MRI simulation-based evaluation of image-processing and classification methods.

IEEE Trans Med Imaging

Brain Imaging Centre, Montreal Neurological Institute, McGill University, PQ, Canada.

Published: November 1999

With the increased interest in computer-aided image analysis methods, there is a greater need for objective methods of algorithm evaluation. Validation of in vivo MRI studies is complicated by a lack of reference data and the difficulty of constructing anatomically realistic physical phantoms. We present here an extensible MRI simulator that efficiently generates realistic three-dimensional (3-D) brain images using a hybrid Bloch equation and tissue template simulation that accounts for image contrast, partial volume, and noise. This allows image analysis methods to be evaluated with controlled degradations of image data.

Download full-text PDF

Source
http://dx.doi.org/10.1109/42.816072DOI Listing

Publication Analysis

Top Keywords

image analysis
8
analysis methods
8
mri simulation-based
4
simulation-based evaluation
4
evaluation image-processing
4
image-processing classification
4
methods
4
classification methods
4
methods increased
4
increased interest
4

Similar Publications

Innovative Method for Reliable Measurement of PEM Water Electrolyzer Component Resistances.

Small Methods

January 2025

Forschungszentrum Juelich GmbH, Institute of Energy Technologies, IET-4, Electrochemical Process Engineering, 52425, Juelich, Germany.

Understanding the sheet resistance of porous electrodes is essential for improving the performance of polymer electrolyte membrane (PEM) water electrolyzers and related technologies. Despite its importance, existing methods often fail to provide reliable and comprehensive data, especially for porous materials with complex morphologies and non-uniform thicknesses. This study introduces a robust and straightforward method for determining the sheet resistance of porous electrodes using a novel probe concept based on industrial printed circuit board (PCB) technology.

View Article and Find Full Text PDF

ApoNecV: A macro for cell death type differentiation.

J Microsc

January 2025

Department of Medical Biophysics, Faculty of Medicine and Dentistry, Palacky University, Olomouc, Czech Republic.

The evaluation of large experimental datasets is a fundamental aspect of research in every scientific field. Streamlining this process can improve the reliability of results while making data analysis more efficient and faster to execute. In biomedical research it is often very important to determine the type of cell death after various treatments.

View Article and Find Full Text PDF

Preferential Sites of Retinal Capillary Occlusion in Sickle Cell Disease.

Invest Ophthalmol Vis Sci

January 2025

Department of Ophthalmology, New York Eye and Ear Infirmary of Mount Sinai, New York, New York, United States.

Purpose: To assess the preferential sites of retinal capillary occlusion at the parafovea in patients with sickle cell disease (SCD) using optical coherence tomography angiography (OCT-A).

Methods: OCT-A scans from 107 patients with SCD and 51 race-matched unaffected controls were obtained using a commercial spectral domain-OCT system. At least eight sequential 3 × 3 mm scans centered at the fovea were acquired and averaged for image analysis.

View Article and Find Full Text PDF

Background: There is a need to improve risk stratification of primary cutaneous melanomas to better guide adjuvant therapy. Taking into account that haematoxylin and eosin (HE)-stained tumour tissue contains a huge amount of clinically unexploited morphological informations, we developed a weakly-supervised deep-learning approach, SmartProg-MEL, to predict survival outcomes in stages I to III melanoma patients from HE-stained whole slide image (WSI).

Methods: We designed a deep neural network that extracts morphological features from WSI to predict 5-y overall survival (OS), and assign a survival risk score to each patient.

View Article and Find Full Text PDF

Importance: The D842V platelet-derived growth factor receptor α (PDGFRA) mutation identifies a molecular subgroup of gastrointestinal stromal tumors (GISTs), primarily resistant to standard tyrosine kinase inhibitors and with an overall more indolent behavior. Although functional imaging with 18F-fluorodeoxyglucose-labeled positron emission tomography ([18F]FDG-PET) plays a proven role in GISTs, especially in early assessment of tumor response, less is known about [18F]FDG uptake according to the GIST molecular subtypes.

Objective: To evaluate the degree of [18F]FDG uptake in PDGFRA-mutant GISTs and better define the role of functional imaging in this rare and peculiar subset of GISTs.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!