首页 > 最新文献

European Radiology Experimental最新文献

英文 中文
Investigating patellar motion using weight-bearing dynamic CT: normative values and morphological considerations for healthy volunteers. 使用负重动态 CT 调查髌骨运动:健康志愿者的标准值和形态学考虑因素。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-19 DOI: 10.1186/s41747-024-00505-6
Luca Buzzatti, Benyameen Keelson, Savanah Héréus, Jona Van den Broeck, Thierry Scheerlinck, Gert Van Gompel, Jef Vandemeulebroucke, Johan De Mey, Nico Buls, Erik Cattrysse

Background: Patellar instability is a well-known pathology in which kinematics can be investigated using metrics such as tibial tuberosity tracheal groove (TTTG), the bisect offset (BO), and the lateral patellar tilt (LPT). We used dynamic computed tomography (CT) to investigate the patellar motion of healthy subjects in weight-bearing conditions to provide normative values for TTTG, BO, and LPT, as well as to define whether BO and LPT are affected by the morphology of the trochlear groove.

Methods: Dynamic scanning was used to acquire images during weight-bearing in 21 adult healthy volunteers. TTTG, BO, and LPT metrics were computed between 0° and 30° of knee flexion. Sulcus angle, sulcus depth, and lateral trochlear inclination were calculated and used with the TTTG for simple linear regression models.

Results: All metrics gradually decreased during eccentric movement (TTTG, -6.9 mm; BO, -12.6%; LPT, -4.3°). No significant differences were observed between eccentric and concentric phases at any flexion angle for all metrics. Linear regression between kinematic metrics towards full extension showed a moderate fit between BO and TTTG (R2 0.60, β 1.75) and BO and LPT (R2 0.59, β 1.49), and a low fit between TTTG and LPT (R2 0.38, β 0.53). A high impact of the TTTG distance over BO was shown in male participants (R2 0.71, β 1.89) and patella alta individuals (R2 0.55, β 1.91).

Conclusion: We provided preliminary normative values of three common metrics during weight-bearing dynamic CT and showed the substantial impact of lateralisation of the patella tendon over patella displacement.

Relevance statement: These normative values can be used by clinicians when evaluating knee patients using TTTG, BO, and LPT metrics. The lateralisation of the patellar tendon in subjects with patella alta or in males significantly impacts the lateral displacement of the patella.

Key points: Trochlear groove morphology had no substantial impact on motion prediction. The lateralisation of the patellar tendon seems a strong predictor of lateral displacement of the patella in male participants. Participants with patella alta displayed a strong fit between the patellar lateral displacement and tilt. TTTG, BO, and LPT decreased during concentric movement. Concentric and eccentric phases did not show differences for all metrics.

背景:髌骨不稳是一种众所周知的病理现象,其运动学指标包括胫骨结节气管沟(TTTG)、髌骨平分偏移(BO)和髌骨外侧倾斜(LPT)。我们使用动态计算机断层扫描(CT)来研究健康受试者在负重条件下的髌骨运动,以提供 TTTG、BO 和 LPT 的标准值,并确定 BO 和 LPT 是否受胫骨结节气管沟形态的影响:方法:对 21 名成年健康志愿者进行动态扫描,获取其负重时的图像。在膝关节屈曲 0° 和 30° 之间计算 TTTG、BO 和 LPT 指标。计算出沟角度、沟深度和外侧套骨倾斜度,并与 TTTG 一起用于简单线性回归模型:在偏心运动过程中,所有指标都逐渐下降(TTTG,-6.9 mm;BO,-12.6%;LPT,-4.3°)。在任何屈曲角度下,偏心和同心阶段的所有指标均无明显差异。完全伸展运动指标之间的线性回归显示,BO 和 TTTG(R2 0.60,β 1.75)以及 BO 和 LPT(R2 0.59,β 1.49)之间的拟合度适中,而 TTTG 和 LPT 之间的拟合度较低(R2 0.38,β 0.53)。男性参与者(R2 0.71,β 1.89)和髌骨畸形者(R2 0.55,β 1.91)的 TTTG 距离对 BO 的影响较大:我们提供了负重动态 CT 中三个常见指标的初步标准值,并显示了髌骨肌腱外侧化对髌骨位移的重大影响:这些标准值可供临床医生在使用 TTTG、BO 和 LPT 指标评估膝关节患者时使用。髌骨外翻或男性患者的髌骨肌腱外侧化对髌骨外侧移位有显著影响:关键点:韧带沟形态对运动预测没有实质性影响。髌骨肌腱的外侧化似乎对男性受试者的髌骨外侧位移有很大的预测作用。髌骨外翻的参与者的髌骨外侧位移与倾斜度之间有很强的拟合。在同心运动时,TTTG、BO 和 LPT 均有所下降。同心和偏心阶段的所有指标均无差异。
{"title":"Investigating patellar motion using weight-bearing dynamic CT: normative values and morphological considerations for healthy volunteers.","authors":"Luca Buzzatti, Benyameen Keelson, Savanah Héréus, Jona Van den Broeck, Thierry Scheerlinck, Gert Van Gompel, Jef Vandemeulebroucke, Johan De Mey, Nico Buls, Erik Cattrysse","doi":"10.1186/s41747-024-00505-6","DOIUrl":"https://doi.org/10.1186/s41747-024-00505-6","url":null,"abstract":"<p><strong>Background: </strong>Patellar instability is a well-known pathology in which kinematics can be investigated using metrics such as tibial tuberosity tracheal groove (TTTG), the bisect offset (BO), and the lateral patellar tilt (LPT). We used dynamic computed tomography (CT) to investigate the patellar motion of healthy subjects in weight-bearing conditions to provide normative values for TTTG, BO, and LPT, as well as to define whether BO and LPT are affected by the morphology of the trochlear groove.</p><p><strong>Methods: </strong>Dynamic scanning was used to acquire images during weight-bearing in 21 adult healthy volunteers. TTTG, BO, and LPT metrics were computed between 0° and 30° of knee flexion. Sulcus angle, sulcus depth, and lateral trochlear inclination were calculated and used with the TTTG for simple linear regression models.</p><p><strong>Results: </strong>All metrics gradually decreased during eccentric movement (TTTG, -6.9 mm; BO, -12.6%; LPT, -4.3°). No significant differences were observed between eccentric and concentric phases at any flexion angle for all metrics. Linear regression between kinematic metrics towards full extension showed a moderate fit between BO and TTTG (R<sup>2</sup> 0.60, β 1.75) and BO and LPT (R<sup>2</sup> 0.59, β 1.49), and a low fit between TTTG and LPT (R<sup>2</sup> 0.38, β 0.53). A high impact of the TTTG distance over BO was shown in male participants (R<sup>2</sup> 0.71, β 1.89) and patella alta individuals (R<sup>2</sup> 0.55, β 1.91).</p><p><strong>Conclusion: </strong>We provided preliminary normative values of three common metrics during weight-bearing dynamic CT and showed the substantial impact of lateralisation of the patella tendon over patella displacement.</p><p><strong>Relevance statement: </strong>These normative values can be used by clinicians when evaluating knee patients using TTTG, BO, and LPT metrics. The lateralisation of the patellar tendon in subjects with patella alta or in males significantly impacts the lateral displacement of the patella.</p><p><strong>Key points: </strong>Trochlear groove morphology had no substantial impact on motion prediction. The lateralisation of the patellar tendon seems a strong predictor of lateral displacement of the patella in male participants. Participants with patella alta displayed a strong fit between the patellar lateral displacement and tilt. TTTG, BO, and LPT decreased during concentric movement. Concentric and eccentric phases did not show differences for all metrics.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11413284/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142297415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Training and validation of a deep learning U-net architecture general model for automated segmentation of inner ear from CT 训练和验证用于从 CT 自动分割内耳的深度学习 U-net 架构通用模型
IF 3.8 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-12 DOI: 10.1186/s41747-024-00508-3
Jonathan Lim, Aurore Abily, Douraïed Ben Salem, Loïc Gaillandre, Arnaud Attye, Julien Ognard

Background

The intricate three-dimensional anatomy of the inner ear presents significant challenges in diagnostic procedures and critical surgical interventions. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNN), have shown promise for segmenting specific structures in medical imaging. This study aimed to train and externally validate an open-source U-net DL general model for automated segmentation of the inner ear from computed tomography (CT) scans, using quantitative and qualitative assessments.

Methods

In this multicenter study, we retrospectively collected a dataset of 271 CT scans to train an open-source U-net CNN model. An external set of 70 CT scans was used to evaluate the performance of the trained model. The model’s efficacy was quantitatively assessed using the Dice similarity coefficient (DSC) and qualitatively assessed using a 4-level Likert score. For comparative analysis, manual segmentation served as the reference standard, with assessments made on both training and validation datasets, as well as stratified analysis of normal and pathological subgroups.

Results

The optimized model yielded a mean DSC of 0.83 and achieved a Likert score of 1 in 42% of the cases, in conjunction with a significantly reduced processing time. Nevertheless, 27% of the patients received an indeterminate Likert score of 4. Overall, the mean DSCs were notably higher in the validation dataset than in the training dataset.

Conclusion

This study supports the external validation of an open-source U-net model for the automated segmentation of the inner ear from CT scans.

Relevance statement

This study optimized and assessed an open-source general deep learning model for automated segmentation of the inner ear using temporal CT scans, offering perspectives for application in clinical routine. The model weights, study datasets, and baseline model are worldwide accessible.

Key Points

  • A general open-source deep learning model was trained for CT automated inner ear segmentation.

  • The Dice similarity coefficient was 0.83 and a Likert score of 1 was attributed to 42% of automated segmentations.

  • The influence of scanning protocols on the model performances remains to be assessed.

Graphical Abstract

背景内耳错综复杂的三维解剖结构给诊断程序和关键手术干预带来了巨大挑战。深度学习(DL),尤其是卷积神经网络(CNN)的最新进展已显示出在医学成像中分割特定结构的前景。本研究旨在通过定量和定性评估,训练并从外部验证一个开源 U-net DL 通用模型,用于从计算机断层扫描(CT)扫描中自动分割内耳。方法在这项多中心研究中,我们回顾性地收集了 271 个 CT 扫描数据集,用于训练一个开源 U-net CNN 模型。外部的 70 个 CT 扫描数据集用于评估训练模型的性能。该模型的功效使用 Dice 相似性系数 (DSC) 进行定量评估,并使用 4 级 Likert 分数进行定性评估。结果优化模型的平均 DSC 值为 0.83,42% 的病例 Likert 评分达到 1 分,同时处理时间显著缩短。总体而言,验证数据集的平均 DSC 明显高于训练数据集。相关性声明本研究优化并评估了一个开源通用深度学习模型,该模型可用于利用颞部 CT 扫描自动分割内耳,为临床常规应用提供了前景。该模型的权重、研究数据集和基线模型可在全球范围内访问.Key Points针对CT自动内耳分割训练了一个通用开源深度学习模型.Dice相似性系数为0.83,42%的自动分割得到了1分的Likert评分.扫描协议对模型性能的影响仍有待评估.Graphical Abstract.
{"title":"Training and validation of a deep learning U-net architecture general model for automated segmentation of inner ear from CT","authors":"Jonathan Lim, Aurore Abily, Douraïed Ben Salem, Loïc Gaillandre, Arnaud Attye, Julien Ognard","doi":"10.1186/s41747-024-00508-3","DOIUrl":"https://doi.org/10.1186/s41747-024-00508-3","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Background</h3><p>The intricate three-dimensional anatomy of the inner ear presents significant challenges in diagnostic procedures and critical surgical interventions. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNN), have shown promise for segmenting specific structures in medical imaging. This study aimed to train and externally validate an open-source U-net DL general model for automated segmentation of the inner ear from computed tomography (CT) scans, using quantitative and qualitative assessments.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>In this multicenter study, we retrospectively collected a dataset of 271 CT scans to train an open-source U-net CNN model. An external set of 70 CT scans was used to evaluate the performance of the trained model. The model’s efficacy was quantitatively assessed using the Dice similarity coefficient (DSC) and qualitatively assessed using a 4-level Likert score. For comparative analysis, manual segmentation served as the reference standard, with assessments made on both training and validation datasets, as well as stratified analysis of normal and pathological subgroups.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>The optimized model yielded a mean DSC of 0.83 and achieved a Likert score of 1 in 42% of the cases, in conjunction with a significantly reduced processing time. Nevertheless, 27% of the patients received an indeterminate Likert score of 4. Overall, the mean DSCs were notably higher in the validation dataset than in the training dataset.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>This study supports the external validation of an open-source U-net model for the automated segmentation of the inner ear from CT scans.</p><h3 data-test=\"abstract-sub-heading\">Relevance statement</h3><p>This study optimized and assessed an open-source general deep learning model for automated segmentation of the inner ear using temporal CT scans, offering perspectives for application in clinical routine. The model weights, study datasets, and baseline model are worldwide accessible.</p><h3 data-test=\"abstract-sub-heading\">Key Points</h3><ul>\u0000<li>\u0000<p>A general open-source deep learning model was trained for CT automated inner ear segmentation.</p>\u0000</li>\u0000<li>\u0000<p>The Dice similarity coefficient was 0.83 and a Likert score of 1 was attributed to 42% of automated segmentations.</p>\u0000</li>\u0000<li>\u0000<p>The influence of scanning protocols on the model performances remains to be assessed.</p>\u0000</li>\u0000</ul><h3 data-test=\"abstract-sub-heading\">Graphical Abstract</h3>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142193327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Efficacy of compressed sensing and deep learning reconstruction for adult female pelvic MRI at 1.5 T 压缩传感和深度学习重建在 1.5 T 下用于成年女性盆腔磁共振成像的功效
IF 3.8 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-10 DOI: 10.1186/s41747-024-00506-5
Takahiro Ueda, Kaori Yamamoto, Natsuka Yazawa, Ikki Tozawa, Masato Ikedo, Masao Yui, Hiroyuki Nagata, Masahiko Nomura, Yoshiyuki Ozawa, Yoshiharu Ohno

Background

We aimed to determine the capabilities of compressed sensing (CS) and deep learning reconstruction (DLR) with those of conventional parallel imaging (PI) for improving image quality while reducing examination time on female pelvic 1.5-T magnetic resonance imaging (MRI).

Methods

Fifty-two consecutive female patients with various pelvic diseases underwent MRI with T1- and T2-weighted sequences using CS and PI. All CS data was reconstructed with and without DLR. Signal-to-noise ratio (SNR) of muscle and contrast-to-noise ratio (CNR) between fat tissue and iliac muscle on T1-weighted images (T1WI) and between myometrium and straight muscle on T2-weighted images (T2WI) were determined through region-of-interest measurements. Overall image quality (OIQ) and diagnostic confidence level (DCL) were evaluated on 5-point scales. SNRs and CNRs were compared using Tukey’s test, and qualitative indexes using the Wilcoxon signed-rank test.

Results

SNRs of T1WI and T2WI obtained using CS with DLR were higher than those using CS without DLR or conventional PI (p < 0.010). CNRs of T1WI and T2WI obtained using CS with DLR were higher than those using CS without DLR or conventional PI (p < 0.003). OIQ of T1WI and T2WI obtained using CS with DLR were higher than that using CS without DLR or conventional PI (p < 0.001). DCL of T2WI obtained using CS with DLR was higher than that using conventional PI or CS without DLR (p < 0.001).

Conclusion

CS with DLR provided better image quality and shorter examination time than those obtainable with PI for female pelvic 1.5-T MRI.

Relevance statement

CS with DLR can be considered effective for attaining better image quality and shorter examination time for female pelvic MRI at 1.5 T compared with those obtainable with PI.

Key Points

  • Patients underwent MRI with T1- and T2-weighted sequences using CS and PI.

  • All CS data was reconstructed with and without DLR.

  • CS with DLR allowed for examination times significantly shorter than those of PI and provided significantly higher signal- and CNRs, as well as OIQ.

Graphical Abstract

背景我们旨在确定压缩传感(CS)和深度学习重建(DLR)与传统平行成像(PI)在提高图像质量的同时缩短女性盆腔 1.5 T 磁共振成像(MRI)检查时间方面的能力。方法52 名患有各种盆腔疾病的女性患者连续接受了使用 CS 和 PI 进行 T1 和 T2 加权序列的 MRI 检查。所有 CS 数据都在有 DLR 和无 DLR 的情况下进行了重建。通过感兴趣区测量确定了 T1 加权图像(T1WI)上肌肉的信噪比(SNR)和脂肪组织与髂肌之间的对比度-噪声比(CNR),以及 T2 加权图像(T2WI)上子宫肌层与直肌之间的对比度-噪声比(CNR)。整体图像质量(OIQ)和诊断置信度(DCL)按 5 分制进行评估。结果使用带 DLR 的 CS 所获得的 T1WI 和 T2WI 的信噪比高于使用不带 DLR 的 CS 或传统 PI 所获得的信噪比(p < 0.010)。使用带 DLR 的 CS 获得的 T1WI 和 T2WI 的 CNRs 高于使用不带 DLR 的 CS 或传统 PI 的 CNRs(p < 0.003)。使用带 DLR 的 CS 获得的 T1WI 和 T2WI 的 OIQ 高于使用不带 DLR 的 CS 或传统 PI(p < 0.001)。使用带 DLR 的 CS 获得的 T2WI 的 DCL 高于使用传统 PI 或不带 DLR 的 CS(p < 0.001)。带 DLR 的 CS 可使检查时间明显短于 PI,并提供明显更高的信号和 CNR 以及 OIQ。
{"title":"Efficacy of compressed sensing and deep learning reconstruction for adult female pelvic MRI at 1.5 T","authors":"Takahiro Ueda, Kaori Yamamoto, Natsuka Yazawa, Ikki Tozawa, Masato Ikedo, Masao Yui, Hiroyuki Nagata, Masahiko Nomura, Yoshiyuki Ozawa, Yoshiharu Ohno","doi":"10.1186/s41747-024-00506-5","DOIUrl":"https://doi.org/10.1186/s41747-024-00506-5","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Background</h3><p>We aimed to determine the capabilities of compressed sensing (CS) and deep learning reconstruction (DLR) with those of conventional parallel imaging (PI) for improving image quality while reducing examination time on female pelvic 1.5-T magnetic resonance imaging (MRI).</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>Fifty-two consecutive female patients with various pelvic diseases underwent MRI with T1- and T2-weighted sequences using CS and PI. All CS data was reconstructed with and without DLR. Signal-to-noise ratio (SNR) of muscle and contrast-to-noise ratio (CNR) between fat tissue and iliac muscle on T1-weighted images (T1WI) and between myometrium and straight muscle on T2-weighted images (T2WI) were determined through region-of-interest measurements. Overall image quality (OIQ) and diagnostic confidence level (DCL) were evaluated on 5-point scales. SNRs and CNRs were compared using Tukey’s test, and qualitative indexes using the Wilcoxon signed-rank test.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>SNRs of T1WI and T2WI obtained using CS with DLR were higher than those using CS without DLR or conventional PI (<i>p</i> &lt; 0.010). CNRs of T1WI and T2WI obtained using CS with DLR were higher than those using CS without DLR or conventional PI (<i>p</i> &lt; 0.003). OIQ of T1WI and T2WI obtained using CS with DLR were higher than that using CS without DLR or conventional PI (<i>p</i> &lt; 0.001). DCL of T2WI obtained using CS with DLR was higher than that using conventional PI or CS without DLR (<i>p</i> &lt; 0.001).</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>CS with DLR provided better image quality and shorter examination time than those obtainable with PI for female pelvic 1.5-T MRI.</p><h3 data-test=\"abstract-sub-heading\">Relevance statement</h3><p>CS with DLR can be considered effective for attaining better image quality and shorter examination time for female pelvic MRI at 1.5 T compared with those obtainable with PI.</p><h3 data-test=\"abstract-sub-heading\">Key Points</h3><ul>\u0000<li>\u0000<p>Patients underwent MRI with T1- and T2-weighted sequences using CS and PI.</p>\u0000</li>\u0000<li>\u0000<p>All CS data was reconstructed with and without DLR.</p>\u0000</li>\u0000<li>\u0000<p>CS with DLR allowed for examination times significantly shorter than those of PI and provided significantly higher signal- and CNRs, as well as OIQ.</p>\u0000</li>\u0000</ul><h3 data-test=\"abstract-sub-heading\">Graphical Abstract</h3>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142193328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Accuracy of ultra-high resolution and virtual non-calcium reconstruction algorithm for stenosis evaluation with photon-counting CT: results from a dynamic phantom study. 用光子计数 CT 评估血管狭窄的超高分辨率和虚拟无钙重建算法的准确性:动态模型研究的结果。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-08-29 DOI: 10.1186/s41747-024-00482-w
Emese Zsarnoczay, Nicola Fink, U Joseph Schoepf, Daniel Pinos, Jim O'Doherty, Thomas Allmendinger, Junia Hagenauer, Joseph P Griffith Iii, Milán Vecsey-Nagy, Pál Maurovich-Horvat, Tilman Emrich, Akos Varga-Szemes

Background: We compared ultra-high resolution (UHR), standard resolution (SR), and virtual non-calcium (VNCa) reconstruction for coronary artery stenosis evaluation using photon-counting computed tomography (PC-CT).

Methods: One vessel phantom (4-mm diameter) containing solid calcified lesions with 25% and 50% stenoses inside a thorax phantom with motion simulation underwent PC-CT using UHR (0.2-mm slice thickness) and SR (0.6-mm slice thickness) at heart rates of 60 beats per minute (bpm), 80 bpm, and 100 bpm. A paired t-test or Wilcoxon test with Bonferroni correction was used.

Results: For 50% stenosis, differences in percent mean diameter stenosis between UHR and SR at 60 bpm (51.0 vs 60.3), 80 bpm (51.7 vs 59.6), and 100 bpm (53.7 vs 59.0) (p ≤ 0.011), as well as between VNCa and SR at 60 bpm (50.6 vs 60.3), 80 bpm (51.5 vs 59.6), and 100 bpm (53.7 vs 59.0) were significant (p ≤ 0.011), while differences between UHR and VNCa at all heart rates (p ≥ 0.327) were not significant. For 25% stenosis, differences between UHR and SR at 60 bpm (28.0 vs 33.7), 80 bpm (28.4 vs 34.3), and VNCa vs SR at 60 bpm (29.1 vs 33.7) were significant (p ≤ 0.015), while differences for UHR vs SR at 100 bpm (29.9 vs 34.0), as well as for VNCa vs SR at 80 bpm (30.7 vs 34.3) and 100 bpm (33.1 vs 34.0) were not significant (p ≥ 0.028).

Conclusion: Stenosis quantification accuracy with PC-CT improved using either UHR acquisition or VNCa reconstruction.

Relevance statement: PC-CT offers to scan with UHR mode and the reconstruction of VNCa images both of them could provide improved coronary stenosis quantification at increased heart rates, allowing a more accurate stenosis grading at low and high heart rates compared to SR.

Key points: Evaluation of coronary stenosis with conventional CT is challenging at high heart rates. PC-CT allows for scanning with ECG-gated UHR and SR modes. UHR and VNCa images were compared in a dynamic phantom. UHR improves stenosis quantification up to 100 bpm. VNCa reconstruction improves stenosis evaluation up to 80 bpm.

背景:我们比较了使用光子计数计算机断层扫描(PC-CT)进行冠状动脉狭窄评估的超高分辨率(UHR)、标准分辨率(SR)和虚拟无钙(VNCa)重建:方法:在一个具有运动模拟功能的胸腔模型中,使用 UHR(0.2 毫米切片厚度)和 SR(0.6 毫米切片厚度),在心率为每分钟 60 次、80 次和 100 次的条件下,对一个含有 25% 和 50% 狭窄实心钙化病变的血管模型(直径为 4 毫米)进行 PC-CT。采用配对 t 检验或带有 Bonferroni 校正的 Wilcoxon 检验:结果:对于 50%的狭窄,UHR 和 SR 在 60 bpm(51.0 vs 60.3)、80 bpm(51.7 vs 59.6)和 100 bpm(53.7 vs 59.0)时的平均直径狭窄百分比差异(p ≤ 0.011),以及 VNCa 和 SR 在 60 bpm(50.6 vs 60.3)、80 bpm(51.7 vs 59.6)和 100 bpm(53.7 vs 59.0)时的平均直径狭窄百分比差异(p ≤ 0.011)。6 vs 60.3)、80 bpm(51.5 vs 59.6)和 100 bpm(53.7 vs 59.0)时 VNCa 和 SR 之间的差异显著(p ≤ 0.011),而 UHR 和 VNCa 在所有心率下的差异均不显著(p ≥ 0.327)。对于 25% 的狭窄,UHR 与 SR 在 60 bpm(28.0 vs 33.7)、80 bpm(28.4 vs 34.3)以及 VNCa 与 SR 在 60 bpm(29.1 vs 33.7)时的差异均有显著性(p ≤ 0.015),而 100 bpm 时 UHR vs SR(29.9 vs 34.0)以及 80 bpm 时 VNCa vs SR(30.7 vs 34.3)和 100 bpm 时 VNCa vs SR(33.1 vs 34.0)的差异不显著(P ≥ 0.028):结论:使用 UHR 采集或 VNCa 重建,PC-CT 的狭窄量化准确性有所提高:PC-CT提供UHR模式扫描和VNCa图像重建,两者都能在心率增加时改善冠状动脉狭窄的量化,与SR相比,在低心率和高心率时能更准确地进行狭窄分级:要点:使用传统 CT 评估冠状动脉狭窄在高心率下具有挑战性。PC-CT 允许使用心电图门控的 UHR 和 SR 模式进行扫描。在动态模型中比较了 UHR 和 VNCa 图像。UHR 可改善血管狭窄的量化,最高可达 100 bpm。VNCa 重建可改善血管狭窄评估,最高可达 80 bpm。
{"title":"Accuracy of ultra-high resolution and virtual non-calcium reconstruction algorithm for stenosis evaluation with photon-counting CT: results from a dynamic phantom study.","authors":"Emese Zsarnoczay, Nicola Fink, U Joseph Schoepf, Daniel Pinos, Jim O'Doherty, Thomas Allmendinger, Junia Hagenauer, Joseph P Griffith Iii, Milán Vecsey-Nagy, Pál Maurovich-Horvat, Tilman Emrich, Akos Varga-Szemes","doi":"10.1186/s41747-024-00482-w","DOIUrl":"https://doi.org/10.1186/s41747-024-00482-w","url":null,"abstract":"<p><strong>Background: </strong>We compared ultra-high resolution (UHR), standard resolution (SR), and virtual non-calcium (VNCa) reconstruction for coronary artery stenosis evaluation using photon-counting computed tomography (PC-CT).</p><p><strong>Methods: </strong>One vessel phantom (4-mm diameter) containing solid calcified lesions with 25% and 50% stenoses inside a thorax phantom with motion simulation underwent PC-CT using UHR (0.2-mm slice thickness) and SR (0.6-mm slice thickness) at heart rates of 60 beats per minute (bpm), 80 bpm, and 100 bpm. A paired t-test or Wilcoxon test with Bonferroni correction was used.</p><p><strong>Results: </strong>For 50% stenosis, differences in percent mean diameter stenosis between UHR and SR at 60 bpm (51.0 vs 60.3), 80 bpm (51.7 vs 59.6), and 100 bpm (53.7 vs 59.0) (p ≤ 0.011), as well as between VNCa and SR at 60 bpm (50.6 vs 60.3), 80 bpm (51.5 vs 59.6), and 100 bpm (53.7 vs 59.0) were significant (p ≤ 0.011), while differences between UHR and VNCa at all heart rates (p ≥ 0.327) were not significant. For 25% stenosis, differences between UHR and SR at 60 bpm (28.0 vs 33.7), 80 bpm (28.4 vs 34.3), and VNCa vs SR at 60 bpm (29.1 vs 33.7) were significant (p ≤ 0.015), while differences for UHR vs SR at 100 bpm (29.9 vs 34.0), as well as for VNCa vs SR at 80 bpm (30.7 vs 34.3) and 100 bpm (33.1 vs 34.0) were not significant (p ≥ 0.028).</p><p><strong>Conclusion: </strong>Stenosis quantification accuracy with PC-CT improved using either UHR acquisition or VNCa reconstruction.</p><p><strong>Relevance statement: </strong>PC-CT offers to scan with UHR mode and the reconstruction of VNCa images both of them could provide improved coronary stenosis quantification at increased heart rates, allowing a more accurate stenosis grading at low and high heart rates compared to SR.</p><p><strong>Key points: </strong>Evaluation of coronary stenosis with conventional CT is challenging at high heart rates. PC-CT allows for scanning with ECG-gated UHR and SR modes. UHR and VNCa images were compared in a dynamic phantom. UHR improves stenosis quantification up to 100 bpm. VNCa reconstruction improves stenosis evaluation up to 80 bpm.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11362394/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Intraindividual reproducibility of myocardial radiomic features between energy-integrating detector and photon-counting detector CT angiography. 能量积分探测器和光子计数探测器 CT 血管造影术心肌放射学特征的个体内再现性。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-08-28 DOI: 10.1186/s41747-024-00493-7
Giuseppe Tremamunno, Akos Varga-Szemes, U Joseph Schoepf, Andrea Laghi, Emese Zsarnoczay, Nicola Fink, Gilberto J Aquino, Jim O'Doherty, Tilman Emrich, Milan Vecsey-Nagy

Background: Radiomics is not yet used in clinical practice due to concerns regarding its susceptibility to technical factors. We aimed to assess the stability and interscan and interreader reproducibility of myocardial radiomic features between energy-integrating detector computed tomography (EID-CT) and photon-counting detector CT (PCD-CT) in patients undergoing coronary CT angiography (CCTA) on both systems.

Methods: Consecutive patients undergoing clinically indicated CCTA on an EID-CT were prospectively enrolled for a PCD-CT CCTA within 30 days. Virtual monoenergetic images (VMI) at various keV levels and polychromatic images (T3D) were generated for PCD-CT, with image reconstruction parameters standardized between scans. Two readers performed myocardial segmentation and 110 radiomic features were compared intraindividually between EID-CT and PDC-CT series. The agreement of parameters was assessed using the intraclass correlation coefficient and paired t-test for the stability of the parameters.

Results: Eighteen patients (15 males) aged 67.6 ± 9.7 years (mean ± standard deviation) were included. Besides polychromatic PCD-CT reconstructions, 60- and 70-keV VMIs showed the highest feature stability compared to EID-CT (96%, 90%, and 92%, respectively). The interscan reproducibility of features was moderate even in the most favorable comparisons (median ICC 0.50 [interquartile range 0.20-0.60] for T3D; 0.56 [0.33-0.74] for 60 keV; 0.50 [0.36-0.62] for 70 keV). Interreader reproducibility was excellent for the PCD-CT series and good for EID-CT segmentations.

Conclusion: Most myocardial radiomic features remain stable between EID-CT and PCD-CT. While features demonstrated moderate reproducibility between scanners, technological advances associated with PCD-CT may lead to greater reproducibility, potentially expediting future standardization efforts.

Relevance statement: While the use of PCD-CT may facilitate reduced interreader variability in radiomics analysis, the observed interscanner variations in comparison to EID-CT should be taken into account in future research, with efforts being made to minimize their impact in future radiomics studies.

Key points: Most myocardial radiomic features resulted in being stable between EID-CT and PCD-CT on certain VMIs. The reproducibility of parameters between detector technologies was limited. PCD-CT improved interreader reproducibility of myocardial radiomic features.

背景:由于放射组学易受技术因素的影响,目前尚未应用于临床实践。我们的目的是评估在能量积分探测器计算机断层扫描(EID-CT)和光子计数探测器计算机断层扫描(PCD-CT)两种系统上进行冠状动脉 CT 血管造影(CCTA)的患者的心肌放射组学特征的稳定性以及扫描间和读片机间的再现性:连续接受有临床指征的 EID-CT CCTA 检查的患者在 30 天内接受 PCD-CT CCTA 检查。为 PCD-CT 生成不同 KeV 水平的虚拟单能图像 (VMI) 和多色图像 (T3D),扫描之间的图像重建参数标准化。两名读片员进行心肌分割,并对 EID-CT 和 PDC-CT 系列的 110 个放射学特征进行单独比较。使用类内相关系数和配对 t 检验评估参数的一致性,以确定参数的稳定性:共纳入 18 名患者(15 名男性),年龄为 67.6 ± 9.7 岁(平均 ± 标准差)。除多色 PCD-CT 重建外,与 EID-CT 相比,60 和 70-keV VMI 的特征稳定性最高(分别为 96%、90% 和 92%)。即使在最有利的比较中,特征的扫描间再现性也处于中等水平(T3D 的 ICC 中位数为 0.50 [四分位间范围为 0.20-0.60];60 keV 为 0.56 [0.33-0.74];70 keV 为 0.50 [0.36-0.62])。PCD-CT系列的读片机间重现性极佳,EID-CT分割的重现性良好:结论:大多数心肌放射学特征在 EID-CT 和 PCD-CT 之间保持稳定。虽然不同扫描仪之间的特征显示出中等程度的可重复性,但 PCD-CT 相关技术的进步可能会带来更高的可重复性,从而有可能加快未来的标准化工作:虽然 PCD-CT 的使用有助于减少放射组学分析中读片机之间的差异,但在未来的研究中应考虑到与 EID-CT 相比观察到的扫描仪之间的差异,并努力将其对未来放射组学研究的影响降至最低:要点:在某些 VMIs 上,EID-CT 和 PCD-CT 的大多数心肌放射组学特征是稳定的。不同检测器技术之间参数的再现性有限。PCD-CT 提高了心肌放射学特征的读片机间再现性。
{"title":"Intraindividual reproducibility of myocardial radiomic features between energy-integrating detector and photon-counting detector CT angiography.","authors":"Giuseppe Tremamunno, Akos Varga-Szemes, U Joseph Schoepf, Andrea Laghi, Emese Zsarnoczay, Nicola Fink, Gilberto J Aquino, Jim O'Doherty, Tilman Emrich, Milan Vecsey-Nagy","doi":"10.1186/s41747-024-00493-7","DOIUrl":"10.1186/s41747-024-00493-7","url":null,"abstract":"<p><strong>Background: </strong>Radiomics is not yet used in clinical practice due to concerns regarding its susceptibility to technical factors. We aimed to assess the stability and interscan and interreader reproducibility of myocardial radiomic features between energy-integrating detector computed tomography (EID-CT) and photon-counting detector CT (PCD-CT) in patients undergoing coronary CT angiography (CCTA) on both systems.</p><p><strong>Methods: </strong>Consecutive patients undergoing clinically indicated CCTA on an EID-CT were prospectively enrolled for a PCD-CT CCTA within 30 days. Virtual monoenergetic images (VMI) at various keV levels and polychromatic images (T3D) were generated for PCD-CT, with image reconstruction parameters standardized between scans. Two readers performed myocardial segmentation and 110 radiomic features were compared intraindividually between EID-CT and PDC-CT series. The agreement of parameters was assessed using the intraclass correlation coefficient and paired t-test for the stability of the parameters.</p><p><strong>Results: </strong>Eighteen patients (15 males) aged 67.6 ± 9.7 years (mean ± standard deviation) were included. Besides polychromatic PCD-CT reconstructions, 60- and 70-keV VMIs showed the highest feature stability compared to EID-CT (96%, 90%, and 92%, respectively). The interscan reproducibility of features was moderate even in the most favorable comparisons (median ICC 0.50 [interquartile range 0.20-0.60] for T3D; 0.56 [0.33-0.74] for 60 keV; 0.50 [0.36-0.62] for 70 keV). Interreader reproducibility was excellent for the PCD-CT series and good for EID-CT segmentations.</p><p><strong>Conclusion: </strong>Most myocardial radiomic features remain stable between EID-CT and PCD-CT. While features demonstrated moderate reproducibility between scanners, technological advances associated with PCD-CT may lead to greater reproducibility, potentially expediting future standardization efforts.</p><p><strong>Relevance statement: </strong>While the use of PCD-CT may facilitate reduced interreader variability in radiomics analysis, the observed interscanner variations in comparison to EID-CT should be taken into account in future research, with efforts being made to minimize their impact in future radiomics studies.</p><p><strong>Key points: </strong>Most myocardial radiomic features resulted in being stable between EID-CT and PCD-CT on certain VMIs. The reproducibility of parameters between detector technologies was limited. PCD-CT improved interreader reproducibility of myocardial radiomic features.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11358367/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
3D fascicular reconstruction of median and ulnar nerve: initial experience and comparison between high-resolution ultrasound and MR microscopy. 正中神经和尺神经的三维筋膜重建:高分辨率超声和磁共振显微镜的初步经验和比较。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-08-28 DOI: 10.1186/s41747-024-00495-5
Luka Pušnik, Lisa Lechner, Igor Serša, Erika Cvetko, Philipp Haas, Suren Armeni Jengojan, Žiga Snoj

Background: The complex anatomy of peripheral nerves has been traditionally investigated through histological microsections, with inherent limitations. We aimed to compare three-dimensional (3D) reconstructions of median and ulnar nerves acquired with tomographic high-resolution ultrasound (HRUS) and magnetic resonance microscopy (MRM) and assess their capacity to depict intraneural anatomy.

Methods: Three fresh-frozen human upper extremity specimens were prepared for HRUS imaging by submersion in a water medium. The median and ulnar nerves were pierced with sutures to improve orientation during imaging. Peripheral nerve 3D HRUS scanning was performed on the mid-upper arm using a broadband linear probe (10-22 MHz) equipped with a tomographic 3D HRUS system. Following excision, nerves were cut into 16-mm segments and loaded into the MRM probe of a 9.4-T system (scanning time 27 h). Fascicle and nerve counting was performed to estimate the nerve volume, fascicle volume, fascicle count, and number of interfascicular connections. HRUS reconstructions employed artificial intelligence-based algorithms, while MRM reconstructions were generated using an open-source imaging software 3D slicer.

Results: Compared to MRM, 3D HRUS underestimated nerve volume by up to 22% and volume of all fascicles by up to 11%. Additionally, 3D HRUS depicted 6-60% fewer fascicles compared to MRM and visualized approximately half as many interfascicular connections.

Conclusion: MRM demonstrated a more detailed fascicular depiction compared to 3D HRUS, with a greater capacity for visualizing smaller fascicles. While 3D HRUS reconstructions can offer supplementary data in peripheral nerve assessment, their limitations in depicting interfascicular connections and small fascicles within clusters necessitate cautious interpretation.

Clinical relevance statement: Although 3D HRUS reconstructions can offer supplementary data in peripheral nerve assessment, even in intraoperative settings, their limitations in depicting interfascicular branches and small fascicles within clusters require cautious interpretation.

Key points: 3D HRUS was limited in visualizing nerve interfascicular connections. MRM demonstrated better nerve fascicle depiction than 3D HRUS. MRM depicted more nerve interfascicular connections than 3D HRUS.

背景:传统上通过组织学显微切片来研究周围神经的复杂解剖结构,但这种方法存在固有的局限性。我们旨在比较通过断层高分辨率超声(HRUS)和磁共振显微镜(MRM)获得的正中神经和尺神经的三维(3D)重建,并评估它们描述神经内解剖结构的能力:方法:将三个新鲜冷冻的人体上肢标本浸没在水介质中,以准备进行 HRUS 成像。正中神经和尺神经用缝线穿孔,以改善成像时的定向。使用配备了断层三维 HRUS 系统的宽带线性探针(10-22 MHz)对中上臂进行外周神经三维 HRUS 扫描。切除后,神经被切成 16 毫米的小段,并装入 9.4-T 系统的 MRM 探头(扫描时间为 27 小时)。对神经束和神经进行计数,以估算神经体积、神经束体积、神经束数量和束间连接数量。HRUS 重建采用基于人工智能的算法,而 MRM 重建则使用开源成像软件 3D slicer 生成:结果:与 MRM 相比,三维 HRUS 对神经体积的低估高达 22%,对所有筋膜体积的低估高达 11%。此外,与 MRM 相比,三维 HRUS 显示的筋膜数量减少了 6-60%,可视筋膜间连接的数量减少了约一半:结论:与三维 HRUS 相比,MRM 显示了更详细的筋膜描绘,更有能力显示较小的筋膜。虽然三维 HRUS 重建可为周围神经评估提供补充数据,但由于其在描绘筋膜间连接和簇内小筋膜方面存在局限性,因此需要谨慎解读:尽管三维 HRUS 重建可为周围神经评估提供补充数据,即使在术中也是如此,但其在描绘筋膜间分支和簇内小束方面存在局限性,需要谨慎解读:要点:三维 HRUS 在观察神经束间连接方面存在局限性。与三维 HRUS 相比,MRM 对神经束的描绘更好。与三维 HRUS 相比,MRM 能显示更多的神经筋膜间连接。
{"title":"3D fascicular reconstruction of median and ulnar nerve: initial experience and comparison between high-resolution ultrasound and MR microscopy.","authors":"Luka Pušnik, Lisa Lechner, Igor Serša, Erika Cvetko, Philipp Haas, Suren Armeni Jengojan, Žiga Snoj","doi":"10.1186/s41747-024-00495-5","DOIUrl":"10.1186/s41747-024-00495-5","url":null,"abstract":"<p><strong>Background: </strong>The complex anatomy of peripheral nerves has been traditionally investigated through histological microsections, with inherent limitations. We aimed to compare three-dimensional (3D) reconstructions of median and ulnar nerves acquired with tomographic high-resolution ultrasound (HRUS) and magnetic resonance microscopy (MRM) and assess their capacity to depict intraneural anatomy.</p><p><strong>Methods: </strong>Three fresh-frozen human upper extremity specimens were prepared for HRUS imaging by submersion in a water medium. The median and ulnar nerves were pierced with sutures to improve orientation during imaging. Peripheral nerve 3D HRUS scanning was performed on the mid-upper arm using a broadband linear probe (10-22 MHz) equipped with a tomographic 3D HRUS system. Following excision, nerves were cut into 16-mm segments and loaded into the MRM probe of a 9.4-T system (scanning time 27 h). Fascicle and nerve counting was performed to estimate the nerve volume, fascicle volume, fascicle count, and number of interfascicular connections. HRUS reconstructions employed artificial intelligence-based algorithms, while MRM reconstructions were generated using an open-source imaging software 3D slicer.</p><p><strong>Results: </strong>Compared to MRM, 3D HRUS underestimated nerve volume by up to 22% and volume of all fascicles by up to 11%. Additionally, 3D HRUS depicted 6-60% fewer fascicles compared to MRM and visualized approximately half as many interfascicular connections.</p><p><strong>Conclusion: </strong>MRM demonstrated a more detailed fascicular depiction compared to 3D HRUS, with a greater capacity for visualizing smaller fascicles. While 3D HRUS reconstructions can offer supplementary data in peripheral nerve assessment, their limitations in depicting interfascicular connections and small fascicles within clusters necessitate cautious interpretation.</p><p><strong>Clinical relevance statement: </strong>Although 3D HRUS reconstructions can offer supplementary data in peripheral nerve assessment, even in intraoperative settings, their limitations in depicting interfascicular branches and small fascicles within clusters require cautious interpretation.</p><p><strong>Key points: </strong>3D HRUS was limited in visualizing nerve interfascicular connections. MRM demonstrated better nerve fascicle depiction than 3D HRUS. MRM depicted more nerve interfascicular connections than 3D HRUS.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11358559/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Vessel-based CTA-image to spatial anatomy registration using tracked catheter position data: preclinical evaluation of in vivo accuracy. 使用跟踪导管位置数据进行基于血管的 CTA 图像与空间解剖学配准:体内准确性的临床前评估。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-08-28 DOI: 10.1186/s41747-024-00499-1
Geir Arne Tangen, Petter Aadahl, Toril A N Hernes, Frode Manstad-Hulaas

Electromagnetic tracking of endovascular instruments has the potential to substantially decrease radiation exposure of patients and personnel. In this study, we evaluated the in vivo accuracy of a vessel-based method to register preoperative computed tomography angiography (CTA) images to physical coordinates using an electromagnetically tracked guidewire. Centerlines of the aortoiliac arteries were extracted from preoperative CTA acquired from five swine. Intravascular positions were obtained from an electromagnetically tracked guidewire. An iterative-closest-point algorithm registered the position data to the preoperative image centerlines. To evaluate the registration accuracy, a guidewire was placed inside the superior mesenteric, left and right renal arteries under fluoroscopic guidance. Position data was acquired with electromagnetic tracking as the guidewire was pulled into the aorta. The resulting measured positions were compared to the corresponding ostia manually identified in the CTA images after applying the registration. The three-dimensional (3D) Euclidean distances were calculated between each corresponding ostial point, and the root mean square (RMS) was calculated for each registration. The median 3D RMS for all registrations was 4.82 mm, with an interquartile range of 3.53-6.14 mm. A vessel-based registration of CTA images to vascular anatomy is possible with acceptable accuracy and encourages further clinical testing. RELEVANCE STATEMENT: This study shows that the centerline algorithm can be used to register preoperative CTA images to vascular anatomy, with the potential to further reduce ionizing radiation exposure during vascular procedures. KEY POINTS: Preoperative images can be used to guide the procedure without ionizing intraoperative imaging. Preoperative imaging can be the only imaging modality used for guidance of vascular procedures. No need to use external fiducial markers to register/match images and spatial anatomy. Acceptable accuracy can be achieved for navigation in a preclinical setting.

对血管内器械进行电磁追踪有可能大大减少对患者和工作人员的辐射照射。在这项研究中,我们评估了使用电磁追踪导丝将术前计算机断层扫描血管造影(CTA)图像注册到物理坐标的基于血管方法的体内准确性。从五头猪的术前 CTA 图像中提取了主动脉髂动脉的中心线。通过电磁追踪导丝获得血管内位置。迭代-闭合点算法将位置数据与术前图像中心线进行配准。为了评估登记的准确性,在透视引导下将一根导丝放置在肠系膜上动脉、左肾动脉和右肾动脉内。当导丝被拉入主动脉时,通过电磁跟踪获取位置数据。在应用配准后,将测得的位置与 CTA 图像中人工识别的相应动脉口进行比较。计算每个相应动脉口点之间的三维(3D)欧氏距离,并计算每次配准的均方根(RMS)。所有配准的三维均方根中位数为 4.82 毫米,四分位数范围为 3.53-6.14 毫米。根据血管解剖结构对 CTA 图像进行基于血管的配准是可行的,其准确性也是可以接受的,值得进一步进行临床测试。相关性声明:本研究表明,中心线算法可用于将术前 CTA 图像与血管解剖结构进行配准,有望进一步减少血管手术过程中的电离辐射暴露。关键点:术前图像可用于指导手术,而无需术中电离成像。术前成像可作为引导血管手术的唯一成像方式。无需使用外部靶标来对图像和空间解剖进行配准/匹配。可在临床前环境中实现可接受的导航精度。
{"title":"Vessel-based CTA-image to spatial anatomy registration using tracked catheter position data: preclinical evaluation of in vivo accuracy.","authors":"Geir Arne Tangen, Petter Aadahl, Toril A N Hernes, Frode Manstad-Hulaas","doi":"10.1186/s41747-024-00499-1","DOIUrl":"10.1186/s41747-024-00499-1","url":null,"abstract":"<p><p>Electromagnetic tracking of endovascular instruments has the potential to substantially decrease radiation exposure of patients and personnel. In this study, we evaluated the in vivo accuracy of a vessel-based method to register preoperative computed tomography angiography (CTA) images to physical coordinates using an electromagnetically tracked guidewire. Centerlines of the aortoiliac arteries were extracted from preoperative CTA acquired from five swine. Intravascular positions were obtained from an electromagnetically tracked guidewire. An iterative-closest-point algorithm registered the position data to the preoperative image centerlines. To evaluate the registration accuracy, a guidewire was placed inside the superior mesenteric, left and right renal arteries under fluoroscopic guidance. Position data was acquired with electromagnetic tracking as the guidewire was pulled into the aorta. The resulting measured positions were compared to the corresponding ostia manually identified in the CTA images after applying the registration. The three-dimensional (3D) Euclidean distances were calculated between each corresponding ostial point, and the root mean square (RMS) was calculated for each registration. The median 3D RMS for all registrations was 4.82 mm, with an interquartile range of 3.53-6.14 mm. A vessel-based registration of CTA images to vascular anatomy is possible with acceptable accuracy and encourages further clinical testing. RELEVANCE STATEMENT: This study shows that the centerline algorithm can be used to register preoperative CTA images to vascular anatomy, with the potential to further reduce ionizing radiation exposure during vascular procedures. KEY POINTS: Preoperative images can be used to guide the procedure without ionizing intraoperative imaging. Preoperative imaging can be the only imaging modality used for guidance of vascular procedures. No need to use external fiducial markers to register/match images and spatial anatomy. Acceptable accuracy can be achieved for navigation in a preclinical setting.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11358569/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Assessment of thoracic disc degeneration using dual-energy CT-based collagen maps. 使用基于双能 CT 的胶原图评估胸椎椎间盘退变。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-08-26 DOI: 10.1186/s41747-024-00500-x
Simon Bernatz, Alexander Tom Hoppe, Leon David Gruenewald, Vitali Koch, Simon S Martin, Lara Engelskirchen, Ivana Radic, Giuseppe Bucolo, Jennifer Gotta, Philipp Reschke, Renate M Hammerstingl, Jan-Erik Scholtz, Tatjana Gruber-Rouh, Katrin Eichler, Thomas J Vogl, Christian Booz, Ibrahim Yel, Scherwin Mahmoudi

Background: We evaluated the role of dual-energy computed tomography (DECT)-based collagen maps in assessing thoracic disc degeneration.

Methods: We performed a retrospective analysis of patients who underwent DECT and magnetic resonance imaging (MRI) of the thoracic spine within a 2-week period from July 2019 to October 2022. Thoracic disc degeneration was classified by three blinded radiologists into three Pfirrmann categories: no/mild (grade 1-2), moderate (grade 3-4), and severe (grade 5). The DECT performance was determined using MRI as a reference standard. Interreader reliability was assessed using intraclass correlation coefficient (ICC). Five-point Likert scales were used to assess diagnostic confidence and image quality.

Results: In total, 612 intervertebral discs across 51 patients aged 68 ± 16 years (mean ± standard deviation), 28 males and 23 females, were assessed. MRI revealed 135 no/mildly degenerated discs (22.1%), 470 moderately degenerated discs (76.8%), and 7 severely degenerated discs (1.1%). DECT collagen maps achieved an overall accuracy of 1,483/1,838 (80.8%) for thoracic disc degeneration. Overall recall (sensitivity) was 331/405 (81.7%) for detecting no/mild degeneration, 1,134/1,410 (80.4%) for moderate degeneration, and 18/21 (85.7%) for severe degeneration. Interrater agreement was good (ICC = 0.89). Assessment of DECT-based collagen maps demonstrated high diagnostic confidence (median 4; interquartile range 3-4) and good image quality (median 4; interquartile range 4-4).

Conclusion: DECT showed an overall 81% accuracy for disc degeneration by visualizing differences in the collagen content of thoracic discs.

Relevance statement: Utilizing DECT-based collagen maps to distinguish various stages of thoracic disc degeneration could be clinically relevant for early detection of disc-related conditions. This approach may be particularly beneficial when MRI is contraindicated.

Key points: A total of 612 intervertebral discs across 51 patients were retrospectively assessed with DECT, using MRI as a reference standard. DECT-based collagen maps allowed thoracic disc degeneration assessment achieving an overall 81% accuracy with good interrater agreement (ICC = 0.89). DECT-based collagen maps could be a good alternative in the case of contraindications to MRI.

背景:我们评估了基于双能计算机断层扫描(DECT)的胶原图在评估胸椎椎间盘退变中的作用:我们对在2019年7月至2022年10月的两周内接受了胸椎双能计算机断层扫描(DECT)和磁共振成像(MRI)的患者进行了回顾性分析。胸椎椎间盘退变由三位盲放射科医生分为三个 Pfirrmann 类别:无/轻度(1-2 级)、中度(3-4 级)和重度(5 级)。DECT 性能以核磁共振成像作为参考标准。读片者之间的可靠性采用类内相关系数(ICC)进行评估。采用五点李克特量表评估诊断信心和图像质量:共对 51 名患者的 612 个椎间盘进行了评估,患者年龄为 68 ± 16 岁(平均 ± 标准差),其中男性 28 人,女性 23 人。磁共振成像显示,135 个椎间盘无/轻度退变(22.1%),470 个椎间盘中度退变(76.8%),7 个椎间盘严重退变(1.1%)。DECT胶原图对胸椎间盘退变的总体准确率为1,483/1,838(80.8%)。检测无/轻度退变的总体召回率(灵敏度)为 331/405(81.7%),检测中度退变的召回率(灵敏度)为 1,134/1,410 (80.4%),检测严重退变的召回率(灵敏度)为 18/21 (85.7%)。相互之间的一致性良好(ICC = 0.89)。对基于 DECT 的胶原图的评估显示,诊断可信度高(中位数为 4;四分位数间距为 3-4),图像质量好(中位数为 4;四分位数间距为 4-4):结论:通过观察胸椎椎间盘胶原蛋白含量的差异,DECT显示椎间盘退变的总体准确率为81%:利用基于 DECT 的胶原图来区分不同阶段的胸椎椎间盘退变,对于早期发现椎间盘相关疾病具有临床意义。这种方法在核磁共振成像禁忌症时可能特别有益:以核磁共振成像为参考标准,使用 DECT 对 51 名患者的 612 个椎间盘进行了回顾性评估。通过基于 DECT 的胶原图,胸椎椎间盘退变评估的总体准确率达到了 81%,且检查者之间具有良好的一致性(ICC = 0.89)。在有核磁共振成像禁忌症的情况下,基于DECT的胶原图是一种很好的替代方法。
{"title":"Assessment of thoracic disc degeneration using dual-energy CT-based collagen maps.","authors":"Simon Bernatz, Alexander Tom Hoppe, Leon David Gruenewald, Vitali Koch, Simon S Martin, Lara Engelskirchen, Ivana Radic, Giuseppe Bucolo, Jennifer Gotta, Philipp Reschke, Renate M Hammerstingl, Jan-Erik Scholtz, Tatjana Gruber-Rouh, Katrin Eichler, Thomas J Vogl, Christian Booz, Ibrahim Yel, Scherwin Mahmoudi","doi":"10.1186/s41747-024-00500-x","DOIUrl":"10.1186/s41747-024-00500-x","url":null,"abstract":"<p><strong>Background: </strong>We evaluated the role of dual-energy computed tomography (DECT)-based collagen maps in assessing thoracic disc degeneration.</p><p><strong>Methods: </strong>We performed a retrospective analysis of patients who underwent DECT and magnetic resonance imaging (MRI) of the thoracic spine within a 2-week period from July 2019 to October 2022. Thoracic disc degeneration was classified by three blinded radiologists into three Pfirrmann categories: no/mild (grade 1-2), moderate (grade 3-4), and severe (grade 5). The DECT performance was determined using MRI as a reference standard. Interreader reliability was assessed using intraclass correlation coefficient (ICC). Five-point Likert scales were used to assess diagnostic confidence and image quality.</p><p><strong>Results: </strong>In total, 612 intervertebral discs across 51 patients aged 68 ± 16 years (mean ± standard deviation), 28 males and 23 females, were assessed. MRI revealed 135 no/mildly degenerated discs (22.1%), 470 moderately degenerated discs (76.8%), and 7 severely degenerated discs (1.1%). DECT collagen maps achieved an overall accuracy of 1,483/1,838 (80.8%) for thoracic disc degeneration. Overall recall (sensitivity) was 331/405 (81.7%) for detecting no/mild degeneration, 1,134/1,410 (80.4%) for moderate degeneration, and 18/21 (85.7%) for severe degeneration. Interrater agreement was good (ICC = 0.89). Assessment of DECT-based collagen maps demonstrated high diagnostic confidence (median 4; interquartile range 3-4) and good image quality (median 4; interquartile range 4-4).</p><p><strong>Conclusion: </strong>DECT showed an overall 81% accuracy for disc degeneration by visualizing differences in the collagen content of thoracic discs.</p><p><strong>Relevance statement: </strong>Utilizing DECT-based collagen maps to distinguish various stages of thoracic disc degeneration could be clinically relevant for early detection of disc-related conditions. This approach may be particularly beneficial when MRI is contraindicated.</p><p><strong>Key points: </strong>A total of 612 intervertebral discs across 51 patients were retrospectively assessed with DECT, using MRI as a reference standard. DECT-based collagen maps allowed thoracic disc degeneration assessment achieving an overall 81% accuracy with good interrater agreement (ICC = 0.89). DECT-based collagen maps could be a good alternative in the case of contraindications to MRI.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11347509/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142056755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Non-invasive CT radiomic biomarkers predict microsatellite stability status in colorectal cancer: a multicenter validation study. 预测结直肠癌微卫星稳定性状态的无创 CT 放射生物标志物:一项多中心验证研究。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-08-26 DOI: 10.1186/s41747-024-00484-8
Zuhir Bodalal, Eun Kyoung Hong, Stefano Trebeschi, Ieva Kurilova, Federica Landolfi, Nino Bogveradze, Francesca Castagnoli, Giovanni Randon, Petur Snaebjornsson, Filippo Pietrantonio, Jeong Min Lee, Geerard Beets, Regina Beets-Tan

Background: Microsatellite instability (MSI) status is a strong predictor of response to immunotherapy of colorectal cancer. Radiogenomic approaches promise the ability to gain insight into the underlying tumor biology using non-invasive routine clinical images. This study investigates the association between tumor morphology and the status of MSI versus microsatellite stability (MSS), validating a novel radiomic signature on an external multicenter cohort.

Methods: Preoperative computed tomography scans with matched MSI status were retrospectively collected for 243 colorectal cancer patients from three hospitals: Seoul National University Hospital (SNUH); Netherlands Cancer Institute (NKI); and Fondazione IRCCS Istituto Nazionale dei Tumori, Milan Italy (INT). Radiologists delineated primary tumors in each scan, from which radiomic features were extracted. Machine learning models trained on SNUH data to identify MSI tumors underwent external validation using NKI and INT images. Performances were compared in terms of area under the receiving operating curve (AUROC).

Results: We identified a radiomic signature comprising seven radiomic features that were predictive of tumors with MSS or MSI (AUROC 0.69, 95% confidence interval [CI] 0.54-0.84, p = 0.018). Integrating radiomic and clinical data into an algorithm improved predictive performance to an AUROC of 0.78 (95% CI 0.60-0.91, p = 0.002) and enhanced the reliability of the predictions.

Conclusion: Differences in the radiomic morphological phenotype between tumors MSS or MSI could be detected using radiogenomic approaches. Future research involving large-scale multicenter prospective studies that combine various diagnostic data is necessary to refine and validate more robust, potentially tumor-agnostic MSI radiogenomic models.

Relevance statement: Noninvasive radiomic signatures derived from computed tomography scans can predict MSI in colorectal cancer, potentially augmenting traditional biopsy-based methods and enhancing personalized treatment strategies.

Key points: Noninvasive CT-based radiomics predicted MSI in colorectal cancer, enhancing stratification. A seven-feature radiomic signature differentiated tumors with MSI from those with MSS in multicenter cohorts. Integrating radiomic and clinical data improved the algorithm's predictive performance.

背景:微卫星不稳定性(MSI)状态是预测结直肠癌免疫疗法反应的重要指标。放射基因组学方法有望利用无创常规临床图像深入了解潜在的肿瘤生物学。本研究调查了肿瘤形态与 MSI 状态和微卫星稳定性(MSS)之间的关联,在外部多中心队列中验证了一种新型放射基因组特征:方法:回顾性收集了三家医院 243 名结直肠癌患者的术前计算机断层扫描图像,并与 MSI 状态相匹配:首尔国立大学医院(SNUH)、荷兰癌症研究所(NKI)和意大利米兰国家肿瘤研究所基金会(INT)。放射科医生在每次扫描中划定原发肿瘤,并从中提取放射学特征。使用 NKI 和 INT 图像对在 SNUH 数据上训练的机器学习模型进行外部验证,以识别 MSI 肿瘤。结果:结果:我们发现了一个由七个放射学特征组成的放射学特征,可预测MSS或MSI肿瘤(AUROC 0.69,95%置信区间[CI] 0.54-0.84,p = 0.018)。将放射学和临床数据整合到一个算法中可提高预测性能,AUROC 为 0.78 (95% CI 0.60-0.91, p = 0.002),并增强了预测的可靠性:结论:使用放射基因组学方法可以检测出MSS或MSI肿瘤在放射形态表型上的差异。未来的研究需要结合各种诊断数据进行大规模多中心前瞻性研究,以完善和验证更可靠、可能具有肿瘤诊断意义的 MSI 放射基因组模型:从计算机断层扫描中提取的无创放射基因组学特征可以预测结直肠癌中的 MSI,从而有可能增强基于活检的传统方法并加强个性化治疗策略:基于计算机断层扫描的无创放射组学可预测结直肠癌中的MSI,从而加强分层。在多中心队列中,七特征放射组学特征可将MSI肿瘤与MSS肿瘤区分开来。整合放射组学和临床数据提高了算法的预测性能。
{"title":"Non-invasive CT radiomic biomarkers predict microsatellite stability status in colorectal cancer: a multicenter validation study.","authors":"Zuhir Bodalal, Eun Kyoung Hong, Stefano Trebeschi, Ieva Kurilova, Federica Landolfi, Nino Bogveradze, Francesca Castagnoli, Giovanni Randon, Petur Snaebjornsson, Filippo Pietrantonio, Jeong Min Lee, Geerard Beets, Regina Beets-Tan","doi":"10.1186/s41747-024-00484-8","DOIUrl":"10.1186/s41747-024-00484-8","url":null,"abstract":"<p><strong>Background: </strong>Microsatellite instability (MSI) status is a strong predictor of response to immunotherapy of colorectal cancer. Radiogenomic approaches promise the ability to gain insight into the underlying tumor biology using non-invasive routine clinical images. This study investigates the association between tumor morphology and the status of MSI versus microsatellite stability (MSS), validating a novel radiomic signature on an external multicenter cohort.</p><p><strong>Methods: </strong>Preoperative computed tomography scans with matched MSI status were retrospectively collected for 243 colorectal cancer patients from three hospitals: Seoul National University Hospital (SNUH); Netherlands Cancer Institute (NKI); and Fondazione IRCCS Istituto Nazionale dei Tumori, Milan Italy (INT). Radiologists delineated primary tumors in each scan, from which radiomic features were extracted. Machine learning models trained on SNUH data to identify MSI tumors underwent external validation using NKI and INT images. Performances were compared in terms of area under the receiving operating curve (AUROC).</p><p><strong>Results: </strong>We identified a radiomic signature comprising seven radiomic features that were predictive of tumors with MSS or MSI (AUROC 0.69, 95% confidence interval [CI] 0.54-0.84, p = 0.018). Integrating radiomic and clinical data into an algorithm improved predictive performance to an AUROC of 0.78 (95% CI 0.60-0.91, p = 0.002) and enhanced the reliability of the predictions.</p><p><strong>Conclusion: </strong>Differences in the radiomic morphological phenotype between tumors MSS or MSI could be detected using radiogenomic approaches. Future research involving large-scale multicenter prospective studies that combine various diagnostic data is necessary to refine and validate more robust, potentially tumor-agnostic MSI radiogenomic models.</p><p><strong>Relevance statement: </strong>Noninvasive radiomic signatures derived from computed tomography scans can predict MSI in colorectal cancer, potentially augmenting traditional biopsy-based methods and enhancing personalized treatment strategies.</p><p><strong>Key points: </strong>Noninvasive CT-based radiomics predicted MSI in colorectal cancer, enhancing stratification. A seven-feature radiomic signature differentiated tumors with MSI from those with MSS in multicenter cohorts. Integrating radiomic and clinical data improved the algorithm's predictive performance.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11347521/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142056757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Automated peripheral nerve segmentation for MR-neurography. 用于磁共振神经成像的自动周围神经分割。
IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-08-26 DOI: 10.1186/s41747-024-00503-8
Nedim Christoph Beste, Johann Jende, Moritz Kronlage, Felix Kurz, Sabine Heiland, Martin Bendszus, Hagen Meredig

Background: Magnetic resonance neurography (MRN) is increasingly used as a diagnostic tool for peripheral neuropathies. Quantitative measures enhance MRN interpretation but require nerve segmentation which is time-consuming and error-prone and has not become clinical routine. In this study, we applied neural networks for the automated segmentation of peripheral nerves.

Methods: A neural segmentation network was trained to segment the sciatic nerve and its proximal branches on the MRN scans of the right and left upper leg of 35 healthy individuals, resulting in 70 training examples, via 5-fold cross-validation (CV). The model performance was evaluated on an independent test set of one-sided MRN scans of 60 healthy individuals.

Results: Mean Dice similarity coefficient (DSC) in CV was 0.892 (95% confidence interval [CI]: 0.888-0.897) with a mean Jaccard index (JI) of 0.806 (95% CI: 0.799-0.814) and mean Hausdorff distance (HD) of 2.146 (95% CI: 2.184-2.208). For the independent test set, DSC and JI were lower while HD was higher, with a mean DSC of 0.789 (95% CI: 0.760-0.815), mean JI of 0.672 (95% CI: 0.642-0.699), and mean HD of 2.118 (95% CI: 2.047-2.190).

Conclusion: The deep learning-based segmentation model showed a good performance for the task of nerve segmentation. Future work will focus on extending training data and including individuals with peripheral neuropathies in training to enable advanced peripheral nerve disease characterization.

Relevance statement: The results will serve as a baseline to build upon while developing an automated quantitative MRN feature analysis framework for application in routine reading of MRN examinations.

Key points: Quantitative measures enhance MRN interpretation, requiring complex and challenging nerve segmentation. We present a deep learning-based segmentation model with good performance. Our results may serve as a baseline for clinical automated quantitative MRN segmentation.

背景:磁共振神经成像(MRN)越来越多地被用作周围神经病的诊断工具。定量测量可提高 MRN 的解释能力,但需要进行神经分割,这既费时又容易出错,而且尚未成为临床常规。在这项研究中,我们应用神经网络自动分割周围神经:方法:通过 5 倍交叉验证(CV),对神经分割网络进行训练,以分割 35 名健康人左右上肢 MRN 扫描的坐骨神经及其近端分支,共获得 70 个训练实例。在 60 名健康人的单侧 MRN 扫描的独立测试集上对模型性能进行了评估:CV中的平均狄斯相似系数(DSC)为0.892(95%置信区间[CI]:0.888-0.897),平均雅卡德指数(JI)为0.806(95% CI:0.799-0.814),平均豪斯多夫距离(HD)为2.146(95% CI:2.184-2.208)。对于独立测试集,DSC 和 JI 较低,而 HD 较高,平均 DSC 为 0.789(95% CI:0.760-0.815),平均 JI 为 0.672(95% CI:0.642-0.699),平均 HD 为 2.118(95% CI:2.047-2.190):基于深度学习的分割模型在神经分割任务中表现良好。未来的工作将侧重于扩展训练数据,并将患有周围神经病的个体纳入训练,以实现高级周围神经疾病特征描述:这些结果将作为一个基线,在此基础上开发一个自动定量 MRN 特征分析框架,应用于 MRN 检查的常规读取:定量测量可增强 MRN 解释,但需要复杂且具有挑战性的神经分割。我们提出的基于深度学习的分割模型性能良好。我们的结果可作为临床自动定量 MRN 分段的基线。
{"title":"Automated peripheral nerve segmentation for MR-neurography.","authors":"Nedim Christoph Beste, Johann Jende, Moritz Kronlage, Felix Kurz, Sabine Heiland, Martin Bendszus, Hagen Meredig","doi":"10.1186/s41747-024-00503-8","DOIUrl":"10.1186/s41747-024-00503-8","url":null,"abstract":"<p><strong>Background: </strong>Magnetic resonance neurography (MRN) is increasingly used as a diagnostic tool for peripheral neuropathies. Quantitative measures enhance MRN interpretation but require nerve segmentation which is time-consuming and error-prone and has not become clinical routine. In this study, we applied neural networks for the automated segmentation of peripheral nerves.</p><p><strong>Methods: </strong>A neural segmentation network was trained to segment the sciatic nerve and its proximal branches on the MRN scans of the right and left upper leg of 35 healthy individuals, resulting in 70 training examples, via 5-fold cross-validation (CV). The model performance was evaluated on an independent test set of one-sided MRN scans of 60 healthy individuals.</p><p><strong>Results: </strong>Mean Dice similarity coefficient (DSC) in CV was 0.892 (95% confidence interval [CI]: 0.888-0.897) with a mean Jaccard index (JI) of 0.806 (95% CI: 0.799-0.814) and mean Hausdorff distance (HD) of 2.146 (95% CI: 2.184-2.208). For the independent test set, DSC and JI were lower while HD was higher, with a mean DSC of 0.789 (95% CI: 0.760-0.815), mean JI of 0.672 (95% CI: 0.642-0.699), and mean HD of 2.118 (95% CI: 2.047-2.190).</p><p><strong>Conclusion: </strong>The deep learning-based segmentation model showed a good performance for the task of nerve segmentation. Future work will focus on extending training data and including individuals with peripheral neuropathies in training to enable advanced peripheral nerve disease characterization.</p><p><strong>Relevance statement: </strong>The results will serve as a baseline to build upon while developing an automated quantitative MRN feature analysis framework for application in routine reading of MRN examinations.</p><p><strong>Key points: </strong>Quantitative measures enhance MRN interpretation, requiring complex and challenging nerve segmentation. We present a deep learning-based segmentation model with good performance. Our results may serve as a baseline for clinical automated quantitative MRN segmentation.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11347527/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142056756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
European Radiology Experimental
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1