Dataset Information

Automatic Inter-Frame Patient Motion Correction for Dynamic Cardiac PET Using Deep Learning.

ABSTRACT: Patient motion during dynamic PET imaging can induce errors in myocardial blood flow (MBF) estimation. Motion correction for dynamic cardiac PET is challenging because the rapid tracer kinetics of 82Rb leads to substantial tracer distribution change across different dynamic frames over time, which can cause difficulties for image registration-based motion correction, particularly for early dynamic frames. In this paper, we developed an automatic deep learning-based motion correction (DeepMC) method for dynamic cardiac PET. In this study we focused on the detection and correction of inter-frame rigid translational motion caused by voluntary body movement and pattern change of respiratory motion. A bidirectional-3D LSTM network was developed to fully utilize both local and nonlocal temporal information in the 4D dynamic image data for motion detection. The network was trained and evaluated over motion-free patient scans with simulated motion so that the motion ground-truths are available, where one million samples based on 65 patient scans were used in training, and 600 samples based on 20 patient scans were used in evaluation. The proposed method was also evaluated using additional 10 patient datasets with real motion. We demonstrated that the proposed DeepMC obtained superior performance compared to conventional registration-based methods and other convolutional neural networks (CNN), in terms of motion estimation and MBF quantification accuracy. Once trained, DeepMC is much faster than the registration-based methods and can be easily integrated into the clinical workflow. In the future work, additional investigation is needed to evaluate this approach in a clinical context with realistic patient motion.

SUBMITTER: Shi L

PROVIDER: S-EPMC8670362 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposePatient motion during PET acquisition may affect measured time-activity curves, thereby reducing accuracy of tracer kinetic analyses. The aim of the present study was to evaluate different off-line frame-by-frame methods to correct patient motion, which is of particular interest when no optical motion tracking system is available or when older data sets have to be reanalysed.MethodsFour different motion correction methods were evaluated. In the first method attenuation-corrected frames were realigned with the summed image of the first 3 min. The second method was identical, except that non-attenuation-corrected images were used. In the third and fourth methods non-attenuation-corrected images were realigned with standard and cupped transmission images, respectively. Two simulation studies were performed, based on [11C]flumazenil and (R)-[11C]PK11195 data sets, respectively. For both simulation studies different types (rotational, translational) and degrees of motion were added. Simulated PET scans were corrected for motion using all correction methods. The optimal method derived from these simulation studies was used to evaluate two (one with and one without visible movement) clinical data sets of [11C]flumazenil, (R)-[11C]PK11195 and [11C]PIB. For these clinical data sets, the volume of distribution (VT) was derived using Logan analysis and values were compared before and after motion correction.ResultsFor both [11C]flumazenil and (R)-[11C]PK11195 simulation studies, optimal results were obtained when realignment was based on non-attenuation-corrected images. For the clinical data sets motion disappeared visually after motion correction. Regional differences of up to 433% in VT before and after motion correction were found for scans with visible movement. On the other hand, when no visual motion was present in the original data set, overall differences in VT before and after motion correction were <1.5 ± 1.3%.ConclusionFrame-by-frame motion correction using non-attenuation-corrected images improves the accuracy of tracer kinetic analysis compared to non-motion-corrected data. Electronic supplementary material The online version of this article (doi:10.1007/s00259-009-1193-y) contains supplementary material, which is available to authorised users.

Project description:BackgroundA variety of external factors might seriously degrade PET image quality and lead to inconsistent results. The aim of this study is to explore a potential PET image quality assessment (QA) method with deep learning (DL).MethodsA total of 89 PET images were acquired from Peking Union Medical College Hospital (PUMCH) in China in this study. Ground-truth quality for images was assessed by two senior radiologists and classified into five grades (grade 1, grade 2, grade 3, grade 4, and grade 5). Grade 5 is the best image quality. After preprocessing, the Dense Convolutional Network (DenseNet) was trained to automatically recognize optimal- and poor-quality PET images. Accuracy (ACC), sensitivity, specificity, receiver operating characteristic curve (ROC), and area under the ROC Curve (AUC) were used to evaluate the diagnostic properties of all models. All indicators of models were assessed using fivefold cross-validation. An image quality QA tool was developed based on our deep learning model. A PET QA report can be automatically obtained after inputting PET images.ResultsFour tasks were generated. Task2 showed worst performance in AUC,ACC, specificity and sensitivity among 4 tasks, and task1 showed unstable performance between training and testing and task3 showed low specificity in both training and testing. Task 4 showed the best diagnostic properties and discriminative performance between poor image quality (grade 1, grade 2) and good quality (grade 3, grade 4, grade 5) images. The automated quality assessment of task 4 showed ACC = 0.77, specificity = 0.71, and sensitivity = 0.83, in the train set; ACC = 0.85, specificity = 0.79, and sensitivity = 0.91, in the test set, respectively. The ROC measuring performance of task 4 had an AUC of 0.86 in the train set and 0.91 in the test set. The image QA tool could output basic information of images, scan and reconstruction parameters, typical instances of PET images, and deep learning score.ConclusionsThis study highlights the feasibility of the assessment of image quality in PET images using a deep learning model, which may assist with accelerating clinical research by reliably assessing image quality.

Project description:Study objectivesDevelopment of inter-database generalizable sleep staging algorithms represents a challenge due to increased data variability across different datasets. Sharing data between different centers is also a problem due to potential restrictions due to patient privacy protection. In this work, we describe a new deep learning approach for automatic sleep staging, and address its generalization capabilities on a wide range of public sleep staging databases. We also examine the suitability of a novel approach that uses an ensemble of individual local models and evaluate its impact on the resulting inter-database generalization performance.MethodsA general deep learning network architecture for automatic sleep staging is presented. Different preprocessing and architectural variant options are tested. The resulting prediction capabilities are evaluated and compared on a heterogeneous collection of six public sleep staging datasets. Validation is carried out in the context of independent local and external dataset generalization scenarios.ResultsBest results were achieved using the CNN_LSTM_5 neural network variant. Average prediction capabilities on independent local testing sets achieved 0.80 kappa score. When individual local models predict data from external datasets, average kappa score decreases to 0.54. Using the proposed ensemble-based approach, average kappa performance on the external dataset prediction scenario increases to 0.62. To our knowledge this is the largest study by the number of datasets so far on validating the generalization capabilities of an automatic sleep staging algorithm using external databases.ConclusionsValidation results show good general performance of our method, as compared with the expected levels of human agreement, as well as to state-of-the-art automatic sleep staging methods. The proposed ensemble-based approach enables flexible and scalable design, allowing dynamic integration of local models into the final ensemble, preserving data locality, and increasing generalization capabilities of the resulting system at the same time.

Project description:PET imaging of nonhuman primates (NHPs) requires correction of head motion if the subjects are scanned awake and their heads are unrestrained, because the NHPs move their heads faster and more frequently than human subjects. This work focuses on designing and validating 2 motion-correction algorithms for awake NHP brain PET imaging.Two motion-correction methods were implemented for awake NHP brain PET imaging: multiacquisition frame (MAF) and event-by-event (EBE). Motion data were acquired from an external motion-tracking device. The MAF method divides scan data into short subframes, reconstructs each subframe individually, and registers them to a reference orientation. This method suffers from residual intraframe motion and data loss when motion is large because a minimum frame duration is often required. The EBE method, previously implemented for a human brain scanner and adapted for a small-animal PET scanner in this work, eliminates intraframe motion and should have a best accuracy. We first evaluated the accuracy of both motion-correction methods with moving phantom scans. Both motion-correction methods were then applied to awake NHP brain PET studies with a gamma-aminobutyric acid A-benzodiazepine receptor ligand, (11)C-flumazenil, and the reconstructed images were compared with those from a motion-free anesthetized study.The phantom studies showed that EBE motion correction recovers the contrast (within 3%) similarly to the static study, whereas MAF motion correction using the standard algorithm setting showed a 25% reduction in contrast from the static case. In awake NHP brain PET imaging, EBE motion correction better recovers the fine structures than the MAF method, as compared with anesthetized studies.The large magnitude and frequency of NHP head motion suggests that EBE motion correction with accurate externally measured motion data can noticeably alleviate image blurring due to the intraframe motion in the MAF motion-correction method.

Project description:Background Cardiac MRI is limited by long acquisition times, yet faster acquisition of smaller-matrix images reduces spatial detail. Deep learning (DL) might enable both faster acquisition and higher spatial detail via super-resolution. Purpose To explore the feasibility of using DL to enhance spatial detail from small-matrix MRI acquisitions and evaluate its performance against that of conventional image upscaling methods. Materials and Methods Short-axis cine cardiac MRI examinations performed between January 2012 and December 2018 at one institution were retrospectively collected for algorithm development and testing. Convolutional neural networks (CNNs), a form of DL, were trained to perform super resolution in image space by using synthetically generated low-resolution data. There were 70%, 20%, and 10% of examinations allocated to training, validation, and test sets, respectively. CNNs were compared against bicubic interpolation and Fourier-based zero padding by calculating the structural similarity index (SSIM) between high-resolution ground truth and each upscaling method. Means and standard deviations of the SSIM were reported, and statistical significance was determined by using the Wilcoxon signed-rank test. For evaluation of clinical performance, left ventricular volumes were measured, and statistical significance was determined by using the paired Student t test. Results For CNN training and retrospective analysis, 400 MRI scans from 367 patients (mean age, 48 years ± 18; 214 men) were included. All CNNs outperformed zero padding and bicubic interpolation at upsampling factors from two to 64 (P < .001). CNNs outperformed zero padding on more than 99.2% of slices (9828 of 9907). In addition, 10 patients (mean age, 51 years ± 22; seven men) were prospectively recruited for super-resolution MRI. Super-resolved low-resolution images yielded left ventricular volumes comparable to those from full-resolution images (P > .05), and super-resolved full-resolution images appeared to further enhance anatomic detail. Conclusion Deep learning outperformed conventional upscaling methods and recovered high-frequency spatial information. Although training was performed only on short-axis cardiac MRI examinations, the proposed strategy appeared to improve quality in other imaging planes. © RSNA, 2020 Online supplemental material is available for this article.

Project description:The authors aimed to develop an image-based registration scheme to detect and correct patient motion in stress and rest cardiac positron emission tomography (PET)/CT images. The patient motion correction was of primary interest and the effects of patient motion with the use of flurpiridaz F 18 and (82)Rb were demonstrated.The authors evaluated stress/rest PET myocardial perfusion imaging datasets in 30 patients (60 datasets in total, 21 male and 9 female) using a new perfusion agent (flurpiridaz F 18) (n = 16) and (82)Rb (n = 14), acquired on a Siemens Biograph-64 scanner in list mode. Stress and rest images were reconstructed into 4 ((82)Rb) or 10 (flurpiridaz F 18) dynamic frames (60 s each) using standard reconstruction (2D attenuation weighted ordered subsets expectation maximization). Patient motion correction was achieved by an image-based registration scheme optimizing a cost function using modified normalized cross-correlation that combined global and local features. For comparison, visual scoring of motion was performed on the scale of 0 to 2 (no motion, moderate motion, and large motion) by two experienced observers.The proposed registration technique had a 93% success rate in removing left ventricular motion, as visually assessed. The maximum detected motion extent for stress and rest were 5.2 mm and 4.9 mm for flurpiridaz F 18 perfusion and 3.0 mm and 4.3 mm for (82)Rb perfusion studies, respectively. Motion extent (maximum frame-to-frame displacement) obtained for stress and rest were (2.2 ± 1.1, 1.4 ± 0.7, 1.9 ± 1.3) mm and (2.0 ± 1.1, 1.2 ±0 .9, 1.9 ± 0.9) mm for flurpiridaz F 18 perfusion studies and (1.9 ± 0.7, 0.7 ± 0.6, 1.3 ± 0.6) mm and (2.0 ± 0.9, 0.6 ± 0.4, 1.2 ± 1.2) mm for (82)Rb perfusion studies, respectively. A visually detectable patient motion threshold was established to be ≥2.2 mm, corresponding to visual user scores of 1 and 2. After motion correction, the average increases in contrast-to-noise ratio (CNR) from all frames for larger than the motion threshold were 16.2% in stress flurpiridaz F 18 and 12.2% in rest flurpiridaz F 18 studies. The average increases in CNR were 4.6% in stress (82)Rb studies and 4.3% in rest (82)Rb studies.Fully automatic motion correction of dynamic PET frames can be performed accurately, potentially allowing improved image quantification of cardiac PET data.

Dataset Information

Automatic Inter-Frame Patient Motion Correction for Dynamic Cardiac PET Using Deep Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets