Left Ventricle Detection from Cardiac Magnetic Resonance Relaxometry Images Using Visual Transformer

Left Ventricle (LV) detection from Cardiac Magnetic Resonance (CMR) imaging is a fundamental step, preliminary to myocardium segmentation and characterization. This paper focuses on the application of a Visual Transformer (ViT), a novel neural network architecture, to automatically detect LV from CMR relaxometry sequences. We implemented an object detector based on the ViT model to identify LV from CMR multi-echo T2* sequences. We evaluated performances differentiated by slice location according to the American Heart Association model using 5-fold cross-validation and on an independent dataset of CMR T2*, T2, and T1 acquisitions. To the best of our knowledge, this is the first attempt to localize LV from relaxometry sequences and the first application of ViT for LV detection. We collected an Intersection over Union ([Formula: see text]) index of 0.68 and a Correct Identification Rate ([Formula: see text]) of blood pool centroid of 0.99, comparable with other state-of-the-art methods. [Formula: see text] and [Formula: see text] values were significantly lower in apical slices. No significant differences in performances were assessed on independent T2* dataset ([Formula: see text] = 0.68, p = 0.405; [Formula: see text] = 0.94, p = 0.066). Performances were significantly worse on the T2 and T1 independent datasets (T2: [Formula: see text] = 0.62, [Formula: see text] = 0.95; T1: [Formula: see text] = 0.67, [Formula: see text] = 0.98), but still encouraging considering the different types of acquisition. This study confirms the feasibility of the application of ViT architectures in LV detection and defines a benchmark for relaxometry imaging.