Training and clinical testing of artificial intelligence derived right atrial cardiovascular magnetic resonance measurements

Development and validation of AI-derived segmentation of four-chamber cine cardiac magnetic resonance

BACKGROUND

Cardiac magnetic resonance (CMR) in the four-chamber plane offers comprehensive insight into the volumetrics of the heart. We aimed to develop an artificial intelligence (AI) model of time-resolved segmentation using the four-chamber cine.

METHODS

A fully automated deep learning algorithm was trained using retrospective multicentre and multivendor data of 814 subjects. Validation, reproducibility, and mortality prediction were evaluated on an independent cohort of 101 subjects.

RESULTS

The mean age of the validation cohort was 54 years, and 66 (65%) were males. Left and right heart parameters demonstrated strong correlations between automated and manual analysis, with a ρ of 0.91-0.98 and 0.89-0.98, respectively, with minimal bias. All AI four-chamber volumetrics in repeatability analysis demonstrated high correlation (ρ = 0.99-1.00) and no bias. Automated four-chamber analysis underestimated both left ventricular (LV) and right ventricular (RV) volumes compared to ground-truth short-axis cine analysis. Two correction factors for LV and RV four-chamber analysis were proposed based on systematic bias. After applying the correction factors, a strong correlation and minimal bias for LV volumetrics were observed. During a mean follow-up period of 6.75 years, 16 patients died. On stepwise multivariable analysis, left atrial ejection fraction demonstrated an independent association with death in both manual (hazard ratio (HR) = 0.96, p = 0.003) and AI analyses (HR = 0.96, p < 0.001).

CONCLUSION

Fully automated four-chamber CMR is feasible, reproducible, and has the same real-world prognostic value as manual analysis. LV volumes by four-chamber segmentation were comparable to short-axis volumetric assessment.

TRIALS REGISTRATION

ClinicalTrials.gov: NCT05114785.

RELEVANCE STATEMENT

Integrating fully automated AI in CMR promises to revolutionise clinical cardiac assessment, offering efficient, accurate, and prognostically valuable insights for improved patient care and outcomes.

KEY POINTS

• Four-chamber cine sequences remain one of the most informative acquisitions in CMR examination. • This deep learning-based, time-resolved, fully automated four-chamber volumetric, functional, and deformation analysis solution. • LV and RV were underestimated by four-chamber analysis compared to ground truth short-axis segmentation. • Correction bias for both LV and RV volumes by four-chamber segmentation, minimises the systematic bias.

Validation of Left Atrial Volume Correction for Single Plane Method on Four-Chamber Cine Cardiac MRI

BACKGROUND

Left atrial (LA) assessment is an important marker of adverse cardiovascular outcomes. Cardiovascular magnetic resonance (CMR) accurately quantifies LA volume and function based on biplane long-axis imaging. We aimed to validate single-plane-derived LA indices against the biplane method to simplify the post-processing of cine CMR.

METHODS

In this study, 100 patients from Leeds Teaching Hospitals were used as the derivation cohort. Bias correction for the single plane method was applied and subsequently validated in 79 subjects.

RESULTS

There were significant differences between the biplane and single plane mean LA maximum and minimum volumes and LA ejection fraction (EF) (all p < 0.01). After correcting for biases in the validation cohort, significant correlations in all LA indices were observed (0.89 to 0.98). The area under the curve (AUC) for the single plane to predict biplane cutoffs of LA maximum volume ≥ 112 mL was 0.97, LA minimum volume ≥ 44 mL was 0.99, LA stroke volume (SV) ≤ 21 mL was 1, and LA EF ≤ 46% was 1, (all p < 0.001).

CONCLUSIONS

LA volumetric and functional assessment by the single plane method has a systematic bias compared to the biplane method. After bias correction, single plane LA volume and function are comparable to the biplane method.

The Right Ventricle in Pulmonary Hypertension

The right ventricle plays a pivotal role in patients with pulmonary hypertension (PH). Its adaptation to pressure overload determines a patient's functional status as well as survival. In a healthy situation, the right ventricle is part of a low pressure, high compliance system. It is built to accommodate changes in preload, but not very well suited for dealing with pressure overload. In PH, right ventricular (RV) contractility must increase to maintain cardiac output. In other words, the balance between the degree of RV contractility and afterload determines stroke volume. Hypertrophy is one of the major hallmarks of RV adaptation, but it may cause stiffening of the ventricle in addition to intrinsic changes to the RV myocardium. Ventricular filling becomes more difficult for which the right atrium tries to compensate through increased stroke work. Interaction of RV diastolic stiffness and right atrial (RA) function determines RV filling, but also causes vena cava backflow. Assessment of RV and RA function is critical in the evaluation of patient status. In recent guidelines, this is acknowledged by incorporating additional RV parameters in the risk stratification in PH. Several conventional parameters of RV and RA function have been part of risk stratification for many years. Understanding the pathophysiology of RV failure and the interactions with the pulmonary circulation and right atrium requires consideration of the unique RV anatomy. This review will therefore describe normal RV structure and function and changes that occur during adaptation to increased afterload. Consequences of a failing right ventricle and its implications for RA function will be discussed. Subsequently, we will describe RV and RA assessment in clinical practice.

Establishing minimally important differences for cardiac MRI end-points in pulmonary arterial hypertension

BACKGROUND

Cardiac magnetic resonance (CMR) is the gold standard technique to assess biventricular volumes and function, and is increasingly being considered as an end-point in clinical studies. Currently, with the exception of right ventricular (RV) stroke volume and RV end-diastolic volume, there is only limited data on minimally important differences (MIDs) reported for CMR metrics. Our study aimed to identify MIDs for CMR metrics based on US Food and Drug Administration recommendations for a clinical outcome measure that should reflect how a patient "feels, functions or survives".

METHODS

Consecutive treatment-naïve patients with pulmonary arterial hypertension (PAH) between 2010 and 2022 who had two CMR scans (at baseline prior to treatment and 12 months following treatment) were identified from the ASPIRE registry. All patients were followed up for 1 additional year after the second scan. For both scans, cardiac measurements were obtained from a validated fully automated segmentation tool. The MID in CMR metrics was determined using two distribution-based (0.5sd and minimal detectable change) and two anchor-based (change difference and generalised linear model regression) methods benchmarked to how a patient "feels" (emPHasis-10 quality of life questionnaire), "functions" (incremental shuttle walk test) or "survives" for 1-year mortality to changes in CMR measurements.

RESULTS

254 patients with PAH were included (mean±sd age 53±16 years, 79% female and 66% categorised as intermediate risk based on the 2022 European Society of Cardiology/European Respiratory Society risk score). We identified a 5% absolute increase in RV ejection fraction and a 17 mL decrease in RV end-diastolic or end-systolic volumes as the MIDs for improvement. Conversely, a 5% decrease in RV ejection fraction and a 10 mL increase in RV volumes were associated with worsening.

CONCLUSIONS

This study establishes clinically relevant CMR MIDs for how a patient "feels, functions or survives" in response to PAH treatment. These findings provide further support for the use of CMR as a clinically relevant clinical outcome measure and will aid trial size calculations for studies using CMR.

Assessment of Right Ventricular Function-a State of the Art

PURPOSE OF REVIEW

The right ventricle (RV) has a complex geometry and physiology which is distinct from the left. RV dysfunction and failure can be the aftermath of volume- and/or pressure-loading conditions, as well as myocardial and pericardial diseases.

RECENT FINDINGS

Echocardiography, magnetic resonance imaging and right heart catheterisation can assess RV function by using several qualitative and quantitative parameters. In pulmonary hypertension (PH) in particular, RV function can be impaired and is related to survival. An accurate assessment of RV function is crucial for the early diagnosis and management of these patients. This review focuses on the different modalities and indices used for the evaluation of RV function with an emphasis on PH.

How should studies using AI be reported? lessons from a systematic review in cardiac MRI

Recent years have seen a dramatic increase in studies presenting artificial intelligence (AI) tools for cardiac imaging. Amongst these are AI tools that undertake segmentation of structures on cardiac MRI (CMR), an essential step in obtaining clinically relevant functional information. The quality of reporting of these studies carries significant implications for advancement of the field and the translation of AI tools to clinical practice. We recently undertook a systematic review to evaluate the quality of reporting of studies presenting automated approaches to segmentation in cardiac MRI (Alabed et al. 2022 Quality of reporting in AI cardiac MRI segmentation studies-a systematic review and recommendations for future studies. Frontiers in Cardiovascular Medicine 9:956811). 209 studies were assessed for compliance with the Checklist for AI in Medical Imaging (CLAIM), a framework for reporting. We found variable-and sometimes poor-quality of reporting and identified significant and frequently missing information in publications. Compliance with CLAIM was high for descriptions of models (100%, IQR 80%-100%), but lower than expected for descriptions of study design (71%, IQR 63-86%), datasets used in training and testing (63%, IQR 50%-67%) and model performance (60%, IQR 50%-70%). Here, we present a summary of our key findings, aimed at general readers who may not be experts in AI, and use them as a framework to discuss the factors determining quality of reporting, making recommendations for improving the reporting of research in this field. We aim to assist researchers in presenting their work and readers in their appraisal of evidence. Finally, we emphasise the need for close scrutiny of studies presenting AI tools, even in the face of the excitement surrounding AI in cardiac imaging.

Semi-automatic thresholding of RV trabeculation improves repeatability and diagnostic value in suspected pulmonary hypertension

Objectives

Right ventricle (RV) mass is an imaging biomarker of mean pulmonary artery pressure (MPAP) and pulmonary vascular resistance (PVR). Some methods of RV mass measurement on cardiac MRI (CMR) exclude RV trabeculation. This study assessed the reproducibility of measurement methods and evaluated whether the inclusion of trabeculation in RV mass affects diagnostic accuracy in suspected pulmonary hypertension (PH).

Materials and methods

Two populations were enrolled prospectively. (i) A total of 144 patients with suspected PH who underwent CMR followed by right heart catheterization (RHC). Total RV mass (including trabeculation) and compacted RV mass (excluding trabeculation) were measured on the end-diastolic CMR images using both semi-automated pixel-intensity-based thresholding and manual contouring techniques. (ii) A total of 15 healthy volunteers and 15 patients with known PH. Interobserver agreement and scan-scan reproducibility were evaluated for RV mass measurements using the semi-automated thresholding and manual contouring techniques.

Results

Total RV mass correlated more strongly with MPAP and PVR (r = 0.59 and 0.63) than compacted RV mass (r = 0.25 and 0.38). Using a diagnostic threshold of MPAP ≥ 25 mmHg, ROC analysis showed better performance for total RV mass (AUC 0.77 and 0.81) compared to compacted RV mass (AUC 0.61 and 0.66) when both parameters were indexed for LV mass. Semi-automated thresholding was twice as fast as manual contouring (p < 0.001).

Conclusion

Using a semi-automated thresholding technique, inclusion of trabecular mass and indexing RV mass for LV mass (ventricular mass index), improves the diagnostic accuracy of CMR measurements in suspected PH.

Quality of reporting in AI cardiac MRI segmentation studies - A systematic review and recommendations for future studies

Background

There has been a rapid increase in the number of Artificial Intelligence (AI) studies of cardiac MRI (CMR) segmentation aiming to automate image analysis. However, advancement and clinical translation in this field depend on researchers presenting their work in a transparent and reproducible manner. This systematic review aimed to evaluate the quality of reporting in AI studies involving CMR segmentation.

Methods

MEDLINE and EMBASE were searched for AI CMR segmentation studies in April 2022. Any fully automated AI method for segmentation of cardiac chambers, myocardium or scar on CMR was considered for inclusion. For each study, compliance with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) was assessed. The CLAIM criteria were grouped into study, dataset, model and performance description domains.

Results

209 studies published between 2012 and 2022 were included in the analysis. Studies were mainly published in technical journals (58%), with the majority (57%) published since 2019. Studies were from 37 different countries, with most from China (26%), the United States (18%) and the United Kingdom (11%). Short axis CMR images were most frequently used (70%), with the left ventricle the most commonly segmented cardiac structure (49%). Median compliance of studies with CLAIM was 67% (IQR 59-73%). Median compliance was highest for the model description domain (100%, IQR 80-100%) and lower for the study (71%, IQR 63-86%), dataset (63%, IQR 50-67%) and performance (60%, IQR 50-70%) description domains.

Conclusion

This systematic review highlights important gaps in the literature of CMR studies using AI. We identified key items missing-most strikingly poor description of patients included in the training and validation of AI models and inadequate model failure analysis-that limit the transparency, reproducibility and hence validity of published AI studies. This review may support closer adherence to established frameworks for reporting standards and presents recommendations for improving the quality of reporting in this field.

Systematic Review Registration

[www.crd.york.ac.uk/prospero/], identifier [CRD42022279214].

The Applications of Artificial Intelligence in Cardiovascular Magnetic Resonance-A Comprehensive Review

Cardiovascular disease remains an integral field on which new research in both the biomedical and technological fields is based, as it remains the leading cause of mortality and morbidity worldwide. However, despite the progress of cardiac imaging techniques, the heart remains a challenging organ to study. Artificial intelligence (AI) has emerged as one of the major innovations in the field of diagnostic imaging, with a dramatic impact on cardiovascular magnetic resonance imaging (CMR). AI will be increasingly present in the medical world, with strong potential for greater diagnostic efficiency and accuracy. Regarding the use of AI in image acquisition and reconstruction, the main role was to reduce the time of image acquisition and analysis, one of the biggest challenges concerning magnetic resonance; moreover, it has been seen to play a role in the automatic correction of artifacts. The use of these techniques in image segmentation has allowed automatic and accurate quantification of the volumes and masses of the left and right ventricles, with occasional need for manual correction. Furthermore, AI can be a useful tool to directly help the clinician in the diagnosis and derivation of prognostic information of cardiovascular diseases. This review addresses the applications and future prospects of AI in CMR imaging, from image acquisition and reconstruction to image segmentation, tissue characterization, diagnostic evaluation, and prognostication.

Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning

Introduction

Computed tomography pulmonary angiography (CTPA) is an essential test in the work-up of suspected pulmonary vascular disease including pulmonary hypertension and pulmonary embolism. Cardiac and great vessel assessments on CTPA are based on visual assessment and manual measurements which are known to have poor reproducibility. The primary aim of this study was to develop an automated whole heart segmentation (four chamber and great vessels) model for CTPA.

Methods

A nine structure semantic segmentation model of the heart and great vessels was developed using 200 patients (80/20/100 training/validation/internal testing) with testing in 20 external patients. Ground truth segmentations were performed by consultant cardiothoracic radiologists. Failure analysis was conducted in 1,333 patients with mixed pulmonary vascular disease. Segmentation was achieved using deep learning via a convolutional neural network. Volumetric imaging biomarkers were correlated with invasive haemodynamics in the test cohort.

Results

Dice similarity coefficients (DSC) for segmented structures were in the range 0.58-0.93 for both the internal and external test cohorts. The left and right ventricle myocardium segmentations had lower DSC of 0.83 and 0.58 respectively while all other structures had DSC >0.89 in the internal test cohort and >0.87 in the external test cohort. Interobserver comparison found that the left and right ventricle myocardium segmentations showed the most variation between observers: mean DSC (range) of 0.795 (0.785-0.801) and 0.520 (0.482-0.542) respectively. Right ventricle myocardial volume had strong correlation with mean pulmonary artery pressure (Spearman's correlation coefficient = 0.7). The volume of segmented cardiac structures by deep learning had higher or equivalent correlation with invasive haemodynamics than by manual segmentations. The model demonstrated good generalisability to different vendors and hospitals with similar performance in the external test cohort. The failure rates in mixed pulmonary vascular disease were low (<3.9%) indicating good generalisability of the model to different diseases.

Conclusion

Fully automated segmentation of the four cardiac chambers and great vessels has been achieved in CTPA with high accuracy and low rates of failure. DL volumetric biomarkers can potentially improve CTPA cardiac assessment and invasive haemodynamic prediction.