Predictive uncertainty in deep learning-based MR image reconstruction using deep ensembles: Evaluation on the fastMRI data set

PURPOSE

To estimate pixel-wise predictive uncertainty for deep learning-based MR image reconstruction and to examine the impact of domain shifts and architecture robustness.

METHODS

Uncertainty prediction could provide a measure for robustness of deep learning (DL)-based MR image reconstruction from undersampled data. DL methods bear the risk of inducing reconstruction errors like in-painting of unrealistic structures or missing pathologies. These errors may be obscured by visual realism of DL reconstruction and thus remain undiscovered. Furthermore, most methods are task-agnostic and not well calibrated to domain shifts. We propose a strategy that estimates aleatoric (data) and epistemic (model) uncertainty, which entails training a deep ensemble (epistemic) with nonnegative log-likelihood (aleatoric) loss in addition to the conventional applied losses terms. The proposed procedure can be paired with any DL reconstruction, enabling investigations of their predictive uncertainties on a pixel level. Five different architectures were investigated on the fastMRI database. The impact on the examined uncertainty of in-distributional and out-of-distributional data with changes to undersampling pattern, imaging contrast, imaging orientation, anatomy, and pathology were explored.

RESULTS

Predictive uncertainty could be captured and showed good correlation to normalized mean squared error. Uncertainty was primarily focused along the aliased anatomies and on hyperintense and hypointense regions. The proposed uncertainty measure was able to detect disease prevalence shifts. Distinct predictive uncertainty patterns were observed for changing network architectures.

CONCLUSION

The proposed approach enables aleatoric and epistemic uncertainty prediction for DL-based MR reconstruction with an interpretable examination on a pixel level.

A Deep Learning-Based Integrated Framework for Quality-Aware Undersampled Cine Cardiac MRI Reconstruction and Analysis

Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation. However, cine CMR acquisition is inherently slow and in recent decades considerable effort has been put into accelerating scan times without compromising image quality or the accuracy of derived results. In this article, we present a fully-automated, quality-controlled integrated framework for reconstruction, segmentation and downstream analysis of undersampled cine CMR data. The framework produces high quality reconstructions and segmentations, leading to undersampling factors that are optimised on a scan-by-scan basis. This results in reduced scan times and automated analysis, enabling robust and accurate estimation of functional biomarkers. To demonstrate the feasibility of the proposed approach, we perform simulations of radial k-space acquisitions using in-vivo cine CMR data from 270 subjects from the UK Biobank (with synthetic phase) and in-vivo cine CMR data from 16 healthy subjects (with real phase). The results demonstrate that the optimal undersampling factor varies for different subjects by approximately 1 to 2 seconds per slice. We show that our method can produce quality-controlled images in a mean scan time reduced from 12 to 4 seconds per slice, and that image quality is sufficient to allow clinically relevant parameters to be automatically estimated to lie within 5% mean absolute difference.

Reconstruction-driven motion estimation for motion-compensated MR CINE imaging

In cardiac CINE, motion-compensated MR reconstruction (MCMR) is an effective approach to address highly undersampled acquisitions by incorporating motion information between frames. In this work, we propose a novel perspective for addressing the MCMR problem and a more integrated and efficient solution to the MCMR field. Contrary to state-of-the-art (SOTA) MCMR methods which break the original problem into two sub-optimization problems, i.e. motion estimation and reconstruction, we formulate this problem as a single entity with one single optimization. Our approach is unique in that the motion estimation is directly driven by the ultimate goal, reconstruction, but not by the canonical motion-warping loss (similarity measurement between motion-warped images and target images). We align the objectives of motion estimation and reconstruction, eliminating the drawbacks of artifacts-affected motion estimation and therefore error-propagated reconstruction. Further, we can deliver high-quality reconstruction and realistic motion without applying any regularization/smoothness loss terms, circumventing the non-trivial weighting factor tuning. We evaluate our method on two datasets: 1) an in-house acquired 2D CINE dataset for the retrospective study and 2) the public OCMR cardiac dataset for the prospective study. The conducted experiments indicate that the proposed MCMR framework can deliver artifact-free motion estimation and high-quality MR images even for imaging accelerations up to 20x, outperforming SOTA non-MCMR and MCMR methods in both qualitative and quantitative evaluation across all experiments.

Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review

Motion represents one of the major challenges in magnetic resonance imaging (MRI). Since the MR signal is acquired in frequency space, any motion of the imaged object leads to complex artefacts in the reconstructed image in addition to other MR imaging artefacts. Deep learning has been frequently proposed for motion correction at several stages of the reconstruction process. The wide range of MR acquisition sequences, anatomies and pathologies of interest, and motion patterns (rigid vs. deformable and random vs. regular) makes a comprehensive solution unlikely. To facilitate the transfer of ideas between different applications, this review provides a detailed overview of proposed methods for learning-based motion correction in MRI together with their common challenges and potentials. This review identifies differences and synergies in underlying data usage, architectures, training and evaluation strategies. We critically discuss general trends and outline future directions, with the aim to enhance interaction between different application areas and research fields.

Unrolled and rapid motion-compensated reconstruction for cardiac CINE MRI

In recent years Motion-Compensated MR reconstruction (MCMR) has emerged as a promising approach for cardiac MR (CMR) imaging reconstruction. MCMR estimates cardiac motion and incorporates this information in the reconstruction. However, two obstacles prevent the practical use of MCMR in clinical situations: First, inaccurate motion estimation often leads to inferior CMR reconstruction results. Second, the motion estimation frequently leads to a long processing time for the reconstruction. In this work, we propose a learning-based and unrolled MCMR framework that can perform precise and rapid CMR reconstruction. We achieve accurate reconstruction by developing a joint optimization between the motion estimation and reconstruction, in which a deep learning-based motion estimation framework is unrolled within an iterative optimization procedure. With progressive iterations, a mutually beneficial interaction can be established in which the reconstruction quality is improved with more accurate motion estimation. Further, we propose a groupwise motion estimation framework to speed up the MCMR process. A registration template based on the cardiac sequence average is introduced, while the motion estimation is conducted between the cardiac frames and the template. By applying this framework, cardiac sequence registration can be accomplished with linear time complexity. Experiments on 43 in-house acquired 2D CINE datasets indicate that the proposed unrolled MCMR framework can deliver artifacts-free motion estimation and high-quality CMR reconstruction even for imaging acceleration rates up to 20x. We compare our approach with state-of-the-art reconstruction methods and it outperforms them quantitatively and qualitatively in all adapted metrics across all acceleration rates.

Single-heartbeat cardiac cine imaging via jointly regularized nonrigid motion-corrected reconstruction

The aim of the current study was to develop a novel approach for 2D breath-hold cardiac cine imaging from a single heartbeat, by combining cardiac motion-corrected reconstructions and nonrigidly aligned patch-based regularization. Conventional cardiac cine imaging is obtained via motion-resolved reconstructions of data acquired over multiple heartbeats. Here, we achieve single-heartbeat cine imaging by incorporating nonrigid cardiac motion correction into the reconstruction of each cardiac phase, in conjunction with a motion-aligned patch-based regularization. The proposed Motion-Corrected CINE (MC-CINE) incorporates all acquired data into the reconstruction of each (motion-corrected) cardiac phase, resulting in a better posed problem than motion-resolved approaches. MC-CINE was compared with iterative sensitivity encoding (itSENSE) and Extra-Dimensional Golden Angle Radial Sparse Parallel (XD-GRASP) in 14 healthy subjects in terms of image sharpness, reader scoring (range: 1-5) and reader ranking (range: 1-9) of image quality, and single-slice left ventricular assessment. MC-CINE was significantly superior to both itSENSE and XD-GRASP using 20 heartbeats, two heartbeats, and one heartbeat. Iterative SENSE, XD-GRASP, and MC-CINE achieved a sharpness of 74%, 74%, and 82% using 20 heartbeats, and 53%, 66%, and 82% with one heartbeat, respectively. The corresponding results for reader scoring were 4.0, 4.7, and 4.9 with 20 heartbeats, and 1.1, 3.0, and 3.9 with one heartbeat. The corresponding results for reader ranking were 5.3, 7.3, and 8.6 with 20 heartbeats, and 1.0, 3.2, and 5.4 with one heartbeat. MC-CINE using a single heartbeat presented nonsignificant differences in image quality to itSENSE with 20 heartbeats. MC-CINE and XD-GRASP at one heartbeat both presented a nonsignificant negative bias of less than 2% in ejection fraction relative to the reference itSENSE. It was concluded that the proposed MC-CINE significantly improves image quality relative to itSENSE and XD-GRASP, enabling 2D cine from a single heartbeat.

Rapid estimation of 2D relative B 1 + -maps from localizers in the human heart at 7T using deep learning

PURPOSE

Subject-tailored parallel transmission pulses for ultra-high fields body applications are typically calculated based on subject-specific B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps of all transmit channels, which require lengthy adjustment times. This study investigates the feasibility of using deep learning to estimate complex, channel-wise, relative 2D B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps from a single gradient echo localizer to overcome long calibration times.

METHODS

126 channel-wise, complex, relative 2D B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps of the human heart from 44 subjects were acquired at 7T using a Cartesian, cardiac gradient-echo sequence obtained under breath-hold to create a library for network training and cross-validation. The deep learning predicted maps were qualitatively compared to the ground truth. Phase-only B 1 + $$ {\mathrm{B}}_1^{+} $$ -shimming was subsequently performed on the estimated B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps for a region of interest covering the heart. The proposed network was applied at 7T to 3 unseen test subjects.

RESULTS

The deep learning-based B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps, derived in approximately 0.2 seconds, match the ground truth for the magnitude and phase. The static, phase-only pulse design performs best when maximizing the mean transmission efficiency. In-vivo application of the proposed network to unseen subjects demonstrates the feasibility of this approach: the network yields predicted B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps comparable to the acquired ground truth and anatomical scans reflect the resulting B 1 + $$ {\mathrm{B}}_1^{+} $$ -pattern using the deep learning-based maps.

CONCLUSION

The feasibility of estimating 2D relative B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps from initial localizer scans of the human heart at 7T using deep learning is successfully demonstrated. Because the technique requires only sub-seconds to derive channel-wise B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps, it offers high potential for advancing clinical body imaging at ultra-high fields.

Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging: Combining physics and machine learning for improved medical imaging

Physics-driven deep learning methods have emerged as a powerful tool for computational magnetic resonance imaging (MRI) problems, pushing reconstruction performance to new limits. This article provides an overview of the recent developments in incorporating physics information into learning-based MRI reconstruction. We consider inverse problems with both linear and non-linear forward models for computational MRI, and review the classical approaches for solving these. We then focus on physics-driven deep learning approaches, covering physics-driven loss functions, plug-and-play methods, generative models, and unrolled networks. We highlight domain-specific challenges such as real- and complex-valued building blocks of neural networks, and translational applications in MRI with linear and non-linear forward models. Finally, we discuss common issues and open challenges, and draw connections to the importance of physics-driven learning when combined with other downstream tasks in the medical imaging pipeline.

Cardiac MR: From Theory to Practice

Cardiovascular disease (CVD) is the leading single cause of morbidity and mortality, causing over 17. 9 million deaths worldwide per year with associated costs of over $800 billion. Improving prevention, diagnosis, and treatment of CVD is therefore a global priority. Cardiovascular magnetic resonance (CMR) has emerged as a clinically important technique for the assessment of cardiovascular anatomy, function, perfusion, and viability. However, diversity and complexity of imaging, reconstruction and analysis methods pose some limitations to the widespread use of CMR. Especially in view of recent developments in the field of machine learning that provide novel solutions to address existing problems, it is necessary to bridge the gap between the clinical and scientific communities. This review covers five essential aspects of CMR to provide a comprehensive overview ranging from CVDs to CMR pulse sequence design, acquisition protocols, motion handling, image reconstruction and quantitative analysis of the obtained data. (1) The basic MR physics of CMR is introduced. Basic pulse sequence building blocks that are commonly used in CMR imaging are presented. Sequences containing these building blocks are formed for parametric mapping and functional imaging techniques. Commonly perceived artifacts and potential countermeasures are discussed for these methods. (2) CMR methods for identifying CVDs are illustrated. Basic anatomy and functional processes are described to understand the cardiac pathologies and how they can be captured by CMR imaging. (3) The planning and conduct of a complete CMR exam which is targeted for the respective pathology is shown. Building blocks are illustrated to create an efficient and patient-centered workflow. Further strategies to cope with challenging patients are discussed. (4) Imaging acceleration and reconstruction techniques are presented that enable acquisition of spatial, temporal, and parametric dynamics of the cardiac cycle. The handling of respiratory and cardiac motion strategies as well as their integration into the reconstruction processes is showcased. (5) Recent advances on deep learning-based reconstructions for this purpose are summarized. Furthermore, an overview of novel deep learning image segmentation and analysis methods is provided with a focus on automatic, fast and reliable extraction of biomarkers and parameters of clinical relevance.

Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction

Recent deep learning approaches focus on improving quantitative scores of dedicated benchmarks, and therefore only reduce the observation-related (aleatoric) uncertainty. However, the model-immanent (epistemic) uncertainty is less frequently systematically analyzed. In this work, we introduce a Bayesian variational framework to quantify the epistemic uncertainty. To this end, we solve the linear inverse problem of undersampled MRI reconstruction in a variational setting. The associated energy functional is composed of a data fidelity term and the total deep variation (TDV) as a learned parametric regularizer. To estimate the epistemic uncertainty we draw the parameters of the TDV regularizer from a multivariate Gaussian distribution, whose mean and covariance matrix are learned in a stochastic optimal control problem. In several numerical experiments, we demonstrate that our approach yields competitive results for undersampled MRI reconstruction. Moreover, we can accurately quantify the pixelwise epistemic uncertainty, which can serve radiologists as an additional resource to visualize reconstruction reliability.

Complementary time-frequency domain networks for dynamic parallel MR image reconstruction

PURPOSE

To introduce a novel deep learning-based approach for fast and high-quality dynamic multicoil MR reconstruction by learning a complementary time-frequency domain network that exploits spatiotemporal correlations simultaneously from complementary domains.

THEORY AND METHODS

Dynamic parallel MR image reconstruction is formulated as a multivariable minimization problem, where the data are regularized in combined temporal Fourier and spatial (x-f) domain as well as in spatiotemporal image (x-t) domain. An iterative algorithm based on variable splitting technique is derived, which alternates among signal de-aliasing steps in x-f and x-t spaces, a closed-form point-wise data consistency step and a weighted coupling step. The iterative model is embedded into a deep recurrent neural network which learns to recover the image via exploiting spatiotemporal redundancies in complementary domains.

RESULTS

Experiments were performed on two datasets of highly undersampled multicoil short-axis cardiac cine MRI scans. Results demonstrate that our proposed method outperforms the current state-of-the-art approaches both quantitatively and qualitatively. The proposed model can also generalize well to data acquired from a different scanner and data with pathologies that were not seen in the training set.

CONCLUSION

The work shows the benefit of reconstructing dynamic parallel MRI in complementary time-frequency domains with deep neural networks. The method can effectively and robustly reconstruct high-quality images from highly undersampled dynamic multicoil data ( 16 × and 24 × yielding 15 s and 10 s scan times respectively) with fast reconstruction speed (2.8 seconds). This could potentially facilitate achieving fast single-breath-hold clinical 2D cardiac cine imaging.

Systematic evaluation of iterative deep neural networks for fast parallel MRI reconstruction with sensitivity-weighted coil combination

PURPOSE

To systematically investigate the influence of various data consistency layers and regularization networks with respect to variations in the training and test data domain, for sensitivity-encoded accelerated parallel MR image reconstruction.

THEORY AND METHODS

Magnetic resonance (MR) image reconstruction is formulated as a learned unrolled optimization scheme with a down-up network as regularization and varying data consistency layers. The proposed networks are compared to other state-of-the-art approaches on the publicly available fastMRI knee and neuro dataset and tested for stability across different training configurations regarding anatomy and number of training samples.

RESULTS

Data consistency layers and expressive regularization networks, such as the proposed down-up networks, form the cornerstone for robust MR image reconstruction. Physics-based reconstruction networks outperform post-processing methods substantially for R = 4 in all cases and for R = 8 when the training and test data are aligned. At R = 8, aligning training and test data is more important than architectural choices.

CONCLUSION

In this work, we study how dataset sizes affect single-anatomy and cross-anatomy training of neural networks for MRI reconstruction. The study provides insights into the robustness, properties, and acceleration limits of state-of-the-art networks, and our proposed down-up networks. These key insights provide essential aspects to successfully translate learning-based MRI reconstruction to clinical practice, where we are confronted with limited datasets and various imaged anatomies.

CG-SENSE revisited: Results from the first ISMRM reproducibility challenge

PURPOSE

The aim of this work is to shed light on the issue of reproducibility in MR image reconstruction in the context of a challenge. Participants had to recreate the results of "Advances in sensitivity encoding with arbitrary k-space trajectories" by Pruessmann et al. METHODS: The task of the challenge was to reconstruct radially acquired multicoil k-space data (brain/heart) following the method in the original paper, reproducing its key figures. Results were compared to consolidated reference implementations created after the challenge, accounting for the two most common programming languages used in the submissions (Matlab/Python).

RESULTS

Visually, differences between submissions were small. Pixel-wise differences originated from image orientation, assumed field-of-view, or resolution. The reference implementations were in good agreement, both visually and in terms of image similarity metrics.

DISCUSSION AND CONCLUSION

While the description level of the published algorithm enabled participants to reproduce CG-SENSE in general, details of the implementation varied, for example, density compensation or Tikhonov regularization. Implicit assumptions about the data lead to further differences, emphasizing the importance of sufficient metadata accompanying open datasets. Defining reproducibility quantitatively turned out to be nontrivial for this image reconstruction challenge, in the absence of ground-truth results. Typical similarity measures like NMSE of SSIM were misled by image intensity scaling and outlier pixels. Thus, to facilitate reproducibility, researchers are encouraged to publish code and data alongside the original paper. Future methodological papers on MR image reconstruction might benefit from the consolidated reference implementations of CG-SENSE presented here, as a benchmark for methods comparison.

Rapid mono and biexponential 3D-T1ρ mapping of knee cartilage using variational networks

In this study we use undersampled MRI acquisition methods to obtain accelerated 3D mono and biexponential spin-lattice relaxation time in the rotating frame (T1ρ) mapping of knee cartilage, reducing the usual long scan time. We compare the accelerated T1ρ maps obtained by deep learning-based variational network (VN) and compressed sensing (CS). Both methods were compared with spatial (S) and spatio-temporal (ST) filters. Complex-valued fitting was used for T1ρ parameters estimation. We tested with seven in vivo and six synthetic datasets, with acceleration factors (AF) from 2 to 10. Median normalized absolute deviation (MNAD), analysis of variance (ANOVA), and coefficient of variation (CV) were used for analysis. The methods CS-ST, VN-S, and VN-ST performed well for accelerating monoexponential T1ρ mapping, with MNAD around 5% for AF = 2, which increases almost linearly with the AF to an MNAD of 13% for AF = 8, with all methods. For biexponential mapping, the VN-ST was the best method starting with MNAD of 7.4% for AF = 2 and reaching MNAD of 13.1% for AF = 8. The VN was able to produce 3D-T1ρ mapping of knee cartilage with lower error than CS. The best results were obtained by VN-ST, improving CS-ST method by nearly 7.5%.

CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions

Cardiac CINE magnetic resonance imaging is the gold-standard for the assessment of cardiac function. Imaging accelerations have shown to enable 3D CINE with left ventricular (LV) coverage in a single breath-hold. However, 3D imaging remains limited to anisotropic resolution and long reconstruction times. Recently deep learning has shown promising results for computationally efficient reconstructions of highly accelerated 2D CINE imaging. In this work, we propose a novel 4D (3D + time) deep learning-based reconstruction network, termed 4D CINENet, for prospectively undersampled 3D Cartesian CINE imaging. CINENet is based on (3 + 1)D complex-valued spatio-temporal convolutions and multi-coil data processing. We trained and evaluated the proposed CINENet on in-house acquired 3D CINE data of 20 healthy subjects and 15 patients with suspected cardiovascular disease. The proposed CINENet network outperforms iterative reconstructions in visual image quality and contrast (+ 67% improvement). We found good agreement in LV function (bias ± 95% confidence) in terms of end-systolic volume (0 ± 3.3 ml), end-diastolic volume (− 0.4 ± 2.0 ml) and ejection fraction (0.1 ± 3.2%) compared to clinical gold-standard 2D CINE, enabling single breath-hold isotropic 3D CINE in less than 10 s scan and ~ 5 s reconstruction time.

Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues

Following the success of deep learning in a wide range of applications, neural network-based machine learning techniques have received interest as a means of accelerating magnetic resonance imaging (MRI). A number of ideas inspired by deep learning techniques from computer vision and image processing have been successfully applied to non-linear image reconstruction in the spirit of compressed sensing for both low dose computed tomography and accelerated MRI. The additional integration of multi-coil information to recover missing k-space lines in the MRI reconstruction process, is still studied less frequently, even though it is the de-facto standard for currently used accelerated MR acquisitions. This manuscript provides an overview of the recent machine learning approaches that have been proposed specifically for improving parallel imaging. A general background introduction to parallel MRI is given that is structured around the classical view of image space and k-space based methods. Both linear and non-linear methods are covered, followed by a discussion of recent efforts to further improve parallel imaging using machine learning, and specifically using artificial neural networks. Image-domain based techniques that introduce improved regularizers are covered as well as k-space based methods, where the focus is on better interpolation strategies using neural networks. Issues and open problems are discussed as well as recent efforts for producing open datasets and benchmarks for the community.

Assessment of the generalization of learned image reconstruction and the potential for transfer learning

PURPOSE

Although deep learning has shown great promise for MR image reconstruction, an open question regarding the success of this approach is the robustness in the case of deviations between training and test data. The goal of this study is to assess the influence of image contrast, SNR, and image content on the generalization of learned image reconstruction, and to demonstrate the potential for transfer learning.

METHODS

Reconstructions were trained from undersampled data using data sets with varying SNR, sampling pattern, image contrast, and synthetic data generated from a public image database. The performance of the trained reconstructions was evaluated on 10 in vivo patient knee MRI acquisitions from 2 different pulse sequences that were not used during training. Transfer learning was evaluated by fine-tuning baseline trainings from synthetic data with a small subset of in vivo MR training data.

RESULTS

Deviations in SNR between training and testing led to substantial decreases in reconstruction image quality, whereas image contrast was less relevant. Trainings from heterogeneous training data generalized well toward the test data with a range of acquisition parameters. Trainings from synthetic, non-MR image data showed residual aliasing artifacts, which could be removed by transfer learning-inspired fine-tuning.

CONCLUSION

This study presents insights into the generalization ability of learned image reconstruction with respect to deviations in the acquisition settings between training and testing. It also provides an outlook for the potential of transfer learning to fine-tune trainings to a particular target application using only a small number of training cases.

Learning a variational network for reconstruction of accelerated MRI data

PURPOSE

To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning.

THEORY AND METHODS

Generalized compressed sensing reconstruction formulated as a variational model is embedded in an unrolled gradient descent scheme. All parameters of this formulation, including the prior model defined by filter kernels and activation functions as well as the data term weights, are learned during an offline training procedure. The learned model can then be applied online to previously unseen data.

RESULTS

The variational network approach is evaluated on a clinical knee imaging protocol for different acceleration factors and sampling patterns using retrospectively and prospectively undersampled data. The variational network reconstructions outperform standard reconstruction algorithms, verified by quantitative error measures and a clinical reader study for regular sampling and acceleration factor 4.

CONCLUSION

Variational network reconstructions preserve the natural appearance of MR images as well as pathologies that were not included in the training data set. Due to its high computational performance, that is, reconstruction time of 193 ms on a single graphics card, and the omission of parameter tuning once the network is trained, this new approach to image reconstruction can easily be integrated into clinical workflow. Magn Reson Med 79:3055-3071, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

A multi-center milestone study of clinical vertebral CT segmentation

A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention.