EVALUATION OF COMPUTER ALGORITHMS FOR THE ANALYSIS AND RECONSTRUCTION OF CARDIAC IMAGES
PARAGES, FELIPE M.
MetadataShow full item record
In the medical imaging field, image processing algorithms must be evaluated by measuring performance at some clinically-relevant task of interest (i.e. task-based quality assessment). This dissertation relies on the task-based paradigm to evaluate motion-estimation and image-reconstruction methods, respectively, for two cardiac-imaging modalities, namely: cardiac-gated tagged Magnetic Resonance Imaging (MRI), and Single Photon Emission Computerized Tomography for Myocardial Perfusion Imaging (SPECT-MPI). First, a task-based approach is followed to evaluate three motion-estimation methods for clinical cardiac-gated tagged MRI, namely: non-rigid registration using a Deformable Mesh Model (DMM), Strain from Unwrapped Harmonic Phase (SUPHARP), and Feature-Based (FB) algorithms. More specifically, the goal is to quantify and rank their performances at both detection and estimation tasks. For detection, methods are evaluated per their ability to discern between normal and abnormal motion patterns in known cardiomyopathies (e.g. hypertension and mitral regurgitation). For estimation tasks, methods are evaluated per their accuracy at estimating several rotation/twist and strain features of clinical interest; since true values for these features are generally unknown, a statistical Regression Without Truth (RWT) model is adopted, which does not assume the existence of a “gold-standard” method to use as a ground-truth reference. Moreover, the RWT model provides with an objective figure-of-merit that allows ranking methods in absolute fashion. Second, a novel anthropomorphic Model Observer (MO) is proposed for optimization of SPECT-MPI reconstruction algorithms such as Filtered Back-projection (FBP) and Ordered-subsets Expectation Maximization (OSEM). MOs are computer models that aim to mimic the performance of human readers (typically radiologists) at some clinically relevant task of interest. The proposed MO is based on supervised machine-learning classification, for the diagnostic tasks of detection, localization and assessment of perfusion defects. The MO is trained using an ensemble of synthetic cases whose perfusion were scored (i.e. labeled) by human specialists. The trained MO is subsequently applied on images not read by humans (both synthetic and clinical), aiming to predict their diagnostic scores. Results show that the proposed MO accurately predicts human diagnostic performances. Furthermore, it generalizes well to new images not used during training, not only from different reconstruction algorithms, but also from synthetic to clinical cases.