BACKGROUND
Cardiac magnetic resonance feature tracking (CMR-FT) of left atrial (LA) strain is hindered by thin-wall contouring errors, motion heterogeneity, and temporal drift, while manual or landmark-based methods lack reproducibility and scalability.
METHODS
We retrospectively collected a multi-center, two-vendor cine MRI dataset. A multi-task learning model was developed to quantify LA strain directly from two-chamber and four-chamber cine images, by coupling a groupwise registration network with a segmentation network through a spatiotemporal cross-attention module and synergistic losses. Performance was benchmarked against common feature tracking algorithms, including optical flow, pairwise registration, and VoxelMorph, via various metrics such as mean-squared error, contour distance, mitral annular tracking accuracy, and drift error. Diagnostic performance to distinguish healthy from diseased subjects was assessed by ROC analysis.
RESULTS
546 subjects (142 healthy; age 49±18 years; 343 male) were included for method development and internal/external testing. The proposed method outperformed all other methods in tracking accuracy and reduced the drift effect commonly observed in optical flow and pairwise registration to a level comparable to fixed-reference learning-based registration. Inference required half a second. Automatic strains agreed closely with manual-segmentation-derived values (reservoir r=0.95, conduit r=0.96, booster r=0.92; all p<0.001). In the external dataset, all three strain components were lower in diseased subjects than normal controls (reservoir 24.4±13.2% vs 45.7±12.6%, conduit 14.1±8.8% vs 31.1±10.2%, and booster 10.3±6.4% vs 14.6±5.1%, all p<0.001). Compared with alternative methods, the automatic reservoir strain achieved the highest discriminative power across multiple diseased groups (AUC: 0.81-0.97).
CONCLUSION
A fully automatic, multi-task learning framework for LA strain quantification, validated in multi-center two-vendor data, enhances tracking accuracy and speed over prior methods, enabling rapid, scalable atrial function assessment in routine care. Source code is available at SJTU-CMRLab/Dual_Task_LA_Strain_Quantification.
Yi-Chen Zhao, Haiyang Chen, Yiwen Gong et al.· Journal of Cardiovascular Ma...· 0 citations
Summary Background In parallel with diagnostic advances and awareness of cardiac amyloidosis (CA) in aging populations, frailty is increasingly observed in CA. However, the relationship between the frailty and CA remains poorly characterized owing to limited studies that have defined frailty a priori. We performed a meta-analysis to characterize the impact of frailty on clinical and functional patient outcomes in CA. Methods Systematic review of four electronic databases was performed for all studies reporting frailty prevalence, functional and clinical endpoints in patients with CA from January 2015 to April 2026 (CRD420251152212). Frailty was classified based on individual study scoring systems. The primary outcome of interest was all-cause mortality, expressed as pooled hazard (HR) or risk ratios (RR) with 95% confidence intervals (CI) using inverse-variance random-effects models. Other outcomes included hospitalizations, quality of life, functional status (6-min walk distance [6MWD]), and prescription of disease modifying treatment. Heterogeneity was summarized using the I2 statistic; study quality was rated with the Newcastle–Ottawa Scale; and certainty of evidence was graded using the GRADE framework. Leave-one-out sensitivity analyses and visual funnel plots were performed where applicable. Findings Fifteen studies with a total of 5048 patients, predominantly (>95%) with transthyretin amyloid cardiomyopathy (ATTR-CM), were included. The prevalence of frailty ranged between 6.7% and 75% across studies with a pooled mean of 33.9% (826/2435 frail). Pooling 2141 patients with outcomes available, both pre-frailty (RR 2.22, 95% CI 1.37–3.60, p < 0.01) and frailty (RR 3.93, 95% CI 2.09–7.40, p < 0.01) significantly associated with increased risks of all-cause mortality after adjustment for age and frailty assessment tool. 6MWD, a functional surrogate of frailty, predicted poorer outcomes both using baseline 6MWD (<350/300 m: HR 2.22, 95% CI 1.15–4.31, p = 0.02) and 1-year interval change in 6MWD (>35 reduction: HR 1.80, 95% CI 1.52–2.14; >5% reduction: HR 1.89, 95% CI 1.60–2.23; both p < 0.01). Beyond mortality, frailty also predicted increased risk of functional decline, poorer quality of life, and reduced prescription of disease-modifying treatment. Interpretation Patients with ATTR-CM and frailty have higher mortality risk, poorer functional outcomes and reduced prescription of disease-modifying treatment compared to those without frailty. Findings were consistent across frailty instruments and sensitivity analyses, supporting the incorporation of routine frailty assessment and 6MWD into clinical management of ATTR amyloidosis. Funding None.
Haowen Jiang, D. J. Lim, C. Khoo et al.· EClinicalMedicine· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
