A5066758852- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Colorectal Cancer Surgical Treatments
- AI in cancer detection
- Advanced Radiotherapy Techniques
- Pelvic floor disorders treatments
- Generative Adversarial Networks and Image Synthesis
- Image and Signal Denoising Methods
- Advanced X-ray and CT Imaging
- Cardiovascular Disease and Adiposity
- Image Processing and 3D Reconstruction
- Fetal and Pediatric Neurological Disorders
- Digital Radiography and Breast Imaging
- Lanthanide and Transition Metal Complexes
- Prostate Cancer Diagnosis and Treatment
Champalimaud Foundation
2025
Iberia (Spain)
2019
Philips (Spain)
2019
Purpose To investigate the repeatability and reproducibility of radiomic features extracted from MR images provide a workflow to identify robust features. Methods T 2 ‐weighted pelvic phantom were acquired on three scanners two manufacturers magnetic field strengths. The assessed by intraclass correlation coefficient concordance coefficient, respectively, within‐subject variation, considering repeated acquisitions with without repositioning, different scanner acquisition parameters. showing...
This study aims to determine the feasibility, image quality, intra-subject repeatability and inter-reader variability of Diffusion tensor (DTI) kurtosis imaging (DKI) for pancreatic using different protocols report normative values in healthy individuals. Single-institution prospective performed on volunteers a clinical 3T scanner, two (6/16 diffusion directions). Acquisitions were repeated twice assess repeatability. To variability, Mean diffusivity (MD), Axial (AD), Radial (RD), Apparent...
Breast cancer, the most common cancer type among women worldwide, requires early detection and accurate diagnosis for improved treatment outcomes. Segmenting fat fibroglandular tissue (FGT) in magnetic resonance imaging (MRI) is essential creating volumetric models, enhancing surgical workflow, improving clinical Manual segmentation time-consuming subjective, prompting development of automated deep-learning algorithms to perform this task. However, configuring these 3D medical images...
Mesorectal lymph node staging plays an important role in treatment decision making. Here, we explore the benefit of higher-order diffusion MRI models accounting for non-Gaussian effects to classify mesorectal nodes both 1) ex vivo at ultrahigh field correlated with histology and 2) a clinical scanner upon patient staging.The preclinical investigation included 54 nodes, which were scanned 16.4 T extensive acquisition. Eight compared terms goodness fit, classification ability, correlation. In...
Noninvasive characterization of lymph node involvement in cancer is an enduring onerous challenge. In rectal cancer, pathologic status constitutes the most important determinant local recurrence and overall survival, patients with involved nodes may benefit from preoperative chemo and/or radiotherapy. However, knowledge before surgery currently hampered by limited imaging accuracy. Here, we introduce Susceptibility-Perturbation MRI (SPI) as a novel source contrast to map malignant...
To study the diffusion tensor-based fiber tracking feasibility to access male urethral sphincter complex of patients with prostate cancer undergoing Retzius-sparing robot-assisted laparoscopic radical prostatectomy (RS-RARP).Twenty-eight (median age 64.5 years old) underwent 3 T multiparametric-MRI prostate, including an additional echo-planar tensor imaging (DTI) sequence, using 15 diffusion-encoding directions and a b value = 600 s/mm2. Acquisition parameters, together patient motion eddy...
In this study we investigated the repeatability and reproducibility of radiomic features extracted from MRI images provide a workflow to identify robust features. 2D 3D T$_2$-weighted pelvic phantom were acquired on three scanners two manufacturers magnetic field strengths. The assessed respectively by intraclass correlation coefficient (ICC) concordance (CCC), considering repeated acquisitions with or without repositioning, different scanner/acquisition type, acquisition parameters. showing...
Abstract Renal hypoxia is generally accepted as a key pathophysiologic event in acute kidney injury of various origins and has also been suggested to play role the development chronic disease. Here we describe step-by-step data analysis protocols for MRI monitoring renal oxygenation rodents via deoxyhemoglobin concentration sensitive MR parameters T 2 * —a contrast mechanism known blood level dependent (BOLD) effect. This chapter describes how use tools provided by vendors animal clinical...
Deep learning (DL) models in medical imaging face challenges generalizability and robustness due to variations image acquisition parameters (IAP). In this work, we introduce a novel method using conditional denoising diffusion generative (cDDGMs) generate counterfactual magnetic resonance (MR) images that simulate different IAP without altering patient anatomy. We demonstrate these for data augmentation can improve segmentation accuracy, particularly out-of-distribution settings, enhancing...
<div>Abstract<p>Noninvasive characterization of lymph node involvement in cancer is an enduring onerous challenge. In rectal cancer, pathologic status constitutes the most important determinant local recurrence and overall survival, patients with involved nodes may benefit from preoperative chemo and/or radiotherapy. However, knowledge before surgery currently hampered by limited imaging accuracy. Here, we introduce Susceptibility-Perturbation MRI (SPI) as a novel source contrast...
<div>Abstract<p>Noninvasive characterization of lymph node involvement in cancer is an enduring onerous challenge. In rectal cancer, pathologic status constitutes the most important determinant local recurrence and overall survival, patients with involved nodes may benefit from preoperative chemo and/or radiotherapy. However, knowledge before surgery currently hampered by limited imaging accuracy. Here, we introduce Susceptibility-Perturbation MRI (SPI) as a novel source contrast...
<p>Figure S1. Raw data from MGE MRI on a representative patient in-vivo at 1.5 T.</p>
<p>Figure S1. Raw data from MGE MRI on a representative patient in-vivo at 1.5 T.</p>
Purpose or ObjectiveMR delineations in radiotherapy are generally more accurate than on CT but for dose calculations data mandatory.However, software has become available that transforms MR into pseudo-CT data.In this abstract we study the pros and cons of switching to MR-only planning rectal cancer. Material MethodsPreliminary five patients with locally advanced cancer were available.Radiotherapy VMAT plans (Varian) developed using our clinical simulation protocol includes use FDG...