Search Results for author: Ivana Išgum

Found 33 papers, 3 papers with code

Robust deformable image registration using cycle-consistent implicit representations

1 code implementation3 Oct 2023 Louis D. van Harten, Jaap Stoker, Ivana Išgum

To improve robustness, we propose a deformable registration method using pairs of cycle-consistent Implicit Neural Representations: each implicit representation is linked to a second implicit representation that estimates the opposite transformation, causing each network to act as a regularizer for its paired opposite.

Image Registration Medical Image Registration

Deep Learning-Based Prediction of Fractional Flow Reserve along the Coronary Artery

no code implementations9 Aug 2023 Nils Hampe, Sanne G. M. van Velzen, Jean-Paul Aben, Carlos Collet, Ivana Išgum

Functionally significant coronary artery disease (CAD) is caused by plaque buildup in the coronary arteries, potentially leading to narrowing of the arterial lumen, i. e. coronary stenosis, that significantly obstructs blood flow to the myocardium.

Generative Models for Reproducible Coronary Calcium Scoring

no code implementations24 May 2022 Sanne G. M. van Velzen, Bob D. de Vos, Julia M. H. Noothout, Helena M. Verkooijen, Max A. Viergever, Ivana Išgum

Interscan reproducibility was compared to clinical calcium scoring in radiotherapy treatment planning CTs of 1, 662 patients, each having two scans.

Generative Adversarial Network

Autoencoding Low-Resolution MRI for Semantically Smooth Interpolation of Anisotropic MRI

no code implementations18 Feb 2022 Jörg Sander, Bob D. de Vos, Ivana Išgum

Given the unsupervised nature of the method, high-resolution training data is not required and hence, the method can be readily applied in clinical settings.

Semantic Similarity Semantic Textual Similarity +1

AI for Calcium Scoring

no code implementations24 May 2021 Sanne G. M. van Velzen, Nils Hampe, Bob D. de Vos, Ivana Išgum

Calcium scoring, a process in which arterial calcifications are detected and quantified in CT, is valuable in estimating the risk of cardiovascular disease events.

Automatic segmentation with detection of local segmentation failures in cardiac MRI

1 code implementation13 Nov 2020 Jörg Sander, Bob D. de Vos, Ivana Išgum

The experiments reveal that combining automatic segmentation with simulated manual correction of detected segmentation failures leads to statistically significant performance increase.

Segmentation

Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Images

no code implementations10 Jul 2020 Julia M. H. Noothout, Bob D. de Vos, Jelmer M. Wolterink, Elbrich M. Postma, Paul A. M. Smeets, Richard A. P. Takx, Tim Leiner, Max A. Viergever, Ivana Išgum

Global landmark locations are obtained by averaging the predicted displacement vectors, where the contribution of each displacement vector is weighted by the posterior classification probability of the patch that it is pointing from.

Classification General Classification +1

Exploiting Clinically Available Delineations for CNN-based Segmentation in Radiotherapy Treatment Planning

no code implementations12 Nov 2019 Louis D. van Harten, Jelmer M. Wolterink, Joost J. C. Verhoeff, Ivana Išgum

We empirically assess how many clinical delineations would be sufficient to train a CNN for the segmentation of OARs and find that increasing the training set size beyond a limited number of images leads to sharply diminishing returns.

Image Segmentation Medical Image Segmentation +2

Automatic Online Quality Control of Synthetic CTs

no code implementations12 Nov 2019 Louis D. van Harten, Jelmer M. Wolterink, Joost J. C. Verhoeff, Ivana Išgum

We show that this uncertainty measure can be used for two kinds of online quality control.

Combined analysis of coronary arteries and the left ventricular myocardium in cardiac CT angiography for detection of patients with functionally significant stenosis

no code implementations10 Nov 2019 Majd Zreik, Tim Leiner, Nadieh Khalili, Robbert W. van Hamersvelt, Jelmer M. Wolterink, Michiel Voskuil, Max A. Viergever, Ivana Išgum

We combine our previous works for the analysis of the complete coronary artery tree and the LV myocardium: Coronary arteries are encoded by two disjoint convolutional autoencoders (CAEs) and the LV myocardium is characterized by a convolutional neural network (CNN) and a CAE.

Multiple Instance Learning

Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography

no code implementations14 Aug 2019 Jelmer M. Wolterink, Tim Leiner, Ivana Išgum

In this work, we propose to use graph convolutional networks (GCNs) to predict the spatial location of vertices in a tubular surface mesh that segments the coronary artery lumen.

Coronary Artery Segmentation

Generative adversarial networks and adversarial methods in biomedical image analysis

no code implementations24 Oct 2018 Jelmer M. Wolterink, Konstantinos Kamnitsas, Christian Ledig, Ivana Išgum

Generative adversarial networks (GANs) and other adversarial methods are based on a game-theoretical perspective on joint optimization of two neural networks as players in a game.

Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifier

no code implementations7 Oct 2018 Jelmer M. Wolterink, Robbert W. van Hamersvelt, Max A. Viergever, Tim Leiner, Ivana Išgum

Evaluation using 24 test images of the CAT08 challenge showed that extracted centerlines had an average overlap of 93. 7% with 96 manually annotated reference centerlines.

Towards increased trustworthiness of deep learning segmentation methods on cardiac MRI

no code implementations27 Sep 2018 Jörg Sander, Bob D. de Vos, Jelmer M. Wolterink, Ivana Išgum

Current state-of-the-art deep learning segmentation methods have not yet made a broad entrance into the clinical setting in spite of high demand for such automatic methods.

Image Segmentation Segmentation +1

Improving Myocardium Segmentation in Cardiac CT Angiography using Spectral Information

no code implementations27 Sep 2018 Steffen Bruns, Jelmer M. Wolterink, Robbert W. van Hamersvelt, Majd Zreik, Tim Leiner, Ivana Išgum

We propose augmentation of the training data with virtual mono-energetic reconstructions from a spectral CT scanner which show different attenuation levels of the contrast agent.

Data Augmentation Myocardium Segmentation +1

CNN-based Landmark Detection in Cardiac CTA Scans

no code implementations13 Apr 2018 Julia M. H. Noothout, Bob D. de Vos, Jelmer M. Wolterink, Tim Leiner, Ivana Išgum

Under the assumption that patches close to a landmark can determine the landmark location more precisely than patches farther from it, only those patches that contain the landmark according to classification are used to determine the landmark location.

Classification General Classification +1

Iterative fully convolutional neural networks for automatic vertebra segmentation and identification

1 code implementation12 Apr 2018 Nikolas Lessmann, Bram van Ginneken, Pim A. de Jong, Ivana Išgum

Precise segmentation and anatomical identification of the vertebrae provides the basis for automatic analysis of the spine, such as detection of vertebral compression fractures or other abnormalities.

Instance Segmentation Segmentation +1

Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions

no code implementations1 Nov 2017 Nikolas Lessmann, Bram van Ginneken, Majd Zreik, Pim A. de Jong, Bob D. de Vos, Max A. Viergever, Ivana Išgum

On soft filter reconstructions, the method achieved F1 scores of 0. 89, 0. 89, 0. 67, and 0. 55 for coronary artery, thoracic aorta, aortic valve and mitral valve calcifications, respectively.

ConvNet-Based Localization of Anatomical Structures in 3D Medical Images

no code implementations19 Apr 2017 Bob D. de Vos, Jelmer M. Wolterink, Pim A. de Jong, Tim Leiner, Max A. Viergever, Ivana Išgum

We propose a method for automatic localization of one or more anatomical structures in 3D medical images through detection of their presence in 2D image slices using a convolutional neural network (ConvNet).

Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease

no code implementations12 Apr 2017 Jelmer M. Wolterink, Tim Leiner, Max A. Viergever, Ivana Išgum

Ten training and ten test CMR scans cropped to an ROI around the heart were provided in the MICCAI 2016 HVSMR challenge.

Segmentation

Automatic segmentation of MR brain images with a convolutional neural network

no code implementations11 Apr 2017 Pim Moeskops, Max A. Viergever, Adriënne M. Mendrik, Linda S. de Vries, Manon J. N. L. Benders, Ivana Išgum

Automatic segmentation in MR brain images is important for quantitative analysis in large-scale studies with images acquired at all ages.

Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.