Search

Your search keyword '"Frederik De Keyzer"' showing total 4 results
Start Over Author "Frederik De Keyzer" Publication Year Range Last 3 years
4 results on '"Frederik De Keyzer"'

1. Segmentation-based quantitative measurements in renal CT imaging using deep learning

Author

Konstantinos Koukoutegos, Richard ’s Heeren, Liesbeth De Wever, Frederik De Keyzer, Frederik Maes, and Hilde Bosmans

Subjects
Abdomen, Artificial intelligence, Deep learning, Kidney, Tomography (x-ray computed), Medical physics. Medical radiology. Nuclear medicine, R895-920
Abstract

Abstract Background Renal quantitative measurements are important descriptors for assessing kidney function. We developed a deep learning-based method for automated kidney measurements from computed tomography (CT) images. Methods The study datasets comprised potential kidney donors (n = 88), both contrast-enhanced (Dataset 1 CE) and noncontrast (Dataset 1 NC) CT scans, and test sets of contrast-enhanced cases (Test set 2, n = 18), cases from a photon-counting (PC)CT scanner reconstructed at 60 and 190 keV (Test set 3 PCCT, n = 15), and low-dose cases (Test set 4, n = 8), which were retrospectively analyzed to train, validate, and test two networks for kidney segmentation and subsequent measurements. Segmentation performance was evaluated using the Dice similarity coefficient (DSC). The quantitative measurements’ effectiveness was compared to manual annotations using the intraclass correlation coefficient (ICC). Results The contrast-enhanced and noncontrast models demonstrated excellent reliability in renal segmentation with DSC of 0.95 (Test set 1 CE), 0.94 (Test set 2), 0.92 (Test set 3 PCCT) and 0.94 (Test set 1 NC), 0.92 (Test set 3 PCCT), and 0.93 (Test set 4). Volume estimation was accurate with mean volume errors of 4%, 3%, 6% mL (contrast test sets) and 4%, 5%, 7% mL (noncontrast test sets). Renal axes measurements (length, width, and thickness) had ICC values greater than 0.90 (p

Published
2024
Full Text
View/download PDF

2. AI-based MRI auto-segmentation of brain tumor in rodents, a multicenter study

Author

Shuncong Wang, Xin Pang, Frederik de Keyzer, Yuanbo Feng, Johan V. Swinnen, Jie Yu, and Yicheng Ni

Subjects
Artificial intelligence, Brain malignancy, MRI, Segmentation, Rodent, Neurology. Diseases of the nervous system, RC346-429
Abstract

Abstract Automatic segmentation of rodent brain tumor on magnetic resonance imaging (MRI) may facilitate biomedical research. The current study aims to prove the feasibility for automatic segmentation by artificial intelligence (AI), and practicability of AI-assisted segmentation. MRI images, including T2WI, T1WI and CE-T1WI, of brain tumor from 57 WAG/Rij rats in KU Leuven and 46 mice from the cancer imaging archive (TCIA) were collected. A 3D U-Net architecture was adopted for segmentation of tumor bearing brain and brain tumor. After training, these models were tested with both datasets after Gaussian noise addition. Reduction of inter-observer disparity by AI-assisted segmentation was also evaluated. The AI model segmented tumor-bearing brain well for both Leuven and TCIA datasets, with Dice similarity coefficients (DSCs) of 0.87 and 0.85 respectively. After noise addition, the performance remained unchanged when the signal–noise ratio (SNR) was higher than two or eight, respectively. For the segmentation of tumor lesions, AI-based model yielded DSCs of 0.70 and 0.61 for Leuven and TCIA datasets respectively. Similarly, the performance is uncompromised when the SNR was over two and eight respectively. AI-assisted segmentation could significantly reduce the inter-observer disparities and segmentation time in both rats and mice. Both AI models for segmenting brain or tumor lesions could improve inter-observer agreement and therefore contributed to the standardization of the following biomedical studies.

Published
2023
Full Text
View/download PDF

3. Morphometric evaluation of traumatic axonal injury and the correlation with post-traumatic cerebral atrophy and functional outcome

Author

Philippe Demaerel, Frederik De Keyzer, Thijs Vande Vyvere, Diana M. Sima, and Cedric Bohyn

Subjects
Cerebral atrophy, medicine.medical_specialty, medicine.diagnostic_test, business.industry, Traumatic brain injury, Computed tomography, Diffuse Axonal Injury, General Medicine, Fluid-attenuated inversion recovery, medicine.disease, Magnetic Resonance Imaging, Brain Injuries, Traumatic, medicine, Image Processing, Computer-Assisted, Humans, Radiology, Nuclear Medicine and imaging, Neurology (clinical), Radiology, Atrophy, business
Abstract

Introduction Imaging plays a crucial role in the diagnosis, prognosis and follow-up of traumatic brain injury. Whereas computed tomography plays a pivotal role in the acute setting, magnetic resonance imaging is best suited to detect the true extent of traumatic brain injury, and more specifically diffuse axonal injury. Post-traumatic brain atrophy is a well-known complication of traumatic brain injury. Purpose This study investigated the correlation between diffuse axonal injury detected with fluid-attenuated inversion recovery and susceptibility-weighted imaging magnetic resonance imaging, post-traumatic brain atrophy and functional outcome (Glasgow outcome scale – extended). Materials and methods Twenty patients with a closed head injury and diffuse axonal injury detected with fluid-attenuated inversion recovery and susceptibility-weighted imaging were included. The total volumes of the diffuse axonal injury fluid-attenuated inversion recovery lesions were determined for each subject’s initial (Results The volumetric fluid-attenuated inversion recovery diffuse axonal injury lesion load showed a significant inverse correlation with functional outcome (Glasgow outcome scale – extended) ( r = −0.57; P = 0.0094) and white matter volume change ( r = −0.50; P = 0.027). In addition, white matter volume change correlated significantly with the Glasgow outcome scale – extended score ( P = 0.0072; r = 0.58). Moreover, there was a strong inverse correlation between longitudinal fluid-attenuated inversion recovery lesion volume change and whole brain volume change ( r = −0.63; P = 0.0028). No significant correlation existed between the number of diffuse axonal injury susceptibility-weighted imaging lesions, brain atrophy and functional outcome. Conclusions Volumetric analysis of diffuse axonal injury on fluid-attenuated inversion recovery imaging and automated brain atrophy calculation are potentially useful tools in the clinical management and follow-up of traumatic brain injury patients with diffuse axonal injury.

Published
2023

4. Early Whole-Body Diffusion-weighted MRI Helps Predict Long-term Outcome Following Peptide Receptor Radionuclide Therapy for Metastatic Neuroendocrine Tumors

Author

Vincent Vandecaveye, Raphaëla C. Dresen, Elin Pauwels, Sofie Van Binnebeek, Ragna Vanslembrouck, Kristof Baete, Felix M. Mottaghy, Paul M. Clement, Kristiaan Nackaerts, Eric Van Cutsem, Chris Verslype, Frederik De Keyzer, Christophe M. Deroose, Beeldvorming, RS: GROW - R3 - Innovative Cancer Diagnostics & Therapy, RS: NUTRIM - R1 - Obesity, diabetes and cardiovascular health, RS: Carim - B06 Imaging, and RS: MHeNs - R1 - Cognitive Neuropsychiatry and Clinical Neuroscience

Subjects
Male, BIOMARKER, Tumor Response, Receptors, Peptide, PET/CT, Gallium Radioisotopes, Metastases, PARAMETERS, LIVER METASTASES, Positron Emission Tomography Computed Tomography, Humans, Prospective Studies, Aged, Original Research, MR-Diffusion-Weighted Imaging, Whole-Body Imaging, Treatment Effects, Radionuclide Therapy, General Medicine, Middle Aged, CANCER, Neuroendocrine Tumors, SOMATOSTATIN ANALOGS, Ki-67 Antigen, Female, RESPONSE ASSESSMENT
Abstract

PURPOSE: To evaluate the predictive value of 7-week apparent diffusion coefficient change from baseline (ADCratio(7w)) at whole-body diffusion-weighted MRI (WB-DWI MRI) after one peptide receptor radionuclide therapy (PRRT) cycle to predict outcome in patients with metastatic neuroendocrine tumor (mNET). MATERIALS AND METHODS: From April 2009 to May 2012, participants in a prospective clinical trial investigating yttrium 90–DOTA Phe1-Tyr(3)-octreotide (DOTATOC) treatment for mNET (EudraCT no. 2008–007965–22) underwent WB-DWI MRI and gallium 68 ((68)Ga)–DOTATOC PET/CT before and 7 weeks after one PRRT cycle. ADCratio(7w) response was compared with the 7-week Response Evaluation Criteria in Solid Tumors version 1.1 and (68)Ga-DOTATOC PET/CT quantitative responses to predict overall survival (OS) and progression-free survival (PFS) with Cox regression analysis. RESULTS: Forty participants were analyzed (mean age, 60 years ± 11 [SD]; 21 men). Median PFS and OS were 10.5 months (range, 2–36 months) and 18 months (range, 3–81 months), respectively. Survival analysis showed significantly positive effects on PFS by age (hazard ratio [HR] = 0.96, P = .007), tumor grade (HR = 2.84, P = .006), Ki-67 index (HR = 1.05, P = .01), ADCratio(7w) of the least-responding lesion (ADCratio(7w-least)) (HR = 0.94, P < .001), and baseline mean standardized uptake values (SUV(mean)) (HR = 0.89, P = .02), with ADCratio(7w-least) and SUV(mean) remaining significant in multivariable analysis (P < .001, P = .02, respectively). There were significantly positive effects on OS by pretreatment lesion volume (HR = 1.004, P = .004), tumor grade (HR = 2.14, P = .04), Ki-67 index (HR = 1.05, P = .01), and ADCratio(7w-least) (HR = 0.97, P < .001), with pretreatment volume and ADCratio(7w-least) remaining significant at multivariable analysis (P = .005, P = .002, respectively). CONCLUSION: The ADCratio(7w) after start of PRRT for mNET was an independent predictor of patient outcome. Keywords: MR–Diffusion-Weighted Imaging, Radionuclide Therapy, Whole-Body Imaging, Metastases, Tumor Response, Treatment Effects EudraCT no. 2008-007965-22 © RSNA, 2022

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results