Open Access
Contributions of artificial intelligence to low resolution renal multiparametric magnetic resonance analysis
(2021) Oyarzun Domeño, Anne; Villanueva Larre, Arantxa; Ingeniería Eléctrica, Electrónica y de Comunicación; Institute of Smart Cities - ISC; Ingeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzaren
Arterial spin labeling (ASL), is a Multiparametric Magnetic Resonance Imaging (MRI) technique used to quantify and evaluate Renal Blood Flow (RBF) and detect perfusion failure by labelling blood water as it flows throughout the kidney. This study aims at providing an automatic quantifying and evaluation tool for Chronic Kidney Disease (CKD) patients’s follow-up.
Open Access
A deep learning image analysis method for renal perfusion estimation in pseudo-continuous arterial spin labelling MRI
(Elsevier, 2023) Oyarzun Domeño, Anne; Cia Alonso, Izaskun; Echeverría Chasco, Rebeca; Fernández Seara, María A.; Martín Moreno, Paloma L.; Bastarrika, Gorka; Navallas Irujo, Javier; Villanueva Larre, Arantxa; Ingeniería Eléctrica, Electrónica y de Comunicación; Institute of Smart Cities - ISC; Ingeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzaren; Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa
Accurate segmentation of renal tissues is an essential step for renal perfusion estimation and postoperative assessment of the allograft. Images are usually manually labeled, which is tedious and prone to human error. We present an image analysis method for the automatic estimation of renal perfusion based on perfusion magnetic resonance imaging. Specifically, non-contrasted pseudo-continuous arterial spin labeling (PCASL) images are used for kidney transplant evaluation and perfusion estimation, as a biomarker of the status of the allograft. The proposed method uses machine/deep learning tools for the segmentation and classification of renal cortical and medullary tissues and automates the estimation of perfusion values. Data from 16 transplant patients has been used for the experiments. The automatic analysis of differentiated tissues within the kidney, such as cortex and medulla, is performed by employing the time-intensity-curves of non-contrasted T1-weighted MRI series. Specifically, using the Dice similarity coefficient as a figure of merit, results above 93%, 92% and 82% are obtained for whole kidney, cortex, and medulla, respectively. Besides, estimated cortical and medullary perfusion values are considered to be within the acceptable ranges within clinical practice.
Open Access
Advancing ASL kidney image registration: a tailored pipeline with VoxelMorph
(Springer, 2025-01-31) Oyarzun Domeño, Anne; Cia Alonso, Izaskun; Echeverría Chasco, Rebeca; Fernández Seara, María A.; Martín Moreno, Paloma L.; García Fernández, Nuria; Bastarrika, Gorka; Navallas Irujo, Javier; Villanueva Larre, Arantxa; Ingeniería Eléctrica, Electrónica y de Comunicación; Ingeniaritza Elektrikoa, Elektronikoa eta Telekomunikazio Ingeniaritza; Institute of Smart Cities - ISC; Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa; Gobierno de Navarra / Nafarroako Gobernua
In clinical renal assessment, image registration plays a pivotal role, as patient movement during data acquisition can significantly impede image post-processing and the accurate estimation of hemodynamic parameters. This study introduces a deep learning-based image registration framework specifically for arterial spin labeling (ASL) imaging. ASL is a magnetic resonance imaging technique that modifies the longitudinal magnetization of blood perfusing the kidney using a series of radiofrequency pulses combined with slice-selective gradients. After tagging the arterial blood, label images are captured following a delay, allowing the tagged blood bolus to enter the renal tissue, while control images are acquired without tagging the arterial spins. Given that perfusion maps are generated at the pixel level by subtracting control images from label images and considering the relatively small signal intensity difference, precise alignment of these images is crucial to minimize motion artefacts and prevent significant errors in perfusion calculations. Moreover, due to the extended ASL acquisition times and the anatomical location of the kidneys, renal images are often susceptible to pulsation, peristalsis, and breathing motion. These motion-induced noises and other instabilities can adversely affect ASL imaging outcomes, making image registration essential. However, research on renal MRI registration, particularly with respect to learning-based techniques, remains limited, with even less focus on renal ASL. Our study proposes a learning-based image registration approach that builds upon VoxelMorph and introduces groupwise inference as a key enhancement. The dataset includes 2448 images of transplanted kidneys (TK) and 2456 images of healthy kidneys (HK). We compared the automatic image registration results with the widely recognized optimization method Elastix. The model’s performance was evaluated using the mean structural similarity index (MSSIM), normalized correlation coefficient (NCC), temporal signal-tonoise ratio (TSNR) of the samples, and the mean cortical signal (CSIM) in perfusion-weighted images, thereby extending the evaluation beyond traditional similarity-based metrics. Our method achieved superior image registration performance, with peak NCC (0.987 ± 0.006) and MSSIM (0.869 ± 0.048) values in the kidney region, significantly surpassing Elastix and the unregistered series (p\ 0.05) on TK and HK datasets. Regularization analysis showed that higher k values (1, 2) produced smoother deformation fields, while moderate k values (0.5, 0.9) balanced smoothness and detail, maintaining low non-positive Jacobian percentages (\1%) comparable to Elastix. Additionally, our method improved CSIM by 14.3% (2.304 ± 1.167) and TSNR by 13.1% (3.888 ± 2.170) in TK, and achieved up to 13.2% (CSIM) and 29.8% (TSNR) enhancements in HK, demonstrating robustness and improved signal quality across datasets and acquisition techniques.
Open Access
Contributions of artificial intelligence based image processing techniques to Multiparametric Magnetic Resonance Thoracoabdominal Imaging
(2025) Oyarzun Domeño, Anne; Villanueva Larre, Arantxa; Fernández Seara, María A.; Ingeniería Eléctrica, Electrónica y de Comunicación; Ingeniaritza Elektriko eta Elektronikoaren eta Komunikazio Ingeniaritzaren
Esta Tesis se centra en el desarrollo de un marco de procesado de imagen basado en aprendizaje profundo, específicamente diseñado para imágenes de tipo arterial spin labeling (ASL), cuyo carácter no invasivo resulta esencial para el estudio de perfusión en pacientes. Se ha abordado la falta de métodos de aprendizaje profundo dedicados al procesado de imágenes ASL, específicamente en imágenes renales y se ha demostrado la capacidad de dicho marco de adaptarse a otros dominios, como la imagen médica miocárdica. Los avances clave que aporta esta Tesis incluyen la implementación de técnicas de registro de imágenes, segmentación y generación de bases de datos sintéticos. Se ha introducido una adaptación de la arquitectura VoxelMorph para el registro de imágenes ASL en riñones. Además, se ha desarrollado un método de segmentación automática para riñones, corteza y médula, optimizando la estimación de la perfusión renal. Por otro lado, a través del uso de datos sintéticos generados mediante la arquitectura CycleGAN, se ha demostrado que los modelos entrenados con imágenes sintéticas pueden superar a aquellos entrenados con datos reales, enfatizando el valor de los datos sintéticos en la mejora de los modelos de segmentación y en la barrera que supone la escasez y privacidad de los datos clínicos. Asimismo, el marco de procesado de imagen desarrollado ha establecido un sistema totalmente automatizado para estimar los valores de perfusión renal. Para asegurar la adaptabilidad a otros dominios clínicos, se han explorado imágenes ASL de miocardio, y se ha presentado un método automático para la segmentación del miocardio en ASL, que proporciona una estimación del flujo sanguíneo miocárdico. En general, esta Tesis contribuye significativamente al campo de la imagen médica al abordar desafíos clave en el procesamiento de imágenes ASL en riñón y miocardio a través de técnicas basadas en aprendizaje profundo, mejorando las capacidades diagnósticas y sentando las bases para futuros avances en técnicas de imagen médica no invasiva.

Oyarzun Domeño, Anne

Email Address

person.page.identifierURI

Birth Date

Job Title

Last Name

First Name

person.page.departamento

person.page.instituteName

ORCID

person.page.observainves

person.page.upna

Name

Filters

Author

Subject

Date

Has files

Item Type

Type

Settings

Sort By

Results per page

Search Results