A5016848156- Glioma Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Meningioma and schwannoma management
- Ocular Oncology and Treatments
- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- Adrenal and Paraganglionic Tumors
- Cancer, Hypoxia, and Metabolism
- AI in cancer detection
- Advanced MRI Techniques and Applications
- Mathematical Biology Tumor Growth
- Glaucoma and retinal disorders
- MRI in cancer diagnosis
- Optical Coherence Tomography Applications
- Epigenetics and DNA Methylation
- Advanced Neuroimaging Techniques and Applications
- Explainable Artificial Intelligence (XAI)
- Vascular Malformations Diagnosis and Treatment
- Advanced Neural Network Applications
- Brain Metastases and Treatment
- Retinal Imaging and Analysis
- Medical Imaging and Analysis
- Cancer Genomics and Diagnostics
Erasmus MC
2021-2024
Rotterdam Eye Hospital
2024
Erasmus University Rotterdam
2021-2024
Erasmus MC Cancer Institute
2021-2023
In recent years, deep learning has become the leading method for medical image segmentation. While majority of studies focus on developments network architectures, several have shown that non-architectural factors also play a substantial role in performance improvement. An important factor is preprocessing. However, there no agreement which preprocessing steps work best different applications. The aim this study was to investigate effect model performance. To end, we conducted systematic...
IDH-mutant glioma is classified as oligodendroglioma or astrocytoma based on 1p19q-codeletion. Whether prognostic factors are similar between these tumor types not well understood.
1 Abstract To study the evolutionary processes that drive malignant progression of IDH-mutant astrocytomas, we performed multi-omics on a large cohort matched initial and recurrent tumor samples. The overlay genetic, epigenetic, transcriptomic proteomic data, combined with single-cell analysis, have identified overlapping features associated progression. These are derived from three molecular mechanisms provide rationale underlying biology malignancy: cell-cycling, cell (de-)differentiation...
Relative cerebral blood volume (rCBV) is the most widely used parameter derived from DSC perfusion MR imaging for predicting brain tumor aggressiveness. However, accurate rCBV estimation challenging in enhancing glioma, because of contrast agent extravasation through a disrupted blood-brain barrier (BBB), and even nonenhancing glioma with an intact BBB, due to elevated steady-state concentration vasculature after first passage. In this study thorough investigation effects two different...
Tumor growth models have the potential to model and predict spatiotemporal evolution of glioma in individual patients. Infiltration cells is known be faster along white matter tracts, therefore structural magnetic resonance imaging (MRI) diffusion tensor (DTI) can used inform model. However, applying evaluating real patient data challenging. In this work, we propose formulate problem tumor as a ranking problem, opposed segmentation use average precision (AP) performance metric. This enables...
Quantitative MR imaging is becoming more feasible to be used in clinical work since new approaches have been proposed order substantially accelerate the acquisition and due possibility of synthetically deriving weighted images from parametric maps. However, their applicability has thoroughly validated included practice. In this pilot study, we acquired Magnetic Resonance Image Compilation scans obtain T1, T2 PD maps 14 glioma patients. Abnormal tissue was segmented based on conventional...
PurposeWe retrospectively evaluated the association between postoperative pre-radiotherapy tumour burden and overall survival (OS) adjusted for prognostic value of O6-methylguanine DNA methyltransferase (MGMT) promoter methylation in patients with newly diagnosed glioblastoma treated radio-/chemotherapy temozolomide.Materials methodsPatients were included from CENTRIC (EORTC 26071-22072) CORE trials if magnetic resonance imaging scans available within a timeframe up to 4 weeks before...
The T2-FLAIR mismatch sign is defined by signal loss of the T2-weighted hyperintense area with Fluid-Attenuated Inversion Recovery (FLAIR) on magnetic resonance imaging, causing a hypointense region FLAIR. It highly specific diagnostic marker for IDH-mutant astrocytoma and postulated to be caused intercellular microcystic change in tumor tissue. However, not all astrocytomas show this some phenomenon only part lesion. aim study determine whether has any prognostic value beyond initial...
The growth rate of non-enhancing low-grade glioma has prognostic value for both malignant progression and survival, but quantification is difficult due to the irregular shape tumor. Volumetric assessment could provide a reliable tumor growth, only feasible if fully automated. Recent advances in automated segmentation have made such volume possible, this work describes clinical implementation an application named EASE: Erasmus Automated SEgmentation. visual quality control segmentations by...
<div>AbstractPurpose:<p>IDH-mutant glioma is classified as oligodendroglioma or astrocytoma based on <i>1p19q</i>-codeletion. Whether prognostic factors are similar between these tumor types not well understood.</p>Experimental Design:<p>Retrospective cohort study. Molecular characterization was performed with targeted next-generation sequencing. Tumor volumes were calculated using semiautomatic 3D segmentation all pre- and post-operative MRI scans....
<p>Supplementary Figure S1. Assessment of the linearity effect age and tumor volume.</p>
<p>Supplementary Figure S1. Assessment of the linearity effect age and tumor volume.</p>
<div>AbstractPurpose:<p>IDH-mutant glioma is classified as oligodendroglioma or astrocytoma based on <i>1p19q</i>-codeletion. Whether prognostic factors are similar between these tumor types not well understood.</p>Experimental Design:<p>Retrospective cohort study. Molecular characterization was performed with targeted next-generation sequencing. Tumor volumes were calculated using semiautomatic 3D segmentation all pre- and post-operative MRI scans....
Purpose: Optical coherence tomography (OCT)-derived measurements of the optic nerve head (ONH) from different devices are not interchangeable. This poses challenges to patient follow-up and collaborative studies. Here, we present a device-agnostic method for extraction OCT biomarkers using artificial intelligence. Methods: ONH-centered volumes Heidelberg SPECTRALIS, ZEISS CIRRUS HD-OCT 5000, Topcon 3D OCT-1000 Mark I/II OCT-2000 were annotated by trained graders. A convolutional neural...
Abstract Background Evidence suggests that smaller residual tumor volumes after initial surgery are associated with longer survival in patients astrocytoma, IDH-mutant, grade II. For IDH-mutant glioma of higher but also for oligodendroglioma, and 1p/19q codeleted, the impact on more is unclear. This could be related to limited follow-up oligodendroglioma typically have long overall survival. We expanded a previously published series increase duration spectrum grades. Material Methods Single...
We analyze quantitative values in glioma obtained with MAGiC, which allows obtaining T1, T2 and PD maps one single acquisition of less than 6 minutes for a whole brain. The were before contrast-agent injection 14 patients glioma. investigated the possibility characterizing tumor regions based on acquired without contrast-agent. results showed significant differences among tumoral tissue, tissue T1w-enhancement, normal white matter. Voxel-wise, this allowed to distinguish but did not allow...
The problem of tumor growth prediction is challenging, but promising results have been achieved with both model-driven and statistical methods. In this work, we present a framework for the evaluation predictions that focuses on spatial infiltration patterns, specifically evaluating future growth. We propose to frame as ranking rather than segmentation problem. Using average precision metric, can evaluate segmentations while using full spatiotemporal prediction. Furthermore, by separating...