Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset.

Objectives: To assess the feasibility of extracting radiomics signal intensity based features from the myocardium using cardiovascular magnetic resonance (CMR) imaging stress perfusion sequences. Furthermore, to compare the diagnostic performance of radiomics models against standard-of-care qualitative visual assessment of stress perfusion images, with the ground truth stenosis label being defined by invasive Fractional Flow Reserve (FFR) and quantitative coronary angiography. Methods: We used the Dan-NICAD 1 dataset, a multi-centre study with coronary computed tomography angiography, 1,5 T CMR stress perfusion, and invasive FFR available for a subset of 148 patients with suspected coronary artery disease. Image segmentation was performed by two independent readers. We used the Pyradiomics platform to extract radiomics first-order (n = 14) and texture (n = 75) features from the LV myocardium (basal, mid, apical) in rest and stress perfusion images. Results: Overall, 92 patients (mean age 62 years, 56 men) were included in the study, 39 with positive FFR. We double-cross validated the model and, in each inner fold, we trained and validated a per territory model. The conventional analysis results reported sensitivity of 41% and specificity of 84%. Our final radiomics model demonstrated an improvement on these results with an average sensitivity of 53% and specificity of 86%. Conclusion: In this proof-of-concept study from the Dan-NICAD dataset, we demonstrate the feasibility of radiomics analysis applied to CMR perfusion images with a suggestion of superior diagnostic performance of radiomics models over conventional visual analysis of perfusion images in picking up perfusion defects defined by invasive coronary angiography.

Deep Learning Segmentation of the Right Ventricle in Cardiac MRI: The M&Ms Challenge.

In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

MyoPS: A benchmark of myocardial pathology segmentation combining three-sequence cardiac magnetic resonance images.

Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on the myocardium is the key to this assessment. This work defines a new task of medical image analysis, i.e., to perform myocardial pathology segmentation (MyoPS) combining three-sequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. Note that MyoPS refers to both myocardial pathology segmentation and the challenge in this paper. The challenge provided 45 paired and pre-aligned CMR images, allowing algorithms to combine the complementary information from the three CMR sequences for pathology segmentation. In this article, we provide details of the challenge, survey the works from fifteen participants and interpret their methods according to five aspects, i.e., preprocessing, data augmentation, learning strategy, model architecture and post-processing. In addition, we analyze the results with respect to different factors, in order to examine the key obstacles and explore the potential of solutions, as well as to provide a benchmark for future research. The average Dice scores of submitted algorithms were 0.614±0.231 and 0.644±0.153 for myocardial scars and edema, respectively. We conclude that while promising results have been reported, the research is still in the early stage, and more in-depth exploration is needed before a successful application to the clinics. MyoPS data and evaluation tool continue to be publicly available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/myops20/).

Prediction of incident cardiovascular events using machine learning and CMR radiomics.

OBJECTIVES: Evaluation of the feasibility of using cardiovascular magnetic resonance (CMR) radiomics in the prediction of incident atrial fibrillation (AF), heart failure (HF), myocardial infarction (MI), and stroke using machine learning techniques. METHODS: We identified participants from the UK Biobank who experienced incident AF, HF, MI, or stroke during the continuous longitudinal follow-up. The CMR indices and the vascular risk factors (VRFs) as well as the CMR images were obtained for each participant. Three-segmented regions of interest (ROIs) were computed: right ventricle cavity, left ventricle (LV) cavity, and LV myocardium in end-systole and end-diastole phases. Radiomics features were extracted from the 3D volumes of the ROIs. Seven integrative models were built for each incident cardiovascular disease (CVD) as an outcome. Each model was built with VRF, CMR indices, and radiomics features and a combination of them. Support vector machine was used for classification. To assess the model performance, the accuracy, sensitivity, specificity, and AUC were reported. RESULTS: AF prediction model using the VRF+CMR+Rad model (accuracy: 0.71, AUC 0.76) obtained the best result. However, the AUC was similar to the VRF+Rad model. HF showed the most significant improvement with the inclusion of CMR metrics (VRF+CMR+Rad: 0.79, AUC 0.84). Moreover, adding only the radiomics features to the VRF reached an almost similarly good performance (VRF+Rad: accuracy 0.77, AUC 0.83). Prediction models looking into incident MI and stroke reached slightly smaller improvement. CONCLUSIONS: Radiomics features may provide incremental predictive value over VRF and CMR indices in the prediction of incident CVDs. KEY POINTS: • Prediction of incident atrial fibrillation, heart failure, stroke, and myocardial infarction using machine learning techniques. • CMR radiomics, vascular risk factors, and standard CMR indices will be considered in the machine learning models. • The experiments show that radiomics features can provide incremental predictive value over VRF and CMR indices in the prediction of incident cardiovascular diseases.

Atrial fibrillation prediction by combining ECG markers and CMR radiomics.

Atrial fibrillation (AF) is the most common cardiac arrhythmia. It is associated with a higher risk of important adverse health outcomes such as stroke and death. AF is linked to distinct electro-anatomic alterations. The main tool for AF diagnosis is the Electrocardiogram (ECG). However, an ECG recorded at a single time point may not detect individuals with paroxysmal AF. In this study, we developed machine learning models for discrimination of prevalent AF using a combination of image-derived radiomics phenotypes and ECG features. Thus, we characterize the phenotypes of prevalent AF in terms of ECG and imaging alterations. Moreover, we explore sex-differential remodelling by building sex-specific models. Our integrative model including radiomics and ECG together resulted in a better performance than ECG alone, particularly in women. ECG had a lower performance in women than men (AUC: 0.77 vs 0.88, p < 0.05) but adding radiomics features, the accuracy of the model was able to improve significantly. The sensitivity also increased considerably in women by adding the radiomics (0.68 vs 0.79, p < 0.05) having a higher detection of AF events. Our findings provide novel insights into AF-related electro-anatomic remodelling and its variations by sex. The integrative radiomics-ECG model also presents a potential novel approach for earlier detection of AF.

Cardiac aging synthesis from cross-sectional data with conditional generative adversarial networks.

Age has important implications for health, and understanding how age manifests in the human body is the first step for a potential intervention. This becomes especially important for cardiac health, since age is the main risk factor for development of cardiovascular disease. Data-driven modeling of age progression has been conducted successfully in diverse applications such as face or brain aging. While longitudinal data is the preferred option for training deep learning models, collecting such a dataset is usually very costly, especially in medical imaging. In this work, a conditional generative adversarial network is proposed to synthesize older and younger versions of a heart scan by using only cross-sectional data. We train our model with more than 14,000 different scans from the UK Biobank. The induced modifications focused mainly on the interventricular septum and the aorta, which is consistent with the existing literature in cardiac aging. We evaluate the results by measuring image quality, the mean absolute error for predicted age using a pre-trained regressor, and demonstrate the application of synthetic data for counter-balancing biased datasets. The results suggest that the proposed approach is able to model realistic changes in the heart using only cross-sectional data and that these data can be used to correct age bias in a dataset.

Domain generalization in deep learning for contrast-enhanced imaging.

BACKGROUND: The domain generalization problem has been widely investigated in deep learning for non-contrast imaging over the last years, but it received limited attention for contrast-enhanced imaging. However, there are marked differences in contrast imaging protocols across clinical centers, in particular in the time between contrast injection and image acquisition, while access to multi-center contrast-enhanced image data is limited compared to available datasets for non-contrast imaging. This calls for new tools for generalizing single-domain, single-center deep learning models across new unseen domains and clinical centers in contrast-enhanced imaging. METHODS: In this paper, we present an exhaustive evaluation of deep learning techniques to achieve generalizability to unseen clinical centers for contrast-enhanced image segmentation. To this end, several techniques are investigated, optimized and systematically evaluated, including data augmentation, domain mixing, transfer learning and domain adaptation. To demonstrate the potential of domain generalization for contrast-enhanced imaging, the methods are evaluated for ventricular segmentation in contrast-enhanced cardiac magnetic resonance imaging (MRI). RESULTS: The results are obtained based on a multi-center cardiac contrast-enhanced MRI dataset acquired in four hospitals located in three countries (France, Spain and China). They show that the combination of data augmentation and transfer learning can lead to single-center models that generalize well to new clinical centers not included during training. CONCLUSIONS: Single-domain neural networks enriched with suitable generalization procedures can reach and even surpass the performance of multi-center, multi-vendor models in contrast-enhanced imaging, hence eliminating the need for comprehensive multi-center datasets to train generalizable models.

Minimising multi-centre radiomics variability through image normalisation: a pilot study.

Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features' variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification ( balanced accuracy in between 0.78 ± 0.08 and 0.79 ± 0.09). Models trained with features from images without normalisation showed the worst performance overall ( balanced accuracy in between 0.45 ± 0.28 and 0.60 ± 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.

Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance.

Left Ventricular (LV) Non-compaction (LVNC), Hypertrophic Cardiomyopathy (HCM), and Dilated Cardiomyopathy (DCM) share morphological and functional traits that increase the diagnosis complexity. Additional clinical information, besides imaging data such as cardiovascular magnetic resonance (CMR), is usually required to reach a definitive diagnosis, including electrocardiography (ECG), family history, and genetics. Alternatively, indices of hypertrabeculation have been introduced, but they require tedious and time-consuming delineations of the trabeculae on the CMR images. In this paper, we propose a radiomics approach to automatically encode differences in the underlying shape, gray-scale and textural information in the myocardium and its trabeculae, which may enhance the capacity to differentiate between these overlapping conditions. A total of 118 subjects, including 35 patients with LVNC, 25 with HCM, 37 with DCM, as well as 21 healthy volunteers (NOR), underwent CMR imaging. A comprehensive radiomics characterization was applied to LV short-axis images to quantify shape, first-order, co-occurrence matrix, run-length matrix, and local binary patterns. Conventional CMR indices (LV volumes, mass, wall thickness, LV ejection fraction-LVEF-), as well as hypertrabeculation indices by Petersen and Jacquier, were also analyzed. State-of-the-art Machine Learning (ML) models (one-vs.-rest Support Vector Machine-SVM-, Logistic Regression-LR-, and Random Forest Classifier-RF-) were used for one-vs.-rest classification tasks. The use of radiomics models for the automated diagnosis of LVNC, HCM, and DCM resulted in excellent one-vs.-rest ROC-AUC values of 0.95 while generating these results without the need for the delineation of the trabeculae. First-order and texture features resulted to be among the most discriminative features in the obtained radiomics signatures, indicating their added value for quantifying relevant tissue patterns in cardiomyopathy differential diagnosis.

Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge.

The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.

Cardiac magnetic resonance radiomics: basic principles and clinical perspectives.

Radiomics is a novel image analysis technique, whereby voxel-level information is extracted from digital images and used to derive multiple numerical quantifiers of shape and tissue character. Cardiac magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function. Conventional analysis of CMR scans is mostly reliant on qualitative image analysis and basic geometric quantifiers. Small proof-of-concept studies have demonstrated the feasibility and superior diagnostic accuracy of CMR radiomics analysis over conventional reporting. CMR radiomics has the potential to transform our approach to defining image phenotypes and, through this, improve diagnostic accuracy, treatment selection, and prognostication. The purpose of this article is to provide an overview of radiomics concepts for clinicians, with particular consideration of application to CMR. We will also review existing literature on CMR radiomics, discuss challenges, and consider directions for future work.

Image-Based Cardiac Diagnosis With Machine Learning: A Review.

Cardiac imaging plays an important role in the diagnosis of cardiovascular disease (CVD). Until now, its role has been limited to visual and quantitative assessment of cardiac structure and function. However, with the advent of big data and machine learning, new opportunities are emerging to build artificial intelligence tools that will directly assist the clinician in the diagnosis of CVDs. This paper presents a thorough review of recent works in this field and provide the reader with a detailed presentation of the machine learning methods that can be further exploited to enable more automated, precise and early diagnosis of most CVDs.