Deep learning enabled ultra-fast-pitch acquisition in clinical X-ray computed tomography.
Deep learning enabled ultra-fast-pitch acquisition in clinical X-ray computed tomography.
复制标题
DOI：
10.1002/mp.15176
复制
发表时间：
2021-10
期刊：
影响因子：
3.8
通讯作者：
Yu L
中科院分区：
文献类型：
--
作者：
Gong H;Ren L;Hsieh SS;McCollough CH;Yu L
在X射线计算机断层扫描（CT）中，许多重要的临床应用可能受益于快速采集速度。螺旋扫描是临床CT中应用最广泛的采集模式，其中快速螺距可以提高采集速度。然而，在典型的单源螺旋CT（SSCT）系统上，螺距p通常不能超过1.5;否则，将由于数据不足而导致重建伪影。这项工作的目的是开发一个深度卷积神经网络（CNN），以纠正超快音高引起的伪影，这可以实现比目前更快的采集速度。开发了定制的CNN（表示为超快音高网络（UFP-net）），以从从具有超快音高的SSCT获取的伪影损坏的重建后数据恢复底层解剖结构（即，p ≥ 2）。UFP-net采用残差学习来捕获图像伪影的特征。UFP-net进一步部署了内部定制的功能块，包括空域局部算子和频域非局部算子，以探索多尺度特征表示。常规螺距设置（即，p < 1），用作训练和测试数据集。该患者队列涉及解剖结构（胸部、腹部和骨盆）和CT系统（Siemens Definition、Definition Flash、Definition AS+，Siemens Healthcare，Inc.）的不同扫描范围内的CT检查，并且相应的基本CT扫描协议使用主要扫描参数的一致设置（例如，准直和间距）。计算原始图像的前向投影，以合成具有一个规则螺距设置（p = 1）和两个超快速螺距设置（p = 2和3）的螺旋CT扫描。所有患者图像均采用标准滤波反投影（FBP）算法重建。提出了一种自定义的多阶段训练方案，以超快速基音图像为网络输入，规则基音图像为标签，逐步优化UFP网络的参数。进行目视检查以评价图像质量。采用结构相似性指数（SSIM）和相对均方根误差（rRMSE）作为定量质量指标。在超快音高设置下，UFP-net与标准FBP相比显著提高了图像质量。在p = 2时，与FBP（平均SSIM < 0.93;平均rRMSE > 9.1%）相比，UFP-net产生了更高的平均SSIM（> 0.98）和更低的平均rRMSE（< 2.9%）。p = 3时的定量指标：UFP-净-平均SSIM [0.86，0.94]和平均rRMSE [5.0%，8.2%]; FBP-平均SSIM [0.36，0.61]和平均rRMSE [36.0%，58.6%]。所提出的UFP-net具有在临床CT中实现超快速数据采集而不牺牲图像质量的潜力。当相应的CT检查涉及一致的基础扫描参数时，该方法在不同的身体部位上表现出合理的普遍性。
In X-raycomputed tomography (CT), many important clinical applications may benefit from a fast acquisition speed. The helical scan is the most widely used acquisition mode in clinical CT, where a fast helical pitch can improve the acquisition speed. However, on a typical single-source helical CT (SSCT) system, the helical pitch p typically cannot exceed 1.5; otherwise, reconstruction artifacts will result from data insufficiency. The purpose of this work is to develop a deep convolutional neural network (CNN) to correct for artifacts caused by an ultra-fast pitch, which can enable faster acquisition speed than what is currently achievable. A customized CNN (denoted as ultra-fast-pitch network (UFP-net)) was developed to restore the underlying anatomical structure from the artifact-corrupted post-reconstruction data acquired from SSCT with ultra-fast pitch (i.e., p ≥ 2). UFP-net employed residual learning to capture the features of image artifacts. UFP-net further deployed in-house-customized functional blocks with spatial-domain local operators and frequency-domain non-local operators, to explore multi-scale feature representation. Images of contrast-enhanced patient exams (n = 83) with routine pitch setting (i.e., p < 1) were retrospectively collected, which were used as training and testing datasets. This patient cohort involved CT exams over different scan ranges of anatomy (chest, abdomen, and pelvis) and CT systems (Siemens Definition, Definition Flash, Definition AS+, Siemens Healthcare, Inc.), and the corresponding base CT scanning protocols used consistent settings of major scan parameters (e.g., collimation and pitch). Forward projection of the original images was calculated to synthesize helical CT scans with one regular pitch setting (p = 1) and two ultra-fast-pitch setting (p = 2 and 3). All patient images were reconstructed using the standard filtered-back-projection (FBP) algorithm. A customized multi-stage training scheme was developed to incrementally optimize the parameters of UFP-net, using ultra-fast-pitch images as network inputs and regular pitch images as labels. Visual inspection was conducted to evaluate image quality. Structural similarity index (SSIM) and relative root-mean-square error (rRMSE) were used as quantitative quality metrics. The UFP-net dramatically improved image quality over standard FBP at both ultra-fast-pitch settings. At p = 2, UFP-net yielded higher mean SSIM (> 0.98) with lower mean rRMSE (< 2.9%), compared to FBP (mean SSIM < 0.93; mean rRMSE > 9.1%). Quantitative metrics at p = 3: UFP-net—mean SSIM [0.86, 0.94] and mean rRMSE [5.0%, 8.2%]; FBP—mean SSIM [0.36, 0.61] and mean rRMSE [36.0%, 58.6%]. The proposed UFP-net has the potential to enable ultra-fast data acquisition in clinical CT without sacrificing image quality. This method has demonstrated reasonable generalizability over different body parts when the corresponding CT exams involved consistent base scan parameters.
登录
查看更多内容
影响因子：
10.6
作者：
Jin, Kyong Hwan;McCann, Michael T.;Unser, Michael
通讯作者：
Unser, Michael
影响因子：
3.8
作者：
Flohr, TG;Stierstorfer, K;McCollough, CH
通讯作者：
McCollough, CH
影响因子：
5.4
作者：
Achenbach, Stephan;Boehmer, Kerstin;Marwan, Mohamed
通讯作者：
Marwan, Mohamed
影响因子：
6.2
作者：
Aydin, Tunc Ozan;Mantiuk, Rafal;Seidel, Hans-Peter
通讯作者：
Seidel, Hans-Peter
影响因子：
3.8
作者：
Gong H;Tao S;Rajendran K;Zhou W;McCollough CH;Leng S
通讯作者：
Leng S