当前位置: X-MOL 学术Phys. Med. Biol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Single patient convolutional neural networks for real-time MR reconstruction: coherent low-resolution versus incoherent undersampling.
Physics in Medicine & Biology ( IF 3.3 ) Pub Date : 2020-03-05 , DOI: 10.1088/1361-6560/ab7d13
Bryson Dietz 1 , Jihyun Yun , Eugene Yip , Zsolt Gabos , B Gino Fallone , Keith Wachowicz
Affiliation  

Accelerated MRI involves undersampling k-space, creating unwanted artifacts when reconstructing the data. While the strategy of incoherent k-space acquisition is proven for techniques such as compressed sensing, it may not be optimal for all techniques. This study compares the use of coherent low-resolution (coherent-LR) and incoherent undersampling phase-encoding for real-time 3D CNN image reconstruction. Data were acquired with our 3 T Philips Achieva system. A retrospective analysis was performed on six non-small cell lung cancer patients who received dynamic acquisitions consisting of 650 free breathing images using a bSSFP sequence. We retrospectively undersampled the data by 5x and 10x acceleration using the two phase-encoding schemes. A quantitative analysis was conducted evaluating the tumor segmentations from the CNN reconstructed data using the Dice coefficient (DC) and centroid displacement. The reconstruction noise was evaluated using the structural similarity index (SSIM). Furthermore, we qualitatively investigated the CNN reconstruction using prospectively undersampled data, where the fully sampled training data set is acquired separately from the accelerated undersampled data. The patient averaged DC, centroid displacement, and SSIM for the tumor segmentation at 5x and 10x was superior using coherent low-resolution undersampling. Furthermore, the patient-specific CNN can be trained in under 6 h and the reconstruction time was 54 ms per image. Both the incoherent and coherent-LR prospective CNN reconstructions yielded qualitatively acceptable images; however, the coherent-LR reconstruction appeared superior to the incoherent reconstruction. We have demonstrated that coherent-LR undersampling for real-time CNN image reconstruction performs quantitatively better for the retrospective case of lung tumor segmentation, and qualitatively better for the prospective case. The tumor segmentation mean DC increased for all six patients at 5x acceleration and the temporal (dynamic) variance of the segmentation was reduced. The reconstruction speed achieved for our current implementation was 54 ms, providing an acceptable frame rate for real-time on-the-fly MR imaging.

中文翻译:

用于实时MR重建的单患者卷积神经网络:相干低分辨率与不相干欠采样。

加速MRI涉及对k空间的欠采样,在重建数据时会产生不必要的伪影。尽管非相干k空间获取策略已针对诸如压缩感测之类的技术进行了验证,但它可能并非对所有技术都是最佳的。这项研究比较了使用相干低分辨率(coherent-LR)和不相干欠采样相位编码进行实时3D CNN图像重建的情况。数据是通过我们的3 T Philips Achieva系统获取的。对六名非小细胞肺癌患者进行了回顾性分析,这些患者使用bSSFP序列获得了由650次自由呼吸图像组成的动态采集。我们使用两种相位编码方案以5倍和10倍加速度对数据进行追溯欠采样。进行了定量分析,使用Dice系数(DC)和质心位移从CNN重建数据评估了肿瘤分割。使用结构相似性指数(SSIM)评估重建噪声。此外,我们使用预期的欠采样数据定性地研究了CNN重建,其中完全采样的训练数据集与加速的欠采样数据分开获得。使用相干的低分辨率欠采样,患者在5倍和10倍的肿瘤分割下的平均DC,质心位移和SSIM均好。此外,可以在6小时内训练患者特定的CNN,每张图像的重建时间为54毫秒。非相干和相干LR前瞻性CNN重建均产生了定性可接受的图像。然而,相干LR重建似乎优于非相干重建。我们已经证明,用于实时CNN图像重建的相干LR欠采样在回顾性肺肿瘤分割情况下在定量上表现更好,在定性情况下在质量上更好。所有六位患者的肿瘤分割平均DC均以5倍的加速度增加,并且分割的时间(动态)方差减小。当前实现的重建速度为54 ms,为实时实时MR成像提供了可接受的帧速率。从质量上来说,对预期的情况更好。所有六位患者的肿瘤分割平均DC均以5倍的加速度增加,并且分割的时间(动态)方差减小。当前实现的重建速度为54 ms,为实时实时MR成像提供了可接受的帧速率。从质量上来说,对预期的情况更好。所有六位患者的肿瘤分割平均DC均以5倍的加速度增加,并且分割的时间(动态)方差减小。当前实现的重建速度为54 ms,为实时实时MR成像提供了可接受的帧速率。
更新日期:2020-04-24
down
wechat
bug