Search Results for author: Ilkay Oksuz

Found 21 papers, 5 papers with code

Explainable Image Quality Assessment for Medical Imaging

1 code implementation25 Mar 2023 Caner Ozer, Arda Guler, Aysel Turkvatan Cansever, Ilkay Oksuz

We apply a variety of techniques to measure the faithfulness of the saliency detectors, and our explainable pipeline relies on NormGrad, an algorithm which can efficiently localise image quality issues with saliency maps of the classifier.

Image Quality Assessment object-detection +2

Semi-Supervised Segmentation of Multi-vendor and Multi-center Cardiac MRI using Histogram Matching

no code implementations22 Feb 2023 Mahyar Bolhassani, Ilkay Oksuz

In this paper, we propose a semi-supervised segmentation setup for leveraging unlabeled data to segment Left-ventricle, Right-ventricle, and Myocardium.

Prostate Lesion Estimation using Prostate Masks from Biparametric MRI

no code implementations11 Jan 2023 Ahmet Karagoz, Mustafa Ege Seker, Mert Yergin, Tarkan Atak Kan, Mustafa Said Kartal, Ercan Karaarslan, Deniz Alis, Ilkay Oksuz

Biparametric MRI has emerged as an alternative to multiparametric prostate MRI, which eliminates the need for the potential harms to the patient due to the contrast medium.

Detecting respiratory motion artefacts for cardiovascular MRIs to ensure high-quality segmentation

1 code implementation20 Sep 2022 Amin Ranem, John Kalkhof, Caner Özer, Anirban Mukhopadhyay, Ilkay Oksuz

In cardiovascular magnetic resonance imaging (CMR), respiratory motion represents a major challenge in terms of acquisition quality and therefore subsequent analysis and final diagnosis.

Shifted Windows Transformers for Medical Image Quality Assessment

no code implementations11 Aug 2022 Caner Ozer, Arda Guler, Aysel Turkvatan Cansever, Deniz Alis, Ercan Karaarslan, Ilkay Oksuz

While we obtain a classification accuracy of 87. 1% and 95. 48% on the Object-CXR and LVOT datasets, our experimental results suggest that the use of Swin Transformer improves the Object-CXR classification performance while obtaining a comparable performance for the LVOT dataset.

Classification Image Classification +1

A survey on shape-constraint deep learning for medical image segmentation

no code implementations19 Jan 2021 Simon Bohlender, Ilkay Oksuz, Anirban Mukhopadhyay

Since the advent of U-Net, fully convolutional deep neural networks and its many variants have completely changed the modern landscape of deep learning based medical image segmentation.

Image Segmentation Medical Image Segmentation +1

Channel Attention Networks for Robust MR Fingerprinting Matching

no code implementations2 Dec 2020 Refik Soyak, Ebru Navruz, Eda Ozgu Ersoy, Gastao Cruz, Claudia Prieto, Andrew P. King, Devrim Unay, Ilkay Oksuz

Magnetic Resonance Fingerprinting (MRF) enables simultaneous mapping of multiple tissue parameters such as T1 and T2 relaxation times.

Magnetic Resonance Fingerprinting

Transfer Learning for Electricity Price Forecasting

no code implementations5 Jul 2020 Salih Gunduz, Umut Ugurlu, Ilkay Oksuz

The accurate prediction of the day-ahead electricity prices is an active research field and available data from various markets can be used as an input for forecasting.

Transfer Learning

Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation

no code implementations11 Oct 2019 Ilkay Oksuz, James R. Clough, Bram Ruijsink, Esther Puyol Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Andrew P. King, Julia A. Schnabel

In this paper, we discuss the implications of image motion artefacts on cardiac MR segmentation and compare a variety of approaches for jointly correcting for artefacts and segmenting the cardiac cavity.

Image Reconstruction Image Segmentation +1

A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology

1 code implementation4 Oct 2019 James R. Clough, Nicholas Byrne, Ilkay Oksuz, Veronika A. Zimmer, Julia A. Schnabel, Andrew P. King

We show that the incorporation of the prior knowledge of the topology of this anatomy improves the resulting segmentations in terms of both the topological accuracy and the Dice coefficient.

Anatomy Image Segmentation +2

dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance

1 code implementation24 Sep 2019 Jo Schlemper, Ilkay Oksuz, James R. Clough, Jinming Duan, Andrew P. King, Julia A. Schnabel, Joseph V. Hajnal, Daniel Rueckert

AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited.

Assessing the Impact of Blood Pressure on Cardiac Function Using Interpretable Biomarkers and Variational Autoencoders

no code implementations13 Aug 2019 Esther Puyol-Antón, Bram Ruijsink, James R. Clough, Ilkay Oksuz, Daniel Rueckert, Reza Razavi, Andrew P. King

Maintaining good cardiac function for as long as possible is a major concern for healthcare systems worldwide and there is much interest in learning more about the impact of different risk factors on cardiac health.

Global and Local Interpretability for Cardiac MRI Classification

no code implementations14 Jun 2019 James R. Clough, Ilkay Oksuz, Esther Puyol-Anton, Bram Ruijsink, Andrew P. King, Julia A. Schnabel

Deep learning methods for classifying medical images have demonstrated impressive accuracy in a wide range of tasks but often these models are hard to interpret, limiting their applicability in clinical practice.

Classification General Classification +1

Explicit topological priors for deep-learning based image segmentation using persistent homology

no code implementations29 Jan 2019 James R. Clough, Ilkay Oksuz, Nicholas Byrne, Julia A. Schnabel, Andrew P. King

We present a novel method to explicitly incorporate topological prior knowledge into deep learning based segmentation, which is, to our knowledge, the first work to do so.

Image Segmentation Left Ventricle Segmentation +2

Magnetic Resonance Fingerprinting using Recurrent Neural Networks

no code implementations19 Dec 2018 Ilkay Oksuz, Gastao Cruz, James Clough, Aurelien Bustin, Nicolo Fuin, Rene M. Botnar, Claudia Prieto, Andrew P. King, Julia A. Schnabel

Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition.

Magnetic Resonance Fingerprinting

Automatic CNN-based detection of cardiac MR motion artefacts using k-space data augmentation and curriculum learning

no code implementations29 Oct 2018 Ilkay Oksuz, Bram Ruijsink, Esther Puyol-Anton, James Clough, Gastao Cruz, Aurelien Bustin, Claudia Prieto, Rene Botnar, Daniel Rueckert, Julia A. Schnabel, Andrew P. King

Due to the high number of good quality images compared to the relatively low number of images with motion artefacts, we propose a novel data augmentation scheme based on synthetic artefact creation in k-space.

Data Augmentation General Classification +2

Deep Learning using K-space Based Data Augmentation for Automated Cardiac MR Motion Artefact Detection

no code implementations15 Aug 2018 Ilkay Oksuz, Bram Ruijsink, Esther Puyol-Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Daniel Rueckert, Julia A. Schnabel, Andrew P. King

As this is a highly imbalanced classification problem (due to the high number of good quality images compared to the low number of images with motion artefacts), we propose a novel k-space based training data augmentation approach in order to address this problem.

Data Augmentation Image Quality Assessment +1

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