Deformation-encoding Deep Learning Transformer for High-Frame-Rate Cardiac Cine MRI.

Purpose To develop a deep learning model for increasing cardiac cine frame rate while maintaining spatial resolution and scan time. Materials and Methods A transformer-based model was trained and tested on a retrospective sample of cine images from 5840 patients (mean age, 55 years ± 19 [SD]; 3527 male patients) referred for clinical cardiac MRI from 2003 to 2021 at nine centers; images were acquired using 1.5- and 3-T scanners from three vendors. Data from three centers were used for training and testing (4:1 ratio). The remaining data were used for external testing. Cines with downsampled frame rates were restored using linear, bicubic, and model-based interpolation. The root mean square error between interpolated and original cine images was modeled using ordinary least squares regression. In a prospective study of 49 participants referred for clinical cardiac MRI (mean age, 56 years ± 13; 25 male participants) and 12 healthy participants (mean age, 51 years ± 16; eight male participants), the model was applied to cines acquired at 25 frames per second (fps), thereby doubling the frame rate, and these interpolated cines were compared with actual 50-fps cines. The preference of two readers based on perceived temporal smoothness and image quality was evaluated using a noninferiority margin of 10%. Results The model generated artifact-free interpolated images. Ordinary least squares regression analysis accounting for vendor and field strength showed lower error (P < .001) with model-based interpolation compared with linear and bicubic interpolation in internal and external test sets. The highest proportion of reader choices was "no preference" (84 of 122) between actual and interpolated 50-fps cines. The 90% CI for the difference between reader proportions favoring collected (15 of 122) and interpolated (23 of 122) high-frame-rate cines was -0.01 to 0.14, indicating noninferiority. Conclusion A transformer-based deep learning model increased cardiac cine frame rates while preserving both spatial resolution and scan time, resulting in images with quality comparable to that of images obtained at actual high frame rates. Keywords: Functional MRI, Heart, Cardiac, Deep Learning, High Frame Rate Supplemental material is available for this article. © RSNA, 2024.

Highly accelerated free-breathing real-time myocardial tagging for exercise cardiovascular magnetic resonance.

BACKGROUND: Exercise cardiovascular magnetic resonance (Ex-CMR) myocardial tagging would enable quantification of myocardial deformation after exercise. However, current electrocardiogram (ECG)-segmented sequences are limited for Ex-CMR. METHODS: We developed a highly accelerated balanced steady-state free-precession real-time tagging technique for 3 T. A 12-fold acceleration was achieved using incoherent sixfold random Cartesian sampling, twofold truncated outer phase encoding, and a deep learning resolution enhancement model. The technique was tested in two prospective studies. In a rest study of 27 patients referred for clinical CMR and 19 healthy subjects, a set of ECG-segmented for comparison and two sets of real-time tagging images for repeatability assessment were collected in 2-chamber and short-axis views with spatiotemporal resolution 2.0 × 2.0 mm2 and 29 ms. In an Ex-CMR study of 26 patients with known or suspected cardiac disease and 23 healthy subjects, real-time images were collected before and after exercise. Deformation was quantified using measures of short-axis global circumferential strain (GCS). Two experienced CMR readers evaluated the image quality of all real-time data pooled from both studies using a 4-point Likert scale for tagline quality (1-excellent; 2-good; 3-moderate; 4-poor) and artifact level (1-none; 2-minimal; 3-moderate; 4-significant). Statistical evaluation included Pearson correlation coefficient (r), intraclass correlation coefficient (ICC), and coefficient of variation (CoV). RESULTS: In the rest study, deformation was successfully quantified in 90% of cases. There was a good correlation (r = 0.71) between ECG-segmented and real-time measures of GCS, and repeatability was good to excellent (ICC = 0.86 [0.71, 0.94]) with a CoV of 4.7%. In the Ex-CMR study, deformation was successfully quantified in 96% of subjects pre-exercise and 84% of subjects post-exercise. Short-axis and 2-chamber tagline quality were 1.6 ± 0.7 and 1.9 ± 0.8 at rest and 1.9 ± 0.7 and 2.5 ± 0.8 after exercise, respectively. Short-axis and 2-chamber artifact level was 1.2 ± 0.5 and 1.4 ± 0.7 at rest and 1.3 ± 0.6 and 1.5 ± 0.8 post-exercise, respectively. CONCLUSION: We developed a highly accelerated real-time tagging technique and demonstrated its potential for Ex-CMR quantification of myocardial deformation. Further studies are needed to assess the clinical utility of our technique.

Accelerated Cardiac MRI Cine with Use of Resolution Enhancement Generative Adversarial Inline Neural Network.

Background Cardiac cine can benefit from deep learning-based image reconstruction to reduce scan time and/or increase spatial and temporal resolution. Purpose To develop and evaluate a deep learning model that can be combined with parallel imaging or compressed sensing (CS). Materials and Methods The deep learning model was built on the enhanced super-resolution generative adversarial inline neural network, trained with use of retrospectively identified cine images and evaluated in participants prospectively enrolled from September 2021 to September 2022. The model was applied to breath-hold electrocardiography (ECG)-gated segmented and free-breathing real-time cine images collected with reduced spatial resolution with use of generalized autocalibrating partially parallel acquisitions (GRAPPA) or CS. The deep learning model subsequently restored spatial resolution. For comparison, GRAPPA-accelerated cine images were collected. Diagnostic quality and artifacts were evaluated by two readers with use of Likert scales and compared with use of Wilcoxon signed-rank tests. Agreement for left ventricle (LV) function, volume, and strain was assessed with Bland-Altman analysis. Results The deep learning model was trained on 1616 patients (mean age ± SD, 56 years ± 16; 920 men) and evaluated in 181 individuals, 126 patients (mean age, 57 years ± 16; 77 men) and 55 healthy subjects (mean age, 27 years ± 10; 15 men). In breath-hold ECG-gated segmented cine and free-breathing real-time cine, the deep learning model and GRAPPA showed similar diagnostic quality scores (2.9 vs 2.9, P = .41, deep learning vs GRAPPA) and artifact score (4.4 vs 4.3, P = .55, deep learning vs GRAPPA). Deep learning acquired more sections per breath-hold than GRAPPA (3.1 vs one section, P < .001). In free-breathing real-time cine, the deep learning showed a similar diagnostic quality score (2.9 vs 2.9, P = .21, deep learning vs GRAPPA) and lower artifact score (3.9 vs 4.3, P < .001, deep learning vs GRAPPA). For both sequences, the deep learning model showed excellent agreement for LV parameters, with near-zero mean differences and narrow limits of agreement compared with GRAPPA. Conclusion Deep learning-accelerated cardiac cine showed similarly accurate quantification of cardiac function, volume, and strain to a standardized parallel imaging method. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Vannier and Wang in this issue.

Spatiotemporal Free-Form Registration Method Assisted by a Minimum Spanning Tree During Discontinuous Transformations.

The sliding motion along the boundaries of discontinuous regions has been actively studied in B-spline free-form deformation framework. This study focusses on the sliding motion for a velocity field-based 3D+t registration. The discontinuity of the tangent direction guides the deformation of the object region, and a separate control of two regions provides a better registration accuracy. The sliding motion under the velocity field-based transformation is conducted under the [Formula: see text]-Rényi entropy estimator using a minimum spanning tree (MST) topology. Moreover, a new topology changing method of the MST is proposed. The topology change is performed as follows: inserting random noise, constructing the MST, and removing random noise while preserving a local connection consistency of the MST. This random noise process (RNP) prevents the [Formula: see text]-Rényi entropy-based registration from degrading in sliding motion, because the RNP creates a small disturbance around special locations. Experiments were performed using two publicly available datasets: the DIR-Lab dataset, which consists of 4D pulmonary computed tomography (CT) images, and a benchmarking framework dataset for cardiac 3D ultrasound. For the 4D pulmonary CT images, RNP produced a significantly improved result for the original MST with sliding motion (p<0.05). For the cardiac 3D ultrasound dataset, only a discontinuity-based registration indicated activity of the RNP. In contrast, the single MST without sliding motion did not show any improvement. These experiments proved the effectiveness of the RNP for sliding motion.

Topological recovery for non-rigid 2D/3D registration of coronary artery models.

BACKGROUND AND OBJECTIVE: Intra-operative X-ray angiography, the current standard method for visualizing and diagnosing cardiovascular disease, is limited in its ability to provide essential 3D information. These limitations are disadvantages in treating patients. For example, it is a cause of lowering the success rate of interventional procedures. Here, we propose a novel 2D-3D non-rigid registration method to understand vascular geometry during percutaneous coronary intervention. METHODS: The proposed method uses the local bijection pair distance as a cost function to minimize the effect of inconsistencies from center-line extraction. Moreover, novel cage-based 3D deformation and multi-threaded particle swarm optimization are utilized to implement real-time registration. We evaluated the proposed method for 154 examinations from 10 anonymous patients by coverage percentage, comparing the average distance of the 2D extracted center-line with that of the registered 3D center-line. RESULTS: The proposed 2D-3D non-rigid registration method achieved an average distance of 1.98 mm with a 0.54 s computation time. Additionally, in aiming to reduce the uncertainty of XA images, we used the proposed method to retrospectively visualize the connections between 2D vascular segments and the distal part of occlusions. CONCLUSIONS: Ultimately, the proposed 2D/3D non-rigid registration method can successfully register the 3D center-line of coronary arteries with corresponding 2D XA images, and is computationally sufficient for online usage. Therefore, this method can improve the success rate of such procedures as a percutaneous coronary intervention and provide the information necessary to diagnose cardiovascular diseases better.

A Patient-Specific 3Dt Coronary Artery Motion Modeling Method Using Hierarchical Deformation with Electrocardiogram.

Cardiovascular-related diseases are one of the leading causes of death worldwide. An understanding of heart movement based on images plays a vital role in assisting postoperative procedures and processes. In particular, if shape information can be provided in real-time using electrocardiogram (ECG) signal information, the corresponding heart movement information can be used for cardiovascular analysis and imaging guides during surgery. In this paper, we propose a 3D+t cardiac coronary artery model which is rendered in real-time, according to the ECG signal, where hierarchical cage-based deformation modeling is used to generate the mesh deformation used during the procedure. We match the blood vessel's lumen obtained from the ECG-gated 3D+t CT angiography taken at multiple cardiac phases, in order to derive the optimal deformation. Splines for 3D deformation control points are used to continuously represent the obtained deformation in the multi-view, according to the ECG signal. To verify the proposed method, we compare the manually segmented lumen and the results of the proposed method for eight patients. The average distance and dice coefficient between the two models were 0.543 mm and 0.735, respectively. The required time for registration of the 3D coronary artery model was 23.53 s/model. The rendering speed to derive the model, after generating the 3D+t model, was faster than 120 FPS.

An anatomical neurovascular study for procedures targeting peri-articular nerves in patients with anterior knee pain.

BACKGROUND: Radiofrequency ablation (RFA) of the articular branches innervating the anterior knee capsule has been studied as a possible alternative to surgery for degenerative arthritis. However, the neurovascular topography of the anterior knee capsule remains unclear. METHODS: One leg from each of the 20 formalin-embalmed cadaveric specimens was investigated. Modified ablation points (MAPs) were evaluated for a possible alternative for conventional target points (CAPs). RESULTS: For the nerve to vastus medialis (NVM), the probability of identifying the nerve was higher at MAP compared with CAP (62.5% vs. 25%). The mean shortest distance from the nerve was shorter at MAP compared with CAP (18.0 mm vs. 29.9 mm). The probabilities and distances for other nerves were not significantly different between the points. However, the probability of identifying the artery was significantly lower at MAPs compared with CAPs for arteries (0%, 5.3%, and 0% vs. 84.2%, 84.2%, and 73.3% for superior medial genicular, superior lateral genicular, and inferior medial genicular artery, respectively). For the recurrent peroneal nerve (RPN), a new target point was set in MAPs. CONCLUSIONS: The current landmark for genicular nerve procedures may not accurately target the correct nerve position, or reduce the risk for vessel damage. A more proximal target may reduce complications and increase the probability of successful procedures, although clinical correlation is needed.

Preliminary Study for Designing a Novel Vein-Visualizing Device.

Venipuncture is an important health diagnosis process. Although venipuncture is one of the most commonly performed procedures in medical environments, locating the veins of infants, obese, anemic, or colored patients is still an arduous task even for skilled practitioners. To solve this problem, several devices using infrared light have recently become commercially available. However, such devices for venipuncture share a common drawback, especially when visualizing deep veins or veins of a thick part of the body like the cubital fossa. This paper proposes a new vein-visualizing device applying a new penetration method using near-infrared (NIR) light. The light module is attached directly on to the declared area of the skin. Then, NIR beam is rayed from two sides of the light module to the vein with a specific angle. This gives a penetration effect. In addition, through an image processing procedure, the vein structure is enhanced to show it more accurately. Through a phantom study, the most effective penetration angle of the NIR module is decided. Additionally, the feasibility of the device is verified through experiments in vivo. The prototype allows us to visualize the vein patterns of thicker body parts, such as arms.

Markerless surgical robotic system for intracerebral hemorrhage surgery.

Conventional intracerebral hemorrhage (ICH) surgery uses a stereotactic frame to access an intracerebral hematoma. Using a stereotactic frame for ICH surgery requires a long preparation time. In order to resolve this problem, we propose a markerless surgical robotic system. This system uses weighted iterative closest point technology for surface registration, hand-eye calibration for needle insertion, and 3D surface scanning for registration. We need calibration to integrate the technologies: calibration of robot and needle coordinates and calibration of 3D surface scanning and needle coordinates. These calibrations are essential elements of the markerless surgical robotic system. This system has the advantages of being non-invasive, a short total operation time, and low radiation exposure compared to conventional ICH surgery.