Pranav Bhagirath

47 Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images Table 2. Image acquisition parameters for the challenge LGE patient and porcine datasets. KCL–IM UL Scanner type Philips Achieva 1.5T Siemens Trio 3.0T Sequence Segmented 2D, inversion recovery gradient echo ECG triggered, breath-hold Segmented 3D inversion recovery, gradient echo ECG triggered breath-hold TI, TR, TE, FA 280 ms, 3.4 ms, 2.0 ms, 25 ° 340-370 ms, 2.19 ms, 0.78 ms, 15 ° Resolution 1.8 × 1.8 × 8 mm 1.8 × 1.8 × 6 mm Interleaving Every R-R interval in ECG Every other R-R interval in ECG Subjects Human Porcine TI, Inversion time; TR, Repetition time; TE, Echo time; FA, Flip angle; ECG, Electrocardiogram. Imaging centers: KCL-IM - Imaging Sciences, King’s College London and UL - Universiteit Leuven. Note that the patient dataset was acquired at KCL- IM and porcine dataset was acquired at UL. The human data (n=15) were from randomly selected patients who had a known history of ischemic cardiomyopathy andwere under assessment for an implantable cardioverter defibrillator (ICD) device for primary or secondary prevention after infarction. In addition to this, the patients chosen had a history of myocardial infarction at least three months prior to their MRI scan. There was also evidence of significant coronary artery disease on angiography and evidence of left ventricular impaired systolic function on echocardiography. The images were acquired on a clinical 1.5T MRI unit (Philips Achieva, The Netherlands). All patients gave written informed consent. The porcine data (n = 15) were randomly selected from an experimental database of a pre-clinical model of chronic myocardial ischemia (Wu et al., 2011), with induced lesions obtained by occluding either the left-anterior descending or left-circumflex artery. The data were acquired six weeks after the induction of the coronary lesion on a clinical 3T MRI unit (Siemens Healthcare, Germany). Representative images are shown in figure 1 . Five research groups segmented the above datasets, leaving ten images aside, which were utilized for training. A brief summary of their algorithms is given in Table 3 . They are described in greater detail in the sections below with a brief background on each technique implemented and details of their implementation.