Performance of federated learning-based models in the Dutch TAVI population was comparable to central strategies and outperformed local strategies.

Background: Federated learning (FL) is a technique for learning prediction models without sharing records between hospitals. Compared to centralized training approaches, the adoption of FL could negatively impact model performance.

Aim: This study aimed to evaluate four types of multicenter model development strategies for predicting 30-day mortality for patients undergoing transcatheter aortic valve implantation (TAVI): (1) , learning one model from a centralized dataset of all hospitals; (2) , learning one model per hospital; (3) (), averaging of local model coefficients; and (4) , aggregating local model predictions.

Probing the glioma microvasculature: a case series of the comparison between perfusion MRI and intraoperative high-frame-rate ultrafast Doppler ultrasound.

Background: We aimed to describe the microvascular features of three types of adult-type diffuse glioma by comparing dynamic susceptibility contrast (DSC) perfusion magnetic resonance imaging (MRI) with intraoperative high-frame-rate ultrafast Doppler ultrasound.

Methods: Case series of seven patients with primary brain tumours underwent both DSC perfusion MRI and intra-operative high-frame-rate ultrafast Doppler ultrasound. From the ultrasound images, three-dimensional vessel segmentation was obtained of the tumour vascular bed.

MRI-Based Assessment of Brain Tumor Hypoxia: Correlation with Histology.

Cerebral hypoxia significantly impacts the progression of brain tumors and their resistance to radiotherapy. This study employed streamlined quantitative blood-oxygen-level-dependent (sqBOLD) MRI to assess the oxygen extraction fraction (OEF)-a measure of how much oxygen is being extracted from vessels, with higher OEF values indicating hypoxia. Simultaneously, we utilized vessel size imaging (VSI) to evaluate microvascular dimensions and blood volume.

Reproducibility of APT-weighted CEST-MRI at 3T in healthy brain and tumor across sessions and scanners.

Amide proton transfer (APT)-weighted chemical exchange saturation transfer (CEST) imaging is a recent MRI technique making its way into clinical application. In this work, we investigated whether APT-weighted CEST imaging can provide reproducible measurements across scan sessions and scanners. Within-session, between-session and between scanner reproducibility was calculated for 19 healthy volunteers and 7 patients with a brain tumor on two 3T MRI scanners.

Microvasculature Features Derived from Hybrid EPI MRI in Non-Enhancing Adult-Type Diffuse Glioma Subtypes.

In this study, we used the vessel size imaging (VSI) MRI technique to characterize the microvasculature features of three subtypes of adult-type diffuse glioma lacking enhancement. Thirty-eight patients with confirmed non-enhancing glioma were categorized into three subtypes: Oligo (IDH-mut&1p/19q-codeleted), Astro (IDH-mut), and GBM (IDH-wt). The VSI technique provided quantitative maps of cerebral blood volume (CBV), microvasculature (µCBV), and vessel size for each patient.

Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning.

Background: Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict the genetic or histological features of glioma, or that can automatically delineate the tumor, but not both tasks at the same time.

Noninvasive differentiation of molecular subtypes of adult nonenhancing glioma using MRI perfusion and diffusion parameters.

Background: Nonenhancing glioma typically have a favorable outcome, but approximately 19-44% have a highly aggressive course due to a glioblastoma genetic profile. The aim of this retrospective study is to use physiological MRI parameters of both perfusion and diffusion to distinguish the molecular profiles of glioma without enhancement at presentation.

Methods: Ninety-nine patients with nonenhancing glioma were included, in whom molecular status (including 1p/19q codeletion status and IDH mutation) and preoperative MRI (T2w/FLAIR, dynamic susceptibility-weighted, and diffusion-weighted imaging) were available.

EASE: Clinical Implementation of Automated Tumor Segmentation and Volume Quantification for Adult Low-Grade Glioma.

The growth rate of non-enhancing low-grade glioma has prognostic value for both malignant progression and survival, but quantification of growth is difficult due to the irregular shape of the tumor. Volumetric assessment could provide a reliable quantification of tumor growth, but is only feasible if fully automated. Recent advances in automated tumor segmentation have made such a volume quantification possible, and this work describes the clinical implementation of automated volume quantification in an application named EASE: Erasmus Automated SEgmentation.

Distinguishing pure histopathological growth patterns of colorectal liver metastases on CT using deep learning and radiomics: a pilot study.

Histopathological growth patterns (HGPs) are independent prognosticators for colorectal liver metastases (CRLM). Currently, HGPs are determined postoperatively. In this study, we evaluated radiomics for preoperative prediction of HGPs on computed tomography (CT), and its robustness to segmentation and acquisition variations.

The Erasmus Glioma Database (EGD): Structural MRI scans, WHO 2016 subtypes, and segmentations of 774 patients with glioma.

The Erasmus Glioma Database (EGD) contains structural magnetic resonance imaging (MRI) scans, genetic and histological features (specifying the WHO 2016 subtype), and whole tumor segmentations of patients with glioma. Pre-operative MRI data of 774 patients with glioma (281 female, 492 male, 1 unknown, age range 19-86 years) treated at the Erasmus MC between 2008 and 2018 is available. For all patients a pre-contrast T1-weighted, post-contrast T1-weighted, T2-weighted, and T2-weighted FLAIR scan are available, made on a variety of scanners from four different vendors.

The Association Between the Extent of Glioblastoma Resection and Survival in Light of MGMT Promoter Methylation in 326 Patients With Newly Diagnosed IDH-Wildtype Glioblastoma.

The association between contrast enhanced (CE) and non-contrast enhanced (NCE) tumor resection and survival in patients with glioblastoma in relation to molecular subtypes is poorly understood. The aim of this study was to assess the association between CE and NCE tumor resection and survival in light of MGMT promoter methylation in newly diagnosed IDH-wildtype glioblastoma. Patients with newly diagnosed IDH-wildtype glioblastoma who underwent surgery were eligible.

DeepDicomSort: An Automatic Sorting Algorithm for Brain Magnetic Resonance Imaging Data.

With the increasing size of datasets used in medical imaging research, the need for automated data curation is arising. One important data curation task is the structured organization of a dataset for preserving integrity and ensuring reusability. Therefore, we investigated whether this data organization step can be automated.

Topographical Mapping of 436 Newly Diagnosed IDH Wildtype Glioblastoma With vs. Without MGMT Promoter Methylation.

O methylguanine-methyltransferase (MGMT) promoter methylation and isocitrate dehydrogenase (IDH) mutation status are important prognostic factors for patients with glioblastoma. There are conflicting reports about a differential topographical distribution of glioblastoma with vs. without MGMT promoter methylation, possibly caused by molecular heterogeneity in glioblastoma populations.

Predicting the 1p/19q Codeletion Status of Presumed Low-Grade Glioma with an Externally Validated Machine Learning Algorithm.

Purpose: Patients with 1p/19q codeleted low-grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative MRI.

Differences in spatial distribution between WHO 2016 low-grade glioma molecular subgroups.

Background: Several studies reported a correlation between anatomic location and genetic background of low-grade gliomas (LGGs). As such, tumor location may contribute to presurgical clinical decision-making. Our purpose was to visualize and compare the spatial distribution of different WHO 2016 gliomas, frequently aberrated single genes and DNA copy number alterations within subgroups, and groups of postoperative tumor volume.

Fast and accurate sensitivity analysis of IMPT treatment plans using Polynomial Chaos Expansion.

The highly conformal planned dose distribution achievable in intensity modulated proton therapy (IMPT) can severely be compromised by uncertainties in patient setup and proton range. While several robust optimization approaches have been presented to address this issue, appropriate methods to accurately estimate the robustness of treatment plans are still lacking. To fill this gap we present Polynomial Chaos Expansion (PCE) techniques which are easily applicable and create a meta-model of the dose engine by approximating the dose in every voxel with multidimensional polynomials.

Robustness Recipes for Minimax Robust Optimization in Intensity Modulated Proton Therapy for Oropharyngeal Cancer Patients.

Purpose: We aimed to derive a "robustness recipe" giving the range robustness (RR) and setup robustness (SR) settings (ie, the error values) that ensure adequate clinical target volume (CTV) coverage in oropharyngeal cancer patients for given gaussian distributions of systematic setup, random setup, and range errors (characterized by standard deviations of Σ, σ, and ρ, respectively) when used in minimax worst-case robust intensity modulated proton therapy (IMPT) optimization.

Methods And Materials: For the analysis, contoured computed tomography (CT) scans of 9 unilateral and 9 bilateral patients were used. An IMPT plan was considered robust if, for at least 98% of the simulated fractionated treatments, 98% of the CTV received 95% or more of the prescribed dose.