are strategically stacked for multi-level post-processing to enable fast and high-quality low-field MRI. Finally, extensive phantom and brain experiments were conducted on a home-built 0.2 T mobile brain scanner for the evaluation of the proposed strategy.</p><p><strong>Results: </strong>20 healthy volunteers were recruited to participate in the experiment. The results show that the proposed strategy enables the 0.2 T scanner to generate images with sufficient anatomical information and diagnostic value under unshielded conditions using a single sensing coil. In particular, the EMI elimination outperforms the state-of-the-art deep learning methods and numerical computation methods. In addition, 2 × super-resolution (DDSRNet) and denoising (SwinIR) techniques enable further improvements in imaging speed and quality.</p><p><strong>Discussion: </strong>The proposed strategy enables low-field mobile MRI scanners to achieve fast, high-quality imaging under unshielded conditions using minimal hardware resources, which has great significance for the widespread deployment of low-field mobile MRI scanners.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141534759","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 : 2024-07-01Epub Date: 2024-06-08DOI: 10.1007/s10334-024-01175-6
Joana Pinto, Allison McGee, Hendrik Mattern, Karin Markenroth Bloch, Roy A M Haast, Thomas Küstner, S Johanna Vannesjo
{"title":"ESMRMB 2024 focus topic \"MR Beyond Structures: The dynamic body at different scales\".","authors":"Joana Pinto, Allison McGee, Hendrik Mattern, Karin Markenroth Bloch, Roy A M Haast, Thomas Küstner, S Johanna Vannesjo","doi":"10.1007/s10334-024-01175-6","DOIUrl":"10.1007/s10334-024-01175-6","url":null,"abstract":"","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141293525","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 : 2024-07-01Epub Date: 2024-06-12DOI: 10.1007/s10334-024-01176-5
Milan Hájek, Ulrich Flögel, Adriana A S Tavares, Lucia Nichelli, Aneurin Kennerley, Thomas Kahn, Jurgen J Futterer, Aikaterini Firsiori, Holger Grüll, Nandita Saha, Felipe Couñago, Dogu Baran Aydogan, Maria Eugenia Caligiuri, Cornelius Faber, Laura C Bell, Patrícia Figueiredo, Joan C Vilanova, Francesco Santini, Ralf Mekle, Sonia Waiczies
{"title":"MR beyond diagnostics at the ESMRMB annual meeting: MR theranostics and intervention.","authors":"Milan Hájek, Ulrich Flögel, Adriana A S Tavares, Lucia Nichelli, Aneurin Kennerley, Thomas Kahn, Jurgen J Futterer, Aikaterini Firsiori, Holger Grüll, Nandita Saha, Felipe Couñago, Dogu Baran Aydogan, Maria Eugenia Caligiuri, Cornelius Faber, Laura C Bell, Patrícia Figueiredo, Joan C Vilanova, Francesco Santini, Ralf Mekle, Sonia Waiczies","doi":"10.1007/s10334-024-01176-5","DOIUrl":"10.1007/s10334-024-01176-5","url":null,"abstract":"","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11316697/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141306257","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}
Objectives: To investigate the utility of deep learning (DL)-based image reconstruction using a model-based approach in head and neck diffusion-weighted imaging (DWI).
Materials and methods: We retrospectively analyzed the cases of 41 patients who underwent head/neck DWI. The DWI in 25 patients demonstrated an untreated lesion. We performed qualitative and quantitative assessments in the DWI analyses with both deep learning (DL)- and conventional parallel imaging (PI)-based reconstructions. For the qualitative assessment, we visually evaluated the overall image quality, soft tissue conspicuity, degree of artifact(s), and lesion conspicuity based on a five-point system. In the quantitative assessment, we measured the signal-to-noise ratio (SNR) of the bilateral parotid glands, submandibular gland, the posterior muscle, and the lesion. We then calculated the contrast-to-noise ratio (CNR) between the lesion and the adjacent muscle.
Results: Significant differences were observed in the qualitative analysis between the DWI with PI-based and DL-based reconstructions for all of the evaluation items (p < 0.001). In the quantitative analysis, significant differences in the SNR and CNR between the DWI with PI-based and DL-based reconstructions were observed for all of the evaluation items (p = 0.002 ~ p < 0.001).
Discussion: DL-based image reconstruction with the model-based technique effectively provided sufficient image quality in head/neck DWI.
{"title":"Improvement of image quality in diffusion-weighted imaging with model-based deep learning reconstruction for evaluations of the head and neck.","authors":"Noriyuki Fujima, Junichi Nakagawa, Hiroyuki Kameda, Yohei Ikebe, Taisuke Harada, Yukie Shimizu, Nayuta Tsushima, Satoshi Kano, Akihiro Homma, Jihun Kwon, Masami Yoneyama, Kohsuke Kudo","doi":"10.1007/s10334-023-01129-4","DOIUrl":"10.1007/s10334-023-01129-4","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate the utility of deep learning (DL)-based image reconstruction using a model-based approach in head and neck diffusion-weighted imaging (DWI).</p><p><strong>Materials and methods: </strong>We retrospectively analyzed the cases of 41 patients who underwent head/neck DWI. The DWI in 25 patients demonstrated an untreated lesion. We performed qualitative and quantitative assessments in the DWI analyses with both deep learning (DL)- and conventional parallel imaging (PI)-based reconstructions. For the qualitative assessment, we visually evaluated the overall image quality, soft tissue conspicuity, degree of artifact(s), and lesion conspicuity based on a five-point system. In the quantitative assessment, we measured the signal-to-noise ratio (SNR) of the bilateral parotid glands, submandibular gland, the posterior muscle, and the lesion. We then calculated the contrast-to-noise ratio (CNR) between the lesion and the adjacent muscle.</p><p><strong>Results: </strong>Significant differences were observed in the qualitative analysis between the DWI with PI-based and DL-based reconstructions for all of the evaluation items (p < 0.001). In the quantitative analysis, significant differences in the SNR and CNR between the DWI with PI-based and DL-based reconstructions were observed for all of the evaluation items (p = 0.002 ~ p < 0.001).</p><p><strong>Discussion: </strong>DL-based image reconstruction with the model-based technique effectively provided sufficient image quality in head/neck DWI.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138291348","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}
Object: To review recent advances of artificial intelligence (AI) in enhancing the efficiency and throughput of the MRI acquisition workflow in neuroimaging, including planning, sequence design, and correction of acquisition artifacts.
Materials and methods: A comprehensive analysis was conducted on recent AI-based methods in neuro MRI acquisition. The study focused on key technological advances, their impact on clinical practice, and potential risks associated with these methods.
Results: The findings indicate that AI-based algorithms have a substantial positive impact on the MRI acquisition process, improving both efficiency and throughput. Specific algorithms were identified as particularly effective in optimizing acquisition steps, with reported improvements in workflow efficiency.
Discussion: The review highlights the transformative potential of AI in neuro MRI acquisition, emphasizing the technological advances and clinical benefits. However, it also discusses potential risks and challenges, suggesting areas for future research to mitigate these concerns and further enhance AI integration in MRI acquisition.
{"title":"Artificial intelligence for neuro MRI acquisition: a review.","authors":"Hongjia Yang, Guanhua Wang, Ziyu Li, Haoxiang Li, Jialan Zheng, Yuxin Hu, Xiaozhi Cao, Congyu Liao, Huihui Ye, Qiyuan Tian","doi":"10.1007/s10334-024-01182-7","DOIUrl":"10.1007/s10334-024-01182-7","url":null,"abstract":"<p><strong>Object: </strong>To review recent advances of artificial intelligence (AI) in enhancing the efficiency and throughput of the MRI acquisition workflow in neuroimaging, including planning, sequence design, and correction of acquisition artifacts.</p><p><strong>Materials and methods: </strong>A comprehensive analysis was conducted on recent AI-based methods in neuro MRI acquisition. The study focused on key technological advances, their impact on clinical practice, and potential risks associated with these methods.</p><p><strong>Results: </strong>The findings indicate that AI-based algorithms have a substantial positive impact on the MRI acquisition process, improving both efficiency and throughput. Specific algorithms were identified as particularly effective in optimizing acquisition steps, with reported improvements in workflow efficiency.</p><p><strong>Discussion: </strong>The review highlights the transformative potential of AI in neuro MRI acquisition, emphasizing the technological advances and clinical benefits. However, it also discusses potential risks and challenges, suggesting areas for future research to mitigate these concerns and further enhance AI integration in MRI acquisition.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141450833","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 : 2024-07-01Epub Date: 2024-05-14DOI: 10.1007/s10334-024-01157-8
Chi Zhang, Davide Piccini, Omer Burak Demirel, Gabriele Bonanno, Christopher W Roy, Burhaneddin Yaman, Steen Moeller, Chetan Shenoy, Matthias Stuber, Mehmet Akçakaya
Object: To enable high-quality physics-guided deep learning (PG-DL) reconstruction of large-scale 3D non-Cartesian coronary MRI by overcoming challenges of hardware limitations and limited training data availability.
Materials and methods: While PG-DL has emerged as a powerful image reconstruction method, its application to large-scale 3D non-Cartesian MRI is hindered by hardware limitations and limited availability of training data. We combine several recent advances in deep learning and MRI reconstruction to tackle the former challenge, and we further propose a 2.5D reconstruction using 2D convolutional neural networks, which treat 3D volumes as batches of 2D images to train the network with a limited amount of training data. Both 3D and 2.5D variants of the PG-DL networks were compared to conventional methods for high-resolution 3D kooshball coronary MRI.
Results: Proposed PG-DL reconstructions of 3D non-Cartesian coronary MRI with 3D and 2.5D processing outperformed all conventional methods both quantitatively and qualitatively in terms of image assessment by an experienced cardiologist. The 2.5D variant further improved vessel sharpness compared to 3D processing, and scored higher in terms of qualitative image quality.
Discussion: PG-DL reconstruction of large-scale 3D non-Cartesian MRI without compromising image size or network complexity is achieved, and the proposed 2.5D processing enables high-quality reconstruction with limited training data.
{"title":"Large-scale 3D non-Cartesian coronary MRI reconstruction using distributed memory-efficient physics-guided deep learning with limited training data.","authors":"Chi Zhang, Davide Piccini, Omer Burak Demirel, Gabriele Bonanno, Christopher W Roy, Burhaneddin Yaman, Steen Moeller, Chetan Shenoy, Matthias Stuber, Mehmet Akçakaya","doi":"10.1007/s10334-024-01157-8","DOIUrl":"10.1007/s10334-024-01157-8","url":null,"abstract":"<p><strong>Object: </strong>To enable high-quality physics-guided deep learning (PG-DL) reconstruction of large-scale 3D non-Cartesian coronary MRI by overcoming challenges of hardware limitations and limited training data availability.</p><p><strong>Materials and methods: </strong>While PG-DL has emerged as a powerful image reconstruction method, its application to large-scale 3D non-Cartesian MRI is hindered by hardware limitations and limited availability of training data. We combine several recent advances in deep learning and MRI reconstruction to tackle the former challenge, and we further propose a 2.5D reconstruction using 2D convolutional neural networks, which treat 3D volumes as batches of 2D images to train the network with a limited amount of training data. Both 3D and 2.5D variants of the PG-DL networks were compared to conventional methods for high-resolution 3D kooshball coronary MRI.</p><p><strong>Results: </strong>Proposed PG-DL reconstructions of 3D non-Cartesian coronary MRI with 3D and 2.5D processing outperformed all conventional methods both quantitatively and qualitatively in terms of image assessment by an experienced cardiologist. The 2.5D variant further improved vessel sharpness compared to 3D processing, and scored higher in terms of qualitative image quality.</p><p><strong>Discussion: </strong>PG-DL reconstruction of large-scale 3D non-Cartesian MRI without compromising image size or network complexity is achieved, and the proposed 2.5D processing enables high-quality reconstruction with limited training data.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140922652","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 : 2024-07-01Epub Date: 2023-09-15DOI: 10.1007/s10334-023-01120-z
Yu-Long Huang, Yi-Ru Lin, Shang-Yueh Tsai
Background: Quantification of metabolites concentrations in institutional unit (IU) is important for inter-subject and long-term comparisons in the applications of magnetic resonance spectroscopy (MRS). Recently, deep learning (DL) algorithms have found a variety of applications on the process of MRS data. A quantification strategy compatible to DL base MRS spectral processing method is, therefore, useful.
Materials and methods: This study aims to investigate whether metabolite concentrations quantified using a convolutional neural network (CNN) based method, coupled with a scaling procedure that normalizes spectral signals for CNN input and linear regression, can effectively reflect variations in metabolite concentrations in IU across different brain regions with varying signal-to-noise ratios (SNR) and linewidths (LW). An error index based on standard error (SE) is proposed to indicate the confidence levels associated with metabolite predictions. In vivo MRS spectra were acquired from three brain regions of 43 subjects using a 3T system.
Results: The metabolite concentrations in IU of five major metabolites, quantified using CNN and LCModel, exhibit similar ranges with Pearson's correlation coefficients ranging from 0.24 to 0.78. The SE of the metabolites shows a positive correlation with Cramer-Rao lower bound (CRLB) (r=0.46) and absolute CRLB (r=0.81), calculated by multiplying CRLBs with the quantified metabolite content.
Conclusion: In conclusion, the CNN based method with the proposed scaling procedures can be employed to quantify in vivo MRS spectra and derive metabolites concentrations in IU. The SE can be used as error index, indicating predicted uncertainties for metabolites and sharing information similar to the absolute CRLB.
{"title":"Comparison of convolutional-neural-networks-based method and LCModel on the quantification of in vivo magnetic resonance spectroscopy.","authors":"Yu-Long Huang, Yi-Ru Lin, Shang-Yueh Tsai","doi":"10.1007/s10334-023-01120-z","DOIUrl":"10.1007/s10334-023-01120-z","url":null,"abstract":"<p><strong>Background: </strong>Quantification of metabolites concentrations in institutional unit (IU) is important for inter-subject and long-term comparisons in the applications of magnetic resonance spectroscopy (MRS). Recently, deep learning (DL) algorithms have found a variety of applications on the process of MRS data. A quantification strategy compatible to DL base MRS spectral processing method is, therefore, useful.</p><p><strong>Materials and methods: </strong>This study aims to investigate whether metabolite concentrations quantified using a convolutional neural network (CNN) based method, coupled with a scaling procedure that normalizes spectral signals for CNN input and linear regression, can effectively reflect variations in metabolite concentrations in IU across different brain regions with varying signal-to-noise ratios (SNR) and linewidths (LW). An error index based on standard error (SE) is proposed to indicate the confidence levels associated with metabolite predictions. In vivo MRS spectra were acquired from three brain regions of 43 subjects using a 3T system.</p><p><strong>Results: </strong>The metabolite concentrations in IU of five major metabolites, quantified using CNN and LCModel, exhibit similar ranges with Pearson's correlation coefficients ranging from 0.24 to 0.78. The SE of the metabolites shows a positive correlation with Cramer-Rao lower bound (CRLB) (r=0.46) and absolute CRLB (r=0.81), calculated by multiplying CRLBs with the quantified metabolite content.</p><p><strong>Conclusion: </strong>In conclusion, the CNN based method with the proposed scaling procedures can be employed to quantify in vivo MRS spectra and derive metabolites concentrations in IU. The SE can be used as error index, indicating predicted uncertainties for metabolites and sharing information similar to the absolute CRLB.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10235915","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 : 2024-07-01Epub Date: 2024-02-01DOI: 10.1007/s10334-023-01146-3
Sevgi Gokce Kafali, Shu-Fu Shih, Xinzhou Li, Grace Hyun J Kim, Tristan Kelly, Shilpy Chowdhury, Spencer Loong, Jeremy Moretz, Samuel R Barnes, Zhaoping Li, Holden H Wu
Objective: Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs.
Materials and methods: 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC).
Results: ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis.
Discussion: ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.
目的:皮下和内脏脂肪组织(SAT/VAT)体积的增加与心血管代谢疾病的风险有关。这项工作旨在利用基于注意力的竞争性密集(ACD)三维 U-Net 和三维 nnU-Net 以及全视场容积多对比度输入,开发和评估超重/肥胖症成人纵向 MRI 上的腹部 SAT/VAT 自动分割。第一次扫描分为训练/验证/测试集(n = 646/92/182)。测试集受试者的第二次扫描用于评估纵向分析的通用性。通过测量 Dice 分数(DICE-SAT、DICE-VAT)、假阴性(FN)和假阳性(FP)来评估分割性能。采用类内相关系数(ICC)评估体量一致性:结果:ACD 3D U-Net 在纵向分析中达到了快速(0.997):讨论:ACD 3D U-Net 和 3D nnU-Net 可作为自动化工具,快速、准确、纵向地量化超重/肥胖成人的腹部 SAT/VAT 容积。
{"title":"Automated abdominal adipose tissue segmentation and volume quantification on longitudinal MRI using 3D convolutional neural networks with multi-contrast inputs.","authors":"Sevgi Gokce Kafali, Shu-Fu Shih, Xinzhou Li, Grace Hyun J Kim, Tristan Kelly, Shilpy Chowdhury, Spencer Loong, Jeremy Moretz, Samuel R Barnes, Zhaoping Li, Holden H Wu","doi":"10.1007/s10334-023-01146-3","DOIUrl":"10.1007/s10334-023-01146-3","url":null,"abstract":"<p><strong>Objective: </strong>Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs.</p><p><strong>Materials and methods: </strong>920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC).</p><p><strong>Results: </strong>ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis.</p><p><strong>Discussion: </strong>ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11316694/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139651021","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}
Pub Date : 2024-07-01Epub Date: 2023-11-21DOI: 10.1007/s10334-023-01127-6
Rishabh Sharma, Panagiotis Tsiamyrtzis, Andrew G Webb, Ernst L Leiss, Nikolaos V Tsekos
Objective: This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics.
Materials and methods: To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters.
Results: ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA.
Discussion: These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.
{"title":"Learning to deep learning: statistics and a paradigm test in selecting a UNet architecture to enhance MRI.","authors":"Rishabh Sharma, Panagiotis Tsiamyrtzis, Andrew G Webb, Ernst L Leiss, Nikolaos V Tsekos","doi":"10.1007/s10334-023-01127-6","DOIUrl":"10.1007/s10334-023-01127-6","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics.</p><p><strong>Materials and methods: </strong>To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters.</p><p><strong>Results: </strong>ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA.</p><p><strong>Discussion: </strong>These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138291349","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}