ABSTRACT
Dynamic contrast-enhanced MRI (DCE-MRI) is an imaging protocol where MRI scans are acquired repetitively throughout the injection of a contrast agent. The analysis of dynamic scans is widely used for the detection and quantification of blood-brain barrier (BBB) permeability. Extraction of the pharmacokinetic (PK) parameters from the DCE-MRI concentration curves allows quantitative assessment of the integrity of the BBB functionality. However, curve fitting required for the analysis of DCE-MRI data is error-prone as the dynamic scans are subject to non-white, spatially-dependent and anisotropic noise. We present a novel spatio-temporal framework based on Deep Neural Networks (DNNs) to address the DCE-MRI denoising challenges. This is accomplished by an ensemble of expert DNNs constructed as deep autoencoders, where each is trained on a specific subset of the input space to accommodate different noise characteristics and curve prototypes. Spatial dependencies of the PK dynamics are captured by incorporating the curves of neighboring voxels in the entire process. The most likely reconstructed curves are then chosen using a classifier DNN followed by a quadratic programming optimization. As clean signals (ground-truth) for training are not available, a fully automatic model for generating realistic training sets with complex nonlinear dynamics is introduced. The proposed approach has been successfully applied to full and even temporally down-sampled DCE-MRI sequences, from two different databases, of stroke and brain tumor patients, and is shown to favorably compare to state-of-the-art denoising methods.
Subject(s)
Brain Mapping/methods , Contrast Media/pharmacokinetics , Image Enhancement/methods , Magnetic Resonance Imaging , Neural Networks, Computer , Algorithms , Anisotropy , Blood-Brain Barrier , Humans , Reproducibility of Results , Sensitivity and SpecificitySubject(s)
Diagnostic Errors , Keratomileusis, Laser In Situ/adverse effects , Ocular Hypertension/diagnosis , Acetazolamide/therapeutic use , Adult , Body Fluids , Carbonic Anhydrase Inhibitors/therapeutic use , Humans , Intraocular Pressure , Keratitis/diagnosis , Keratitis/etiology , Male , Ocular Hypertension/drug therapy , Ocular Hypertension/etiology , Tonometry, OcularSubject(s)
Corneal Diseases/etiology , Epithelium, Corneal/pathology , Keratotomy, Radial/adverse effects , Alkylating Agents/administration & dosage , Corneal Diseases/pathology , Corneal Diseases/surgery , Debridement , Epithelium, Corneal/surgery , Fibrosis/etiology , Fibrosis/pathology , Fibrosis/surgery , Humans , Lasers, Excimer , Mitomycin/administration & dosage , Ophthalmic Solutions , Photorefractive Keratectomy , Reoperation , Secondary PreventionABSTRACT
PURPOSE: The authors determine the safety and effectiveness of pericardial patch grafts in glaucoma implant surgery. METHODS: A retrospective chart review was conducted on all patients who underwent a glaucoma implant procedure with the use of a pericardial patch graft to cover the subconjunctival portion of the tube at The New York Eye and Ear Infirmary between September 1, 1995 and June 30, 1996. Charts were assessed for evidence of delle formation, graft rejection, graft-related infection, graft thinning, or tube erosion. RESULTS: Forty-four eyes of 44 patients were enrolled. Mean follow-up was 10.2 +/- 4.0 months (range, 2.3 to 18.6 months). Infection, tube erosion, graft rejection, and graft-related inflammation did not occur. Five eyes were noted to have asymptomatic thinning of the patch without evidence of tube erosion. CONCLUSIONS: Preserved human cadaveric pericardial patch grafts appear to be well-tolerated for use with glaucoma drainage devices. As with other grafting material, potential for graft thinning is possible and further long-term experience is needed.