Gülnur Ungan

MRSdecomposer (software)

Lili Fanni Tóth, Sandra Ortega‐Martorell, Gülnur Ungan, Carles Arús et autres

Convex-NMF provides a powerful unsupervised approach to extract spectral patterns from a dataset of MR spectroscopy, without requiring labelled training data. This interface facilitates analysis workflows by supporting multiple data formats. It offers various options for filtering the input data and to …

es, gb, us (code pays fourni par la source)

HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging

Paul J. Weiser, Gülnur Ungan, Amirmohammad Shamaei, Georg Langs et autres

Purpose: Proton magnetic resonance spectroscopic imaging ($^1$H MRSI) enables the mapping of whole-brain metabolites concentrations in-vivo. However, a long-standing problem for its clinical applicability is the metabolic quantification, which can require extensive time for spectral fitting. Recently, deep learning methods have been …

HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging

Paul J. Weiser, Gülnur Ungan, Amirmohammad Shamaei, Georg Langs et autres

Purpose: Proton magnetic resonance spectroscopic imaging ($^1$H MRSI) enables the mapping of whole-brain metabolites concentrations in-vivo. However, a long-standing problem for its clinical applicability is the metabolic quantification, which can require extensive time for spectral fitting. Recently, deep learning methods have been …

us, ca, at (code pays fourni par la source)

WALINET+: A water and lipid identification Neural Network for nuisance removal of water Unsuppressed Magnetic Resonance Spectroscopic Imaging.

Paul Weiser, Georg Langs, Stanislav Motyka, Wolfgang Bogner et autres

Motivation: Magnetic resonance spectroscopic imaging (MRSI) enables the 3-dimensional visualization of metabolic concentrations in healthy subjects and patients. However, metabolic maps can be distorted due to artifacts originating from large water and lipid signals. Goal(s): The removal of nuisance signal in water …

Unsupervised Learning to Dissect the Metabolic Heterogeneity in mutant IDH Astrocytoma and Oligodendroglioma Using 3D MRSI

Gülnur Ungan, Paul Weiser, Jörg Dietrich, Daniel P. Cahill et autres

Motivation: Glioma classification, particularly between IDH-mutant astrocytomas (AC) and oligodendrogliomas (OG), is challenging due to overlapping metabolic profiles. Improved differentiation is crucial for accurate tumor identification and treatment planning. Goal(s): To enhance the classification of IDH-mutant AC and OG gliomas by identifying …

Deep-ERx2: Deep Learning Reconstruction for fast high-resolution non-Cartesian Compressed-Sensing MR Spectroscopic Imaging at 3T and 7T

Paul Weiser, Georg Langs, Stanislav Motyka, Bernhard Strasser et autres

Motivation: High-Resolution magnetic resonance spectroscopic imaging (MRSI) is a powerful, non-invasive method for detailed imaging of brain metabolism. However, traditional methods for reconstructing accelerated high-resolution whole-brain MRSI are time-consuming, posing challenges for its routine clinical application. Goal(s): Reconstruction of high-resolution whole-brain MRSI …

Evaluating Non-Negative Matrix Underapproximation for the Analysis of Long Echo Time Magnetic Resonance Spectroscopy Data in Human Brain Tumors

Gülnur Ungan, Alfredo Vellido, Margarida Julià‐Sapé

Abstract Magnetic Resonance Spectroscopy (MRS) provides metabolic profiles for brain tumor classification but its use for analytical purposes is hindered by spectral variability and data sparsity. This study compares the performance of several Non-Negative Matrix Underapproximation (NMU) methods, namely Sparse NMU (S-NMU), …

us, es (code pays fourni par la source)

Unsupervised learning of metabolic fingerprints from 3D magnetic resonance spectroscopic imaging enables glioma subtype classification

Gülnur Ungan, Jörg Dietrich, Daniel P. Cahill, Ovidiu C. Andronesi

Background: Accurate classification of glioma subtypes is essential for personalized treatment, yet current diagnostic approaches rely on invasive procedures to determine molecular profiles. This study aims to enhance non-invasive glioma classification by integrating metabolic imaging with advanced unsupervised learning. Methods: Whole-brain 3D …

us, at (code pays fourni par la source)

Nosological images of brain tumor MV-MRS 3T data based on classifiers trained with SV-MRS 1.5T data, a proof-of-concept

Gülnur Ungan, Albert Pons‐Escoda, Daniel Ulinic, Carles Arús et autres

We used SV-MRS 1.5T data of patients with brain tumors to create colored-classification images of MV-MRS 3T grids of an independent cohort of patients. In 10 out of 15 MV cases the solid tumor region corresponded to the correct class. In the …

Early pseudoprogression and progression lesions in glioblastoma patients are both metabolically heterogeneous

Gülnur Ungan, Albert Pons‐Escoda, Daniel Ulinic, Carles Arús et autres

The standard treatment in glioblastoma includes maximal safe resection followed by concomitant radiotherapy plus chemotherapy and adjuvant temozolomide. The first follow-up study to evaluate treatment response is performed 1 month after concomitant treatment, when contrast-enhancing regions may appear that can correspond to …

es, gb (code pays fourni par la source)

Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology

Carla Pitarch, Gülnur Ungan, Margarida Julià‐Sapé, Alfredo Vellido

Machine Learning is entering a phase of maturity, but its medical applications still lag behind in terms of practical use. The field of oncological radiology (and neuro-oncology in particular) is at the forefront of these developments, now boosted by the success of …

es (code pays fourni par la source)

A comparison of non‐negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

Gülnur Ungan, Carles Arús, Alfredo Vellido, Margarida Julià‐Sapé

Magnetic resonance spectroscopy (MRS) is an MR technique that provides information about the biochemistry of tissues in a noninvasive way. MRS has been widely used for the study of brain tumors, both preoperatively and during follow-up. In this study, we investigated the …

es (code pays fourni par la source)