Three-dimensional Deep Convolutional Neural Networks for Automated Myocardial Scar Quantification in Hypertrophic Cardiomyopathy: A Multicenter Multivendor Study

[Artificial intelligence in cardiovascular radiology : Image acquisition, image reconstruction and workflow optimization]

BACKGROUND

Artificial intelligence (AI) has the potential to fundamentally change radiology workflow.

OBJECTIVES

This review article provides an overview of AI applications in cardiovascular radiology with a focus on image acquisition, image reconstruction, and workflow optimization.

MATERIALS AND METHODS

First, established applications of AI are presented for cardiovascular computed tomography (CT) and magnetic resonance imaging (MRI). Building on this, we describe the range of applications that are currently being developed and evaluated. The practical benefits, opportunities, and potential risks of artificial intelligence in cardiovascular imaging are critically discussed. The presentation is based on the relevant specialist literature and our own clinical and scientific experience.

RESULTS

AI-based techniques for image reconstruction are already commercially available and enable dose reduction in cardiovascular CT and accelerated image acquisition in cardiac MRI. Postprocessing of cardiovascular CT and MRI examinations can already be considerably simplified using established AI-based segmentation algorithms. In contrast, the practical benefits of many AI applications aimed at the diagnosis of cardiovascular diseases are less evident. Potential risks such as automation bias and considerations regarding cost efficiency should also be taken into account.

CONCLUSIONS

In a market characterized by great expectations and rapid technical development, it is important to realistically assess the practical benefits of AI applications for your own hospital or practice.

The role of artificial intelligence in cardiovascular magnetic resonance imaging

Cardiovascular magnetic resonance (CMR) imaging is the gold standard test for myocardial tissue characterization and chamber volumetric and functional evaluation. However, manual CMR analysis can be time-consuming and is subject to intra- and inter-observer variability. Artificial intelligence (AI) is a field that permits automated task performance through the identification of high-level and complex data relationships. In this review, we review the rapidly growing role of AI in CMR, including image acquisition, sequence prescription, artifact detection, reconstruction, segmentation, and data reporting and analysis including quantification of volumes, function, myocardial infarction (MI) and scar detection, and prediction of outcomes. We conclude with a discussion of the emerging challenges to widespread adoption and solutions that will allow for successful, broader uptake of this powerful technology.

Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis

BACKGROUND

Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge.

METHODS

Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.).

RESULTS

The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005).

CONCLUSIONS

The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.

Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis

Background

Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge.

Methods

Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.).

Results

The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005).

Conclusions

The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.

Automated prediction of isthmus areas in scar-related atrial tachycardias using artificial intelligence

INTRODUCTION

Ablation of scar-related reentrant atrial tachycardia (SRRAT) involves identification and ablation of a critical isthmus. A graph convolutional network (GCN) is a machine learning structure that is well-suited to analyze the irregularly-structured data obtained in mapping procedures and may be used to identify potential isthmuses.

METHODS

Electroanatomic maps from 29 SRRATs were collected, and custom electrogram features assessing key tissue and wavefront properties were calculated for each point. Isthmuses were labeled off-line. Training data was used to determine the optimal GCN parameters and train the final model. Putative isthmus points were predicted in the training and test populations and grouped into proposed isthmus areas based on density and distance thresholds. The primary outcome was the distance between the centroids of the true and closest proposed isthmus areas.

RESULTS

A total of 193 821 points were collected. Thirty isthmuses were detected in 29 tachycardias among 25 patients (median age 65.0, 5 women). The median (IQR) distance between true and the closest proposed isthmus area centroids was 8.2 (3.5, 14.4) mm in the training and 7.3 (2.8, 16.1) mm in the test group. The mean overlap in areas, measured by the Dice coefficient, was 11.5 ± 3.2% in the training group and 13.9 ± 4.6% in the test group.

CONCLUSION

A GCN can be trained to identify isthmus areas in SRRATs and may help identify critical ablation targets.

Imaging of Cardiac Fibrosis: An Update, From the AJR Special Series on Imaging of Fibrosis

Myocardial fibrosis (MF) is defined as excessive production and deposition of extra-cellular matrix proteins that result in pathologic myocardial remodeling. Three types of MF have been identified: replacement fibrosis from tissue necrosis, reactive fibrosis from myocardial stress, and infiltrative interstitial fibrosis from progressive deposition of nondegradable material such as amyloid. Although echocardiography, nuclear medicine, and CT play important roles in the assessment of MF, MRI is pivotal in the evaluation of MF, with the late gadolinium enhancement (LGE) technique used as a primary end point. The LGE technique focuses on the pattern and distribution of gadolinium accumulation in the myocardium and assists in the diagnosis and establishment of the cause of both ischemic and nonischemic cardiomyopathy. LGE MRI also aids prognostication and risk stratification. In addition, LGE MRI is used to guide the management of patients considered for ablation for arrhythmias. Parametric mapping techniques, including T1 mapping and extracellular volume measurement, allow detection and quantification of diffuse fibrosis, which may not be detected by LGE MRI. These techniques also allow monitoring of disease progression and therapy response. This review provides an update on the imaging of MF, including prognostication and risk stratification tools, electrophysiologic considerations, and disease monitoring.

Deep learning for automatic volumetric segmentation of left ventricular myocardium and ischaemic scar from multi-slice late gadolinium enhancement cardiovascular magnetic resonance

AIMS

This study details application of deep learning for automatic volumetric segmentation of left ventricular (LV) myocardium and scar and automated quantification of myocardial ischaemic scar burden from late gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR).

METHODS AND RESULTS

We included 501 images and manual segmentations of short-axis LGE-CMR from over 20 multinational sites, from which 377 studies were used for training and 124 studies from unique participants for internal validation. A third test set of 52 images was used for external evaluation. Three models, U-Net, Cascaded U-Net, and U-Net++, were trained with a novel adaptive weighted categorical cross-entropy loss function. Model performance was evaluated using concordance correlation coefficients (CCCs) for LV mass and per cent myocardial scar burden. Cascaded U-Net was found to be the best model for the quantification of LV mass and scar percentage. The model exhibited a mean difference of -5 ± 23 g for LV mass, -0.4 ± 11.2 g for scar mass, and -0.8 ± 7% for per cent scar. CCC were 0.87, 0.77, and 0.78 for LV mass, scar mass, and per cent scar burden, respectively, in the internal validation set and 0.75, 0.71, and 0.69, respectively, in the external test set. For segmental scar mass, CCC was 0.74 for apical scar, 0.91 for mid-ventricular scar, and 0.73 for basal scar, demonstrating moderate to strong agreement.

CONCLUSION

We successfully trained a convolutional neural network for volumetric segmentation and analysis of LV scar burden from LGE-CMR images in a large, multinational cohort of participants with ischaemic scar.

Harmonizing T1-Weighted Images to Improve Consistency of Brain Morphology Among Different Scanner Manufacturers in Alzheimer's disease

BACKGROUND

Brain MRI scanner variability can introduce bias in measurements. Harmonizing scanner variability is crucial.

PURPOSE

To develop a harmonization method aimed at removing scanner variability, and to evaluate the consistency of results in multicenter studies.

STUDY TYPE

Retrospective.

POPULATION

Multicenter data from 170 healthy participants (males/females = 98/72; age = 73.8 ± 7.3) and 170 Alzheimer's disease patients (males/females = 98/72; age = 76.2 ± 8.5) were compared with reference data from another 340 participants.

FIELD STRENGTH/SEQUENCE

3-T, magnetization prepared rapid gradient echo and turbo field echo; 1.5-T, inversion recovery prepared fast spoiled gradient echo T1-weighted sequences.

ASSESSMENT

Gray matter (GM) brain images, obtained through segmentation of T1-weighted images, were utilized to evaluate the performance of the harmonization method using common orthogonal basis extraction (HCOBE) and four other methods (removal of artificial voxel effect by linear regression, RAVEL; Z_score; general linear model, GLM; ComBat). Linear discriminant analysis (LDA) was used to access the effectiveness of different methods in reducing scanner variability. The performance of harmonization methods in preserving GM volumes heterogeneity was evaluated by the similarity of the relationship between GM proportion and age in the reference and multicenter data. Furthermore, the consistency of the harmonized multicenter data with the reference data were evaluated based on classification results (train/test = 7/3) and brain atrophy.

STATISTICAL TESTS

Two-sample t-tests, area under the curve (AUC), and Dice coefficients were used to analyze the consistency of results from the reference and harmonized multicenter data. A P-value <0.01 was considered statistically significant.

RESULTS

HCOBE reduced the scanner variability from 0.09 before harmonization to 0.003 (ideal: 0, RAVEL/Z_score/GLM/ComBat = 0.087/0.003/0.006/0.013). GM volumes showed no significant difference (P = 0.52) between the reference and HCOBE-harmonized multicenter data. Consistency evaluation showed that AUC values of 0.95 for both reference and HCOBE-harmonized multicenter data (RAVEL/Z_score/GLM/ComBat = 0.86/0.86/0.84/0.89), and the Dice coefficient increased from 0.73 before harmonization to 0.82 (ideal: 1, RAVEL/Z_score/GLM/ComBat = 0.39/0.64/0.59/0.74).

DATA CONCLUSION

HCOBE may help to remove scanner variability and could improve the consistency of results in multicenter studies.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY STAGE: 1.

Impact of late gadolinium enhancement image acquisition resolution on neural network based automatic scar segmentation

BACKGROUND

Automatic myocardial scar segmentation from late gadolinium enhancement (LGE) images using neural networks promises an alternative to time-consuming and observer-dependent semi-automatic approaches. However, alterations in data acquisition, reconstruction as well as post-processing may compromise network performance. The objective of the present work was to systematically assess network performance degradation due to a mismatch of point-spread function between training and testing data.

METHODS

Thirty-six high-resolution (0.7×0.7×2.0 mm3) LGE k-space datasets were acquired post-mortem in porcine models of myocardial infarction. The in-plane point-spread function and hence in-plane resolution Δx was retrospectively degraded using k-space lowpass filtering, while field-of-view and matrix size were kept constant. Manual segmentation of the left ventricle (LV) and healthy remote myocardium was performed to quantify location and area (% of myocardium) of scar by thresholding (≥ SD5 above remote). Three standard U-Nets were trained on training resolutions Δxtrain = 0.7, 1.2 and 1.7 mm to predict endo- and epicardial borders of LV myocardium and scar. The scar prediction of the three networks for varying test resolutions (Δxtest = 0.7 to 1.7 mm) was compared against the reference SD5 thresholding at 0.7 mm. Finally, a fourth network trained on a combination of resolutions (Δxtrain = 0.7 to 1.7 mm) was tested.

RESULTS

The prediction of relative scar areas showed the highest precision when the resolution of the test data was identical to or close to the resolution used during training. The median fractional scar errors and precisions (IQR) from networks trained and tested on the same resolution were 0.0 percentage points (p.p.) (1.24 - 1.45), and - 0.5 - 0.0 p.p. (2.00 - 3.25) for networks trained and tested on the most differing resolutions, respectively. Deploying the network trained on multiple resolutions resulted in reduced resolution dependency with median scar errors and IQRs of 0.0 p.p. (1.24 - 1.69) for all investigated test resolutions.

CONCLUSION

A mismatch of the imaging point-spread function between training and test data can lead to degradation of scar segmentation when using current U-Net architectures as demonstrated on LGE porcine myocardial infarction data. Training networks on multi-resolution data can alleviate the resolution dependency.

Current perspectives of sudden cardiac death management in hypertrophic cardiomyopathy

Hypertrophic cardiomyopathy (HCM) is an autosomal dominant disorder characterized by left ventricular hypertrophy. Sudden cardiac death (SCD) is a rare but the most catastrophic complication in patients with HCM. Implantable cardioverter-defibrillators (ICDs) are widely recognized as effective preventive measures for SCD. Individualized risk stratification and early intervention in HCM can significantly improve patient prognosis. In this study, we review the latest findings regarding pathogenesis, risk stratification, and prevention of SCD in HCM patients, highlighting the clinic practice of cardiovascular magnetic resonance imaging for SCD management.

Lightweight preprocessing and template matching facilitate streamlined ischemic myocardial scar classification

Purpose

Ischemic myocardial scarring (IMS) is a common outcome of coronary artery disease that potentially leads to lethal arrythmias and heart failure. Late-gadolinium-enhanced cardiac magnetic resonance (CMR) imaging scans have served as the diagnostic bedrock for IMS, with recent advancements in machine learning enabling enhanced scar classification. However, the trade-off for these improvements is intensive computational and time demands. As a solution, we propose a combination of lightweight preprocessing (LWP) and template matching (TM) to streamline IMS classification.

Approach

CMR images from 279 patients (151 IMS, 128 control) were classified for IMS presence using two convolutional neural networks (CNNs) and TM, both with and without LWP. Evaluation metrics included accuracy, sensitivity, specificity, F1-score, area under the receiver operating characteristic curve (AUROC), and processing time. External testing dataset analysis encompassed patient-level classifications (PLCs) and a CNN versus TM classification comparison (CVTCC).

Results

LWP enhanced the speed of both CNNs (4.9x) and TM (21.9x). Furthermore, in the absence of LWP, TM outpaced CNNs by over 10x, while with LWP, TM was more than 100x faster. Additionally, TM performed similarly to the CNNs in accuracy, sensitivity, specificity, F1-score, and AUROC, with PLCs demonstrating improvements across all five metrics. Moreover, the CVTCC revealed a substantial 90.9% agreement.

Conclusions

Our results highlight the effectiveness of LWP and TM in streamlining IMS classification. Anticipated enhancements to LWP's region of interest (ROI) isolation and TM's ROI targeting are expected to boost accuracy, positioning them as a potential alternative to CNNs for IMS classification, supporting the need for further research.

Artificial intelligence applied in cardiovascular disease: a bibliometric and visual analysis

Background

With the rapid development of technology, artificial intelligence (AI) has been widely used in the diagnosis and prognosis prediction of a variety of diseases, including cardiovascular disease. Facts have proved that AI has broad application prospects in rapid and accurate diagnosis.

Objective

This study mainly summarizes the research on the application of AI in the field of cardiovascular disease through bibliometric analysis and explores possible future research hotpots.

Methods

The articles and reviews regarding application of AI in cardiovascular disease between 2000 and 2023 were selected from Web of Science Core Collection on 30 December 2023. Microsoft Excel 2019 was applied to analyze the targeted variables. VOSviewer (version 1.6.16), Citespace (version 6.2.R2), and a widely used online bibliometric platform were used to conduct co-authorship, co-citation, and co-occurrence analysis of countries, institutions, authors, references, and keywords in this field.

Results

A total of 4,611 articles were selected in this study. AI-related research on cardiovascular disease increased exponentially in recent years, of which the USA was the most productive country with 1,360 publications, and had close cooperation with many countries. The most productive institutions and researchers were the Cedar sinai medical center and Acharya, Ur. However, the cooperation among most institutions or researchers was not close even if the high research outputs. Circulation is the journal with the largest number of publications in this field. The most important keywords are "classification", "diagnosis", and "risk". Meanwhile, the current research hotpots were "late gadolinium enhancement" and "carotid ultrasound".

Conclusions

AI has broad application prospects in cardiovascular disease, and a growing number of scholars are devoted to AI-related research on cardiovascular disease. Cardiovascular imaging techniques and the selection of appropriate algorithms represent the most extensively studied areas, and a considerable boost in these areas is predicted in the coming years.

MyoV: a deep learning-based tool for the automated quantification of muscle fibers

Accurate approaches for quantifying muscle fibers are essential in biomedical research and meat production. In this study, we address the limitations of existing approaches for hematoxylin and eosin-stained muscle fibers by manually and semiautomatically labeling over 660 000 muscle fibers to create a large dataset. Subsequently, an automated image segmentation and quantification tool named MyoV is designed using mask regions with convolutional neural networks and a residual network and feature pyramid network as the backbone network. This design enables the tool to allow muscle fiber processing with different sizes and ages. MyoV, which achieves impressive detection rates of 0.93-0.96 and precision levels of 0.91-0.97, exhibits a superior performance in quantification, surpassing both manual methods and commonly employed algorithms and software, particularly for whole slide images (WSIs). Moreover, MyoV is proven as a powerful and suitable tool for various species with different muscle development, including mice, which are a crucial model for muscle disease diagnosis, and agricultural animals, which are a significant meat source for humans. Finally, we integrate this tool into visualization software with functions, such as segmentation, area determination and automatic labeling, allowing seamless processing for over 400 000 muscle fibers within a WSI, eliminating the model adjustment and providing researchers with an easy-to-use visual interface to browse functional options and realize muscle fiber quantification from WSIs.

Artificial Intelligence in Heart Failure: Friend or Foe?

In recent times, there have been notable changes in cardiovascular medicine, propelled by the swift advancements in artificial intelligence (AI). The present work provides an overview of the current applications and challenges of AI in the field of heart failure. It emphasizes the "garbage in, garbage out" issue, where AI systems can produce inaccurate results with skewed data. The discussion covers issues in heart failure diagnostic algorithms, particularly discrepancies between existing models. Concerns about the reliance on the left ventricular ejection fraction (LVEF) for classification and treatment are highlighted, showcasing differences in current scientific perceptions. This review also delves into challenges in implementing AI, including variable considerations and biases in training data. It underscores the limitations of current AI models in real-world scenarios and the difficulty in interpreting their predictions, contributing to limited physician trust in AI-based models. The overarching suggestion is that AI can be a valuable tool in clinicians' hands for treating heart failure patients, as far as existing medical inaccuracies have been addressed before integrating AI into these frameworks.

Artificial Intelligence-Based Clinical Decision Support Systems in Cardiovascular Diseases

Despite all the advancements in science, medical knowledge, healthcare, and the healthcare industry, cardiovascular disease (CVD) remains the leading cause of morbidity and mortality worldwide. The main reasons are the inadequacy of preventive health services and delays in diagnosis due to the increasing population, the failure of physicians to apply guide-based treatments, the lack of continuous patient follow-up, and the low compliance of patients with doctors' recommendations. Artificial intelligence (AI)-based clinical decision support systems (CDSSs) are systems that support complex decision-making processes by using AI techniques such as data analysis, foresight, and optimization. Artificial intelligence-based CDSSs play an important role in patient care by providing more accurate and personalized information to healthcare professionals in risk assessment, diagnosis, treatment optimization, and monitoring and early warning of CVD. These are just some examples, and the use of AI for CVD decision support systems is rapidly evolving. However, for these systems to be fully reliable and effective, they need to be trained with accurate data and carefully evaluated by medical professionals.

Deep learning for classification of late gadolinium enhancement lesions based on the 16-segment left ventricular model

PURPOSE

This study aimed to develop and validate a deep learning-based method that allows for segmental analysis of myocardial late gadolinium enhancement (LGE) lesions.

METHODS

Cardiac LGE data from 170 patients with coronary artery disease and non-ischemic heart disease were used for training, validation, and testing. Short-axis images were transformed to polar space after identification of the left ventricular (LV) center point and anterior right ventricular (RV) insertion point. Images were obtained after dividing the polar transformed images into segments based on the 16-segment LV model. Five different deep convolutional neural network (CNN) models were developed and validated using the labeled data, where the image after the division corresponded to a segment, and the lesion labeling was based on the 16-segment LV model. Unseen testing data were used to evaluate the performance of the lesion classification.

RESULTS

Without manual lesion segmentation and annotation, the proposed method showed an area under the curve (AUC) of 0.875, and a precision, recall, and F1-score of 0.723, 0.783, and 0.752, respectively for the lesion class when the pretrained ResNet50 model was tested for all slice images. The two pretrained models of ResNet50 and EfficientNet-B0 outperformed the three non-pretrained CNN models in terms of AUCs (0.873-0.875 vs. 0.834-0.841).

CONCLUSION

The proposed method is based on learning a deep CNN model from polar transformed images to predict LGE lesions with good accuracy and does not require time-consuming annotation procedures such as lesion segmentation.

Present and Future Innovations in AI and Cardiac MRI

Cardiac MRI is used to diagnose and treat patients with a multitude of cardiovascular diseases. Despite the growth of clinical cardiac MRI, complicated image prescriptions and long acquisition protocols limit the specialty and restrain its impact on the practice of medicine. Artificial intelligence (AI)-the ability to mimic human intelligence in learning and performing tasks-will impact nearly all aspects of MRI. Deep learning (DL) primarily uses an artificial neural network to learn a specific task from example data sets. Self-driving scanners are increasingly available, where AI automatically controls cardiac image prescriptions. These scanners offer faster image collection with higher spatial and temporal resolution, eliminating the need for cardiac triggering or breath holding. In the future, fully automated inline image analysis will most likely provide all contour drawings and initial measurements to the reader. Advanced analysis using radiomic or DL features may provide new insights and information not typically extracted in the current analysis workflow. AI may further help integrate these features with clinical, genetic, wearable-device, and "omics" data to improve patient outcomes. This article presents an overview of AI and its application in cardiac MRI, including in image acquisition, reconstruction, and processing, and opportunities for more personalized cardiovascular care through extraction of novel imaging markers.

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.

Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets

Dynamic contrast-enhanced (DCE) cardiac magnetic resonance imaging (CMRI) is a widely used modality for diagnosing myocardial blood flow (perfusion) abnormalities. During a typical free-breathing DCE-CMRI scan, close to 300 time-resolved images of myocardial perfusion are acquired at various contrast "wash in/out" phases. Manual segmentation of myocardial contours in each time-frame of a DCE image series can be tedious and time-consuming, particularly when non-rigid motion correction has failed or is unavailable. While deep neural networks (DNNs) have shown promise for analyzing DCE-CMRI datasets, a "dynamic quality control" (dQC) technique for reliably detecting failed segmentations is lacking. Here we propose a new space-time uncertainty metric as a dQC tool for DNN-based segmentation of free-breathing DCE-CMRI datasets by validating the proposed metric on an external dataset and establishing a human-in-the-loop framework to improve the segmentation results. In the proposed approach, we referred the top 10% most uncertain segmentations as detected by our dQC tool to the human expert for refinement. This approach resulted in a significant increase in the Dice score ( p < 0.001 ) and a notable decrease in the number of images with failed segmentation (16.2% to 11.3%) whereas the alternative approach of randomly selecting the same number of segmentations for human referral did not achieve any significant improvement. Our results suggest that the proposed dQC framework has the potential to accurately identify poor-quality segmentations and may enable efficient DNN-based analysis of DCE-CMRI in a human-in-the-loop pipeline for clinical interpretation and reporting of dynamic CMRI datasets.

Temporal Uncertainty Localization to Enable Human-in-the-Loop Analysis of Dynamic Contrast-Enhanced Cardiac MRI Datasets

Dynamic contrast-enhanced (DCE) cardiac magnetic resonance imaging (CMRI) is a widely used modality for diagnosing myocardial blood flow (perfusion) abnormalities. During a typical free-breathing DCE-CMRI scan, close to 300 time-resolved images of myocardial perfusion are acquired at various contrast "wash in/out" phases. Manual segmentation of myocardial contours in each time-frame of a DCE image series can be tedious and time-consuming, particularly when non-rigid motion correction has failed or is unavailable. While deep neural networks (DNNs) have shown promise for analyzing DCE-CMRI datasets, a "dynamic quality control" (dQC) technique for reliably detecting failed segmentations is lacking. Here we propose a new space-time uncertainty metric as a dQC tool for DNN-based segmentation of free-breathing DCE-CMRI datasets by validating the proposed metric on an external dataset and establishing a human-in-the-loop framework to improve the segmentation results. In the proposed approach, we referred the top 10% most uncertain segmentations as detected by our dQC tool to the human expert for refinement. This approach resulted in a significant increase in the Dice score (p < 0.001) and a notable decrease in the number of images with failed segmentation (16.2% to 11.3%) whereas the alternative approach of randomly selecting the same number of segmentations for human referral did not achieve any significant improvement. Our results suggest that the proposed dQC framework has the potential to accurately identify poor-quality segmentations and may enable efficient DNN-based analysis of DCE-CMRI in a human-in-the-loop pipeline for clinical interpretation and reporting of dynamic CMRI datasets.

Evaluation of late gadolinium enhancement cardiac MRI using deep learning reconstruction

BACKGROUND

Deep learning (DL)-based methods have been used to improve the imaging quality of magnetic resonance imaging (MRI) by denoising.

PURPOSE

To assess the effects of DL-based MR reconstruction (DLR) method on late gadolinium enhancement (LGE) image quality.

MATERIAL AND METHODS

A total of 85 patients who underwent cardiovascular magnetic resonance (CMR) examination, including LGE imaging using conventional construction and DLR with varying levels of noise reduction (NR) levels, were included. Both magnitude LGE (MLGE) and phase-sensitive LGE (PSLGE) images were reviewed independently by double-blinded observers who used a 5-point Likert scale for multiple measures regarding image quality. Meanwhile, the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness of images were calculated and compared between conventional LGE imaging and DLR LGE imaging.

RESULTS

Both MLGE and PSLGE with DLR at 50% and 75% noise reduction levels received significantly higher scores than conventional imaging for overall imaging quality (all P < 0.01). In addition, the SNR, CNR, and edge sharpness of all DLR LGE imaging are higher than conventional imaging (all P < 0.01). The highest subjective score and best image quality is obtained when the DLR noise reduction level is at 75%.

CONCLUSION

DLR reduced image noise while improving image contrast and sharpness in the cardiovascular LGE imaging.

Artificial intelligence in cardiovascular imaging: enhancing image analysis and risk stratification

In this review, we summarize state-of-the-art artificial intelligence applications for non-invasive cardiovascular imaging modalities including CT, MRI, echocardiography, and nuclear myocardial perfusion imaging.

MyI-Net: Fully Automatic Detection and Quantification of Myocardial Infarction from Cardiovascular MRI Images

Myocardial infarction (MI) occurs when an artery supplying blood to the heart is abruptly occluded. The "gold standard" method for imaging MI is cardiovascular magnetic resonance imaging (MRI) with intravenously administered gadolinium-based contrast (with damaged areas apparent as late gadolinium enhancement [LGE]). However, no "gold standard" fully automated method for the quantification of MI exists. In this work, we propose an end-to-end fully automatic system (MyI-Net) for the detection and quantification of MI in MRI images. It has the potential to reduce uncertainty due to technical variability across labs and the inherent problems of data and labels. Our system consists of four processing stages designed to maintain the flow of information across scales. First, features from raw MRI images are generated using feature extractors built on ResNet and MoblieNet architectures. This is followed by atrous spatial pyramid pooling (ASPP) to produce spatial information at different scales to preserve more image context. High-level features from ASPP and initial low-level features are concatenated at the third stage and then passed to the fourth stage where spatial information is recovered via up-sampling to produce final image segmentation output into: (i) background, (ii) heart muscle, (iii) blood and (iv) LGE areas. Our experiments show that the model named MI-ResNet50-AC provides the best global accuracy (97.38%), mean accuracy (86.01%), weighted intersection over union (IoU) of 96.47%, and bfscore of 64.46% for the global segmentation. However, in detecting only LGE tissue, a smaller model, MI-ResNet18-AC, exhibited higher accuracy (74.41%) than MI-ResNet50-AC (64.29%). New models were compared with state-of-the-art models and manual quantification. Our models demonstrated favorable performance in global segmentation and LGE detection relative to the state-of-the-art, including a four-fold better performance in matching LGE pixels to contours produced by clinicians.

An accurate and time-efficient deep learning-based system for automated segmentation and reporting of cardiac magnetic resonance-detected ischemic scar

BACKGROUND AND OBJECTIVES

Myocardial infarction scar (MIS) assessment by cardiac magnetic resonance provides prognostic information and guides patients' clinical management. However, MIS segmentation is time-consuming and not performed routinely. This study presents a deep-learning-based computational workflow for the segmentation of left ventricular (LV) MIS, for the first time performed on state-of-the-art dark-blood late gadolinium enhancement (DB-LGE) images, and the computation of MIS transmurality and extent.

METHODS

DB-LGE short-axis images of consecutive patients with myocardial infarction were acquired at 1.5T in two centres between Jan 1, 2019, and June 1, 2021. Two convolutional neural network (CNN) models based on the U-Net architecture were trained to sequentially segment the LV and MIS, by processing an incoming series of DB-LGE images. A 5-fold cross-validation was performed to assess the performance of the models. Model outputs were compared respectively with manual (LV endo- and epicardial border) and semi-automated (MIS, 4-Standard Deviation technique) ground truth to assess the accuracy of the segmentation. An automated post-processing and reporting tool was developed, computing MIS extent (expressed as relative infarcted mass) and transmurality.

RESULTS

The dataset included 1355 DB-LGE short-axis images from 144 patients (MIS in 942 images). High performance (> 0.85) as measured by the Intersection over Union metric was obtained for both the LV and MIS segmentations on the training sets. The performance for both LV and MIS segmentations was 0.83 on the test sets. Compared to the 4-Standard Deviation segmentation technique, our system was five times quicker (<1 min versus 7 ± 3 min), and required minimal user interaction.

CONCLUSIONS

Our solution successfully addresses different issues related to automatic MIS segmentation, including accuracy, time-effectiveness, and the automatic generation of a clinical report.

Diastolic dysfunction assessed by cardiac magnetic resonance imaging tissue tracking on normal-thickness wall segments in hypertrophic cardiomyopathy

OBJECTIVES

Myocardial strain is reported to be a sensitive indicator of myocardial mechanical changes in patients with hypertrophic cardiomyopathy (HCM). The changes in the mechanics of the myocardium of normal wall thickness (< 12 mm) have yet to be well studied. This study aimed to evaluate the function of myocardial segments of normal thickness in patients with HCM.

METHODS

Sixty-three patients with HCM and 30 controls were retrospectively enrolled in this retrospective study. Cine imaging, native and post-contrast T1 maps, T2 maps, and late gadolinium enhancement were performed. In addition, regional myocardial strain was assessed by cardiac magnetic resonance-tissue tracking. Strain parameters were compared between the controls and HCM patients with segments of the myocardium of normal thickness. Subgroup analysis was conducted in obstructive and non-obstructive HCM. Lastly, p < 0.05 was considered statistically significant.

RESULTS

In normal-thickness myocardial segments of HCM (n = 716), diastolic peak strain rates (PSRs) were significantly lower than in the control group (n = 480) (radial, - 2.43 [- 3.36, - 1.78] vs. - 2.67 [- 3.58, - 1.96], p = 0.002; circumferential, 1.28 [1.01,1.60] vs. 1.39 [1.14, 1.78], p < 0.001; and longitudinal, 1.16 [0.75,1.51] vs. 1.28 [0.90, 1.71], p < 0.001). The normal-thickness segments showed no significant difference in systolic PSRs between HCM and the controls. In the subgroup analysis, significantly decreased diastolic PSRs were noted in both obstructive and non-obstructive HCM, compared with the controls (p < 0.05).

CONCLUSIONS

Diastolic changes in myocardial mechanics were observed in normal-thickness segments of HCM, occurring before morphological remodeling and systolic dysfunction developed. This finding contributed to a better understanding of the mechanical pathophysiology of HCM with preserved left ventricular ejection fraction. It may potentially aid in predicting disease progression and risk stratification.

Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients

Scar quantification on cardiovascular magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in risk stratifying patients with hypertrophic cardiomyopathy (HCM) due to the importance of scar burden in predicting clinical outcomes. We aimed to develop a machine learning (ML) model that contours left ventricular (LV) endo- and epicardial borders and quantifies CMR LGE images from HCM patients.We retrospectively studied 2557 unprocessed images from 307 HCM patients followed at the University Health Network (Canada) and Tufts Medical Center (USA). LGE images were manually segmented by two experts using two different software packages. Using 6SD LGE intensity cutoff as the gold standard, a 2-dimensional convolutional neural network (CNN) was trained on 80% and tested on the remaining 20% of the data. Model performance was evaluated using the Dice Similarity Coefficient (DSC), Bland-Altman, and Pearson's correlation. The 6SD model DSC scores were good to excellent at 0.91 ± 0.04, 0.83 ± 0.03, and 0.64 ± 0.09 for the LV endocardium, epicardium, and scar segmentation, respectively. The bias and limits of agreement for the percentage of LGE to LV mass were low (-0.53 ± 2.71%), and correlation high (r = 0.92). This fully automated interpretable ML algorithm allows rapid and accurate scar quantification from CMR LGE images. This program does not require manual image pre-processing, and was trained with multiple experts and software, increasing its generalizability.

Regional left ventricle scar detection from routine cardiac computed tomography angiograms using latent space classification

OBJECTIVES

The aim of this study is to develop an automated method of regional scar detection on clinically standard computed tomography angiography (CTA) using encoder-decoder networks with latent space classification.

BACKGROUND

Localising scar in cardiac patients can assist in diagnosis and guide interventions. Magnetic resonance imaging (MRI) with late gadolinium enhancement (LGE) is the clinical gold standard for scar imaging; however, it is commonly contraindicated. CTA is an alternative imaging modality that has fewer contraindications and is widely used as a first-line imaging modality of cardiac applications.

METHODS

A dataset of 79 patients with both clinically indicated MRI LGE and subsequent CTA scans was used to train and validate networks to classify septal and lateral scar presence within short axis left ventricle slices. Two designs of encoder-decoder networks were compared, with one encoding anatomical shape in the latent space. Ground truth was established by segmenting scar in MRI LGE and registering this to the CTA images. Short axis slices were taken from the CTA, which served as the input to the networks. An independent external set of 22 cases (27% the size of the cross-validation set) was used to test the best network.

RESULTS

A network classifying lateral scar only achieved an area under ROC curve of 0.75, with a sensitivity of 0.79 and specificity of 0.62 on the independent test set. The results of septal scar classification were poor (AUC < 0.6) for all networks. This was likely due to a high class imbalance. The highest AUC network encoded anatomical shape information in the network latent space, indicating it was important for the successful classification of lateral scar.

CONCLUSIONS

Automatic lateral wall scar detection can be performed from a routine cardiac CTA with reasonable accuracy, without any scar specific imaging. This requires only a single acquisition in the cardiac cycle. In a clinical setting, this could be useful for pre-procedure planning, especially where MRI is contraindicated. Further work with more septal scar present is warranted to improve the usefulness of this approach.

Impact of deep learning architectures on accelerated cardiac T1 mapping using MyoMapNet

The objective of the current study was to investigate the performance of various deep learning (DL) architectures for MyoMapNet, a DL model for T1 estimation using accelerated cardiac T1 mapping from four T1 -weighted images collected after a single inversion pulse (Look-Locker 4 [LL4]). We implemented and tested three DL architectures for MyoMapNet: (a) a fully connected neural network (FC), (b) convolutional neural networks (VGG19, ResNet50), and (c) encoder-decoder networks with skip connections (ResUNet, U-Net). Modified Look-Locker inversion recovery (MOLLI) images from 749 patients at 3 T were used for training, validation, and testing. The first four T1 -weighted images from MOLLI5(3)3 and/or MOLLI4(1)3(1)2 protocols were extracted to create accelerated cardiac T1 mapping data. We also prospectively collected data from 28 subjects using MOLLI and LL4 to further evaluate model performance. Despite rigorous training, conventional VGG19 and ResNet50 models failed to produce anatomically correct T1 maps, and T1 values had significant errors. While ResUNet yielded good quality maps, it significantly underestimated T1 . Both FC and U-Net, however, yielded excellent image quality with good T1 accuracy for both native (FC/U-Net/MOLLI = 1217 ± 64/1208 ± 61/1199 ± 61 ms, all p < 0.05) and postcontrast myocardial T1 (FC/U-Net/MOLLI = 578 ± 57/567 ± 54/574 ± 55 ms, all p < 0.05). In terms of precision, the U-Net model yielded better T1 precision compared with the FC architecture (standard deviation of 61 vs. 67 ms for the myocardium for native [p < 0.05], and 31 vs. 38 ms [p < 0.05], for postcontrast). Similar findings were observed in prospectively collected LL4 data. It was concluded that U-Net and FC DL models in MyoMapNet enable fast myocardial T1 mapping using only four T1 -weighted images collected from a single LL sequence with comparable accuracy. U-Net also provides a slight improvement in precision.

Optimized automated cardiac MR scar quantification with GAN-based data augmentation

BACKGROUND

The clinical utility of late gadolinium enhancement (LGE) cardiac MRI is limited by the lack of standardization, and time-consuming postprocessing. In this work, we tested the hypothesis that a cascaded deep learning pipeline trained with augmentation by synthetically generated data would improve model accuracy and robustness for automated scar quantification.

METHODS

A cascaded pipeline consisting of three consecutive neural networks is proposed, starting with a bounding box regression network to identify a region of interest around the left ventricular (LV) myocardium. Two further nnU-Net models are then used to segment the myocardium and, if present, scar. The models were trained on the data from the EMIDEC challenge, supplemented with an extensive synthetic dataset generated with a conditional GAN.

RESULTS

The cascaded pipeline significantly outperformed a single nnU-Net directly segmenting both the myocardium (mean Dice similarity coefficient (DSC) (standard deviation (SD)): 0.84 (0.09) vs 0.63 (0.20), p < 0.01) and scar (DSC: 0.72 (0.34) vs 0.46 (0.39), p < 0.01) on a per-slice level. The inclusion of the synthetic data as data augmentation during training improved the scar segmentation DSC by 0.06 (p < 0.01). The mean DSC per-subject on the challenge test set, for the cascaded pipeline augmented by synthetic generated data, was 0.86 (0.03) and 0.67 (0.29) for myocardium and scar, respectively.

CONCLUSION

A cascaded deep learning-based pipeline trained with augmentation by synthetically generated data leads to myocardium and scar segmentations that are similar to the manual operator, and outperforms direct segmentation without the synthetic images.

Advanced imaging for risk stratification for ventricular arrhythmias and sudden cardiac death

Sudden cardiac death (SCD) is a leading cause of mortality, comprising approximately half of all deaths from cardiovascular disease. In the US, the majority of SCD (85%) occurs in patients with ischemic cardiomyopathy (ICM) and a subset in patients with non-ischemic cardiomyopathy (NICM), who tend to be younger and whose risk of mortality is less clearly delineated than in ischemic cardiomyopathies. The conventional means of SCD risk stratification has been the determination of the ejection fraction (EF), typically via echocardiography, which is currently a means of determining candidacy for primary prevention in the form of implantable cardiac defibrillators (ICDs). Advanced cardiac imaging methods such as cardiac magnetic resonance imaging (CMR), single-photon emission computerized tomography (SPECT) and positron emission tomography (PET), and computed tomography (CT) have emerged as promising and non-invasive means of risk stratification for sudden death through their characterization of the underlying myocardial substrate that predisposes to SCD. Late gadolinium enhancement (LGE) on CMR detects myocardial scar, which can inform ICD decision-making. Overall scar burden, region-specific scar burden, and scar heterogeneity have all been studied in risk stratification. PET and SPECT are nuclear methods that determine myocardial viability and innervation, as well as inflammation. CT can be used for assessment of myocardial fat and its association with reentrant circuits. Emerging methodologies include the development of "virtual hearts" using complex electrophysiologic modeling derived from CMR to attempt to predict arrhythmic susceptibility. Recent developments have paired novel machine learning (ML) algorithms with established imaging techniques to improve predictive performance. The use of advanced imaging to augment risk stratification for sudden death is increasingly well-established and may soon have an expanded role in clinical decision-making. ML could help shift this paradigm further by advancing variable discovery and data analysis.

CT in Transcatheter-delivered Treatment of Valvular Heart Disease

Minimally invasive strategies to treat valvular heart disease have emerged over the past 2 decades. The use of transcatheter aortic valve replacement in the treatment of severe aortic stenosis, for example, has recently expanded from high- to low-risk patients and became an alternative treatment for those with prohibitive surgical risk. With the increase in transcatheter strategies, multimodality imaging, including echocardiography, CT, fluoroscopy, and cardiac MRI, are used. Strategies for preprocedural imaging strategies vary depending on the targeted valve. Herein, an overview of preprocedural imaging strategies and their postprocessing approaches is provided, with a focus on CT. Transcatheter aortic valve replacement is reviewed, as well as less established minimally invasive treatments of the mitral and tricuspid valves. In addition, device-specific details and the goals of CT imaging are discussed. Future imaging developments, such as peri-procedural fusion imaging, machine learning for image processing, and mixed reality applications, are presented.

Toward Generalizability in the Deployment of Artificial Intelligence in Radiology: Role of Computation Stress Testing to Overcome Underspecification

The clinical deployment of artificial intelligence (AI) applications in medical imaging is perhaps the greatest challenge facing radiology in the next decade. One of the main obstacles to the incorporation of automated AI-based decision-making tools in medicine is the failure of models to generalize when deployed across institutions with heterogeneous populations and imaging protocols. The most well-understood pitfall in developing these AI models is overfitting, which has, in part, been overcome by optimizing training protocols. However, overfitting is not the only obstacle to the success and generalizability of AI. Underspecification is also a serious impediment that requires conceptual understanding and correction. It is well known that a single AI pipeline, with prescribed training and testing sets, can produce several models with various levels of generalizability. Underspecification defines the inability of the pipeline to identify whether these models have embedded the structure of the underlying system by using a test set independent of, but distributed identically, to the training set. An underspecified pipeline is unable to assess the degree to which the models will be generalizable. Stress testing is a known tool in AI that can limit underspecification and, importantly, assure broad generalizability of AI models. However, the application of stress tests is new in radiologic applications. This report describes the concept of underspecification from a radiologist perspective, discusses stress testing as a specific strategy to overcome underspecification, and explains how stress tests could be designed in radiology-by modifying medical images or stratifying testing datasets. In the upcoming years, stress tests should become in radiology the standard that crash tests have become in the automotive industry. Keywords: Computer Applications-General, Informatics, Computer-aided Diagnosis © RSNA, 2021.

Diagnostic utility of artificial intelligence for left ventricular scar identification using cardiac magnetic resonance imaging-A systematic review

Background

Accurate, rapid quantification of ventricular scar using cardiac magnetic resonance imaging (CMR) carries importance in arrhythmia management and patient prognosis. Artificial intelligence (AI) has been applied to other radiological challenges with success.

Objective

We aimed to assess AI methodologies used for left ventricular scar identification in CMR, imaging sequences used for training, and its diagnostic evaluation.

Methods

Following PRISMA recommendations, a systematic search of PubMed, Embase, Web of Science, CINAHL, OpenDissertations, arXiv, and IEEE Xplore was undertaken to June 2021 for full-text publications assessing left ventricular scar identification algorithms. No pre-registration was undertaken. Random-effect meta-analysis was performed to assess Dice Coefficient (DSC) overlap of learning vs predefined thresholding methods.

Results

Thirty-five articles were included for final review. Supervised and unsupervised learning models had similar DSC compared to predefined threshold models (0.616 vs 0.633, P = .14) but had higher sensitivity, specificity, and accuracy. Meta-analysis of 4 studies revealed standardized mean difference of 1.11; 95% confidence interval -0.16 to 2.38, P = .09, I2 = 98% favoring learning methods.

Conclusion

Feasibility of applying AI to the task of scar detection in CMR has been demonstrated, but model evaluation remains heterogenous. Progression toward clinical application requires detailed, transparent, standardized model comparison and increased model generalizability.

Landmark Detection in Cardiac MRI by Using a Convolutional Neural Network

PURPOSE

To develop a convolutional neural network (CNN) solution for landmark detection in cardiac MRI (CMR).

MATERIALS AND METHODS

This retrospective study included cine, late gadolinium enhancement (LGE), and T1 mapping examinations from two hospitals. The training set included 2329 patients (34 089 images; mean age, 54.1 years; 1471 men; December 2017 to March 2020). A hold-out test set included 531 patients (7723 images; mean age, 51.5 years; 323 men; May 2020 to July 2020). CNN models were developed to detect two mitral valve plane and apical points on long-axis images. On short-axis images, anterior and posterior right ventricular (RV) insertion points and left ventricular (LV) center points were detected. Model outputs were compared with manual labels assigned by two readers. The trained model was deployed to MRI scanners.

RESULTS

For the long-axis images, successful detection of cardiac landmarks ranged from 99.7% to 100% for cine images and from 99.2% to 99.5% for LGE images. For the short-axis images, detection rates were 96.6% for cine, 97.6% for LGE, and 98.7% for T1 mapping. The Euclidean distances between model-assigned and manually assigned labels ranged from 2 to 3.5 mm for different landmarks, indicating close agreement between model-derived landmarks and manually assigned labels. For all views and imaging sequences, no differences between the models' assessment of images and the readers' assessment of images were found for the anterior RV insertion angle or LV length. Model inference for a typical cardiac cine series took 610 msec with the graphics processing unit and 5.6 seconds with central processing unit.

CONCLUSION

A CNN was developed for landmark detection on both long- and short-axis CMR images acquired with cine, LGE, and T1 mapping sequences, and the accuracy of the CNN was comparable with the interreader variation.Keywords: Cardiac, Heart, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Feature Detection, Quantification, Supervised Learning, MR Imaging Supplemental material is available for this article. Published under a CC BY 4.0 license.

Recent Advances in Fibrosis and Scar Segmentation From Cardiac MRI: A State-of-the-Art Review and Future Perspectives

Segmentation of cardiac fibrosis and scars is essential for clinical diagnosis and can provide invaluable guidance for the treatment of cardiac diseases. Late Gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) has been successful in guiding the clinical diagnosis and treatment reliably. For LGE CMR, many methods have demonstrated success in accurately segmenting scarring regions. Co-registration with other non-contrast-agent (non-CA) modalities [e.g., balanced steady-state free precession (bSSFP) cine magnetic resonance imaging (MRI)] can further enhance the efficacy of automated segmentation of cardiac anatomies. Many conventional methods have been proposed to provide automated or semi-automated segmentation of scars. With the development of deep learning in recent years, we can also see more advanced methods that are more efficient in providing more accurate segmentations. This paper conducts a state-of-the-art review of conventional and current state-of-the-art approaches utilizing different modalities for accurate cardiac fibrosis and scar segmentation.

Artificial intelligence in the diagnosis and management of arrhythmias

The field of cardiac electrophysiology (EP) had adopted simple artificial intelligence (AI) methodologies for decades. Recent renewed interest in deep learning techniques has opened new frontiers in electrocardiography analysis including signature identification of diseased states. Artificial intelligence advances coupled with simultaneous rapid growth in computational power, sensor technology, and availability of web-based platforms have seen the rapid growth of AI-aided applications and big data research. Changing lifestyles with an expansion of the concept of internet of things and advancements in telecommunication technology have opened doors to population-based detection of atrial fibrillation in ways, which were previously unimaginable. Artificial intelligence-aided advances in 3D cardiac imaging heralded the concept of virtual hearts and the simulation of cardiac arrhythmias. Robotics, completely non-invasive ablation therapy, and the concept of extended realities show promise to revolutionize the future of EP. In this review, we discuss the impact of AI and recent technological advances in all aspects of arrhythmia care.

Emerging Techniques in Cardiac Magnetic Resonance Imaging

Cardiovascular disease is the leading cause of death and a significant contributor of health care costs. Noninvasive imaging plays an essential role in the management of patients with cardiovascular disease. Cardiac magnetic resonance (MR) can noninvasively assess heart and vascular abnormalities, including biventricular structure/function, blood hemodynamics, myocardial tissue composition, microstructure, perfusion, metabolism, coronary microvascular function, and aortic distensibility/stiffness. Its ability to characterize myocardial tissue composition is unique among alternative imaging modalities in cardiovascular disease. Significant growth in cardiac MR utilization, particularly in Europe in the last decade, has laid the necessary clinical groundwork to position cardiac MR as an important imaging modality in the workup of patients with cardiovascular disease. Although lack of availability, limited training, physician hesitation, and reimbursement issues have hampered widespread clinical adoption of cardiac MR in the United States, growing clinical evidence will ultimately overcome these challenges. Advances in cardiac MR techniques, particularly faster image acquisition, quantitative myocardial tissue characterization, and image analysis have been critical to its growth. In this review article, we discuss recent advances in established and emerging cardiac MR techniques that are expected to strengthen its capability in managing patients with cardiovascular disease. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

3D Deep Learning Model for the Pretreatment Evaluation of Treatment Response in Esophageal Carcinoma: A Prospective Study (ChiCTR2000039279)

PURPOSE

To develop and validate a pretreatment computed tomography (CT)-based deep-learning (DL) model for predicting the treatment response to concurrent chemoradiation therapy (CCRT) among patients with locally advanced thoracic esophageal squamous cell carcinoma (TESCC).

METHODS AND MATERIALS

We conducted a prospective, multicenter study on the therapeutic efficacy of CCRT among TESCC patients across 9 hospitals in China (ChiCTR2000039279). A total of 306 patients with locally advanced TESCC diagnosed by histopathology from August 2015 to May 2020 were included in this study. A 3-dimensional DL radiomics model (3D-DLRM) was developed and validated based on pretreatment CT images to predict the response to CCRT. Furthermore, the prediction performance of the newly developed 3D-DLRM was analyzed according to 3 categories: radiation therapy plan, radiation field, and prescription dose used.

RESULTS

The 3D-DLRM achieved good prediction performance, with areas under the receiver operating characteristic curve of 0.897 (95% confidence interval, 0.840-0.959) for the training cohort and 0.833 (95% confidence interval, 0.654-1.000) for the validation cohort. Specifically, the 3D-DLRM accurately predicted patients who would not respond to CCRT, with a positive predictive value (PPV) of 100% for the validation cohort. Moreover, the 3D-DLRM performed well in all 3 categories, each with areas under the receiver operating characteristic curve of >0.8 and positive predictive values of approximately 100%.

CONCLUSION

The proposed pretreatment CT-based 3D-DLRM provides a potential tool for predicting the response to CCRT among patients with locally advanced TESCC. With the help of precise pretreatment prediction, we may guide the individualized treatment of patients and improve survival.

Improved Quantification of Myocardium Scar in Late Gadolinium Enhancement Images: Deep Learning Based Image Fusion Approach

BACKGROUND

Quantification of myocardium scarring in late gadolinium enhanced (LGE) cardiac magnetic resonance imaging can be challenging due to low scar-to-background contrast and low image quality. To resolve ambiguous LGE regions, experienced readers often use conventional cine sequences to accurately identify the myocardium borders.

PURPOSE

To develop a deep learning model for combining LGE and cine images to improve the robustness and accuracy of LGE scar quantification.

STUDY TYPE

Retrospective.

POPULATION

A total of 191 hypertrophic cardiomyopathy patients: 1) 162 patients from two sites randomly split into training (50%; 81 patients), validation (25%, 40 patients), and testing (25%; 41 patients); and 2) an external testing dataset (29 patients) from a third site.

FIELD STRENGTH/SEQUENCE

1.5T, inversion-recovery segmented gradient-echo LGE and balanced steady-state free-precession cine sequences ASSESSMENT: Two convolutional neural networks (CNN) were trained for myocardium and scar segmentation, one with and one without LGE-Cine fusion. For CNN with fusion, the input was two aligned LGE and cine images at matched cardiac phase and anatomical location. For CNN without fusion, only LGE images were used as input. Manual segmentation of the datasets was used as reference standard.

STATISTICAL TESTS

Manual and CNN-based quantifications of LGE scar burden and of myocardial volume were assessed using Pearson linear correlation coefficients (r) and Bland-Altman analysis.

RESULTS

Both CNN models showed strong agreement with manual quantification of LGE scar burden and myocardium volume. CNN with LGE-Cine fusion was more robust than CNN without LGE-Cine fusion, allowing for successful segmentation of significantly more slices (603 [95%] vs. 562 (89%) of 635 slices; P < 0.001). Also, CNN with LGE-Cine fusion showed better agreement with manual quantification of LGE scar burden than CNN without LGE-Cine fusion (%ScarLGE-cine = 0.82 × %Scarmanual , r = 0.84 vs. %ScarLGE  = 0.47 × %Scarmanual , r = 0.81) and myocardium volume (VolumeLGE-cine = 1.03 × Volumemanual , r = 0.96 vs. VolumeLGE  = 0.91 × Volumemanual , r = 0.91).

DATA CONCLUSION

CNN based LGE-Cine fusion can improve the robustness and accuracy of automated scar quantification.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: 1.

Fully-automated global and segmental strain analysis of DENSE cardiovascular magnetic resonance using deep learning for segmentation and phase unwrapping

BACKGROUND

Cardiovascular magnetic resonance (CMR) cine displacement encoding with stimulated echoes (DENSE) measures heart motion by encoding myocardial displacement into the signal phase, facilitating high accuracy and reproducibility of global and segmental myocardial strain and providing benefits in clinical performance. While conventional methods for strain analysis of DENSE images are faster than those for myocardial tagging, they still require manual user assistance. The present study developed and evaluated deep learning methods for fully-automatic DENSE strain analysis.

METHODS

Convolutional neural networks (CNNs) were developed and trained to (a) identify the left-ventricular (LV) epicardial and endocardial borders, (b) identify the anterior right-ventricular (RV)-LV insertion point, and (c) perform phase unwrapping. Subsequent conventional automatic steps were employed to compute strain. The networks were trained using 12,415 short-axis DENSE images from 45 healthy subjects and 19 heart disease patients and were tested using 10,510 images from 25 healthy subjects and 19 patients. Each individual CNN was evaluated, and the end-to-end fully-automatic deep learning pipeline was compared to conventional user-assisted DENSE analysis using linear correlation and Bland Altman analysis of circumferential strain.

RESULTS

LV myocardial segmentation U-Nets achieved a DICE similarity coefficient of 0.87 ± 0.04, a Hausdorff distance of 2.7 ± 1.0 pixels, and a mean surface distance of 0.41 ± 0.29 pixels in comparison with manual LV myocardial segmentation by an expert. The anterior RV-LV insertion point was detected within 1.38 ± 0.9 pixels compared to manually annotated data. The phase-unwrapping U-Net had similar or lower mean squared error vs. ground-truth data compared to the conventional path-following method for images with typical signal-to-noise ratio (SNR) or low SNR (p < 0.05), respectively. Bland-Altman analyses showed biases of 0.00 ± 0.03 and limits of agreement of - 0.04 to 0.05 or better for deep learning-based fully-automatic global and segmental end-systolic circumferential strain vs. conventional user-assisted methods.

CONCLUSIONS

Deep learning enables fully-automatic global and segmental circumferential strain analysis of DENSE CMR providing excellent agreement with conventional user-assisted methods. Deep learning-based automatic strain analysis may facilitate greater clinical use of DENSE for the quantification of global and segmental strain in patients with cardiac disease.

Artificial intelligence for a personalized diagnosis and treatment of atrial fibrillation

Although atrial fibrillation (AF) is the most common cardiac arrhythmia, its early identification, diagnosis, and treatment is still challenging. Due to its heterogeneous mechanisms and risk factors, targeting an individualized treatment of AF demands a large amount of patient data to identify specific patterns. Artificial intelligence (AI) algorithms are particularly well suited for treating high-dimensional data, predicting outcomes, and eventually, optimizing strategies for patient management. The analysis of large patient samples combining different sources of information such as blood biomarkers, electrical signals, and medical images opens a new paradigm for improving diagnostic algorithms. In this review, we summarize suitable AI techniques for this purpose. In particular, we describe potential applications for understanding the structural and functional bases of the disease, as well as for improving early noninvasive diagnosis, developing more efficient therapies, and predicting long-term clinical outcomes of patients with AF.

Big data and new information technology: what cardiologists need to know

Technological progress in medicine is constantly garnering pace, requiring that physicians constantly update their knowledge. The new wave of technologies breaking through into clinical practice includes the following: a) mHealth, which allows constant monitoring of biological parameters, anytime, anyplace, of hundreds of patients at the same time; b) artificial intelligence, which, powered by new deep learning techniques, are starting to beat human experts at their own game: diagnosis by imaging or electrocardiography; c) 3-dimensional printing, which may lead to patient-specific prostheses; d) systems medicine, which has arisen from big data, and which will open the way to personalized medicine by bringing together genetic, epigenetic, environmental, clinical and social data into complex integral mathematical models to design highly personalized therapies. This state-of-the-art review aims to summarize in a single document the most recent and most important technological trends that are being applied to cardiology, and to provide an overall view that will allow readers to discern at a glance the direction of cardiology in the next few years.

Artificial Intelligence and Texture Analysis in Cardiac Imaging

PURPOSE OF REVIEW

The aim of this structured review is to summarize the current research applications and opportunities arising from artificial intelligence (AI) and texture analysis with regard to cardiac imaging.

RECENT FINDINGS

Current research findings suggest tremendous potential for AI in cardiac imaging, especially with regard to objective image analyses, overcoming the limitations of an observer-dependent subjective image interpretation. Researchers have used this technique across multiple imaging modalities, for instance to detect myocardial scars in cardiac MR imaging, to predict contrast enhancement in non-contrast studies, and to improve image acquisition and reconstruction. AI in medical imaging has the potential to provide novel, much-needed applications for improving patient care pertaining to the cardiovascular system. While several shortcomings are still present in the current methodology, AI may serve as a resourceful assistant to radiologists and clinicians alike.