Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences

DuDoCFNet: Dual-Domain Coarse-to-Fine Progressive Network for Simultaneous Denoising, Limited-View Reconstruction, and Attenuation Correction of Cardiac SPECT

Single-Photon Emission Computed Tomography (SPECT) is widely applied for the diagnosis of coronary artery diseases. Low-dose (LD) SPECT aims to minimize radiation exposure but leads to increased image noise. Limited-view (LV) SPECT, such as the latest GE MyoSPECT ES system, enables accelerated scanning and reduces hardware expenses but degrades reconstruction accuracy. Additionally, Computed Tomography (CT) is commonly used to derive attenuation maps ( μ -maps) for attenuation correction (AC) of cardiac SPECT, but it will introduce additional radiation exposure and SPECT-CT misalignments. Although various methods have been developed to solely focus on LD denoising, LV reconstruction, or CT-free AC in SPECT, the solution for simultaneously addressing these tasks remains challenging and under-explored. Furthermore, it is essential to explore the potential of fusing cross-domain and cross-modality information across these interrelated tasks to further enhance the accuracy of each task. Thus, we propose a Dual-Domain Coarse-to-Fine Progressive Network (DuDoCFNet), a multi-task learning method for simultaneous LD denoising, LV reconstruction, and CT-free μ -map generation of cardiac SPECT. Paired dual-domain networks in DuDoCFNet are cascaded using a multi-layer fusion mechanism for cross-domain and cross-modality feature fusion. Two-stage progressive learning strategies are applied in both projection and image domains to achieve coarse-to-fine estimations of SPECT projections and CT-derived μ -maps. Our experiments demonstrate DuDoCFNet's superior accuracy in estimating projections, generating μ -maps, and AC reconstructions compared to existing single- or multi-task learning methods, under various iterations and LD levels. The source code of this work is available at https://github.com/XiongchaoChen/DuDoCFNet-MultiTask.

Modeling 3D Cardiac Contraction and Relaxation With Point Cloud Deformation Networks

Global single-valued biomarkers, such as ejection fraction, are widely used in clinical practice to assess cardiac function. However, they only approximate the heart's true 3D deformation process, thus limiting diagnostic accuracy and the understanding of cardiac mechanics. Metrics based on 3D shape have been proposed to alleviate these shortcomings. In this work, we present the Point Cloud Deformation Network (PCD-Net) as a novel geometric deep learning approach for direct modeling of 3D cardiac mechanics of the biventricular anatomy between the extreme ends of the cardiac cycle. Its encoder-decoder architecture combines a low-dimensional latent space with recent advances in point cloud deep learning for effective multi-scale feature learning directly on flexible and memory-efficient point cloud representations of the cardiac anatomy. We first evaluate the PCD-Net's predictive capability for both cardiac contraction and relaxation on a large UK Biobank dataset of over 10,000 subjects and find average Chamfer distances between the predicted and ground truth anatomies below the pixel resolution of the underlying image acquisition. We then show the PCD-Net's ability to capture subpopulation-specific differences in 3D cardiac mechanics between normal and myocardial infarction (MI) subjects and visualize abnormal phenotypes between predicted normal 3D shapes and corresponding observed ones. Finally, we demonstrate that the PCD-Net's learned 3D deformation encodings outperform multiple clinical and machine learning benchmarks by 11% in terms of area under the receiver operating characteristic curve for the tasks of prevalent MI detection and incident MI prediction and by 7% in terms of Harrell's concordance index for MI survival analysis.

Attention-Aware Non-Rigid Image Registration for Accelerated MR Imaging

Accurate motion estimation at high acceleration factors enables rapid motion-compensated reconstruction in Magnetic Resonance Imaging (MRI) without compromising the diagnostic image quality. In this work, we introduce an attention-aware deep learning-based framework that can perform non-rigid pairwise registration for fully sampled and accelerated MRI. We extract local visual representations to build similarity maps between the registered image pairs at multiple resolution levels and additionally leverage long-range contextual information using a transformer-based module to alleviate ambiguities in the presence of artifacts caused by undersampling. We combine local and global dependencies to perform simultaneous coarse and fine motion estimation. The proposed method was evaluated on in-house acquired fully sampled and accelerated data of 101 patients and 62 healthy subjects undergoing cardiac and thoracic MRI. The impact of motion estimation accuracy on the downstream task of motion-compensated reconstruction was analyzed. We demonstrate that our model derives reliable and consistent motion fields across different sampling trajectories (Cartesian and radial) and acceleration factors of up to 16x for cardiac motion and 30x for respiratory motion and achieves superior image quality in motion-compensated reconstruction qualitatively and quantitatively compared to conventional and recent deep learning-based approaches. The code is publicly available at https://github.com/lab-midas/GMARAFT.

Motion-Compensated MR CINE Reconstruction With Reconstruction-Driven Motion Estimation

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. The code is available at https://github.com/JZPeterPan/MCMR-Recon-Driven-Motion.

Deep learning for accelerated and robust MRI reconstruction

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices.

Stop moving: MR motion correction as an opportunity for artificial intelligence

Subject motion is a long-standing problem of magnetic resonance imaging (MRI), which can seriously deteriorate the image quality. Various prospective and retrospective methods have been proposed for MRI motion correction, among which deep learning approaches have achieved state-of-the-art motion correction performance. This survey paper aims to provide a comprehensive review of deep learning-based MRI motion correction methods. Neural networks used for motion artifacts reduction and motion estimation in the image domain or frequency domain are detailed. Furthermore, besides motion-corrected MRI reconstruction, how estimated motion is applied in other downstream tasks is briefly introduced, aiming to strengthen the interaction between different research areas. Finally, we identify current limitations and point out future directions of deep learning-based MRI motion correction.

Multi-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography

Characterizing left ventricular deformation and strain using 3D+time echocardiography provides useful insights into cardiac function and can be used to detect and localize myocardial injury. To achieve this, it is imperative to obtain accurate motion estimates of the left ventricle. In many strain analysis pipelines, this step is often accompanied by a separate segmentation step; however, recent works have shown both tasks to be highly related and can be complementary when optimized jointly. In this work, we present a multi-task learning network that can simultaneously segment the left ventricle and track its motion between multiple time frames. Two task-specific networks are trained using a composite loss function. Cross-stitch units combine the activations of these networks by learning shared representations between the tasks at different levels. We also propose a novel shape-consistency unit that encourages motion propagated segmentations to match directly predicted segmentations. Using a combined synthetic and in-vivo 3D echocardiography dataset, we demonstrate that our proposed model can achieve excellent estimates of left ventricular motion displacement and myocardial segmentation. Additionally, we observe strong correlation of our image-based strain measurements with crystal-based strain measurements as well as good correspondence with SPECT perfusion mappings. Finally, we demonstrate the clinical utility of the segmentation masks in estimating ejection fraction and sphericity indices that correspond well with benchmark measurements.

Automated analysis of pectoralis major thickness in pec-fly exercises: evolving from manual measurement to deep learning techniques

This study addresses a limitation of prior research on pectoralis major (PMaj) thickness changes during the pectoralis fly exercise using a wearable ultrasound imaging setup. Although previous studies used manual measurement and subjective evaluation, it is important to acknowledge the subsequent limitations of automating widespread applications. We then employed a deep learning model for image segmentation and automated measurement to solve the problem and study the additional quantitative supplementary information that could be provided. Our results revealed increased PMaj thickness changes in the coronal plane within the probe detection region when real-time ultrasound imaging (RUSI) visual biofeedback was incorporated, regardless of load intensity (50% or 80% of one-repetition maximum). Additionally, participants showed uniform thickness changes in the PMaj in response to enhanced RUSI biofeedback. Notably, the differences in PMaj thickness changes between load intensities were reduced by RUSI biofeedback, suggesting altered muscle activation strategies. We identified the optimal measurement location for the maximal PMaj thickness close to the rib end and emphasized the lightweight applicability of our model for fitness training and muscle assessment. Further studies can refine load intensities, investigate diverse parameters, and employ different network models to enhance accuracy. This study contributes to our understanding of the effects of muscle physiology and exercise training.

DeepMesh: Mesh-Based Cardiac Motion Tracking Using Deep Learning

3D motion estimation from cine cardiac magnetic resonance (CMR) images is important for the assessment of cardiac function and the diagnosis of cardiovascular diseases. Current state-of-the art methods focus on estimating dense pixel-/voxel-wise motion fields in image space, which ignores the fact that motion estimation is only relevant and useful within the anatomical objects of interest, e.g., the heart. In this work, we model the heart as a 3D mesh consisting of epi- and endocardial surfaces. We propose a novel learning framework, DeepMesh, which propagates a template heart mesh to a subject space and estimates the 3D motion of the heart mesh from CMR images for individual subjects. In DeepMesh, the heart mesh of the end-diastolic frame of an individual subject is first reconstructed from the template mesh. Mesh-based 3D motion fields with respect to the end-diastolic frame are then estimated from 2D short- and long-axis CMR images. By developing a differentiable mesh-to-image rasterizer, DeepMesh is able to leverage 2D shape information from multiple anatomical views for 3D mesh reconstruction and mesh motion estimation. The proposed method estimates vertex-wise displacement and thus maintains vertex correspondences between time frames, which is important for the quantitative assessment of cardiac function across different subjects and populations. We evaluate DeepMesh on CMR images acquired from the UK Biobank. We focus on 3D motion estimation of the left ventricle in this work. Experimental results show that the proposed method quantitatively and qualitatively outperforms other image-based and mesh-based cardiac motion tracking methods.

Aligning Multi-Sequence CMR Towards Fully Automated Myocardial Pathology Segmentation

Myocardial pathology segmentation (MyoPS) is critical for the risk stratification and treatment planning of myocardial infarction (MI). Multi-sequence cardiac magnetic resonance (MS-CMR) images can provide valuable information. For instance, balanced steady-state free precession cine sequences present clear anatomical boundaries, while late gadolinium enhancement and T2-weighted CMR sequences visualize myocardial scar and edema of MI, respectively. Existing methods usually fuse anatomical and pathological information from different CMR sequences for MyoPS, but assume that these images have been spatially aligned. However, MS-CMR images are usually unaligned due to the respiratory motions in clinical practices, which poses additional challenges for MyoPS. This work presents an automatic MyoPS framework for unaligned MS-CMR images. Specifically, we design a combined computing model for simultaneous image registration and information fusion, which aggregates multi-sequence features into a common space to extract anatomical structures (i.e., myocardium). Consequently, we can highlight the informative regions in the common space via the extracted myocardium to improve MyoPS performance, considering the spatial relationship between myocardial pathologies and myocardium. Experiments on a private MS-CMR dataset and a public dataset from the MYOPS2020 challenge show that our framework could achieve promising performance for fully automatic MyoPS.

Semi-Supervised Representation Learning for Segmentation on Medical Volumes and Sequences

Benefiting from the massive labeled samples, deep learning-based segmentation methods have achieved great success for two dimensional natural images. However, it is still a challenging task to segment high dimensional medical volumes and sequences, due to the considerable efforts for clinical expertise to make large scale annotations. Self/semi-supervised learning methods have been shown to improve the performance by exploiting unlabeled data. However, they are still lack of mining local semantic discrimination and exploitation of volume/sequence structures. In this work, we propose a semi-supervised representation learning method with two novel modules to enhance the features in the encoder and decoder, respectively. For the encoder, based on the continuity between slices/frames and the common spatial layout of organs across subjects, we propose an asymmetric network with an attention-guided predictor to enable prediction between feature maps of different slices of unlabeled data. For the decoder, based on the semantic consistency between labeled data and unlabeled data, we introduce a novel semantic contrastive learning to regularize the feature maps in the decoder. The two parts are trained jointly with both labeled and unlabeled volumes/sequences in a semi-supervised manner. When evaluated on three benchmark datasets of medical volumes and sequences, our model outperforms existing methods with a large margin of 7.3% DSC on ACDC, 6.5% on Prostate, and 3.2% on CAMUS when only a few labeled data is available. Further, results on the M&M dataset show that the proposed method yields improvement without using any domain adaption techniques for data from unknown domain. Intensive evaluations reveal the effectiveness of representation mining, and superiority on performance of our method. The code is available at https://github.com/CcchenzJ/BootstrapRepresentation.

Probabilistic Modeling for Image Registration Using Radial Basis Functions: Application to Cardiac Motion Estimation

Cardiovascular diseases (CVDs) are the leading cause of death, affecting the cardiac dynamics over the cardiac cycle. Estimation of cardiac motion plays an essential role in many medical clinical tasks. This article proposes a probabilistic framework for image registration using compact support radial basis functions (CSRBFs) to estimate cardiac motion. A variational inference-based generative model with convolutional neural networks (CNNs) is proposed to learn the probabilistic coefficients of CSRBFs used in image deformation. We designed two networks to estimate the deformation coefficients of CSRBFs: the first one solves the spatial transformation using given control points, and the second one models the transformation using drifting control points. The given-point-based network estimates the probabilistic coefficients of control points. In contrast, the drifting-point-based model predicts the probabilistic coefficients and spatial distribution of control points simultaneously. To regularize these coefficients, we derive the bending energy (BE) in the variational bound by defining the covariance of coefficients. The proposed framework has been evaluated on the cardiac motion estimation and the calculation of the myocardial strain. In the experiments, 1409 slice pairs of end-diastolic (ED) and end-systolic (ES) phase in 4-D cardiac magnetic resonance (MR) images selected from three public datasets are employed to evaluate our networks. The experimental results show that our framework outperforms the state-of-the-art registration methods concerning the deformation smoothness and registration accuracy.

Accelerated respiratory-resolved 4D-MRI with separable spatio-temporal neural networks

BACKGROUND

Respiratory-resolved four-dimensional magnetic resonance imaging (4D-MRI) provides essential motion information for accurate radiation treatments of mobile tumors. However, obtaining high-quality 4D-MRI suffers from long acquisition and reconstruction times.

PURPOSE

To develop a deep learning architecture to quickly acquire and reconstruct high-quality 4D-MRI, enabling accurate motion quantification for MRI-guided radiotherapy (MRIgRT).

METHODS

A small convolutional neural network called MODEST is proposed to reconstruct 4D-MRI by performing a spatial and temporal decomposition, omitting the need for 4D convolutions to use all the spatio-temporal information present in 4D-MRI. This network is trained on undersampled 4D-MRI after respiratory binning to reconstruct high-quality 4D-MRI obtained by compressed sensing reconstruction. The network is trained, validated, and tested on 4D-MRI of 28 lung cancer patients acquired with a T1-weighted golden-angle radial stack-of-stars (GA-SOS) sequence. The 4D-MRI of 18, 5, and 5 patients were used for training, validation, and testing. Network performances are evaluated on image quality measured by the structural similarity index (SSIM) and motion consistency by comparing the position of the lung-liver interface on undersampled 4D-MRI before and after respiratory binning. The network is compared to conventional architectures such as a U-Net, which has 30 times more trainable parameters.

RESULTS

MODEST can reconstruct high-quality 4D-MRI with higher image quality than a U-Net, despite a thirty-fold reduction in trainable parameters. High-quality 4D-MRI can be obtained using MODEST in approximately 2.5 min, including acquisition, processing, and reconstruction.

CONCLUSION

High-quality accelerated 4D-MRI can be obtained using MODEST, which is particularly interesting for MRIgRT.

Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction From Echocardiogram Videos

Left-ventricular ejection fraction (LVEF) is an important indicator of heart failure. Existing methods for LVEF estimation from video require large amounts of annotated data to achieve high performance, e.g. using 10,030 labeled echocardiogram videos to achieve mean absolute error (MAE) of 4.10. Labeling these videos is time-consuming however and limits potential downstream applications to other heart diseases. This paper presents the first semi-supervised approach for LVEF prediction. Unlike general video prediction tasks, LVEF prediction is specifically related to changes in the left ventricle (LV) in echocardiogram videos. By incorporating knowledge learned from predicting LV segmentations into LVEF regression, we can provide additional context to the model for better predictions. To this end, we propose a novel Cyclical Self-Supervision (CSS) method for learning video-based LV segmentation, which is motivated by the observation that the heartbeat is a cyclical process with temporal repetition. Prediction masks from our segmentation model can then be used as additional input for LVEF regression to provide spatial context for the LV region. We also introduce teacher-student distillation to distill the information from LV segmentation masks into an end-to-end LVEF regression model that only requires video inputs. Results show our method outperforms alternative semi-supervised methods and can achieve MAE of 4.17, which is competitive with state-of-the-art supervised performance, using half the number of labels. Validation on an external dataset also shows improved generalization ability from using our method.

Automated segmentation of long and short axis DENSE cardiovascular magnetic resonance for myocardial strain analysis using spatio-temporal convolutional neural networks

BACKGROUND

Cine Displacement Encoding with Stimulated Echoes (DENSE) facilitates the quantification of myocardial deformation, by encoding tissue displacements in the cardiovascular magnetic resonance (CMR) image phase, from which myocardial strain can be estimated with high accuracy and reproducibility. Current methods for analyzing DENSE images still heavily rely on user input, making this process time-consuming and subject to inter-observer variability. The present study sought to develop a spatio-temporal deep learning model for segmentation of the left-ventricular (LV) myocardium, as spatial networks often fail due to contrast-related properties of DENSE images.

METHODS

2D + time nnU-Net-based models have been trained to segment the LV myocardium from DENSE magnitude data in short- and long-axis images. A dataset of 360 short-axis and 124 long-axis slices was used to train the networks, from a combination of healthy subjects and patients with various conditions (hypertrophic and dilated cardiomyopathy, myocardial infarction, myocarditis). Segmentation performance was evaluated using ground-truth manual labels, and a strain analysis using conventional methods was performed to assess strain agreement with manual segmentation. Additional validation was performed using an externally acquired dataset to compare the inter- and intra-scanner reproducibility with respect to conventional methods.

RESULTS

Spatio-temporal models gave consistent segmentation performance throughout the cine sequence, while 2D architectures often failed to segment end-diastolic frames due to the limited blood-to-myocardium contrast. Our models achieved a DICE score of 0.83 ± 0.05 and a Hausdorff distance of 4.0 ± 1.1 mm for short-axis segmentation, and 0.82 ± 0.03 and 7.9 ± 3.9 mm respectively for long-axis segmentations. Strain measurements obtained from automatically estimated myocardial contours showed good to excellent agreement with manual pipelines, and remained within the limits of inter-user variability estimated in previous studies.

CONCLUSION

Spatio-temporal deep learning shows increased robustness for the segmentation of cine DENSE images. It provides excellent agreement with manual segmentation for strain extraction. Deep learning will facilitate the analysis of DENSE data, bringing it one step closer to clinical routine.

Deep learning-based prediction of intra-cardiac blood flow in long-axis cine magnetic resonance imaging

PURPOSE

We aimed to design and evaluate a deep learning-based method to automatically predict the time-varying in-plane blood flow velocity within the cardiac cavities in long-axis cine MRI, validated against 4D flow.

METHODS

A convolutional neural network (CNN) was implemented, taking cine MRI as the input and the in-plane velocity derived from the 4D flow acquisition as the ground truth. The method was evaluated using velocity vector end-point error (EPE) and angle error. Additionally, the E/A ratio and diastolic function classification derived from the predicted velocities were compared to those derived from 4D flow.

RESULTS

For intra-cardiac pixels with a velocity > 5 cm/s, our method achieved an EPE of 8.65 cm/s and angle error of 41.27°. For pixels with a velocity > 25 cm/s, the angle error significantly degraded to 19.26°. Although the averaged blood flow velocity prediction was under-estimated by 26.69%, the high correlation (PCC = 0.95) of global time-varying velocity and the visual evaluation demonstrate a good agreement between our prediction and 4D flow data. The E/A ratio was derived with minimal bias, but with considerable mean absolute error of 0.39 and wide limits of agreement. The diastolic function classification showed a high accuracy of 86.9%.

CONCLUSION

Using a deep learning-based algorithm, intra-cardiac blood flow velocities can be predicted from long-axis cine MRI with high correlation with 4D flow derived velocities. Visualization of the derived velocities provides adjunct functional information and may potentially be used to derive the E/A ratio from conventional CMR exams.

A segmentation-informed deep learning framework to register dynamic two-dimensional magnetic resonance images of the vocal tract during speech

Objective

Dynamic magnetic resonance (MR) imaging enables visualisation of articulators during speech. There is growing interest in quantifying articulator motion in two-dimensional MR images of the vocal tract, to better understand speech production and potentially inform patient management decisions. Image registration is an established way to achieve this quantification. Recently, segmentation-informed deformable registration frameworks have been developed and have achieved state-of-the-art accuracy. This work aims to adapt such a framework and optimise it for estimating displacement fields between dynamic two-dimensional MR images of the vocal tract during speech.

Methods

A deep-learning-based registration framework was developed and compared with current state-of-the-art registration methods and frameworks (two traditional methods and three deep-learning-based frameworks, two of which are segmentation informed). The accuracy of the methods and frameworks was evaluated using the Dice coefficient (DSC), average surface distance (ASD) and a metric based on velopharyngeal closure. The metric evaluated if the fields captured a clinically relevant and quantifiable aspect of articulator motion.

Results

The segmentation-informed frameworks achieved higher DSCs and lower ASDs and captured more velopharyngeal closures than the traditional methods and the framework that was not segmentation informed. All segmentation-informed frameworks achieved similar DSCs and ASDs. However, the proposed framework captured the most velopharyngeal closures.

Conclusions

A framework was successfully developed and found to more accurately estimate articulator motion than five current state-of-the-art methods and frameworks.

Significance

The first deep-learning-based framework specifically for registering dynamic two-dimensional MR images of the vocal tract during speech has been developed and evaluated.

Cross-Modality Image Registration Using a Training-Time Privileged Third Modality

In this work, we consider the task of pairwise cross-modality image registration, which may benefit from exploiting additional images available only at training time from an additional modality that is different to those being registered. As an example, we focus on aligning intra-subject multiparametric Magnetic Resonance (mpMR) images, between T2-weighted (T2w) scans and diffusion-weighted scans with high b-value (DWI [Formula: see text]). For the application of localising tumours in mpMR images, diffusion scans with zero b-value (DWI [Formula: see text]) are considered easier to register to T2w due to the availability of corresponding features. We propose a learning from privileged modality algorithm, using a training-only imaging modality DWI [Formula: see text], to support the challenging multi-modality registration problems. We present experimental results based on 369 sets of 3D multiparametric MRI images from 356 prostate cancer patients and report, with statistical significance, a lowered median target registration error of 4.34 mm, when registering the holdout DWI [Formula: see text] and T2w image pairs, compared with that of 7.96 mm before registration. Results also show that the proposed learning-based registration networks enabled efficient registration with comparable or better accuracy, compared with a classical iterative algorithm and other tested learning-based methods with/without the additional modality. These compared algorithms also failed to produce any significantly improved alignment between DWI [Formula: see text] and T2w in this challenging application.

Automatic myocardium strain quantification in MR synthetic images with Deep Leaning

Accurate quantification of myocardium strain in magnetic resonance images is important to correctly diagnose and monitor cardiac diseases. Currently, available methods to estimate motion are based on tracking brightness pattern differences between images. In cine-MR images, the myocardium interior presents an inhered homogeneity, which reduces the accuracy in estimated motion, and consequently strain. Neural networks have recently been shown to be an important tool for a variety of applications, including motion estimation. In this work, we investigate the feasibility of quantifying myocardium strain in cardiac resonance synthetic images using motion generated by a compact and powerful network called Pyramid, Warping, and Cost Volume (PWC). Using the motion generated by the neural network, the radial myocardium strain obtained presents a mean average error of 12.30% +- 6.50%, and in the circumferential direction 1.20% +-0.61 %, better than the two classical methods evaluated. Clinical Relevance- This work demonstrates the feasibility of estimating myocardium strain using motion estimated by a convolutional neural network.

Regional Cardiac Motion Scoring with Multi-scale Motion-based Spatial Attention

Regional cardiac motion scoring aims to classify the motion status of each myocardium segment into one of the four categories (normal, hypokinetic, akinetic and dyskinetic) from multiple short-axis MR sequences. It is essential for prognosis and early diagnosis for various cardiac diseases. However, the complex motion procedure of myocardium and the invisible pattern differences pose great challenges, leading to low performance for automatic methods. Most existing work mitigate the task by differentiating the normal motion patterns from the abnormal ones, without fine-grained motion scoring. We propose an effective method for the task of cardiac motion scoring by connecting a bottom-up and another top-down branch with a novel motion-based spatial attention module in multi-scale space. Specifically, we use the convolution blocks for low-level feature extraction that acts as a bottom-up mechanism, and the task of optical flow for explicit motion extraction that acts as a top-down mechanism for high-level allocation of spatial attention. To this end, a newly designed Multi-scale Motion-based Spatial Attention (MMSA) mechanism is used as the pivot connecting the bottom-up part and the top-down part, and adaptively weight the low-level features according to the motion information. Experimental results on a newly constructed dataset of 1440 myocardium segments from 90 subjects demonstrate that the proposed MMSA can accurately analyze the regional myocardium motion, with accuracies of 79.3% for 4-way motion scoring, 89.0% for abnormality detection, and correlation of 0.943 for estimation of motion score index. This work has great potential for practical assessment of cardiac motion function.

Simultaneous Segmentation and Motion Estimation of Left Ventricular Myocardium in 3D Echocardiography Using Multi-task Learning

Motion estimation and segmentation are both critical steps in identifying and assessing myocardial dysfunction, but are traditionally treated as unique tasks and solved as separate steps. However, many motion estimation techniques rely on accurate segmentations. It has been demonstrated in the computer vision and medical image analysis literature that both these tasks may be mutually beneficial when solved simultaneously. In this work, we propose a multi-task learning network that can concurrently predict volumetric segmentations of the left ventricle and estimate motion between 3D echocardiographic image pairs. The model exploits complementary latent features between the two tasks using a shared feature encoder with task-specific decoding branches. Anatomically inspired constraints are incorporated to enforce realistic motion patterns. We evaluate our proposed model on an in vivo 3D echocardiographic canine dataset. Results suggest that coupling these two tasks in a learning framework performs favorably when compared against single task learning and other alternative methods.

Learning a Model-Driven Variational Network for Deformable Image Registration

Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this issue and meanwhile retain the fast inference speed of deep learning, we propose VR-Net, a novel cascaded variational network for unsupervised deformable image registration. Using a variable splitting optimization scheme, we first convert the image registration problem, established in a generic variational framework, into two sub-problems, one with a point-wise, closed-form solution and the other one being a denoising problem. We then propose two neural layers (i.e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net (termed generalized denoising layer) to formulate the denoising problem. Finally, we cascade the three neural layers multiple times to form our VR-Net. Extensive experiments on three (two 2D and one 3D) cardiac magnetic resonance imaging datasets show that VR-Net outperforms state-of-the-art deep learning methods on registration accuracy, whilst maintaining the fast inference speed of deep learning and the data-efficiency of variational models.

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

Since its renaissance, deep learning has been widely used in various medical imaging tasks and has achieved remarkable success in many medical imaging applications, thereby propelling us into the so-called artificial intelligence (AI) era. It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. However, medical imaging presents unique challenges that confront deep learning approaches. In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues. We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. Then, we present several case studies that are commonly found in clinical practice, including digital pathology and chest, brain, cardiovascular, and abdominal imaging. Rather than presenting an exhaustive literature survey, we instead describe some prominent research highlights related to these case study applications. We conclude with a discussion and presentation of promising future directions.

SAUN: Stack attention U-Net for left ventricle segmentation from cardiac cine magnetic resonance imaging

PURPOSE

Quantification of left ventricular (LV) volume, ejection fraction and myocardial mass from multi-slice multi-phase cine MRI requires accurate segmentation of the LV in many images. We propose a stack attention-based convolutional neural network (CNN) approach for fully automatic segmentation from short-axis cine MR images.

METHODS

To extract the relevant spatiotemporal image features, we introduce two kinds of stack methods, spatial stack model and temporal stack model, combining the target image with its neighboring images as the input of a CNN. A stack attention mechanism is proposed to weigh neighboring image slices in order to extract the relevant features using the target image as a guide. Based on stack attention and standard U-Net, a novel Stack Attention U-Net (SAUN) is proposed and trained to perform the semantic segmentation task. A loss function combining cross-entropy and Dice is used to train SAUN. The performance of the proposed method was evaluated on an internal and a public dataset using technical metrics including Dice, Hausdorff distance (HD), and mean contour distance (MCD), as well as clinical parameters, including left ventricular ejection fraction (LVEF) and myocardial mass (LVM). In addition, the results of SAUN were compared to previously presented CNN methods, including U-Net and SegNet.

RESULTS

The spatial stack attention model resulted in better segmentation results than the temporal stack model. On the internal dataset comprising of 167 post-myocardial infarction patients and 57 healthy volunteers, our method achieved a mean Dice of 0.91, HD of 3.37 mm, and MCD of 1.08 mm. Evaluation on the publicly available ACDC dataset demonstrated good generalization performance, yielding a Dice of 0.92, HD of 9.4 mm, and MCD of 0.74 mm on end-diastolic images, and a Dice of 0.89, HD of 7.1 mm and MCD of 1.03 mm on end-systolic images. The Pearson correlation coefficient of LVEF and LVM between automatically and manually derived results were higher than 0.98 in both datasets.

CONCLUSION

We developed a CNN with a stack attention mechanism to automatically segment the LV chamber and myocardium from the multi-slice short-axis cine MRI. The experimental results demonstrate that the proposed approach exceeds existing state-of-the-art segmentation methods and verify its potential clinical applicability.

A Semi-supervised Joint Network for Simultaneous Left Ventricular Motion Tracking and Segmentation in 4D Echocardiography

This work presents a novel deep learning method to combine segmentation and motion tracking in 4D echocardiography. The network iteratively trains a motion branch and a segmentation branch. The motion branch is initially trained entirely unsupervised and learns to roughly map the displacements between a source and a target frame. The estimated displacement maps are then used to generate pseudo-ground truth labels to train the segmentation branch. The labels predicted by the trained segmentation branch are fed back into the motion branch and act as landmarks to help retrain the branch to produce smoother displacement estimations. These smoothed out displacements are then used to obtain smoother pseudo-labels to retrain the segmentation branch. Additionally, a biomechanically-inspired incompressibility constraint is implemented in order to encourage more realistic cardiac motion. The proposed method is evaluated against other approaches using synthetic and in-vivo canine studies. Both the segmentation and motion tracking results of our model perform favorably against competing methods.

Artificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy

In many cardiovascular pathologies, the shape and motion of the heart provide important clues to understanding the mechanisms of the disease and how it progresses over time. With the advent of large-scale cardiac data, statistical modeling of cardiac anatomy has become a powerful tool to provide automated, precise quantification of the status of patient-specific heart geometry with respect to reference populations. Powered by supervised or unsupervised machine learning algorithms, statistical cardiac shape analysis can be used to automatically identify and quantify the severity of heart diseases, to provide morphometric indices that are optimally associated with clinical factors, and to evaluate the likelihood of adverse outcomes. Recently, statistical cardiac atlases have been integrated with deep neural networks to enable anatomical consistency of cardiac segmentation, registration, and automated quality control. These combinations have already shown significant improvements in performance and avoid gross anatomical errors that could make the results unusable. This current trend is expected to grow in the near future. Here, we aim to provide a mini review highlighting recent advances in statistical atlasing of cardiac function in the context of artificial intelligence in cardiac imaging.

A SEMI-SUPERVISED JOINT LEARNING APPROACH TO LEFT VENTRICULAR SEGMENTATION AND MOTION TRACKING IN ECHOCARDIOGRAPHY

Accurate interpretation and analysis of echocardiography is important in assessing cardiovascular health. However, motion tracking often relies on accurate segmentation of the myocardium, which can be difficult to obtain due to inherent ultrasound properties. In order to address this limitation, we propose a semi-supervised joint learning network that exploits overlapping features in motion tracking and segmentation. The network simultaneously trains two branches: one for motion tracking and one for segmentation. Each branch learns to extract features relevant to their respective tasks and shares them with the other. Learned motion estimations propagate a manually segmented mask through time, which is used to guide future segmentation predictions. Physiological constraints are introduced to enforce realistic cardiac behavior. Experimental results on synthetic and in vivo canine 2D+t echocardiographic sequences outperform some competing methods in both tasks.

Deep Learning for Cardiac Image Segmentation: A Review

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound and major anatomical structures of interest (ventricles, atria, and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

TeTrIS: Template Transformer Networks for Image Segmentation With Shape Priors

In this paper, we introduce and compare different approaches for incorporating shape prior information into neural network-based image segmentation. Specifically, we introduce the concept of template transformer networks, where a shape template is deformed to match the underlying structure of interest through an end-to-end trained spatial transformer network. This has the advantage of explicitly enforcing shape priors, and this is free of discretization artifacts by providing a soft partial volume segmentation. We also introduce a simple yet effective way of incorporating priors in the state-of-the-art pixel-wise binary classification methods such as fully convolutional networks and U-net. Here, the template shape is given as an additional input channel, incorporating this information significantly reduces false positives. We report results on synthetic data and sub-voxel segmentation of coronary lumen structures in cardiac computed tomography showing the benefit of incorporating priors in neural network-based image segmentation.

A Deep Learning Segmentation Approach in Free-Breathing Real-Time Cardiac Magnetic Resonance Imaging

OBJECTIVES

The purpose of this study was to segment the left ventricle (LV) blood pool, LV myocardium, and right ventricle (RV) blood pool of end-diastole and end-systole frames in free-breathing cardiac magnetic resonance (CMR) imaging. Automatic and accurate segmentation of cardiac structures could reduce the postprocessing time of cardiac function analysis.

METHOD

We proposed a novel deep learning network using a residual block for the segmentation of the heart and a random data augmentation strategy to reduce the training time and the problem of overfitting. Automated cardiac diagnosis challenge (ACDC) data were used for training, and the free-breathing CMR data were used for validation and testing.

RESULTS

The average Dice was 0.919 (LV), 0.806 (myocardium), and 0.818 (RV). The average IoU was 0.860 (LV), 0.699 (myocardium), and 0.761 (RV).

CONCLUSIONS

The proposed method may aid in the segmentation of cardiac images and improves the postprocessing efficiency of cardiac function analysis.