Geometric remodelling of the left ventricle (LV) following myocardial infarction reflects on the geometric characteristics directly. This study focuses on a potential index based on curvedness. Nine consecutive normal volunteers and thirty consecutive myocardial infarction patients underwent MRI scan (twenty-seven patients had follow-up scan). Short-axis cine images of all cases were delineated. Three dimensional LV models were reconstructed and restored for possible motion distortion. The curvedness values were computed over 16-segments nomenclature. The curvedness signal for each segment over twenty-two time frames were fitted using a second order Fourier Series. Fourier coefficients were extracted and unsupervised learning was conducted between normal and patient data. An accuracy of 89% and adjusted Rand Index of 0.5374 suggest that these Fourier Series and curvedness based features can be an useful index for prognosis and diagnosis in clinical practice.