A5054711452- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- MRI in cancer diagnosis
- Medical Image Segmentation Techniques
- Genomic variations and chromosomal abnormalities
- Head and Neck Cancer Studies
- Medical Imaging Techniques and Applications
- Gene expression and cancer classification
- Reproductive Biology and Fertility
- Statistical Methods and Inference
- AI in cancer detection
- Image Processing and 3D Reconstruction
- Ultrasound Imaging and Elastography
- Big Data and Business Intelligence
- Flexible and Reconfigurable Manufacturing Systems
- Image and Signal Denoising Methods
- Digital Transformation in Industry
- Dental Radiography and Imaging
- Advanced Data Processing Techniques
- Atomic and Subatomic Physics Research
- Rough Sets and Fuzzy Logic
- Salivary Gland Tumors Diagnosis and Treatment
- Head and Neck Surgical Oncology
- Radiomics and Machine Learning in Medical Imaging
- Cancer Genomics and Diagnostics
Institut Supérieur de l'Électronique et du Numérique
2024
Erasmus MC
2014-2021
Erasmus University Rotterdam
2014-2018
Erasmus MC Cancer Institute
2018
Background To evaluate the influence of image registration on apparent diffusion coefficient (ADC) images obtained from abdominal free-breathing diffusion-weighted MR (DW-MRIs). Methods A comprehensive pipeline based automatic three-dimensional nonrigid registrations is developed to compensate for misalignments in DW-MRI datasets five healthy subjects scanned twice. Motion corrected both within each and between a time series. ADC distributions are compared with without two volumes interest...
Purpose: Accurately identifying embryo developmental stages is crucial for improving success rates in vitro fertilization (IVF). Traditional assessment relies on 2D imaging with a single focal plane, which may overlook critical morphological details and lead to misclassification. This study investigates whether incorporating depth information through multi-focal plane can enhance the accuracy of stage classification. Methods: We compared 3D convolutional neural network (CNN) architectures...
The most widespread technique used to register sets of medical images consists selecting one image as fixed reference, which all remaining are successively registered. This pairwise scheme requires optimization procedure per pair register. Pairwise mutual information is a common dissimilarity measure applied large variety datasets. Alternative methods, called groupwise registrations, have been presented two or more in single procedure, without the need reference image. Given success...
In quantitative magnetic resonance imaging (qMRI), tissue properties can be estimated by fitting a signal model to the voxel intensities of series images acquired with different settings. To obtain reliable measures, it is necessary that qMRI are spatially aligned so given corresponds in all same anatomical location. The objective present study describe and evaluate novel automatic groupwise registration technique using dissimilarity metric based on an approximated form total correlation....
Multichannel image registration is an important challenge in medical analysis. images result from modalities such as dual-energy CT or multispectral microscopy. Besides, multichannel feature can be derived acquired images, for instance, by applying multiscale banks to the original register. techniques have been proposed, but most of them are applicable only two at a time. In present study, we propose formulate groupwise problem. this way, derive method that allows more fully symmetric manner...
The apparent diffusion coefficient (ADC) is an imaging biomarker providing quantitative information on the of water in biological tissues. This measurement could be relevance oncology drug development, but it suffers from a lack reliability. ADC images are computed by applying voxelwise exponential fitting to multiple diffusion-weighted MR (DW-MRIs) acquired with different gradients. In abdomen, respiratory motion induces misalignments datasets, creating visible artefacts and inducing errors...
This study describes post-processing methodologies to reduce the effects of physiological motion in measurements apparent diffusion coefficient (ADC) liver. The aims are improve accuracy ADC liver disease support quantitative clinical characterisation and number patients required for sequential studies progression therapeutic effects. Two correction methods compared, one based on non-rigid registration (NRA) using freely available open source algorithms other a local-rigid (LRA) specifically...
The aim of this study was to evaluate and present an automated method for registration magnetic resonance imaging (MRI) computed tomography (CT) or cone beam CT (CBCT) images the mandibular region patients with oral squamous cell carcinoma (OSCC). Registered MRI (CB)CT could facilitate three-dimensional virtual planning surgical guides employed resection reconstruction in OSCC invasion. were collected retrospectively from 19 patients. aligned employing a rigid approach (stage 1), using mask...
Fusion of multimodal medical images using deformable registration is high interest for head-and-neck tumour treatment planning. In this context, more than two often have to be aligned a given patient. The conventional, pairwise way register multiple select one them as fixed reference and independently align each remaining image with it. An alternative method would simultaneously the groupwise scheme, thus eliminating need avoiding any bias due arbitrary choice. study, we propose novel...
Cancer, hematological malignancies and inherited genetic diseases can be diagnosed by detecting chromosome abnormalities. This detection is crucial for the management follow-up of these diseases. Biologically, there are two categories abnormalities: either in their number or structure. The process karyotyping involves creating an ordered representation 23 pairs chromosomes. Each given pair presents a specific band pattern, where both chromosomes identical, normal cases. Karyotype images...
The detection of chromosome abnormalities is crucial for the diagnosis, prognosis and management many genetic diseases cancers. This detection, done by highly qualified medical experts, tedious time-consuming. We propose a performing, intelligent automatic method to assist cytogeneticists screen structural chromosomal (SCA). Each present in two copies that make up pair chromosomes. Usually, SCA are only one copy pair. Convolutional neural networks (CNN) with Siamese architecture particularly...