The Future of Imaging in Heart Failure: Toward Precision Phenotyping, Integration, and Intelligence.

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not applicable — no primary data or pooled effect estimates reported

• Primary Outcome: Narrative synthesis demonstrating a paradigm shift in HF imaging from descriptive, modality-siloed practice toward integrated, AI-augmented, molecularly informed, patient-specific phenotyping and therapy prediction

• Nnt Or Sensitivity: Not reported; the review does not synthesise diagnostic accuracy metrics (sensitivity/specificity) or therapeutic effect sizes for individual technologies

• Confidence Interval: Not reported

Clinical Application

Feasibility varies substantially by technology. AI-enabled handheld POCUS is increasingly accessible in primary and emergency care settings. CMR with advanced parametric mapping and 4D flow remains confined to specialist centres with appropriate hardware, software, and expertise. Molecular PET imaging with novel tracers and hyperpolarised MR spectroscopy are largely research tools with very limited clinical availability. Digital twin technology and photon-counting CT are at early translational stages. Cost-effectiveness data are absent for most modalities discussed. In the Australian context, several considerations apply. CMR services are available at major metropolitan tertiary centres but access is limited in regional and rural areas, consistent with the equity concerns raised in this review. AI-enabled echocardiography tools are beginning to enter Australian practice but are not yet subject to specific TGA regulatory guidance as standalone software medical devices (SaMD), though the TGA's Software as a Medical Device framework is evolving. POCUS training is supported by ACEM and RACGP but competency standards for AI-assisted acquisition remain undefined. Novel PET tracers for amyloid and inflammation imaging (e.g., 18F-florbetapir, 68Ga-DOTATATE) are available at selected PET centres but are not PBS-listed for HF indications. The RACGP and CSANZ have not yet issued specific guidance on AI-augmented cardiac imaging in HF. The review's emphasis on equitable access is particularly salient given Australia's geographic and socioeconomic disparities in specialist cardiac imaging access. Adult patients with established or suspected heart failure across all phenotypes (HFrEF, HFmrEF, HFpEF), particularly those where aetiology remains uncertain (e.g., suspected transthyretin amyloid cardiomyopathy, inflammatory cardiomyopathy, metabolic cardiomyopathy) and those being evaluated for device therapy or advanced HF interventions

Abstract

PURPOSE OF REVIEW: Heart failure (HF) is increasingly understood not as a single, uniformly treated diagnosis but as a heterogeneous syndrome requiring aetiological clarification, in which cardiac imaging is central. As the opening article of this journal's 'Imaging in Heart Failure' section, this review surveys the technologies currently reshaping HF imaging and sets out the section's scope and priorities, framing the shift from a descriptive, modality-siloed practice toward an integrated, predictive, patient-specific discipline. RECENT FINDINGS: Artificial intelligence (AI) now delivers expert-level echocardiography automation, guides image acquisition by novices in resource-limited settings, detects aetiologies such as transthyretin amyloid cardiomyopathy from a single acquisition and enables deep phenotyping through radiomics and vendor-agnostic strain analysis. Handheld, AI-enabled point-of-care ultrasound extends imaging-guided triage beyond the echocardiography laboratory. Cardiovascular magnetic resonance (CMR) advances - parametric mapping, four-dimensional flow, diffusion tensor imaging, spectroscopy, and accelerated reconstruction - broaden tissue and metabolic characterisation, including patients with implanted devices. Molecular imaging with novel positron emission tomography tracers and hyperpolarised magnetic resonance is moving from depicting the structural consequences of disease to imaging active pathobiology, while photon-counting computed tomography and image-derived digital twins support one-stop structural assessment and in-silico prediction of therapy response. The convergence of AI, molecular imaging and advanced precision is transforming HF imaging from better pictures into smarter, integrated, personalised data that directly inform care. Realising this promise will require rigorous validation, attention to algorithmic bias and generalisability, demonstrated cost-effectiveness, curricular reform, and equitable access. This section aims to critically appraise these innovations and their translation into practice.

References

1. 1.Hundertmark, M. J. (2026). The future of imaging in heart failure: Toward precision phenotyping, integration, and intelligence. Current Heart Failure Reports. https://doi.org/10.1038/s44161-025-00650-0