Prospective Study
Copyright ©The Author(s) 2025.
World J Cardiol. Jul 26, 2025; 17(7): 108745
Published online Jul 26, 2025. doi: 10.4330/wjc.v17.i7.108745
Table 1 Participant demographics

Male
Female
Total


Participants (%)42 (47)47 (53)89
    Patients26 (43)34 (57)60
    Volunteers16 (55)13 (45)29
Ethnicity (%)WhiteBlackHispanicAsianTotal
    Participants68 (76)15 (18)1 (1)5 (5)89
    Patients46 (77)13 (21)1 (2)0 (0)60
Volunteers22 (77)2 (7)0 (0)5 (16)29
Age (year)MaleFemaleTotal
Participants57.3 (19-83)59.6 (18-83)58.4 (18-83)
Patients62.5 (30-88)63.0 (18-83)62.8 (18-83)
Volunteers48.6 (19-77)50.8 (24-71)49.6 (19-77)
BSA (m2)MaleFemaleTotal
Participants2.04 (1.70-2.45)1.84 (1.31-2.87)1.93 (1.31-2.87)
Heart rateMaleFemaleTotal
Participants66 (46-113)67 (47-108)67 (46-113)
Clinical referral indication Patients
r/o cardiotoxicity29
r/o amyloidosis30
r/o myocarditis3
r/o cardiomyopathy17
Arrhythmia9
Chest pain9
Table 2 Conventional CINE and Artificial-intelligence-assisted compressed sensing CINE image parameters

C-CINE
AI-CS-CINE
ECG modeRetrospectiveRetrospective
TR/TE (millisecond)3.57/1.752.74/1.28
Image matrix224 × 85192 × 100
Reconstruction matrix2.01.5
Spatial resolution (mm)1.89 × 1.611.88 × 1.88
Flip angle (°)8060
Bandwidth (Hz/pixel)15001200
Temporal resolution (millisecond)5441
Reconstructed cardiac phases2525
Field of view (mm)360 × 320360 × 320
Slice thickness (mm)88
Gap (mm)00
Number of slices1111
Longest breath-hold for acquisition (second)1111
Number of slices acquired per 11-sec breath hold16
Number of breath-holds112
Shortest breath-hold time to acquire one slice (second)112
Total acquisition time including breath-holds (second)23837
Table 3 Alignment of left ventricle and right ventricle volume and function metrics with conventional CINE vs artificial-intelligence-assisted compressed sensing CINE excluding outliers (n = 89)
mean ± SD
Bland–Altman
Intraclass coefficient
C-CINE
AI-CS-CINE
Bias ± SD
LoA
r
95%CI
LVEF (%)56.2 ± 11.055.9 ± 11.10.28 ± 3.78-7.13, 7.690.940.91, 0.96
LVEDVi (mL/m2)75.9 ± 19.073.3 ± 19.02.63 ± 5.30-7.76, 13.010.950.93, 0.97
LVESVi (mL/m2)34.4 ± 16.033.4 ± 15.71.02 ± 3.35-5.55, 7.590.980.96, 0.98
LVSVi (mL/m2)41.5 ± 9.339.9 ± 9.61.61 ± 4.21-6.63, 9.850.890.83, 0.92
LVMi (mL/m2)58.4 ± 20.359.3 ± 20.60.91 ± 4.14-9.01, 7.200.980.97, 0.99
Relative wall thickness0.4 ± 0.20.4 ± 0.20.00 ± 0.05-0.10, 0.100.950.93, 0.97
RVEF (%)50.8 ± 10.051.5 ± 10.30.66 ± 7.32-15.01, 13.690.730.62, 0.82
RVEDVi (mL/m2)71.0 ± 14.869.3 ± 14.71.74 ± 6.60-11.21, 14.680.890.84, 0.93
RVESVi (mL/m2)35.1 ± 11.033.6 ± 10.41.51 ± 5.28-8.84, 11.870.870.81, 0.91
RVSVi (mL/m2)35.9 ± 9.735.7 ± 10.50.22 ± 7.12-13.74, 14.180.750.64, 0.83
Table 4 Alignment of left ventricle and right ventricle volume and function metrics with Conventional CINE vs Artificial-intelligence-assisted compressed sensing CINE in patients with cardiac amyloidosis (n = 31)
mean ± SD
Bland–Altman
Intraclass coefficient
C-CINE
AI-CS-CINE
Bias ± SD
LoA
r
95%CI
LVEF (%)55.9 ± 13.257.0 ± 13.2-1.05 ± 4.56-10.00, 7.890.940.87, 0.97
LVEDVi (mL/m2)75.1 ± 21.172.0 ± 20.23.16 ± 7.0710.70, 17.020.930.85, 0.97
LVESVi (mL/m2)34.8 ± 19.032.2 ± 17.22.55 ± 6.12-9.45, 14.550.930.86, 0.97
LVSVi (mL/m2)40.4 ± 10.239.8 ± 11.10.61 ± 4.52-8.26, 9.470.910.82, 0.95
LVMi (mL/m2)69.9 ± 29.070.4 ± 29.5-0.42 ± 5.8111.81, 10.970.980.96, 0.99
Relative wall thickness0.5 ± 0.20.5 ± 0.20.00 ± 0.06-0.13, 0.120.960.91, 0.98
RVEF (%)48.9 ± 14.652.1 ± 13.0-3.14 ± 9.0920.96, 14.680.760.56, 0.88
RVEDVi (mL/m2)70.8 ± 16.270.9 ± 15.1-0.02 ± 8.7217.12, 17.070.840.70, 0.92
RVESVi (mL/m2)37.1 ± 16.534.5 ± 13.52.64 ± 7.6512.36, 17.640.860.72, 0.93
RVSVi (mL/m2)33.7 ± 10.736.4 ± 10.5-2.66 ± 8.5719.46, 14.130.650.40, 0.81