Real-Time Deep-Learning Image Reconstruction and Instrument Tracking in MR-Guided Biopsies.

IF 3.5 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Constant R Noordman, Lauren P W Te Molder, Marnix C Maas, Christiaan G Overduin, Jurgen J Fütterer, Henkjan J Huisman
{"title":"Real-Time Deep-Learning Image Reconstruction and Instrument Tracking in MR-Guided Biopsies.","authors":"Constant R Noordman, Lauren P W Te Molder, Marnix C Maas, Christiaan G Overduin, Jurgen J Fütterer, Henkjan J Huisman","doi":"10.1002/jmri.70138","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Transrectal in-bore MR-guided biopsy (MRGB) is accurate but time-consuming, limiting clinical throughput. Faster imaging could improve workflow and enable real-time instrument tracking. Existing acceleration methods often use simulated data and lack validation in clinical settings.</p><p><strong>Purpose: </strong>To accelerate MRGB by using deep learning for undersampled image reconstruction and instrument tracking, trained on multi-slice MR DICOM images and evaluated on raw k-space acquisitions.</p><p><strong>Study type: </strong>Prospective feasibility study.</p><p><strong>Population: </strong>Briefly, 1289 male patients (aged 44-87, median age 68) for model training, 8 male patients (aged 59-78, median age 65) for prospective feasibility testing.</p><p><strong>Field strength/sequence: </strong>2D Cartesian balanced steady-state free precession, 3 T.</p><p><strong>Assessment: </strong>Segmentation and reconstruction models were trained on 8464 MRGB confirmation scans containing a biopsy needle guide instrument and evaluated on 10 prospectively acquired dynamic k-space samples. Needle guide tracking accuracy was assessed using instrument tip prediction (ITP) error, computed per frame as the Euclidean distance from reference positions defined via pre- and post-movement scans. Feasibility was measured by the proportion of frames with < 5 mm error. Additional experiments tested model robustness under increasing undersampling rates.</p><p><strong>Statistical tests: </strong>In a segmentation validation experiment, a one-sample t-test tested if the mean ITP error was below 5 mm. Statistical significance was defined as p < 0.05. In the tracking experiments, the mean, standard deviation, and Wilson 95% CI of the ITP success rate were computed per sample, across undersampling levels.</p><p><strong>Results: </strong>ITP was first evaluated independently on 201 fully sampled scans, yielding an ITP error of 1.55 ± 1.01 mm (95% CI: 1.41-1.69). Tracking performance was assessed across increasing undersampling factors, achieving high ITP success rates from 97.5% ± 5.8% (68.8%-99.9%) at 8× up to 92.5% ± 10.3% (62.5%-98.9%) at 16× undersampling. Performance declined at 18×, dropping to 74.6% ± 33.6% (43.8%-91.7%).</p><p><strong>Data conclusion: </strong>Results confirm stable needle guide tip prediction accuracy and support the robustness of the reconstruction model for tracking at high undersampling.</p><p><strong>Evidence level: </strong>2.</p><p><strong>Technical efficacy: </strong>Stage 2.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.5000,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Magnetic Resonance Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/jmri.70138","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Transrectal in-bore MR-guided biopsy (MRGB) is accurate but time-consuming, limiting clinical throughput. Faster imaging could improve workflow and enable real-time instrument tracking. Existing acceleration methods often use simulated data and lack validation in clinical settings.

Purpose: To accelerate MRGB by using deep learning for undersampled image reconstruction and instrument tracking, trained on multi-slice MR DICOM images and evaluated on raw k-space acquisitions.

Study type: Prospective feasibility study.

Population: Briefly, 1289 male patients (aged 44-87, median age 68) for model training, 8 male patients (aged 59-78, median age 65) for prospective feasibility testing.

Field strength/sequence: 2D Cartesian balanced steady-state free precession, 3 T.

Assessment: Segmentation and reconstruction models were trained on 8464 MRGB confirmation scans containing a biopsy needle guide instrument and evaluated on 10 prospectively acquired dynamic k-space samples. Needle guide tracking accuracy was assessed using instrument tip prediction (ITP) error, computed per frame as the Euclidean distance from reference positions defined via pre- and post-movement scans. Feasibility was measured by the proportion of frames with < 5 mm error. Additional experiments tested model robustness under increasing undersampling rates.

Statistical tests: In a segmentation validation experiment, a one-sample t-test tested if the mean ITP error was below 5 mm. Statistical significance was defined as p < 0.05. In the tracking experiments, the mean, standard deviation, and Wilson 95% CI of the ITP success rate were computed per sample, across undersampling levels.

Results: ITP was first evaluated independently on 201 fully sampled scans, yielding an ITP error of 1.55 ± 1.01 mm (95% CI: 1.41-1.69). Tracking performance was assessed across increasing undersampling factors, achieving high ITP success rates from 97.5% ± 5.8% (68.8%-99.9%) at 8× up to 92.5% ± 10.3% (62.5%-98.9%) at 16× undersampling. Performance declined at 18×, dropping to 74.6% ± 33.6% (43.8%-91.7%).

Data conclusion: Results confirm stable needle guide tip prediction accuracy and support the robustness of the reconstruction model for tracking at high undersampling.

Evidence level: 2.

Technical efficacy: Stage 2.

磁共振引导活检中的实时深度学习图像重建和仪器跟踪。
背景:经直肠腔内磁共振引导活检(MRGB)准确但耗时,限制了临床吞吐量。更快的成像可以改善工作流程并实现实时仪器跟踪。现有的加速方法通常使用模拟数据,缺乏临床验证。目的:通过使用深度学习进行欠采样图像重建和仪器跟踪,对多层MR DICOM图像进行训练,并对原始k空间获取进行评估,从而加速MRGB。研究类型:前瞻性可行性研究。人群:简而言之,1289例男性患者(年龄44-87岁,中位年龄68岁)进行模型训练,8例男性患者(年龄59-78岁,中位年龄65岁)进行前瞻性可行性测试。场强/序列:二维笛卡尔平衡稳态自由进动,3t。评估:分割和重建模型在8464个包含活检针导仪的MRGB确认扫描上进行训练,并在10个前瞻性获取的动态k空间样本上进行评估。使用仪器尖端预测(ITP)误差来评估针导跟踪精度,该误差以每帧计算,作为通过运动前后扫描定义的参考位置的欧几里德距离。可行性通过帧的比例进行统计检验来衡量:在分割验证实验中,采用单样本t检验来检验平均ITP误差是否小于5 mm。结果:ITP首先在201次全采样扫描中独立评估,ITP误差为1.55±1.01 mm (95% CI: 1.41-1.69)。跟踪性能通过增加欠采样因子进行评估,获得高ITP成功率,从8倍的97.5%±5.8%(68.8%-99.9%)到16倍的92.5%±10.3%(62.5%-98.9%)。业绩下降18倍,降至74.6%±33.6%(43.8%-91.7%)。数据结论:结果证实了稳定的针尖预测精度,并支持重建模型在高欠采样情况下的鲁棒性跟踪。证据等级:2。技术功效:第二阶段。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
9.70
自引率
6.80%
发文量
494
审稿时长
2 months
期刊介绍: The Journal of Magnetic Resonance Imaging (JMRI) is an international journal devoted to the timely publication of basic and clinical research, educational and review articles, and other information related to the diagnostic applications of magnetic resonance.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信