基于深度学习重建欠采样MRI以缩短扫描时间:一项多中心回顾性队列研究
该多中心回顾性队列研究利用胶质母细胞瘤患者MRI数据开发深度卷积神经网络(dCNN),用于从高度欠采样的单线圈k空间数据重建MRI。在EORTC-26101独立测试集中,10倍加速重建的MRI与原图结构相似性中位数为0.92,肿瘤体积测量和进展时间评估与原图高度一致。作者认为深度学习重建可大幅缩短扫描时间并保持影像生物标志物准确性,尚待前瞻性验证。
要点
- dCNN可从R=2至15倍欠采样k空间数据重建MRI,EORTC-26101测试集中10倍加速SSIM中位数为0.92。
- 10倍加速重建MRI评估强化肿瘤体积的DICE中位数为0.89,体积差中位数0.01 cm³(0.21%)。
- 10倍加速重建与原图自动评估的进展时间中位数均为4.27个月,393例中374例(95.2%)进展时间一致。
核心结论
- 基于深度学习重建欠采样MRI可大幅缩短扫描时间,10倍加速显示良好图像质量并保持肿瘤治疗反应影像生物标志物的准确性。
- 作者指出该技术为开源软件,有望提高MRI可及性,但尚待进一步前瞻性验证。
研究设计与样本
- 多中心、回顾性、队列研究,使用海德堡大学医院775例胶质母细胞瘤患者775次检查、CORE试验260例患者1083次检查(58家机构)和CENTRIC试验505例患者3147次检查(139家机构)的MRI数据开发、训练和测试dCNN。
- 独立测试使用EORTC-26101试验528例胶质母细胞瘤患者1974次检查(32家机构)的MRI。
- 使用NYU Langone Health公开fastMRI脑部测试数据集558例患者558次检查验证dCNN从多线圈k空间数据重建MRI的泛化性和稳健性。
主要发现
- EORTC-26101测试集中,欠采样dCNN重建MRI的SSIM中位数在不同加速率下为0.88至0.99,10倍加速(R=10)为0.92(95%CI 0.92-0.93)。
- 10倍欠采样dCNN重建MRI评估强化肿瘤体积时与原图一致性优良:空间一致性DICE中位数0.89(95%CI 0.88-0.89),体积差中位数0.01 cm³(95%CI 0.00-0.03),相当于0.21%,等效性检验p=0.0036。
- 10倍欠采样dCNN重建MRI评估非强化肿瘤或水肿体积时与原图一致性优良:DICE中位数0.94(95%CI 0.94-0.95),体积差中位数-0.79 cm³(95%CI -0.87至-0.72),相当于-1.77%,等效性检验p=0.023。
- EORTC-26101测试集中,使用10倍欠采样dCNN重建或原图进行自动体积肿瘤反应评估,进展时间中位数均为4.27个月(95%CI 4.14-4.57),log-rank p=0.80;393例有数据患者中374例(95.2%)进展时间一致。
- dCNN在fastMRI脑部数据集中泛化良好,使用多线圈相比单线圈k空间数据时SSIM中位数显著改善(p<0.0001)。
关键数值与推荐
- EORTC-26101测试集10倍加速(R=10)重建MRI的SSIM中位数为0.92(95%CI 0.92-0.93)。
- 强化肿瘤体积DICE中位数0.89(95%CI 0.88-0.89),体积差中位数0.01 cm³(95%CI 0.00-0.03),相当于0.21%,等效性p=0.0036。
- 非强化肿瘤或水肿体积DICE中位数0.94(95%CI 0.94-0.95),体积差中位数-0.79 cm³(95%CI -0.87至-0.72),相当于-1.77%,等效性p=0.023。
- 10倍加速重建与原图自动评估进展时间中位数均为4.27个月(95%CI 4.14-4.57),log-rank p=0.80,393例中374例(95.2%)一致。
临床怎么用
- 原文结论指出深度学习重建欠采样MRI可大幅缩短扫描时间,10倍加速图像质量良好并保持肿瘤治疗反应影像生物标志物准确性。
- 作者指出该技术为开源软件,有望提高MRI可及性,但尚待进一步前瞻性验证。
局限性
- 原文在解释部分指出该技术尚待进一步前瞻性验证(pending further prospective validation)。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: The extended acquisition times required for MRI limit its availability in resource-constrained settings. Consequently, accelerating MRI by undersampling k-space data, which is necessary to reconstruct an image, has been a long-standing but important challenge. We aimed to develop a deep convolutional neural network (dCNN) optimisation method for MRI reconstruction and to reduce scan times and evaluate its effect on image quality and accuracy of oncological imaging biomarkers. METHODS: In this multicentre, retrospective, cohort study, MRI data from patients with glioblastoma treated at Heidelberg University Hospital (775 patients and 775 examinations) and from the phase 2 CORE trial (260 patients, 1083 examinations, and 58 institutions) and the phase 3 CENTRIC trial (505 patients, 3147 examinations, and 139 institutions) were used to develop, train, and test dCNN for reconstructing MRI from highly undersampled single-coil k-space data with various acceleration rates (R=2, 4, 6, 8, 10, and 15). Independent testing was performed with MRIs from the phase 2/3 EORTC-26101 trial (528 patients with glioblastoma, 1974 examinations, and 32 institutions). The similarity between undersampled dCNN-reconstructed and original MRIs was quantified with various image quality metrics, including structural similarity index measure (SSIM) and the accuracy of undersampled dCNN-reconstructed MRI on downstream radiological assessment of imaging biomarkers in oncology (automated artificial intelligence-based quantification of tumour burden and treatment response) was performed in the EORTC-26101 test dataset. The public NYU Langone Health fastMRI brain test dataset (558 patients and 558 examinations) was used to validate the generalisability and robustness of the dCNN for reconstructing MRIs from available multi-coil (parallel imaging) k-space data. FINDINGS: In the EORTC-26101 test dataset, the median SSIM of undersampled dCNN-reconstructed MRI ranged from 0·88 to 0·99 across different acceleration rates, with 0·92 (95% CI 0·92-0·93) for 10-times acceleration (R=10). The 10-times undersampled dCNN-reconstructed MRI yielded excellent agreement with original MRI when assessing volumes of contrast-enhancing tumour (median DICE for spatial agreement of 0·89 [95% CI 0·88 to 0·89]; median volume difference of 0·01 cm3 [95% CI 0·00 to 0·03] equalling 0·21%; p=0·0036 for equivalence) or non-enhancing tumour or oedema (median DICE of 0·94 [95% CI 0·94 to 0·95]; median volume difference of -0·79 cm3 [95% CI -0·87 to -0·72] equalling -1·77%; p=0·023 for equivalence) in the EORTC-26101 test dataset. Automated volumetric tumour response assessment in the EORTC-26101 test dataset yielded an identical median time to progression of 4·27 months (95% CI 4·14 to 4·57) when using 10-times-undersampled dCNN-reconstructed or original MRI (log-rank p=0·80) and agreement in the time to progression in 374 (95·2%) of 393 patients with data. The dCNN generalised well to the fastMRI brain dataset, with significant improvements in the median SSIM when using multi-coil compared with single-coil k-space data (p<0·0001). INTERPRETATION: Deep-learning-based reconstruction of undersampled MRI allows for a substantial reduction of scan times, with a 10-times acceleration demonstrating excellent image quality while preserving the accuracy of derived imaging biomarkers for the assessment of oncological treatment response. Our developments are available as open source software and hold considerable promise for increasing the accessibility to MRI, pending further prospective validation. FUNDING: Deutsche Forschungsgemeinschaft (German Research Foundation) and an Else Kröner Clinician Scientist Endowed Professorship by the Else Kröner Fresenius Foundation.
引用
- Rastogi A, Brugnara G, Foltyn-Dumitru M, et al. Deep-learning-based reconstruction of undersampled MRI to reduce scan times: a multicentre, retrospective, cohort study. Lancet Oncol. 2024. PMID: 38423052. doi:10.1016/S1470-2045(23)00641-1
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。