A5033472853- Glioma Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Advanced Neural Network Applications
- Medical Imaging and Analysis
- Gout, Hyperuricemia, Uric Acid
- MRI in cancer diagnosis
- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Veterinary medicine and infectious diseases
- Cardiac, Anesthesia and Surgical Outcomes
- Facial Rejuvenation and Surgery Techniques
- Ferroptosis and cancer prognosis
- Colorectal Cancer Surgical Treatments
- Statistical Methods in Clinical Trials
- Meningioma and schwannoma management
- Traumatic Brain Injury and Neurovascular Disturbances
- Pancreatic and Hepatic Oncology Research
- Cerebrospinal fluid and hydrocephalus
- Advanced Neuroimaging Techniques and Applications
- Bone and Joint Diseases
- Statistical Methods and Bayesian Inference
- Metal Alloys Wear and Properties
- Medical Image Segmentation Techniques
- Anesthesia and Sedative Agents
Amsterdam University Medical Centers
2020-2025
Vrije Universiteit Amsterdam
2021-2025
Cancer Center Amsterdam
2020-2024
University of Amsterdam
2023
The Netherlands Cancer Institute
2017-2021
Oncode Institute
2017-2019
Dutch Cancer Society
2017
University of Twente
2013-2016
Abstract Background Accurate characterization of glioma is crucial for clinical decision making. A delineation the tumor also desirable in initial stages but time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict genetic or histological features glioma, automatically delineate tumor, not both tasks at same time. Here, we present our method molecular subtype and grade, while simultaneously providing a tumor. Methods We single multi-task...
Tumor segmentation of glioma on MRI is a technique to monitor, quantify and report disease progression. Manual the gold standard but very labor intensive. At present quality this not known for different stages disease, prior work has mainly focused treatment-naive glioblastoma. In paper we studied inter-rater agreement manual glioblastoma WHO grade II-III novices experts at three disease. We also impact inter-observer variation extent resection growth rate. 20 patients with IV (defined as...
Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants' privacy. Facial removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis obtain clinically relevant outcome measurements clinical groups.FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects...
Purpose The aim of glioblastoma surgery is to maximize the extent resection while preserving functional integrity, which depends on location within brain. A standard compare these decisions lacking. We present a volumetric voxel-wise method for direct comparison between two multidisciplinary teams throughout Methods Adults undergoing first-time from 2012 2013 performed by neuro-oncologic were included. Patients had diagnostic biopsy or resection. Preoperative tumors and postoperative...
The extent of resection (EOR) and postoperative residual tumor (RT) volume are prognostic factors in glioblastoma. Calculations EOR RT rely on accurate segmentations. Raidionics is an open-access software that enables automatic segmentation preoperative early glioblastoma using pretrained deep learning models. aim this study was to compare the value manually versus automatically assessed volumetric measurements patients. Adult patients who underwent histopathologically confirmed were...
BACKGROUND AND OBJECTIVES: Patients with newly diagnosed lower-grade glioma (World Health Organization grade II and III) are typically of working age. However, work resumption after surgical resection is uncertain, possibly due to loss capacity from tumor-infiltrated brain regions. Therefore, we explore the association between location in addition other patient, tumor, treatment characteristics. METHODS: This retrospective cohort consisted adults undergoing first-time for 2011 2020 hospitals...
To summarize the distribution of glioma location within a patient population, registration individual MR images to anatomical reference space is required. In this study, we quantified accuracy image with linear and non-linear transformations using estimated tumor targets glioblastoma lower-grade glioma, landmarks at pre- post-operative time-points six commonly-used packages (FSL, SPM5, DARTEL, ANTs, Elastix, NiftyReg). Routine clinical post-operative, post-contrast T1-weighted 20 patients...
For patients suffering from brain tumor, prognosis estimation and treatment decisions are made by a multidisciplinary team based on set of preoperative MR scans. Currently, the lack standardized automatic methods for tumor detection generation clinical reports, incorporating wide range characteristics, represents major hurdle. In this study, we investigate most occurring types: glioblastomas, lower grade gliomas, meningiomas, metastases, through four cohorts up to 4,000 patients. Tumor...
This study tests the generalisability of three Brain Tumor Segmentation (BraTS) challenge models using a multi-center dataset varying image quality and incomplete MRI datasets. In this retrospective study, DeepMedic, no-new-Unet (nn-Unet), NVIDIA-net (nv-Net) were trained tested manual segmentations from preoperative glioblastoma (GBM) low-grade gliomas (LGG) BraTS 2021 (1251 in total), addition to 275 GBM 205 LGG acquired clinically across 12 hospitals worldwide. Data was split into 80%...
Extent of resection after surgery is one the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification residual tumor from post-operative MR images essential. The current standard method estimating it subject to high inter- intra-rater variability, an automated in early MRI could lead a more estimation extent resection. In this study, two state-of-the-art neural network architectures pre-operative were trained task. models...
Abstract Gliomas are primary brain tumors that can cause neuropsychiatric symptoms, including severe depressive symptoms (SDS; in 14%) and an absence of (ADS; 29%), determined by Center for Epidemiologic Studies Depression (CES-D) scores. We examined the association between both SDS ADS tumor location 201 patients with diffuse glioma before surgery. Tumors white matter disconnectomes did not relate to CES-D using sparse canonical correlation analysis. were associated right corticospinal...
Purpose To improve the robustness of deep learning–based glioblastoma segmentation in a clinical setting with sparsified datasets. Materials and Methods In this retrospective study, preoperative T1-weighted, T2-weighted, T2-weighted fluid-attenuated inversion recovery, postcontrast T1-weighted MRI from 117 patients (median age, 64 years; interquartile range [IQR], 55–73 76 men) included within Multimodal Brain Tumor Image Segmentation (BraTS) dataset plus (2012–2013) similar imaging...
Decisions in glioblastoma surgery are often guided by presumed eloquence of the tumor location. The authors introduce "expected residual volume" (eRV) and resectability index" (eRI) based on previous decisions aggregated resection probability maps. diagnostic accuracy eRV eRI to predict biopsy decisions, resectability, functional outcome, survival was determined.
The impact of time-to-surgery on clinical outcome for patients with glioblastoma has not been determined. Any delay in treatment is perceived as detrimental, but guidelines do specify acceptable timings. In this study, we relate the time to surgery extent resection and residual tumor volume, performance change, survival, explore identification urgent surgery.
For patients with presumed glioblastoma, essential tumor characteristics are determined from preoperative MR images to optimize the treatment strategy. This procedure is time-consuming and subjective, if performed by crude eyeballing or manually. The standardized GSI-RADS aims provide neurosurgeons automatic segmentations extract features rapidly objectively. In this study, we improved segmentation compared agreement manual raters, describe technical details of different components GSI-RADS,...
Treatment decisions for patients with presumed glioblastoma are based on tumor characteristics available from a preoperative MR scan. Tumor characteristics, including volume, location, and resectability, often estimated or manually delineated. This process is time consuming subjective. Hence, comparison across cohorts, trials, registries subject to assessment bias. In this study, we propose standardized Glioblastoma Surgery Imaging Reporting Data System (GSI-RADS) an automated method of...
Abstract Background Evaluation of molecular markers (IDH, pTERT, 1p/19q codeletion, and MGMT) in adult diffuse gliomas is crucial for accurate diagnosis optimal treatment planning. Dynamic Susceptibility Contrast (DSC) Arterial Spin Labeling (ASL) perfusion MRI techniques have both shown good performance classifying markers, however, their has not been compared side-by-side. Methods Pretreatment data from 90 patients diagnosed with glioma (54 men/36 female, 53.1 ± 15.5 years, grades 2–4)...
Awake craniotomies are often characterized by alternating asleep-awake-asleep periods. Preceding the awake phase, patients weaned from anesthesia and mechanical ventilation. Although clinicians aim to minimize time for patient safety operating room efficiency, in some patients, exceeds 20 minutes. The goal of this study was determine average factors associated with prolonged (> minutes) undergoing craniotomy.Records who underwent craniotomy between 2003 2020 were evaluated. Time defined as...
Detection of glioblastoma progression is important for clinical decision-making on cessation or initiation therapy, enrollment in trials, and response measurement time location. The RANO-criteria are considered standard the timing progression. To evaluate local treatment, we aim to find most accurate We determined differences free survival (PFS) tumor volumes at (Vprog) by three definitions progression.In a consecutive cohort 73 patients with newly-diagnosed between 1/1/2012 31/12/2013, was...
Abstract Extent of resection after surgery is one the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification residual tumor from post-operative MR images essential. The current standard method estimating it subject to high inter-and intra-rater variability, an automated in early MRI could lead a more estimation extent resection. In this study, two state-of-the-art neural network architectures pre-operative were trained...
Purpose During resections of brain tumors, neurosurgeons have to weigh the risk between residual tumor and damage functions. Different perspectives on these risks result in practice variation. We present statistical methods localize differences extent resection institutions which should enable reveal regions affected by such Methods Synthetic data were generated simulating spheres for brain, cavities, an effect region a likelihood surgical avoidance could be varied institutions. Three...
Abstract Background The prospects of a patient with suspected glioblastoma may rely heavily on the indication for surgical resection versus biopsy only. Biopsy percentages vary considerably across hospitals and guidelines treatment lack criteria decision-making. To identify tumor characteristics associated decision to resect or develop validate prediction model support. Material Methods Clinical data pre-operative MRI scans were collected adults who underwent first-time surgery...
Abstract Diffuse gliomas are the most prevalent primary malignant brain tumors in adults and characterized by invasive growth poor prognosis. Tumor cells infiltrate parenchyma spread to distant sites. The aim of this study is characterize spatial heterogeneity, mode, direction tumor development identify key areas for localized treatment. Neuronavigation was employed collect n=134 image-guided samples from n=16 adult patients with diffuse gliomas, including n=7 IDH wild-type (IDHwt) n=9...