Convolutional Neural Network With Shape Prior Applied to Cardiac MRI Segmentation

EMONAS-Net: Efficient multiobjective neural architecture search using surrogate-assisted evolutionary algorithm for 3D medical image segmentation

Deep learning plays a critical role in medical image segmentation. Nevertheless, manually designing a neural network for a specific segmentation problem is a very difficult and time-consuming task due to the massive hyperparameter search space, long training time and large volumetric data. Therefore, most designed networks are highly complex, task specific and over-parametrized. Recently, multiobjective neural architecture search (NAS) methods have been proposed to automate the design of accurate and efficient segmentation architectures. However, they only search for either the micro- or macro-structure of the architecture, do not use the information produced during the optimization process to increase the efficiency of the search, or do not consider the volumetric nature of medical images. In this work, we present EMONAS-Net, an Efficient MultiObjective NAS framework for 3D medical image segmentation that optimizes both the segmentation accuracy and size of the network. EMONAS-Net has two key components, a novel search space that considers the configuration of the micro- and macro-structure of the architecture and a Surrogate-assisted Multiobjective Evolutionary based Algorithm (SaMEA algorithm) that efficiently searches for the best hyperparameter values. The SaMEA algorithm uses the information collected during the initial generations of the evolutionary process to identify the most promising subproblems and select the best performing hyperparameter values during mutation to improve the convergence speed. Furthermore, a Random Forest surrogate model is incorporated to accelerate the fitness evaluation of the candidate architectures. EMONAS-Net is tested on the tasks of prostate segmentation from the MICCAI PROMISE12 challenge, hippocampus segmentation from the Medical Segmentation Decathlon challenge, and cardiac segmentation from the MICCAI ACDC challenge. In all the benchmarks, the proposed framework finds architectures that perform better or comparable with competing state-of-the-art NAS methods while being considerably smaller and reducing the architecture search time by more than 50%.

Left Ventricle Quantification Challenge: A Comprehensive Comparison and Evaluation of Segmentation and Regression for Mid-Ventricular Short-Axis Cardiac MR Data

Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm 2 for the two areas, 2.15 mm for the cavity dimensions, 2.03 mm for RWTs, and a 9.5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications.

Automated cardiac segmentation of cross-modal medical images using unsupervised multi-domain adaptation and spatial neural attention structure

Accurate cardiac segmentation of multimodal images, e.g., magnetic resonance (MR), computed tomography (CT) images, plays a pivot role in auxiliary diagnoses, treatments and postoperative assessments of cardiovascular diseases. However, training a well-behaved segmentation model for the cross-modal cardiac image analysis is challenging, due to their diverse appearances/distributions from different devices and acquisition conditions. For instance, a well-trained segmentation model based on the source domain of MR images is often failed in the segmentation of CT images. In this work, a cross-modal images-oriented cardiac segmentation scheme is proposed using a symmetric full convolutional neural network (SFCNN) with the unsupervised multi-domain adaptation (UMDA) and a spatial neural attention (SNA) structure, termed UMDA-SNA-SFCNN, having the merits of without the requirement of any annotation on the test domain. Specifically, UMDA-SNA-SFCNN incorporates SNA to the classic adversarial domain adaptation network to highlight the relevant regions, while restraining the irrelevant areas in the cross-modal images, so as to suppress the negative transfer in the process of unsupervised domain adaptation. In addition, the multi-layer feature discriminators and a predictive segmentation-mask discriminator are established to connect the multi-layer features and segmentation mask of the backbone network, SFCNN, to realize the fine-grained alignment of unsupervised cross-modal feature domains. Extensive confirmative and comparative experiments on the benchmark Multi-Modality Whole Heart Challenge dataset show that the proposed model is superior to the state-of-the-art cross-modal segmentation methods.

DBAN: Adversarial Network With Multi-Scale Features for Cardiac MRI Segmentation

With the development of medical artificial intelligence, automatic magnetic resonance image (MRI) segmentation method is quite desirable. Inspired by the power of deep neural networks, a novel deep adversarial network, dilated block adversarial network (DBAN), is proposed to perform left ventricle, right ventricle, and myocardium segmentation in short-axis cardiac MRI. DBAN contains a segmentor along with a discriminator. In the segmentor, the dilated block (DB) is proposed to capture, and aggregate multi-scale features. The segmentor can produce segmentation probability maps while the discriminator can differentiate the segmentation probability map, and the ground truth at the pixel level. In addition, confidence probability maps generated by the discriminator can guide the segmentor to modify segmentation probability maps. Extensive experiments demonstrate that DBAN has achieved the state-of-the-art performance on the ACDC dataset. Quantitative analyses indicate that cardiac function indices from DBAN are similar to those from clinical experts. Therefore, DBAN can be a potential candidate for short-axis cardiac MRI segmentation in clinical applications.

Learning With Context Feedback Loop for Robust Medical Image Segmentation

Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead to less output pixel interdependence producing incomplete and unrealistic segmentation results. In this paper, we present a fully automatic deep learning method for robust medical image segmentation by formulating the segmentation problem as a recurrent framework using two systems. The first one is a forward system of an encoder-decoder CNN that predicts the segmentation result from the input image. The predicted probabilistic output of the forward system is then encoded by a fully convolutional network (FCN)-based context feedback system. The encoded feature space of the FCN is then integrated back into the forward system's feed-forward learning process. Using the FCN-based context feedback loop allows the forward system to learn and extract more high-level image features and fix previous mistakes, thereby improving prediction accuracy over time. Experimental results, performed on four different clinical datasets, demonstrate our method's potential application for single and multi-structure medical image segmentation by outperforming the state of the art methods. With the feedback loop, deep learning methods can now produce results that are both anatomically plausible and robust to low contrast images. Therefore, formulating image segmentation as a recurrent framework of two interconnected networks via context feedback loop can be a potential method for robust and efficient medical image analysis.

A Global and Local Enhanced Residual U-Net for Accurate Retinal Vessel Segmentation

Retinal vessel segmentation is a critical procedure towards the accurate visualization, diagnosis, early treatment, and surgery planning of ocular diseases. Recent deep learning-based approaches have achieved impressive performance in retinal vessel segmentation. However, they usually apply global image pre-processing and take the whole retinal images as input during network training, which have two drawbacks for accurate retinal vessel segmentation. First, these methods lack the utilization of the local patch information. Second, they overlook the geometric constraint that retina only occurs in a specific area within the whole image or the extracted patch. As a consequence, these global-based methods suffer in handling details, such as recognizing the small thin vessels, discriminating the optic disk, etc. To address these drawbacks, this study proposes a Global and Local enhanced residual U-nEt (GLUE) for accurate retinal vessel segmentation, which benefits from both the globally and locally enhanced information inside the retinal region. Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed method, which consistently improves the segmentation accuracy over a conventional U-Net and achieves competitive performance compared to the state-of-the-art.

Deep learning to estimate cardiac magnetic resonance-derived left ventricular mass

Background

Cardiac magnetic resonance (CMR) is the gold standard for left ventricular hypertrophy (LVH) diagnosis. CMR-derived LV mass can be estimated using proprietary algorithms (eg, InlineVF), but their accuracy and availability may be limited.

Objective

To develop an open-source deep learning model to estimate CMR-derived LV mass.

Methods

Within participants of the UK Biobank prospective cohort undergoing CMR, we trained 2 convolutional neural networks to estimate LV mass. The first (ML4Hreg) performed regression informed by manually labeled LV mass (available in 5065 individuals), while the second (ML4Hseg) performed LV segmentation informed by InlineVF (version D13A) contours. We compared ML4Hreg, ML4Hseg, and InlineVF against manually labeled LV mass within an independent holdout set using Pearson correlation and mean absolute error (MAE). We assessed associations between CMR-derived LVH and prevalent cardiovascular disease using logistic regression adjusted for age and sex.

Results

We generated CMR-derived LV mass estimates within 38,574 individuals. Among 891 individuals in the holdout set, ML4Hseg reproduced manually labeled LV mass more accurately (r = 0.864, 95% confidence interval [CI] 0.847-0.880; MAE 10.41 g, 95% CI 9.82-10.99) than ML4Hreg (r = 0.843, 95% CI 0.823-0.861; MAE 10.51, 95% CI 9.86-11.15, P = .01) and InlineVF (r = 0.795, 95% CI 0.770-0.818; MAE 14.30, 95% CI 13.46-11.01, P < .01). LVH defined using ML4Hseg demonstrated the strongest associations with hypertension (odds ratio 2.76, 95% CI 2.51-3.04), atrial fibrillation (1.75, 95% CI 1.37-2.20), and heart failure (4.67, 95% CI 3.28-6.49).

Conclusions

ML4Hseg is an open-source deep learning model providing automated quantification of CMR-derived LV mass. Deep learning models characterizing cardiac structure may facilitate broad cardiovascular discovery.

Deep learning based fully automatic segmentation of the left ventricular endocardium and epicardium from cardiac cine MRI

Background

The segmentation of cardiac medical images is a crucial step for calculating clinical indices such as wall thickness, ventricular volume, and ejection fraction.

Methods

In this study, we introduce a method named LsUnet that combines multi-channel, fully convolutional neural network, and annular shape level-set methods for efficiently segmenting cardiac cine magnetic resonance (MR) images. In this method, the multi-channel deep learning algorithm is applied to train the segmentation task to extract the left ventricle (LV) endocardial and epicardial contours. Next, the segmentation contours from the multi-channel deep learning method are incorporated into a level-set formulation, which is dedicated explicitly to detecting annular shapes to assure the segmentation's accuracy and robustness.

Results

The proposed automatic approach was evaluated on 95 volumes (total 1,076 slices, ~80% as for training datasets, ~20% 2D as for testing datasets). This combined multi-channel deep learning and annular shape level-set segmentation method achieved high accuracy with average Dice values reaching 92.15% and 95.42% for LV endocardium and epicardium delineation, respectively, in comparison to the reference standard (the manual segmentation).

Conclusions

A novel method for fully automatic segmentation of the LV endocardium and epicardium from different MRI datasets is presented. The proposed workflow is accurate and robust compared to the reference and other state-of-the-art methods.

Convexity preserving level set for left ventricle segmentation

In clinical applications of cardiac left ventricle (LV) segmentation, the segmented LV is desired to include the cavity, trabeculae, and papillary muscles, which form a convex shape. However, the intensities of trabeculae and papillary muscles are similar to myocardium. Consequently, segmentation algorithms may easily misclassify trabeculae and papillary muscles as myocardium. In this paper, we propose a level set method with a convexity preserving mechanism to ensure the convexity of the segmented LV. In the proposed level set method, the curvature of the level set contours is used to control their convexity, such that the level set contour is finally deformed as a convex shape. The experimental results and the comparison with other level set methods show the advantage of our method in terms of segmentation accuracy. Compared with the state-of-the-art methods using deep-learning, our method is able to achieve comparable segmentation accuracy without the need for training, while the deep-learning based method requires a large set of training data and high-quality manual segmentation. Therefore, our method can be conveniently used in situation where training data and their manual segmentation are not available.

A cascaded FC-DenseNet and level set method (FCDL) for fully automatic segmentation of the right ventricle in cardiac MRI

Accurate segmentation of the right ventricle (RV) from cardiac magnetic resonance imaging (MRI) images is an essential step in estimating clinical indices such as stroke volume and ejection fraction. Recently, image segmentation methods based on fully convolutional neural networks (FCN) have drawn much attention and shown promising results. In this paper, a new fully automatic RV segmentation method combining the FC-DenseNet and the level set method (FCDL) is proposed. The FC-DenseNet is efficiently trained end-to-end, using RV images and ground truth masks to make a per-pixel semantic inference. As a result, probability images are produced, followed by the level set method responsible for smoothing and converging contours to improve accuracy. It is noted that the iteration times of the level set method is only 4 times, which is due to the semantic segmentation of the FC-DenseNet for RV. Finally, multi-object detection algorithm is applied to locate the RV. Experimental results (including 45 cases, 15 cases for training, 30 cases for testing) show that the FCDL method outperforms the U-net + level set (UL) and the level set methods that use the same dataset and the cardiac functional parameters are computed robustly by the FCDL method. The results validate the FCDL method as an efficient and satisfactory approach to RV segmentation.

An Anatomical Thermal 3D Model in Preclinical Research: Combining CT and Thermal Images

Even though animal trials are a controversial topic, they provide knowledge about diseases and the course of infections in a medical context. To refine the detection of abnormalities that can cause pain and stress to the animal as early as possible, new processes must be developed. Due to its noninvasive nature, thermal imaging is increasingly used for severity assessment in animal-based research. Within a multimodal approach, thermal images combined with anatomical information could be used to simulate the inner temperature profile, thereby allowing the detection of deep-seated infections. This paper presents the generation of anatomical thermal 3D models, forming the underlying multimodal model in this simulation. These models combine anatomical 3D information based on computed tomography (CT) data with a registered thermal shell measured with infrared thermography. The process of generating these models consists of data acquisition (both thermal images and CT), camera calibration, image processing methods, and structure from motion (SfM), among others. Anatomical thermal 3D models were successfully generated using three anesthetized mice. Due to the image processing improvement, the process was also realized for areas with few features, which increases the transferability of the process. The result of this multimodal registration in 3D space can be viewed and analyzed within a visualization tool. Individual CT slices can be analyzed axially, sagittally, and coronally with the corresponding superficial skin temperature distribution. This is an important and successfully implemented milestone on the way to simulating the internal temperature profile. Using this temperature profile, deep-seated infections and inflammation can be detected in order to reduce animal suffering.

A survey on incorporating domain knowledge into deep learning for medical image analysis

Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area. To address this problem, researchers have started looking for external information beyond current available medical datasets. Traditional approaches generally leverage the information from natural images via transfer learning. More recent works utilize the domain knowledge from medical doctors, to create networks that resemble how medical doctors are trained, mimic their diagnostic patterns, or focus on the features or areas they pay particular attention to. In this survey, we summarize the current progress on integrating medical domain knowledge into deep learning models for various tasks, such as disease diagnosis, lesion, organ and abnormality detection, lesion and organ segmentation. For each task, we systematically categorize different kinds of medical domain knowledge that have been utilized and their corresponding integrating methods. We also provide current challenges and directions for future research.

Automatic cardiac cine MRI segmentation and heart disease classification

Cardiac cine magnetic resonance imaging (MRI) continues to be recognized as an established modality for non-invasive assessment of the function and structure of the cardiovascular system. Making full use of fully convolutional neural networks CNNs ability to operate pixel-wise classification, cine MRI sequences can be segmented and volumetric features of three key heart structures are computed for disease prediction. The three key heart structures are the left ventricle cavity, right ventricle cavity and the left ventricle myocardium. In this paper, we suggest an automated pipeline for both cardiac segmentation and diagnosis. The study was conducted on a dataset of 150 patients from Dijon Hospital in the context of the post-2017 Medical Image Computing and Computer Assisted Intervention MICCAI, Automated Cardiac Diagnosis Challenge (ACDC). The challenge consists in two phases: (i) a segmentation contest, where performance is evaluated on dice overlap coefficient and Hausdorff distance metrics, and a (ii) diagnosis contest for heart disease classification. For this aim, we propose the use of a deep learning based network for segmentation of the three key cardiac structures within short-axis cine MRI sequences and a classifier ensemble for heart disease classification. The deep learning segmentation network is a UNet fully convolutional neural network variant with fewer trainable parameters. The classifier ensemble consists in combining three classifiers, namely a multilayer perceptron, a random forest and a support vector machine. Before feeding the segmentation network, a preliminary step consists in localizing heart region and cropping input images to a restricted region of interest (ROI). This is achieved by a signal processing based approach and aims at reducing multi-class imbalance and computational load. We achieved nearly state of the art accuracy performances for both the segmentation and disease classification challenges. Reporting a mean dice overlap coefficient of 0.92 for the three cardiac structures segmentation, along with good limits of agreement for the various derived clinical indices, leading to an accuracy of 0.92 for the disease classification on unseen data.

Multi-Scale Self-Guided Attention for Medical Image Segmentation

Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. First, the use of multi-scale approaches, i.e., encoder-decoder architectures, leads to a redundant use of information, where similar low-level features are extracted multiple times at multiple scales. Second, long-range feature dependencies are not efficiently modeled, resulting in non-optimal discriminative feature representations associated with each semantic class. In this paper we attempt to overcome these limitations with the proposed architecture, by capturing richer contextual dependencies based on the use of guided self-attention mechanisms. This approach is able to integrate local features with their corresponding global dependencies, as well as highlight interdependent channel maps in an adaptive manner. Further, the additional loss between different modules guides the attention mechanisms to neglect irrelevant information and focus on more discriminant regions of the image by emphasizing relevant feature associations. We evaluate the proposed model in the context of semantic segmentation on three different datasets: abdominal organs, cardiovascular structures and brain tumors. A series of ablation experiments support the importance of these attention modules in the proposed architecture. In addition, compared to other state-of-the-art segmentation networks our model yields better segmentation performance, increasing the accuracy of the predictions while reducing the standard deviation. This demonstrates the efficiency of our approach to generate precise and reliable automatic segmentations of medical images. Our code is made publicly available at: https://github.com/sinAshish/Multi-Scale-Attention.

Automatic segmentation of medical images using a novel Harris Hawk optimization method and an active contour model

Medical image segmentation is a key step to assist diagnosis of several diseases, and accuracy of a segmentation method is important for further treatments of different diseases. Different medical imaging modalities have different challenges such as intensity inhomogeneity, noise, low contrast, and ill-defined boundaries, which make automated segmentation a difficult task. To handle these issues, we propose a new fully automated method for medical image segmentation, which utilizes the advantages of thresholding and an active contour model. In this study, a Harris Hawks optimizer is applied to determine the optimal thresholding value, which is used to obtain the initial contour for segmentation. The obtained contour is further refined by using a spatially varying Gaussian kernel in the active contour model. The proposed method is then validated using a standard skin dataset (ISBI 2016), which consists of variable-sized lesions and different challenging artifacts, and a standard cardiac magnetic resonance dataset (ACDC, MICCAI 2017) with a wide spectrum of normal hearts, congenital heart diseases, and cardiac dysfunction. Experimental results show that the proposed method can effectively segment the region of interest and produce superior segmentation results for skin (overall Dice Score 0.90) and cardiac dataset (overall Dice Score 0.93), as compared to other state-of-the-art algorithms.

Non-invasive estimation of relative pressure for intracardiac flows using virtual work-energy

Intracardiac blood flow is driven by differences in relative pressure, and assessing these is critical in understanding cardiac disease. Non-invasive image-based methods exist to assess relative pressure, however, the complex flow and dynamically moving fluid domain of the intracardiac space limits assessment. Recently, we proposed a method, νWERP, utilizing an auxiliary virtual field to probe relative pressure through complex, and previously inaccessible flow domains. Here we present an extension of νWERP for intracardiac flow assessments, solving the virtual field over sub-domains to effectively handle the dynamically shifting flow domain. The extended νWERP is validated in an in-silico benchmark problem, as well as in a patient-specific simulation model of the left heart, proving accurate over ranges of realistic image resolutions and noise levels, as well as superior to alternative approaches. Lastly, the extended νWERP is applied on clinically acquired 4D Flow MRI data, exhibiting realistic ventricular relative pressure patterns, as well as indicating signs of diastolic dysfunction in an exemplifying patient case. Summarized, the extended νWERP approach represents a directly applicable implementation for intracardiac flow assessments.

Cardiac Segmentation With Strong Anatomical Guarantees

Convolutional neural networks (CNN) have had unprecedented success in medical imaging and, in particular, in medical image segmentation. However, despite the fact that segmentation results are closer than ever to the inter-expert variability, CNNs are not immune to producing anatomically inaccurate segmentations, even when built upon a shape prior. In this paper, we present a framework for producing cardiac image segmentation maps that are guaranteed to respect pre-defined anatomical criteria, while remaining within the inter-expert variability. The idea behind our method is to use a well-trained CNN, have it process cardiac images, identify the anatomically implausible results and warp these results toward the closest anatomically valid cardiac shape. This warping procedure is carried out with a constrained variational autoencoder (cVAE) trained to learn a representation of valid cardiac shapes through a smooth, yet constrained, latent space. With this cVAE, we can project any implausible shape into the cardiac latent space and steer it toward the closest correct shape. We tested our framework on short-axis MRI as well as apical two and four-chamber view ultrasound images, two modalities for which cardiac shapes are drastically different. With our method, CNNs can now produce results that are both within the inter-expert variability and always anatomically plausible without having to rely on a shape prior.

A Semi-Automatic Method To Segment The Left Atrium in MR Volumes With Varying Slice Numbers

Atrial fibrillation (AF) is the most common sustained arrhythmia and is associated with dramatic increases in mortality and morbidity. Atrial cine MR images are increasingly used in the management of this condition, but there are few specific tools to aid in the segmentation of such data. Some characteristics of atrial cine MR (thick slices, variable number of slices in a volume) preclude the direct use of traditional segmentation tools. When combined with scarcity of labelled data and similarity of the intensity and texture of the left atrium (LA) to other cardiac structures, the segmentation of the LA in CINE MRI becomes a difficult task. To deal with these challenges, we propose a semi-automatic method to segment the left atrium (LA) in MR images, which requires an initial user click per volume. The manually given location information is used to generate a chamber location map to roughly locate the LA, which is then used as an input to a deep network with slightly over 0.5 million parameters. A tracking method is introduced to pass the location information across a volume and to remove unwanted structures in segmentation maps. According to the results of our experiments conducted in an in-house MRI dataset, the proposed method outperforms the U-Net [1] with a margin of 20 mm on Hausdorff distance and 0.17 on Dice score, with limited manual interaction.

Fully Automated 3D Cardiac MRI Localisation and Segmentation Using Deep Neural Networks

Cardiac magnetic resonance (CMR) imaging is used widely for morphological assessment and diagnosis of various cardiovascular diseases. Deep learning approaches based on 3D fully convolutional networks (FCNs), have improved state-of-the-art segmentation performance in CMR images. However, previous methods have employed several pre-processing steps and have focused primarily on segmenting low-resolutions images. A crucial step in any automatic segmentation approach is to first localize the cardiac structure of interest within the MRI volume, to reduce false positives and computational complexity. In this paper, we propose two strategies for localizing and segmenting the heart ventricles and myocardium, termed multi-stage and end-to-end, using a 3D convolutional neural network. Our method consists of an encoder–decoder network that is first trained to predict a coarse localized density map of the target structure at a low resolution. Subsequently, a second similar network employs this coarse density map to crop the image at a higher resolution, and consequently, segment the target structure. For the latter, the same two-stage architecture is trained end-to-end. The 3D U-Net with some architectural changes (referred to as 3D DR-UNet) was used as the base architecture in this framework for both the multi-stage and end-to-end strategies. Moreover, we investigate whether the incorporation of coarse features improves the segmentation. We evaluate the two proposed segmentation strategies on two cardiac MRI datasets, namely, the Automatic Cardiac Segmentation Challenge (ACDC) STACOM 2017, and Left Atrium Segmentation Challenge (LASC) STACOM 2018. Extensive experiments and comparisons with other state-of-the-art methods indicate that the proposed multi-stage framework consistently outperforms the rest in terms of several segmentation metrics. The experimental results highlight the robustness of the proposed approach, and its ability to generate accurate high-resolution segmentations, despite the presence of varying degrees of pathology-induced changes to cardiac morphology and image appearance, low contrast, and noise in the CMR volumes.

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.

Left ventricle segmentation using a Bayesian approach with distance dependent shape priors

We propose a method for segmentation of the left ventricle in magnetic resonance cardiac images. The framework consists of an initial Bayesian segmentation of the central slice of the volume. This segmentation is used to locate a shape prior for the LV myocardial tissue. This shape prior is determined using the fact that the myocardium is approximately annular as seen in the short-axis. Then a second Bayesian segmentation is performed to obtain the final result. This procedure is repeated for the rest of the slices. An extrapolation of the area of the LV is used to determine a stopping criterion. The method was evaluated on the databases of the Cardiac Atlas project. Our results demonstrate a suitable accuracy for myocardial segmentation (≈0.8 Dice's coefficient). For the endocardium and the epicardium the Dice's coefficients are 0.94 and 0.9 respectively. The accuracy was also evaluated in terms of the Hausdorff distance and the average distance. For the myocardium we obtain 8 mm and 2 mm respectively. Our results demonstrate the capability and merits of the proposed method to estimate the structure of the LV. The method requires minimal user input and generates results with quality comparable to more complex approaches. This paper suggests a new efficient approach for automatic LV quantification based on a Bayesian technique with shape priors with errors comparable to state-of-the-art techniques.

A New Framework for Performing Cardiac Strain Analysis from Cine MRI Imaging in Mice

Cardiac magnetic resonance (MR) imaging is one of the most rigorous form of imaging to assess cardiac function in vivo. Strain analysis allows comprehensive assessment of diastolic myocardial function, which is not indicated by measuring systolic functional parameters using with a normal cine imaging module. Due to the small heart size in mice, it is not possible to perform proper tagged imaging to assess strain. Here, we developed a novel deep learning approach for automated quantification of strain from cardiac cine MR images. Our framework starts by an accurate localization of the LV blood pool center-point using a fully convolutional neural network (FCN) architecture. Then, a region of interest (ROI) that contains the LV is extracted from all heart sections. The extracted ROIs are used for the segmentation of the LV cavity and myocardium via a novel FCN architecture. For strain analysis, we developed a Laplace-based approach to track the LV wall points by solving the Laplace equation between the LV contours of each two successive image frames over the cardiac cycle. Following tracking, the strain estimation is performed using the Lagrangian-based approach. This new automated system for strain analysis was validated by comparing the outcome of these analysis with the tagged MR images from the same mice. There were no significant differences between the strain data obtained from our algorithm using cine compared to tagged MR imaging. Furthermore, we demonstrated that our new algorithm can determine the strain differences between normal and diseased hearts.

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.

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.