Journal Article

Automated extracellular volume fraction measurement for diagnosis and prognostication in patients with light-chain cardiac amyloidosis

Park, Jiesuck, Choi, Byoung Wook, Cho, Goo-Yeong, Chun, Eun Ju, Hwang, In-Chang, Choi, Hong-Mi, Yoon, Yeonyee E., Kim, Pan Ki, Kim, Myeongju

2025

Overview

T1 mapping on cardiac magnetic resonance (CMR) imaging is useful for diagnosis and prognostication in patients with light-chain cardiac amyloidosis (AL-CA). We conducted this study to evaluate the performance of T1 mapping parameters, derived from artificial intelligence (AI)-automated segmentation, for detection of cardiac amyloidosis (CA) in patients with left ventricular hypertrophy (LVH) and their prognostic values in patients with AL-CA. A total of 300 consecutive patients who underwent CMR for differential diagnosis of LVH were analyzed. CA was confirmed in 50 patients (39 with AL-CA and 11 with transthyretin amyloidosis), hypertrophic cardiomyopathy in 198, hypertensive heart disease in 47, and Fabry disease in 5. A semi-automated deep learning algorithm (Myomics-Q) was used for the analysis of the CMR images. The optimal cutoff extracellular volume fraction (ECV) for the differentiation of CA from other etiologies was 33.6% (diagnostic accuracy 85.6%). The automated ECV measurement showed a significant prognostic value for a composite of cardiovascular death and heart failure hospitalization in patients with AL-CA (revised Mayo stage III or IV) (adjusted hazard ratio 4.247 for ECV ≥40%, 95% confidence interval 1.215-14.851, p-value = 0.024). Incorporation of automated ECV measurement into the revised Mayo staging system resulted in better risk stratification (integrated discrimination index 27.9%, p = 0.013; categorical net reclassification index 13.8%, p = 0.007). T1 mapping on CMR imaging, derived from AI-automated segmentation, not only allows for improved diagnosis of CA from other etiologies of LVH, but also provides significant prognostic value in patients with AL-CA.

• Publisher: Public Library of Science,Public Library of Science (PLoS)
• Subject: Aged / Algorithms / Amyloidosis / Analysis / Artificial intelligence / Automation / Biology and Life Sciences / Biopsy / Cardiac patients / Cardiomyopathies - diagnosis / Cardiomyopathies - diagnostic imaging / Cardiomyopathy / Cardiovascular disease / Cardiovascular diseases / Care and treatment / Chemotherapy / Comparative analysis / Confidence intervals / Congestive heart failure / Data mining / Deep Learning / Development and progression / Diagnosis / Diagnosis, Differential / Differential diagnosis / Electrocardiogram / Electrocardiography / Etiology / Fabry's disease / Female / Gadobutrol / Heart / Heart diseases / Heart enlargement / Humans / Hypertension / Hypertrophy / Hypertrophy, Left Ventricular - diagnostic imaging / Image segmentation / Immunoglobulin Light-chain Amyloidosis - diagnosis / Immunoglobulin Light-chain Amyloidosis - diagnostic imaging / Immunoglobulin Light-chain Amyloidosis - pathology / Machine learning / Magnetic resonance / Magnetic resonance imaging / Magnetic Resonance Imaging - methods / Male / Mapping / Measurement / Medical diagnosis / Medical imaging / Medical prognosis / Medicine and Health Sciences / Middle Aged / Mutation / Performance evaluation / Prognosis / Questions and answers / Segmentation / Software / Survival analysis / Transthyretin