An Open Benchmark Challenge for Motion Correction of Myocardial Perfusion MRI

Influence of motion correction on the visual analysis of cardiac magnetic resonance stress perfusion imaging

OBJECTIVE

Image post-processing corrects for cardiac and respiratory motion (MoCo) during cardiovascular magnetic resonance (CMR) stress perfusion. The study analyzed its influence on visual image evaluation.

MATERIALS AND METHODS

Sixty-two patients with (suspected) coronary artery disease underwent a standard CMR stress perfusion exam during free-breathing. Image post-processing was performed without (non-MoCo) and with MoCo (image intensity normalization; motion extraction with iterative non-rigid registration; motion warping with the combined displacement field). Images were evaluated regarding the perfusion pattern (perfusion deficit, dark rim artifact, uncertain signal loss, and normal perfusion), the general image quality (non-diagnostic, imperfect, good, and excellent), and the reader's subjective confidence to assess the images (not confident, confident, very confident).

RESULTS

Fifty-three (non-MoCo) and 52 (MoCo) myocardial segments were rated as 'perfusion deficit', 113 vs. 109 as 'dark rim artifacts', 9 vs. 7 as 'uncertain signal loss', and 817 vs. 824 as 'normal'. Agreement between non-MoCo and MoCo was high with no diagnostic difference per-patient. The image quality of MoCo was rated more often as 'good' or 'excellent' (92 vs. 63%), and the diagnostic confidence more often as "very confident" (71 vs. 45%) compared to non-MoCo.

CONCLUSIONS

The comparison of perfusion images acquired during free-breathing and post-processed with and without motion correction demonstrated that both methods led to a consistent evaluation of the perfusion pattern, while the image quality and the reader's subjective confidence to assess the images were rated more favorably for MoCo.

A fast navigator (fastNAV) for prospective respiratory motion correction in first-pass myocardial perfusion imaging

PURPOSE

To develop and evaluate a fast respiratory navigator (fastNAV) for cardiac MR perfusion imaging with subject-specific prospective slice tracking.

METHODS

A fastNAV was developed for dynamic contrast-enhanced cardiac MR perfusion imaging by combining spatially nonselective saturation with slice-selective tip-up and slice-selective excitation pulses. The excitation slice was angulated from the tip-up slice in the transverse plane to overlap only in the right hemidiaphragm for suppression of signal outside the right hemidiaphragm. A calibration scan was developed to enable the estimation of subject-specific tracking factors. Perfusion imaging using subject-specific fastNAV-based slice tracking was then compared to a conventional sequence (ie, without slice tracking) in 10 patients under free-breathing conditions. Respiratory motion in perfusion images was quantitatively assessed by measuring the average overlap of the left ventricle across images (avDice, 0:no overlap/1:perfect overlap) and the average displacement of the center of mass of the left ventricle (avCoM). Image quality was subjectively assessed using a 4-point scoring system (1: poor, 4: excellent).

RESULTS

The fastNAV calibration was successfully performed in all subjects (average tracking factor of 0.46 ± 0.13, R = 0.94 ± 0.03). Prospective motion correction using fastNAV led to higher avDice (0.94 ± 0.02 vs. 0.90 ± 0.03, P < .001) and reduced avCoM (4.03 ± 0.84 vs. 5.22 ± 1.22, P < .001). There were no statistically significant differences between the 2 sequences in terms of image quality (both sequences: median = 3 and interquartile range = 3-4, P = 1).

CONCLUSION

fastNAV enables fast and robust right hemidiaphragm motion tracking in a perfusion sequence. In combination with subject-specific slice tracking, fastNAV reduces the effect of respiratory motion during free-breathing cardiac MR perfusion imaging.

Design and evaluation of an abbreviated pixelwise dynamic contrast enhancement analysis protocol for early extracellular volume fraction estimation

INTRODUCTION

T1-based method is considered as the gold standard for extracellular volume fraction (ECV) mapping. This technique requires at least a 10 min delay after injection to acquire the post injection T1 map. Quantitative analysis of Dynamic Contrast Enhancement (DCE) images could lead to an earlier estimation of an ECV like parameter (2 min). The purpose of this study was to design a quantitative pixel-wise DCE analysis workflow to assess the feasibility of an early estimation of ECV.

METHODS

Fourteen patients with mitral valve prolapse were included in this study. The MR protocol, performed on a 3 T MR scanner, included MOLLI sequences for T1 maps acquisition and a standard SR-turboFlash sequence for dynamic acquisition. DCE data were acquired for at least 120 s. We implemented a full DCE analysis pipeline with a pre-processing step using an innovative motion correction algorithm (RC-REG algorithm) and a post-processing step using the extended Tofts Model (ECV_ETM). Estimated ECV_ETM maps were compared to standard T1-based ECV maps (ECV_T1) with both a Pearson correlation analysis and a group-wise analysis.

RESULTS

Image and map quality assessment showed systematic improvements using the proposed workflow. Strong correlation was found between ECV_ETM, and ECV_T1 values (r-square = 0.87).

CONCLUSION

A DCE analysis workflow based on RC-REG algorithm and ETM analysis can provide good quality parametric maps. Therefore, it is possible to extract ECV values from a 2 min-long DCE acquisition that are strongly correlated with ECV values from the T1 based method.

Automated detection of left ventricle in arterial input function images for inline perfusion mapping using deep learning: A study of 15,000 patients

PURPOSE

Quantification of myocardial perfusion has the potential to improve the detection of regional and global flow reduction. Significant effort has been made to automate the workflow, where one essential step is the arterial input function (AIF) extraction. Failure to accurately identify the left ventricle (LV) prevents AIF estimation required for quantification, therefore high detection accuracy is required. This study presents a robust LV detection method using the convolutional neural network (CNN).

METHODS

CNN models were trained by assembling 25,027 scans (N = 12,984 patients) from three hospitals, seven scanners. Performance was evaluated using a hold-out test set of 5721 scans (N = 2805 patients). Model inputs were a time series of AIF images (2D+T). Two variations were investigated: (1) two classes (2CS) for background and foreground (LV mask), and (2) three classes (3CS) for background, LV, and RV. The final model was deployed on MRI scanners using the Gadgetron reconstruction software framework.

RESULTS

Model loading on the MRI scanner took ~340 ms and applying the model took ~180 ms. The 3CS model successfully detected the LV in 99.98% of all test cases (1 failure out of 5721). The mean Dice ratio for 3CS was 0.87 ± 0.08 with 92.0% of all cases having Dice >0.75. The 2CS model gave a lower Dice ratio of 0.82 ± 0.22 (P < 1e-5). There was no significant difference in foot-time, peak-time, first-pass duration, peak value, and area-under-curve (P > .2) comparing automatically extracted AIF signals with signals from manually drawn contours.

CONCLUSIONS

A CNN-based solution to detect the LV blood pool from the arterial input function image series was developed, validated, and deployed. A high LV detection accuracy of 99.98% was achieved.

ANHIR: Automatic Non-Rigid Histological Image Registration Challenge

Automatic Non-rigid Histological Image Registration (ANHIR) challenge was organized to compare the performance of image registration algorithms on several kinds of microscopy histology images in a fair and independent manner. We have assembled 8 datasets, containing 355 images with 18 different stains, resulting in 481 image pairs to be registered. Registration accuracy was evaluated using manually placed landmarks. In total, 256 teams registered for the challenge, 10 submitted the results, and 6 participated in the workshop. Here, we present the results of 7 well-performing methods from the challenge together with 6 well-known existing methods. The best methods used coarse but robust initial alignment, followed by non-rigid registration, used multiresolution, and were carefully tuned for the data at hand. They outperformed off-the-shelf methods, mostly by being more robust. The best methods could successfully register over 98% of all landmarks and their mean landmark registration accuracy (TRE) was 0.44% of the image diagonal. The challenge remains open to submissions and all images are available for download.

Feasibility of free-breathing quantitative myocardial perfusion using multi-echo Dixon magnetic resonance imaging

Dynamic contrast-enhanced quantitative first-pass perfusion using magnetic resonance imaging enables non-invasive objective assessment of myocardial ischemia without ionizing radiation. However, quantification of perfusion is challenging due to the non-linearity between the magnetic resonance signal intensity and contrast agent concentration. Furthermore, respiratory motion during data acquisition precludes quantification of perfusion. While motion correction techniques have been proposed, they have been hampered by the challenge of accounting for dramatic contrast changes during the bolus and long execution times. In this work we investigate the use of a novel free-breathing multi-echo Dixon technique for quantitative myocardial perfusion. The Dixon fat images, unaffected by the dynamic contrast-enhancement, are used to efficiently estimate rigid-body respiratory motion and the computed transformations are applied to the corresponding diagnostic water images. This is followed by a second non-linear correction step using the Dixon water images to remove residual motion. The proposed Dixon motion correction technique was compared to the state-of-the-art technique (spatiotemporal based registration). We demonstrate that the proposed method performs comparably to the state-of-the-art but is significantly faster to execute. Furthermore, the proposed technique can be used to correct for the decay of signal due to T2* effects to improve quantification and additionally, yields fat-free diagnostic images.

AI in Medical Imaging Informatics: Current Challenges and Future Directions

This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.

Groupwise Non-Rigid Registration with Deep Learning: An Affordable Solution Applied to 2D Cardiac Cine MRI Reconstruction

Groupwise image (GW) registration is customarily used for subsequent processing in medical imaging. However, it is computationally expensive due to repeated calculation of transformations and gradients. In this paper, we propose a deep learning (DL) architecture that achieves GW elastic registration of a 2D dynamic sequence on an affordable average GPU. Our solution, referred to as dGW, is a simplified version of the well-known U-net. In our GW solution, the image that the other images are registered to, referred to in the paper as template image, is iteratively obtained together with the registered images. Design and evaluation have been carried out using 2D cine cardiac MR slices from 2 databases respectively consisting of 89 and 41 subjects. The first database was used for training and validation with 66.6–33.3% split. The second one was used for validation (50%) and testing (50%). Additional network hyperparameters, which are—in essence—those that control the transformation smoothness degree, are obtained by means of a forward selection procedure. Our results show a 9-fold runtime reduction with respect to an optimization-based implementation; in addition, making use of the well-known structural similarity (SSIM) index we have obtained significative differences with dGW with respect to an alternative DL solution based on Voxelmorph.

Quantitative 3D myocardial perfusion with an efficient arterial input function

PURPOSE

The purpose of this study was to further develop and combine several innovative sequence designs to achieve quantitative 3D myocardial perfusion. These developments include an optimized 3D stack-of-stars readout (150 ms per beat), efficient acquisition of a 2D arterial input function, tailored saturation pulse design, and potential whole heart coverage during quantitative stress perfusion.

THEORY AND METHODS

All studies were performed free-breathing on a Prisma 3T MRI scanner. Phantom validation was used to verify sequence accuracy. A total of 21 subjects (3 patients with known disease) were scanned, 12 with a rest only protocol and 9 with both stress (regadenoson) and rest protocols. First pass quantitative perfusion was performed with gadoteridol (0.075 mmol/kg).

RESULTS

Implementation and quantitative perfusion results are shown for healthy subjects and subjects with known coronary disease. Average rest perfusion for the 15 included healthy subjects was 0.79 ± 0.19 mL/g/min, the average stress perfusion for 6 healthy subject studies was 2.44 ± 0.61 mL/g/min, and the average global myocardial perfusion reserve ratio for 6 healthy subjects was 3.10 ± 0.24. Perfusion deficits for 3 patients with ischemia are shown. Average resting heart rate was 59 ± 7 bpm and the average stress heart rate was 81 ± 10 bpm.

CONCLUSION

This work demonstrates that a quantitative 3D myocardial perfusion sequence with the acquisition of a 2D arterial input function is feasible at high stress heart rates such as during stress. T1 values and gadolinium concentrations of the sequence match the reference standard well in a phantom, and myocardial rest and stress perfusion and myocardial perfusion reserve values are consistent with those published in literature.

Automatic in-line quantitative myocardial perfusion mapping: Processing algorithm and implementation

PURPOSE

Quantitative myocardial perfusion mapping has advantages over qualitative assessment, including the ability to detect global flow reduction. However, it is not clinically available and remains a research tool. Building upon the previously described imaging sequence, this study presents algorithm and implementation of an automated solution for inline perfusion flow mapping with step by step performance characterization.

METHODS

Proposed workflow consists of motion correction (MOCO), arterial input function blood detection, intensity to gadolinium concentration conversion, and pixel-wise mapping. A distributed kinetics model, blood-tissue exchange model, is implemented, computing pixel-wise maps of myocardial blood flow (mL/min/g), permeability-surface-area product (mL/min/g), blood volume (mL/g), and interstitial volume (mL/g).

RESULTS

Thirty healthy subjects (11 men; 26.4 ± 10.4 years) were recruited and underwent adenosine stress perfusion cardiovascular MR. Mean MOCO quality score was 3.6 ± 0.4 for stress and 3.7 ± 0.4 for rest. Myocardial Dice similarity coefficients after MOCO were significantly improved (P < 1e-6), 0.87 ± 0.05 for stress and 0.86 ± 0.06 for rest. Arterial input function peak gadolinium concentration was 4.4 ± 1.3 mmol/L at stress and 5.2 ± 1.5 mmol/L at rest. Mean myocardial blood flow at stress and rest were 2.82 ± 0.47 mL/min/g and 0.68 ± 0.16 mL/min/g, respectively. The permeability-surface-area product was 1.32 ± 0.26 mL/min/g at stress and 1.09 ± 0.21 mL/min/g at rest (P < 1e-3). Blood volume was 12.0 ± 0.8 mL/100 g at stress and 9.7 ± 1.0 mL/100 g at rest (P < 1e-9), indicating good adenosine vasodilation response. Interstitial volume was 20.8 ± 2.5 mL/100 g at stress and 20.3 ± 2.9 mL/100 g at rest (P = 0.50).

CONCLUSIONS

An inline perfusion flow mapping workflow is proposed and demonstrated on normal volunteers. Initial evaluation demonstrates this fully automated solution for the respiratory MOCO, arterial input function left ventricle mask detection, and pixel-wise mapping, from free-breathing myocardial perfusion imaging.

Robust Non-Rigid Motion Compensation of Free-Breathing Myocardial Perfusion MRI Data

Kinetic parameter values, such as myocardial perfusion, can be quantified from dynamic contrast-enhanced magnetic resonance imaging data using tracer-kinetic modeling. However, respiratory motion affects the accuracy of this process. Motion compensation of the image series is difficult due to the rapid local signal enhancement caused by the passing of the gadolinium-based contrast agent. This contrast enhancement invalidates the assumptions of the (global) cost functions traditionally used in intensity-based registrations. The algorithms are unable to distinguish whether the differences in signal intensity between frames are caused by the spatial motion artifacts or the local contrast enhancement. In order to address this problem, a fully automated motion compensation scheme is proposed, which consists of two stages. The first of which uses robust principal component analysis (PCA) to separate the local signal enhancement from the baseline signal, before a refinement stage which uses the traditional PCA to construct a synthetic reference series that is free from motion but preserves the signal enhancement. Validation is performed on 18 subjects acquired in free-breathing and 5 clinical subjects acquired with a breath-hold. The validation assesses the visual quality, the temporal smoothness of tissue curves, and the clinically relevant quantitative perfusion values. The expert observers score the visual quality increased by a mean of 1.58/5 after motion compensation and improvement over the previously published methods. The proposed motion compensation scheme also leads to the improved quantitative performance of motion compensated free-breathing image series [30% reduction in the coefficient of variation across quantitative perfusion maps and 53% reduction in temporal variations (p < 0.001)].