Prognostic impact of artificial intelligence-based fully automated global circumferential strain in patients undergoing stress CMR

Prognostic impact of late gadolinium enhancement granularity in non-ischemic dilated cardiomyopathy

OBJECTIVES

We aimed to assess the additional prognostic value of the concept of "late gadolinium enhancement (LGE) granularity" in non-ischemic dilated cardiomyopathy (DCM) patients to predict all-cause death.

METHODS

Between 2008 and 2021, we conducted a bicentric retrospective study including all consecutive DCM patients referred for Cardiovascular Magnetic Resonance (CMR). The primary outcome was all-cause death. Cox regressions were performed to determine the prognostic value of LGE findings.

RESULTS

Of 1668 DCM patients recruited (age 52 ± 8 years, 54% male), 268 (16%) died after a median (interquartile range) follow-up of 9 (7-12) years. In DCM patients with LGE (N = 472), the LGE extent, the septal location, and its presence in multiple areas were independently associated with death after adjustment for all prognostic variables (adjusted hazard ratio (HR): 4.27, 95% CI: 2.22-8.22; HR: 5.74, 95% CI: 3.35-9.85; and HR: 4.38, 95% CI: 2.08-9.22 respectively; all p < 0.001). The LGE granularity model combining all these LGE features showed the best improvement in model discrimination and reclassification over traditional prognostic variables, including the left ventricular ejection fraction (LVEF) value (C-statistic improvement: 0.14; net reclassification improvement = 64.3%; integrative discrimination index = 29.0%; all p < 0.05).

CONCLUSION

In a large cohort of DCM patients, a LGE granularity model combining LGE extent, location and multiple areas had additional prognostic value above traditional prognostic variables including the LVEF value to predict all-cause death.

KEY POINTS

Question Assessment of late gadolinium enhancement (LGE) is recommended in non-ischemic dilated. cardiomyopathy (DCM) patients to stratify the risk of death, but other LGE characteristics are not currently considered. Findings The concept of "LGE granularity," including the extent, location, and number of areas, provides additional prognostic value, especially in predicting all-cause mortality. Clinical relevance "LGE granularity" could play a crucial role not only in guiding the decision to implant a defibrillator in DCM patients but also in providing more personalized management, such as enhanced cardioprotective treatments, for those with high-risk LGE characteristics.

Myocardial deformation in multisystem inflammatory syndrome in children: layer-specific cardiac MRI insights from a pediatric cohort

BACKGROUND

Multilayer strain magnetic resonance imaging (MRI) analysis offers detailed insights into myocardial mechanics and cardiac function by assessing different layers of the heart muscle, enabling a comprehensive understanding of cardiac involvement.

OBJECTIVE

This study aims to explore cardiac strain differences between patients with multisystem inflammatory syndrome and a control group at medium-term follow-up, utilizing a layer-specific cardiac magnetic resonance imaging (CMR) approach.

MATERIALS AND METHODS

In this retrospective study, patients with multisystem inflammatory syndrome in children (MIS-C) and a group of controls who had undergone cardiac magnetic resonance (CMR) imaging were selected and included. CMR was performed 30 days after discharge (range 34-341 days) for MIS-C patients. TrufiStrain research prototype software (Siemens Healthineers AG, Erlangen, Germany) was used for automated myocardial segmentation and strain calculation, to measure radial strain (RS), circumferential strain (CS), and longitudinal strain (LS) at the epicardial, mid-wall, and endocardial levels. Statistical analysis included Shapiro-Wilk tests, Student t-tests, and Mann-Whitney U tests, ANOVA, and regression analysis, maintaining a significance level of α = 0.05.

RESULTS

The study cohort consisted of 32 MIS-C patients (≤ 18 years; 14 females) and 64 control participants (≤ 18 years; 24 females). Median interval to CMR post diagnosis was 142 days (range 34-341) with normal CMR findings for all patients. The mean age of the two groups was similar (MIS-C: 14.2 years; controls: 14.1 years, P = 0.49). There were no significant differences in height (MIS-C: 164.7 cm; controls: 163.9 cm, P = 0.84), weight (MIS-C: 68.2 kg; controls: 59.4 kg, P = 0.11), or body surface area (MIS-C: 1.7 m2; controls: 1.7 m2, P = 0.41). Global strain measurements showed no significant differences between the groups (global LS MIS-C patients - 16.2% vs - 15.7% in controls (P = 0.23); global RS 27.8% in MIS-C patients vs 29.5% in controls (P = 0.35); and global CS - 16.7% in MIS-C patients vs - 16.8% in controls (P = 0.92)). Similarly, layer-specific strain analysis across the endocardial (LS values of - 17.7% vs - 16.8% (P = 0.19), RS of 23.1% vs 24.8% (P = 0.25), and CS of - 19.9% vs - 19.9% (P = 0.92)), epicardial (LS - 14.9% vs - 14.5% (P = 0.31), RS of 31.2% vs 33.1% (P = 0.29), and CS of - 14.1% vs - 14.2% (P = 0.75)), and midmyocardial (LS - 16.5% vs - 16.3% (P = 0.18), RS 29.3% vs 31.8% (P = 0.31), and CS - 17.0% vs - 17.2% (P = 0.95)) levels revealed no significant disparities. The only notable finding was the reduced apical radial strain in MIS-C patients compared to controls (global RS MIS-C 12.4% vs 17.4% in controls, P = 0.03; endocardium RS MIS-C 4.9% vs 10.31% in controls, P = 0.01; epicardial RS MIS-C 17.7% vs 22.6% in controls, P = 0.02; and midmyocardium RS MIS-C 12.5% vs 17.9% in controls, P = 0.02).

CONCLUSION

This study demonstrates that MIS-C does not significantly impact global or layer-specific myocardial strain values, as assessed by CMR, compared to a control group. The lower apical radial strain in MIS-C patients indicates a potential localized myocardial involvement.

Gated SPECT-Derived Myocardial Strain Estimated From Deep-Learning Image Translation Validated From N-13 Ammonia PET

RATIONALE AND OBJECTIVES

This study investigated the use of deep learning-generated virtual positron emission tomography (PET)-like gated single-photon emission tomography (SPECTVP) for assessing myocardial strain, overcoming limitations of conventional SPECT.

MATERIALS AND METHODS

SPECT-to-PET translation models for short-axis, horizontal, and vertical long-axis planes were trained using image pairs from the same patients in stress (720 image pairs from 18 patients) and resting states (920 image pairs from 23 patients). Patients without ejection-fraction changes during SPECT and PET were selected for training. We independently analyzed circumferential strains from short-axis-gated SPECT, PET, and model-generated SPECTVP images using a feature-tracking algorithm. Longitudinal strains were similarly measured from horizontal and vertical long-axis images. Intraclass correlation coefficients (ICCs) were calculated with two-way random single-measure SPECT and SPECTVP (PET). ICCs (95% confidence intervals) were defined as excellent (≥0.75), good (0.60-0.74), moderate (0.40-0.59), or poor (≤0.39).

RESULTS

Moderate ICCs were observed for SPECT-derived stressed circumferential strains (0.56 [0.41-0.69]). Excellent ICCs were observed for SPECTVP-derived stressed circumferential strains (0.78 [0.68-0.85]). Excellent ICCs of stressed longitudinal strains from horizontal and vertical long axes, derived from SPECT and SPECTVP, were observed (0.83 [0.73-0.90], 0.91 [0.85-0.94]).

CONCLUSION

Deep-learning SPECT-to-PET transformation improves circumferential strain measurement accuracy using standard-gated SPECT. Furthermore, the possibility of applying longitudinal strain measurements via both PET and SPECTVP was demonstrated. This study provides preliminary evidence that SPECTVP obtained from standard-gated SPECT with postprocessing potentially adds clinical value through PET-equivalent myocardial strain analysis without increasing the patient burden.

Deep-Learning-Based Disease Classification in Patients Undergoing Cine Cardiac MRI

BACKGROUND

Automated approaches may allow for fast, reproducible clinical assessment of cardiovascular diseases from MRI.

PURPOSE

To develop an MRI-based deep learning (DL) disease classification algorithm to distinguish among normal subjects (NORM), patients with dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy (HCM), and ischemic heart disease (IHD).

STUDY TYPE

Retrospective.

POPULATION

A total of 1337 subjects (55% female), comprising normal subjects (N = 568), and patients with DCM (N = 151), HCM (N = 177), and IHD (N = 441).

FIELD STRENGTH/SEQUENCE

Balanced steady-state free precession cine sequence at 1.5/3.0 T.

ASSESSMENT

Bi-ventricular morphological and functional features and global and segmental left ventricular strain features were automatically extracted from short- and long-axis cine images. Variational autoencoder models were trained on the extracted features and compared against consensus disease label provided by two expert readers (13 and 14 years of experience). Adding unlabeled, normal data to the training was explored to increase specificity of NORM class.

STATISTICAL TESTS

Tenfold cross-validation for model development; mean, standard deviation (SD) for measurements; classification metrics: area under the curve (AUC), confusion matrix, accuracy, specificity, precision, recall; 95% confidence intervals; Mann-Whitney U test for significance.

RESULTS

AUCs of 0.952 for NORM, 0.881 for DCM, 0.908 for HCM, and 0.856 for IHD and overall accuracy of 0.778 were obtained, with specificity of 0.908 for the NORM class using both SAX and LAX features. Longitudinal strain features slightly improved classification metrics by 0.001 to 0.03 points, except for HCM-AUC. Differences in accuracy, metrics for NORM class and HCM-AUC were statistically significant. Cotraining using unlabeled data increased the specificity for the NORM class to 0.961.

DATA CONCLUSION

Cardiac function features automatically extracted from cine MRI have potential to be used for disease classification, especially for normal-abnormal classification. Feature analyses showed that strain features were important for disease labeling. Cotraining using unlabeled data may help to increase specificity for normal-abnormal classification.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 1.

Artificial intelligence-based fully automated stress left ventricular ejection fraction as a prognostic marker in patients undergoing stress cardiovascular magnetic resonance

AIMS

This study aimed to determine in patients undergoing stress cardiovascular magnetic resonance (CMR) whether fully automated stress artificial intelligence (AI)-based left ventricular ejection fraction (LVEFAI) can provide incremental prognostic value to predict death above traditional prognosticators.

METHODS AND RESULTS

Between 2016 and 2018, we conducted a longitudinal study that included all consecutive patients referred for vasodilator stress CMR. LVEFAI was assessed using AI algorithm combines multiple deep learning networks for LV segmentation. The primary outcome was all-cause death assessed using the French National Registry of Death. Cox regression was used to evaluate the association of stress LVEFAI with death after adjustment for traditional risk factors and CMR findings. In 9712 patients (66 ± 15 years, 67% men), there was an excellent correlation between stress LVEFAI and LVEF measured by expert (LVEFexpert) (r = 0.94, P < 0.001). Stress LVEFAI was associated with death [median (interquartile range) follow-up 4.5 (3.7-5.2) years] before and after adjustment for risk factors [adjusted hazard ratio, 0.84 (95% confidence interval, 0.82-0.87) per 5% increment, P < 0.001]. Stress LVEFAI had similar significant association with death occurrence compared with LVEFexpert. After adjustment, stress LVEFAI value showed the greatest improvement in model discrimination and reclassification over and above traditional risk factors and stress CMR findings (C-statistic improvement: 0.11; net reclassification improvement = 0.250; integrative discrimination index = 0.049, all P < 0.001; likelihood-ratio test P < 0.001), with an incremental prognostic value over LVEFAI determined at rest.

CONCLUSION

AI-based fully automated LVEF measured at stress is independently associated with the occurrence of death in patients undergoing stress CMR, with an additional prognostic value above traditional risk factors, inducible ischaemia and late gadolinium enhancement.

Utilizing Artificial Intelligence-Based Deformable Registration for Global and Layer-Specific Cardiac MRI Strain Analysis in Healthy Children and Young Adults

RATIONALE AND OBJECTIVES

The absence of published reference values for multilayer-specific strain measurement using cardiac magnetic resonance (CMR) in young healthy individuals limits its use. This study aimed to establish normal global and layer-specific strain values in healthy children and young adults using a deformable registration algorithm (DRA).

MATERIALS AND METHODS

A retrospective study included 131 healthy children and young adults (62 males and 69 females) with a mean age of 16.6 ± 3.9 years. CMR examinations were conducted using 1.5T scanners, and strain analysis was performed using TrufiStrain research prototype software (Siemens Healthineers, Erlangen, Germany). Global and layer-specific strain parameters were extracted from balanced Steady-state free precession cine images. Statistical analyses were conducted to evaluate the impact of demographic variables on strain measurements.

RESULTS

The peak global longitudinal strain (LS) was -16.0 ± 3.0%, peak global radial strain (RS) was 29.9 ± 6.3%, and peak global circumferential strain (CS) was -17.0 ± 1.8%. Global LS differed significantly between males and females. Transmural strain analysis showed a consistent pattern of decreasing LS and CS from endocardium to epicardium, while radial strain increased. Basal-to-apical strain distribution exhibited decreasing LS and increasing CS in both global and layer-specific analysis.

CONCLUSION

This study uses DRA to provide reference values for global and layer-specific strain in healthy children and young adults. The study highlights the impact of sex and age on LS and body mass index on RS. These insights are vital for future cardiac assessments in children, particularly for early detection of heart diseases.