Model-Based Feature Augmentation for Cardiac Ablation Target Learning From Images

Computational modeling of cardiac electrophysiology and arrhythmogenesis: toward clinical translation

The complexity of cardiac electrophysiology, involving dynamic changes in numerous components across multiple spatial (from ion channel to organ) and temporal (from milliseconds to days) scales, makes an intuitive or empirical analysis of cardiac arrhythmogenesis challenging. Multiscale mechanistic computational models of cardiac electrophysiology provide precise control over individual parameters, and their reproducibility enables a thorough assessment of arrhythmia mechanisms. This review provides a comprehensive analysis of models of cardiac electrophysiology and arrhythmias, from the single cell to the organ level, and how they can be leveraged to better understand rhythm disorders in cardiac disease and to improve heart patient care. Key issues related to model development based on experimental data are discussed, and major families of human cardiomyocyte models and their applications are highlighted. An overview of organ-level computational modeling of cardiac electrophysiology and its clinical applications in personalized arrhythmia risk assessment and patient-specific therapy of atrial and ventricular arrhythmias is provided. The advancements presented here highlight how patient-specific computational models of the heart reconstructed from patient data have achieved success in predicting risk of sudden cardiac death and guiding optimal treatments of heart rhythm disorders. Finally, an outlook toward potential future advances, including the combination of mechanistic modeling and machine learning/artificial intelligence, is provided. As the field of cardiology is embarking on a journey toward precision medicine, personalized modeling of the heart is expected to become a key technology to guide pharmaceutical therapy, deployment of devices, and surgical interventions.

Role of Machine Learning and Artificial Intelligence in Arrhythmias and Electrophysiology

Machine learning (ML), a subset of artificial intelligence (AI) centered on machines learning from extensive datasets, stands at the forefront of a technological revolution shaping various facets of society. Cardiovascular medicine has emerged as a key domain for ML applications, with considerable efforts to integrate these innovations into routine clinical practice. Within cardiac electrophysiology, ML applications, especially in the automated interpretation of electrocardiograms, have garnered substantial attention in existing literature. However, less recognized are the diverse applications of ML in cardiac electrophysiology and arrhythmias, spanning basic science research on arrhythmia mechanisms, both experimental and computational, as well as contributions to enhanced techniques for mapping cardiac electrical function and translational research related to arrhythmia management. This comprehensive review delves into various ML applications within the scope of this journal, organized into 3 parts. The first section provides a fundamental understanding of general ML principles and methodologies, serving as a foundational resource for readers interested in exploring ML applications in arrhythmia research. The second part offers an in-depth review of studies in arrhythmia and electrophysiology that leverage ML methodologies, showcasing the broad potential of ML approaches. Each subject is thoroughly outlined, accompanied by a review of notable ML research advancements. Finally, the review delves into the primary challenges and future perspectives surrounding ML-driven cardiac electrophysiology and arrhythmias research.

Efficient Patient-Specific Simulations of Ventricular Tachycardia Based on Computed Tomography-Defined Wall Thickness Heterogeneity

BACKGROUND

Electrophysiological mapping of ventricular tachycardia (VT) is tedious and poorly reproducible. Substrate analysis on imaging cannot explicitly display VT circuits.

OBJECTIVES

This study sought to introduce a computed tomography-based model personalization approach, allowing for the simulation of postinfarction VT in a clinically compatible time frame.

METHODS

In 10 patients (age 65 ± 11 years, 9 male) referred for post-VT ablation, computed tomography-derived wall thickness maps were registered to 25 electroanatomical maps (sinus rhythm, paced, and VT). The relationship between wall thickness and electrophysiological characteristics (activation-recovery interval) was analyzed. Wall thickness was then employed to parameterize a fast and tractable organ-scale wave propagation model. Pacing protocols were simulated from multiple sites to test VT induction in silico. In silico VTs were compared to VT circuits mapped clinically.

RESULTS

Clinically, 6 different VTs could be induced with detailed maps in 9 patients. The proposed model allowed for fast simulation (median: 6 min/pacing site). Simulations of steady pacing (600 milliseconds) from 100 different sites/patient never triggered any arrhythmia. Applying S1-S2 or S1-S2-S3 induction schemes allowed for the induction of in silico VTs in the 9 of 10 patients who were clinically inducible. The patient who was not inducible clinically was also noninducible in silico. A total of 42 different VTs were simulated (4.2 ± 2 per patient). Six in silico VTs matched a VT circuit mapped clinically.

CONCLUSIONS

The proposed framework allows for personalized simulations in a matter of hours. In 6 of 9 patients, simulations show re-entrant patterns matching intracardiac recordings.

High-resolution structural-functional substrate-trigger characterization: Future roadmap for catheter ablation of ventricular tachycardia

Introduction

Patients with ventricular tachyarrhythmias (VT) are at high risk of sudden cardiac death. When appropriate, catheter ablation is modestly effective, with relatively high VT recurrence and complication rates. Personalized models that incorporate imaging and computational approaches have advanced VT management. However, 3D patient-specific functional electrical information is typically not considered. We hypothesize that incorporating non-invasive 3D electrical and structural characterization in a patient-specific model improves VT-substrate recognition and ablation targeting.

Materials and methods

In a 53-year-old male with ischemic cardiomyopathy and recurrent monomorphic VT, we built a structural-functional model based on high-resolution 3D late-gadolinium enhancement (LGE) cardiac magnetic resonance imaging (3D-LGE CMR), multi-detector computed tomography (CT), and electrocardiographic imaging (ECGI). Invasive data from high-density contact and pace mapping obtained during endocardial VT-substrate modification were also incorporated. The integrated 3D electro-anatomic model was analyzed off-line.

Results

Merging the invasive voltage maps and 3D-LGE CMR endocardial geometry led to a mean Euclidean node-to-node distance of 5 ± 2 mm. Inferolateral and apical areas of low bipolar voltage (<1.5 mV) were associated with high 3D-LGE CMR signal intensity (>0.4) and with higher transmurality of fibrosis. Areas of functional conduction delay or block (evoked delayed potentials, EDPs) were in close proximity to 3D-LGE CMR-derived heterogeneous tissue corridors. ECGI pinpointed the epicardial VT exit at ∼10 mm from the endocardial site of origin, both juxtaposed to the distal ends of two heterogeneous tissue corridors in the inferobasal left ventricle. Radiofrequency ablation at the entrances of these corridors, eliminating all EDPs, and at the VT site of origin rendered the patient non-inducible and arrhythmia-free until the present day (20 months follow-up). Off-line analysis in our model uncovered dynamic electrical instability of the LV inferolateral heterogeneous scar region which set the stage for an evolving VT circuit.

Discussion and conclusion

We developed a personalized 3D model that integrates high-resolution structural and electrical information and allows the investigation of their dynamic interaction during arrhythmia formation. This model enhances our mechanistic understanding of scar-related VT and provides an advanced, non-invasive roadmap for catheter ablation.

From evidence-based medicine to digital twin technology for predicting ventricular tachycardia in ischaemic cardiomyopathy

Survivors of myocardial infarction are at risk of life-threatening ventricular tachycardias (VTs) later in their lives. Current guidelines for implantable cardioverter defibrillators (ICDs) implantation to prevent VT-related sudden cardiac death is solely based on symptoms and left ventricular ejection fraction. Catheter ablation of scar-related VTs is performed following ICD therapy, reducing VTs, painful shocks, anxiety, depression and worsening heart failure. We postulate that better prediction of the occurrence and circuit of VT, will improve identification of patients at risk for VT and boost preventive ablation, reducing mortality and morbidity. For this purpose, multiple time-evolving aspects of the underlying pathophysiology, including the anatomical substrate, triggers and modulators, should be part of VT prediction models. We envision digital twins as a solution combining clinical expertise with three prediction approaches: evidence-based medicine (clinical practice), data-driven models (data science) and mechanistic models (biomedical engineering). This paper aims to create a mutual understanding between experts in the different fields by providing a comprehensive description of the clinical problem and the three approaches in an understandable manner, leveraging future collaborations and technological innovations for clinical decision support. Moreover, it defines open challenges and gains for digital twin solutions and discusses the potential of hybrid modelling.

How synergy between mechanistic and statistical models is impacting research in atrial fibrillation

Atrial fibrillation (AF) with multiple complications, high morbidity and mortality, and low cure rates, has become a global public health problem. Although significant progress has been made in the treatment methods represented by anti-AF drugs and radiofrequency ablation, the therapeutic effect is not as good as expected. The reason is mainly because of our lack of understanding of AF mechanisms. This field has benefited from mechanistic and (or) statistical methodologies. Recent renewed interest in digital twin techniques by synergizing between mechanistic and statistical models has opened new frontiers in AF analysis. In the review, we briefly present findings that gave rise to the AF pathophysiology and current therapeutic modalities. We then summarize the achievements of digital twin technologies in three aspects: understanding AF mechanisms, screening anti-AF drugs and optimizing ablation strategies. Finally, we discuss the challenges that hinder the clinical application of the digital twin heart. With the rapid progress in data reuse and sharing, we expect their application to realize the transition from AF description to response prediction.

Identification of moyamoya disease based on cerebral oxygen saturation signals using machine learning methods

Moyamoya is a cerebrovascular disease with a high mortality rate. Early detection and mechanistic studies are necessary. Near-infrared spectroscopy (NIRS) was used to study the signals of the cerebral tissue oxygen saturation index (TOI) and the changes in oxygenated and deoxygenated hemoglobin concentrations (HbO and Hb) in 64 patients with moyamoya disease and 64 healthy volunteers. The wavelet transforms (WT) of TOI, HbO and Hb signals, as well as the wavelet phase coherence (WPCO) of these signals from the left and right frontal lobes of the same subject, were calculated. Features were extracted from the spontaneous oscillations of TOI, HbO and Hb in five physiological activity-related frequency segments. Machine learning models based on support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost) have been built to classify the two groups. For 20-min signals, the 10-fold cross-validation accuracies of SVM, RF and XGBoost were 87%, 85% and 85%, respectively. For 5-min signals, the accuracies of the three methods were 88%, 88% and 84%, respectively. The method proposed in this article has potential for detecting and screening moyamoya with high proficiency. Evaluating the cerebral oxygenation with NIRS shows great potential in screening moyamoya diseases.

Artificial Intelligence and Machine Learning in Cardiac Electrophysiology

Cardiac electrophysiology requires the processing of several patient-specific data points in real time to provide an accurate diagnosis and determine an optimal therapy. Expanding beyond the traditional tools that have been used to extract information from patient-specific data, machine learning offers a new set of advanced tools capable of revealing previously unknown data patterns and features. This new tool set can substantially improve the speed and level of confidence with which electrophysiologists can determine patient-specific diagnoses and therapies. The ability to process substantial amounts of data in real time also paves the way to novel techniques for data collection and visualization. Extended realities such as virtual and augmented reality can now enable the real-time visualization of 3-dimensional images in space. This enables improved preprocedural planning and intraprocedural interventions. Machine learning supplemented with novel visualization technologies could substantially improve patient care and outcomes by helping physicians to make more informed patient-specific decisions. This article presents current applications of machine learning and their use in cardiac electrophysiology.

Combined In-silico and Machine Learning Approaches Toward Predicting Arrhythmic Risk in Post-infarction Patients

Background: Remodeling due to myocardial infarction (MI) significantly increases patient arrhythmic risk. Simulations using patient-specific models have shown promise in predicting personalized risk for arrhythmia. However, these are computationally- and time- intensive, hindering translation to clinical practice. Classical machine learning (ML) algorithms (such as K-nearest neighbors, Gaussian support vector machines, and decision trees) as well as neural network techniques, shown to increase prediction accuracy, can be used to predict occurrence of arrhythmia as predicted by simulations based solely on infarct and ventricular geometry. We present an initial combined image-based patient-specific in silico and machine learning methodology to assess risk for dangerous arrhythmia in post-infarct patients. Furthermore, we aim to demonstrate that simulation-supported data augmentation improves prediction models, combining patient data, computational simulation, and advanced statistical modeling, improving overall accuracy for arrhythmia risk assessment.

Methods: MRI-based computational models were constructed from 30 patients 5 days post-MI (the “baseline” population). In order to assess the utility biophysical model-supported data augmentation for improving arrhythmia prediction, we augmented the virtual baseline patient population. Each patient ventricular and ischemic geometry in the baseline population was used to create a subfamily of geometric models, resulting in an expanded set of patient models (the “augmented” population). Arrhythmia induction was attempted via programmed stimulation at 17 sites for each virtual patient corresponding to AHA LV segments and simulation outcome, “arrhythmia,” or “no-arrhythmia,” were used as ground truth for subsequent statistical prediction (machine learning, ML) models. For each patient geometric model, we measured and used choice data features: the myocardial volume and ischemic volume, as well as the segment-specific myocardial volume and ischemia percentage, as input to ML algorithms. For classical ML techniques (ML), we trained k-nearest neighbors, support vector machine, logistic regression, xgboost, and decision tree models to predict the simulation outcome from these geometric features alone. To explore neural network ML techniques, we trained both a three - and a four-hidden layer multilayer perceptron feed forward neural networks (NN), again predicting simulation outcomes from these geometric features alone. ML and NN models were trained on 70% of randomly selected segments and the remaining 30% was used for validation for both baseline and augmented populations.

Results: Stimulation in the baseline population (30 patient models) resulted in reentry in 21.8% of sites tested; in the augmented population (129 total patient models) reentry occurred in 13.0% of sites tested. ML and NN models ranged in mean accuracy from 0.83 to 0.86 for the baseline population, improving to 0.88 to 0.89 in all cases.

Conclusion: Machine learning techniques, combined with patient-specific, image-based computational simulations, can provide key clinical insights with high accuracy rapidly and efficiently. In the case of sparse or missing patient data, simulation-supported data augmentation can be employed to further improve predictive results for patient benefit. This work paves the way for using data-driven simulations for prediction of dangerous arrhythmia in MI patients.

Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation

Atrial fibrillation (AF) is the most common cardiac arrhythmia and currently affects more than 650,000 people in the United Kingdom alone. Catheter ablation (CA) is the only AF treatment with a long-term curative effect as it involves destroying arrhythmogenic tissue in the atria. However, its success rate is suboptimal, approximately 50% after a 2-year follow-up, and this high AF recurrence rate warrants significant improvements. Image-guidance of CA procedures have shown clinical promise, enabling the identification of key patient anatomical and pathological (such as fibrosis) features of atrial tissue, which require ablation. However, the latter approach still suffers from a lack of functional information and the need to interpret structures in the images by a clinician. Deep learning plays an increasingly important role in biomedicine, facilitating efficient diagnosis and treatment of clinical problems. This study applies deep reinforcement learning in combination with patient imaging (to provide structural information of the atria) and image-based modelling (to provide functional information) to design patient-specific CA strategies to guide clinicians and improve treatment success rates. To achieve this, patient-specific 2D left atrial (LA) models were derived from late-gadolinium enhancement (LGE) MRI scans of AF patients and were used to simulate patient-specific AF scenarios. Then a reinforcement Q-learning algorithm was created, where an ablating agent moved around the 2D LA, applying CA lesions to terminate AF and learning through feedback imposed by a reward policy. The agent achieved 84% success rate in terminating AF during training and 72% success rate in testing. Finally, AF recurrence rate was measured by attempting to re-initiate AF in the 2D atrial models after CA with 11% recurrence showing a great improvement on the existing therapies. Thus, reinforcement Q-learning algorithms can predict successful CA strategies from patient MRI data and help to improve the patient-specific guidance of CA therapy.

Whole-heart ventricular arrhythmia modeling moving forward: Mechanistic insights and translational applications

Ventricular arrhythmias are the primary cause of sudden cardiac death and one of the leading causes of mortality worldwide. Whole-heart computational modeling offers a unique approach for studying ventricular arrhythmias, offering vast potential for developing both a mechanistic understanding of ventricular arrhythmias and clinical applications for treatment. In this review, the fundamentals of whole-heart ventricular modeling and current methods of personalizing models using clinical data are presented. From this foundation, the authors summarize recent advances in whole-heart ventricular arrhythmia modeling. Efforts in gaining mechanistic insights into ventricular arrhythmias are discussed, in addition to other applications of models such as the assessment of novel therapeutics. The review emphasizes the unique benefits of computational modeling that allow for insights that are not obtainable by contemporary experimental or clinical means. Additionally, the clinical impact of modeling is explored, demonstrating how patient care is influenced by the information gained from ventricular arrhythmia models. The authors conclude with future perspectives about the direction of whole-heart ventricular arrhythmia modeling, outlining how advances in neural network methodologies hold the potential to reduce computational expense and permit for efficient whole-heart modeling.

Cardiac Activation Maps Reconstruction: A Comparative Study Between Data-Driven and Physics-Based Methods

One of the essential diagnostic tools of cardiac arrhythmia is activation mapping. Noninvasive current mapping procedures include electrocardiographic imaging. It allows reconstructing heart surface potentials from measured body surface potentials. Then, activation maps are generated using the heart surface potentials. Recently, a study suggests to deploy artificial neural networks to estimate activation maps directly from body surface potential measurements. Here we carry out a comparative study between the data-driven approach DirectMap and noninvasive classic technique based on reconstructed heart surface potentials using both Finite element method combined with L1-norm regularization (FEM-L1) and the spatial adaptation of Time-delay neural networks (SATDNN-AT). In this work, we assess the performance of the three approaches using a synthetic single paced-rhythm dataset generated on the atria surface. The results show that data-driven approach DirectMap quantitatively outperforms the two other methods. In fact, we observe an absolute activation time error and a correlation coefficient, respectively, equal to 7.20 ms, 93.2% using DirectMap, 14.60 ms, 76.2% using FEM-L1 and 13.58 ms, 79.6% using SATDNN-AT. In addition, results show that data-driven approaches (DirectMap and SATDNN-AT) are strongly robust against additive gaussian noise compared to FEM-L1.

Applications of artificial intelligence in cardiovascular imaging

Research into artificial intelligence (AI) has made tremendous progress over the past decade. In particular, the AI-powered analysis of images and signals has reached human-level performance in many applications owing to the efficiency of modern machine learning methods, in particular deep learning using convolutional neural networks. Research into the application of AI to medical imaging is now very active, especially in the field of cardiovascular imaging because of the challenges associated with acquiring and analysing images of this dynamic organ. In this Review, we discuss the clinical questions in cardiovascular imaging that AI can be used to address and the principal methodological AI approaches that have been developed to solve the related image analysis problems. Some approaches are purely data-driven and rely mainly on statistical associations, whereas others integrate anatomical and physiological information through additional statistical, geometric and biophysical models of the human heart. In a structured manner, we provide representative examples of each of these approaches, with particular attention to the underlying computational imaging challenges. Finally, we discuss the remaining limitations of AI approaches in cardiovascular imaging (such as generalizability and explainability) and how they can be overcome.

Using Machine Learning to Characterize Atrial Fibrotic Substrate From Intracardiac Signals With a Hybrid in silico and in vivo Dataset

In patients with atrial fibrillation, intracardiac electrogram signal amplitude is known to decrease with increased structural tissue remodeling, referred to as fibrosis. In addition to the isolation of the pulmonary veins, fibrotic sites are considered a suitable target for catheter ablation. However, it remains an open challenge to find fibrotic areas and to differentiate their density and transmurality. This study aims to identify the volume fraction and transmurality of fibrosis in the atrial substrate. Simulated cardiac electrograms, combined with a generalized model of clinical noise, reproduce clinically measured signals. Our hybrid dataset approach combines in silico and clinical electrograms to train a decision tree classifier to characterize the fibrotic atrial substrate. This approach captures different in vivo dynamics of the electrical propagation reflected on healthy electrogram morphology and synergistically combines it with synthetic fibrotic electrograms from in silico experiments. The machine learning algorithm was tested on five patients and compared against clinical voltage maps as a proof of concept, distinguishing non-fibrotic from fibrotic tissue and characterizing the patient's fibrotic tissue in terms of density and transmurality. The proposed approach can be used to overcome a single voltage cut-off value to identify fibrotic tissue and guide ablation targeting fibrotic areas.

Machine learning and network medicine: a novel approach for precision medicine and personalized therapy in cardiomyopathies

The early identification of pathogenic mechanisms is essential to predict the incidence and progression of cardiomyopathies and to plan appropriate preventive interventions. Noninvasive cardiac imaging such as cardiac computed tomography, cardiac magnetic resonance, and nuclear imaging plays an important role in diagnosis and management of cardiomyopathies and provides useful prognostic information. Most molecular factors exert their functions by interacting with other cellular components, thus many diseases reflect perturbations of intracellular networks. Indeed, complex diseases and traits such as cardiomyopathies are caused by perturbations of biological networks. The network medicine approach, by integrating systems biology, aims to identify pathological interacting genes and proteins, revolutionizing the way to know cardiomyopathies and shifting the understanding of their pathogenic phenomena from a reductionist to a holistic approach. In addition, artificial intelligence tools, applied to morphological and functional imaging, could allow imaging scans to be automatically analyzed to extract new parameters and features for cardiomyopathy evaluation. The aim of this review is to discuss the tools of network medicine in cardiomyopathies that could reveal new candidate genes and artificial intelligence imaging-based features with the aim to translate into clinical practice as diagnostic, prognostic, and predictive biomarkers and shed new light on the clinical setting of cardiomyopathies. The integration and elaboration of clinical habits, molecular big data, and imaging into machine learning models could provide better disease phenotyping, outcome prediction, and novel drug targets, thus opening a new scenario for the implementation of precision medicine for cardiomyopathies.

Machine Learning in Arrhythmia and Electrophysiology

Machine learning (ML), a branch of artificial intelligence, where machines learn from big data, is at the crest of a technological wave of change sweeping society. Cardiovascular medicine is at the forefront of many ML applications, and there is a significant effort to bring them into mainstream clinical practice. In the field of cardiac electrophysiology, ML applications have also seen a rapid growth and popularity, particularly the use of ML in the automatic interpretation of ECGs, which has been extensively covered in the literature. Much lesser known are the other aspects of ML application in cardiac electrophysiology and arrhythmias, such as those in basic science research on arrhythmia mechanisms, both experimental and computational; in the development of better techniques for mapping of cardiac electrical function; and in translational research related to arrhythmia management. In the current review, we examine comprehensively such ML applications as they match the scope of this journal. The current review is organized in 3 parts. The first provides an overview of general ML principles and methodologies that will afford readers of the necessary information on the subject, serving as the foundation for inviting further ML applications in arrhythmia research. The basic information we provide can serve as a guide on how one might design and conduct an ML study. The second part is a review of arrhythmia and electrophysiology studies in which ML has been utilized, highlighting the broad potential of ML approaches. For each subject, we outline comprehensively the general topics, while reviewing some of the research advances utilizing ML under the subject. Finally, we discuss the main challenges and the perspectives for ML-driven cardiac electrophysiology and arrhythmia research.

Fully automatic segmentation of right and left ventricle on short-axis cardiac MRI images

Cardiac magnetic resonance imaging (CMR) is a widely used non-invasive imaging modality for evaluating cardiovascular diseases. CMR is the gold standard method for left and right ventricular functional assessment due to its ability to characterize myocardial structure and function and low intra- and inter-observer variability. However the post-processing segmentation during the functional evaluation is time-consuming and challenging. A fully automated segmentation method can assist the experts; therefore, they can do more efficient work. In this paper, a regression-based fully automated method is presented for the right- and left ventricle segmentation. For training and evaluation, our dataset contained MRI short-axis scans of 5570 patients, who underwent CMR examinations at Heart and Vascular Center, Semmelweis University Budapest. Our approach is novel and after training the state-of-the-art algorithm on our dataset, our algorithm proved to be superior on both of the ventricles. The evaluation metrics were the Dice index, Hausdorff distance and volume related parameters. We have achieved average Dice index for the left endocardium: 0.927, left epicardium: 0.940 and right endocardium: 0.873 on our dataset. We have also compared the performance of the algorithm to the human-level segmentation on both ventricles and it is similar to experienced readers for the left, and comparable for the right ventricle. We also evaluated the proposed algorithm on the ACDC dataset, which is publicly available, with and without transfer learning. The results on ACDC were also satisfying and similar to human observers. Our method is lightweight, fast to train and does not require more than 2 GB GPU memory for execution and training.

Putting machine learning into motion: applications in cardiovascular imaging

Heart and circulatory diseases cause a quarter of all deaths in the UK and cardiac imaging offers an effective tool for early diagnosis and risk-stratification to improve premature death and disability. This domain of radiology is unique in that assessing flow and motion is essential for understanding and quantifying normal physiology and disease processes. Conventional image interpretation relies on manual analysis but this often fails to capture important prognostic features in the complex disturbances of cardiovascular physiology. Machine learning (ML) in cardiovascular imaging promises to be a transformative tool and addresses an unmet need for patient-specific management, accurate prediction of future events, and the discovery of tractable molecular mechanisms of disease. This review discusses the potential of ML across every aspect of image analysis including efficient acquisition, segmentation and motion tracking, disease classification, prediction tasks and modelling of genotype-phenotype interactions; however, significant challenges remain in access to high-quality data at scale, robust validation, and clinical interpretability.