L. Nunez-Gonzalez | TU Delft Repository

Exogenous Agent-Free Synthetic Post-contrast Imaging with a Cascade of Deep Networks for Enhancement Prediction After Tumor Resection

A Parametric-Map Oriented Approach

Conference paper (2025) - Elisa Moya-Sáez, Rodrigo de Luis-García, Laura Nunez-Gonzalez, Carlos Alberola-López, Juan Antonio Hernández-Tamames

Gadolinium-based contrast agents (GBCAs) have become a cornerstone in clinical routine for detection, characterization and monitoring of several diseases. Particularly, GBCAs are clinically relevant for the detection of blood brain barrier (BBB) damage, which is associated with an aggressive tumor behavior. However, issues such as safety concerns related to deposition of GBCA in the brain, prolonged acquisitions, and cost increase advocate against its usage. In this work, we propose a novel approach based on a cascade of deep networks for pre- and post-contrast parametric mapping and the synthesis of post-contrast T1-weighted images. Only a pair of pre-contrast weighted images acquired with conventional pulse sequences are used as inputs; thus, our approach is GBCAs-free. Results reveal the potential of this approach to obtain T1w-enhancement information after tumor resection which is comparable with another state-of-the-art prediction approach. We provide not only the predictions, but also the pre- and post-contrast parametric maps without the usage of GBCAs. ...

Brain tumor enhancement prediction from pre-contrast conventional weighted images using synthetic multiparametric mapping and generative artificial intelligence

Journal article (2025) - Elisa Moya-Sáez, Rodrigo de Luis-García, Laura Nunez-Gonzalez, Carlos Alberola-López, Juan Antonio Hernández-Tamames

Background: Gadolinium-based contrast agents (GBCAs) are usually employed for glioma diagnosis. However, GBCAs raise safety concerns, lead to patient discomfort and increase costs. Parametric maps offer a potential solution by enabling quantification of subtle tissue changes without GBCAs, but they are not commonly used in clinical practice due to the need for specifically targeted sequences. This work proposes to predict post-contrast T1-weighted enhancement without GBCAs from pre-contrast conventional weighted images through synthetic parametric maps computed with generative artificial intelligence (deep learning). Methods: In this retrospective study, three datasets have been employed: (I) a proprietary dataset with 15 glioma patients (hereafter, GLIOMA dataset); (II) relaxometry maps from 5 healthy volunteers; and (III) UPenn-GBM, a public dataset with 493 glioblastoma patients. A deep learning method for synthesizing parametric maps from only two conventional weighted images is proposed. Particularly, we synthesize longitudinal relaxation time (T1), transversal relaxation time (T2), and proton density (PD) maps. The deep learning method is trained in a supervised manner with the GLIOMA dataset, which comprises weighted images and parametric maps obtained with magnetic resonance image compilation (MAGiC). Thus, MAGiC maps were used as references for the training. For testing, a leave-one-out scheme is followed. Finally, the synthesized maps are employed to predict T1-weighted enhancement without GBCAs. Our results are compared with those obtained by MAGiC; specifically, both the maps obtained with MAGiC and the synthesized maps are used to distinguish between healthy and abnormal tissue (ABN) and, particularly, tissues with and without T1-weighted enhancement. The generalization capability of the method was also tested on two additional datasets (healthy volunteers and the UPenn-GBM). Results: Parametric maps synthesized with deep learning obtained similar performance compared to MAGiC for discriminating normal from ABN (sensitivities: 88.37% vs. 89.35%) and tissue with and without T1-weighted enhancement (sensitivities: 93.26% vs. 87.29%) on the GLIOMA dataset. These values were comparable to those obtained on UPenn-GBM (sensitivities of 91.23% and 81.04% for each classification). Conclusions: Our results suggest the feasibility to predict T1-weighted-enhanced tissues from pre-contrast conventional weighted images using deep learning for the synthesis of parametric maps. ...

Background: Gadolinium-based contrast agents (GBCAs) are usually employed for glioma diagnosis. However, GBCAs raise safety concerns, lead to patient discomfort and increase costs. Parametric maps offer a potential solution by enabling quantification of subtle tissue changes without GBCAs, but they are not commonly used in clinical practice due to the need for specifically targeted sequences. This work proposes to predict post-contrast T1-weighted enhancement without GBCAs from pre-contrast conventional weighted images through synthetic parametric maps computed with generative artificial intelligence (deep learning). Methods: In this retrospective study, three datasets have been employed: (I) a proprietary dataset with 15 glioma patients (hereafter, GLIOMA dataset); (II) relaxometry maps from 5 healthy volunteers; and (III) UPenn-GBM, a public dataset with 493 glioblastoma patients. A deep learning method for synthesizing parametric maps from only two conventional weighted images is proposed. Particularly, we synthesize longitudinal relaxation time (T1), transversal relaxation time (T2), and proton density (PD) maps. The deep learning method is trained in a supervised manner with the GLIOMA dataset, which comprises weighted images and parametric maps obtained with magnetic resonance image compilation (MAGiC). Thus, MAGiC maps were used as references for the training. For testing, a leave-one-out scheme is followed. Finally, the synthesized maps are employed to predict T1-weighted enhancement without GBCAs. Our results are compared with those obtained by MAGiC; specifically, both the maps obtained with MAGiC and the synthesized maps are used to distinguish between healthy and abnormal tissue (ABN) and, particularly, tissues with and without T1-weighted enhancement. The generalization capability of the method was also tested on two additional datasets (healthy volunteers and the UPenn-GBM). Results: Parametric maps synthesized with deep learning obtained similar performance compared to MAGiC for discriminating normal from ABN (sensitivities: 88.37% vs. 89.35%) and tissue with and without T1-weighted enhancement (sensitivities: 93.26% vs. 87.29%) on the GLIOMA dataset. These values were comparable to those obtained on UPenn-GBM (sensitivities of 91.23% and 81.04% for each classification). Conclusions: Our results suggest the feasibility to predict T1-weighted-enhanced tissues from pre-contrast conventional weighted images using deep learning for the synthesis of parametric maps.

Quantitative MRI-based decision model for early-stage parkinsonism diagnosis

A pilot feasibility study

Journal article (2025) - Laura Nunez-Gonzalez, Elise G.P. Dopper, Anke W. van der Eerden, Samy Abo Seada, Agnita J.W. Boon, Marcel M. Verbeek, Bastiaan R. Bloem, Frederick Jan Anton Meijer, Juan Antonio Hernandez-Tamames

Parkinsonism is a clinical syndrome defined as bradykinesia, combined with rest tremor, rigidity, or both (Postuma et al., 2015). Parkinson's disease (PD) is the most common cause of parkinsonism and the fastest-growing neurodegenerative disorder worldwide with currently almost 12 million affected people worldwide (Bloem et al., 2021; Murray, 2024). Atypical parkinsonisms, including progressive supranuclear palsy (PSP), multiple system atrophy (MSA), corticobasal syndrome (CBS), and dementia with Lewy bodies (DLB), are collectively less prevalent than idiopathic PD. These disorders are classified as rare, with estimated prevalence rates ranging from 5 to 22 cases per 100,000 population depending on the specific subtype and diagnostic criteria used (Lo, 2022). MSA and PSP are the most frequently encountered atypical forms. For example, MSA has a reported prevalence of about 3–5 per 100,000, while PSP may reach up to 6 per 100,000 in some studies. DLB, often overlapping with both PD and Alzheimer's disease, appears to be more common, with estimates around 0.4 %–5 % of the elderly population, depending on whether clinical or neuropathological criteria are used (Nysetvold et al., 2024; Sekiya et al., 2024; Delpirou et al., 2024). Diagnosis is typically made based on clinical grounds, and several exclusion criteria as well as red flags have been defined that should urge the clinician to consider an atypical parkinsonian syndrome (Postuma et al., 2015). For instance, in case of early severe autonomic failure or frequent falls, the diagnosis of MSA or PSP should be considered respectively (Wenning et al., 2022; Höglinger et al., 2017). Atypical parkinsonism (AP) has a more aggressive disease course than PD, leading to earlier loss of independent functioning and shorter life spans. Moreover, dopamirgenic treatments are less effective when applied in persons with AP. Therefore, for appropriate guidance and treatment, a timely accurate diagnosis is crucial. However, AP diagnoses are frequently missed in the early stages with reported sensitivities for MSA and PSP below 65 % (Hughes et al., 2002; Joutsa et al., 2014). [...] ...

Parkinsonism is a clinical syndrome defined as bradykinesia, combined with rest tremor, rigidity, or both (Postuma et al., 2015). Parkinson's disease (PD) is the most common cause of parkinsonism and the fastest-growing neurodegenerative disorder worldwide with currently almost 12 million affected people worldwide (Bloem et al., 2021; Murray, 2024). Atypical parkinsonisms, including progressive supranuclear palsy (PSP), multiple system atrophy (MSA), corticobasal syndrome (CBS), and dementia with Lewy bodies (DLB), are collectively less prevalent than idiopathic PD. These disorders are classified as rare, with estimated prevalence rates ranging from 5 to 22 cases per 100,000 population depending on the specific subtype and diagnostic criteria used (Lo, 2022). MSA and PSP are the most frequently encountered atypical forms. For example, MSA has a reported prevalence of about 3–5 per 100,000, while PSP may reach up to 6 per 100,000 in some studies. DLB, often overlapping with both PD and Alzheimer's disease, appears to be more common, with estimates around 0.4 %–5 % of the elderly population, depending on whether clinical or neuropathological criteria are used (Nysetvold et al., 2024; Sekiya et al., 2024; Delpirou et al., 2024). Diagnosis is typically made based on clinical grounds, and several exclusion criteria as well as red flags have been defined that should urge the clinician to consider an atypical parkinsonian syndrome (Postuma et al., 2015). For instance, in case of early severe autonomic failure or frequent falls, the diagnosis of MSA or PSP should be considered respectively (Wenning et al., 2022; Höglinger et al., 2017). Atypical parkinsonism (AP) has a more aggressive disease course than PD, leading to earlier loss of independent functioning and shorter life spans. Moreover, dopamirgenic treatments are less effective when applied in persons with AP. Therefore, for appropriate guidance and treatment, a timely accurate diagnosis is crucial. However, AP diagnoses are frequently missed in the early stages with reported sensitivities for MSA and PSP below 65 % (Hughes et al., 2002; Joutsa et al., 2014). [...]

Accuracy and repeatability of joint sparsity multi-component estimation in MR Fingerprinting

Journal article (2022) - L. Nunez-Gonzalez, M. A. Nagtegaal, D. H.J. Poot, J. de Bresser, M. J.P. van Osch, J. A. Hernandez-Tamames, F. M. Vos

MR fingerprinting (MRF) is a promising method for quantitative characterization of tissues. Often, voxel-wise measurements are made, assuming a single tissue-type per voxel. Alternatively, the Sparsity Promoting Iterative Joint Non-negative least squares Multi-Component MRF method (SPIJN-MRF) facilitates tissue parameter estimation for identified components as well as partial volume segmentations. The aim of this paper was to evaluate the accuracy and repeatability of the SPIJN-MRF parameter estimations and partial volume segmentations. This was done (1) through numerical simulations based on the BrainWeb phantoms and (2) using in vivo acquired MRF data from 5 subjects that were scanned on the same week-day for 8 consecutive weeks. The partial volume segmentations of the SPIJN-MRF method were compared to those obtained by two conventional methods: SPM12 and FSL. SPIJN-MRF showed higher accuracy in simulations in comparison to FSL- and SPM12-based segmentations: Fuzzy Tanimoto Coefficients (FTC) comparing these segmentations and Brainweb references were higher than 0.95 for SPIJN-MRF in all the tissues and between 0.6 and 0.7 for SPM12 and FSL in white and gray matter and between 0.5 and 0.6 in CSF. For the in vivo MRF data, the estimated relaxation times were in line with literature and minimal variation was observed. Furthermore, the coefficient of variation (CoV) for estimated tissue volumes with SPIJN-MRF were 10.5% for the myelin water, 6.0% for the white matter, 5.6% for the gray matter, 4.6% for the CSF and 1.1% for the total brain volume. CoVs for CSF and total brain volume measured on the scanned data for SPIJN-MRF were in line with those obtained with SPM12 and FSL. The CoVs for white and gray matter volumes were distinctively higher for SPIJN-MRF than those measured with SPM12 and FSL. In conclusion, the use of SPIJN-MRF provides accurate and precise tissue relaxation parameter estimations taking into account intrinsic partial volume effects. It facilitates obtaining tissue fraction maps of prevalent tissues including myelin water which can be relevant for evaluating diseases affecting the white matter. ...

MR fingerprinting (MRF) is a promising method for quantitative characterization of tissues. Often, voxel-wise measurements are made, assuming a single tissue-type per voxel. Alternatively, the Sparsity Promoting Iterative Joint Non-negative least squares Multi-Component MRF method (SPIJN-MRF) facilitates tissue parameter estimation for identified components as well as partial volume segmentations. The aim of this paper was to evaluate the accuracy and repeatability of the SPIJN-MRF parameter estimations and partial volume segmentations. This was done (1) through numerical simulations based on the BrainWeb phantoms and (2) using in vivo acquired MRF data from 5 subjects that were scanned on the same week-day for 8 consecutive weeks. The partial volume segmentations of the SPIJN-MRF method were compared to those obtained by two conventional methods: SPM12 and FSL. SPIJN-MRF showed higher accuracy in simulations in comparison to FSL- and SPM12-based segmentations: Fuzzy Tanimoto Coefficients (FTC) comparing these segmentations and Brainweb references were higher than 0.95 for SPIJN-MRF in all the tissues and between 0.6 and 0.7 for SPM12 and FSL in white and gray matter and between 0.5 and 0.6 in CSF. For the in vivo MRF data, the estimated relaxation times were in line with literature and minimal variation was observed. Furthermore, the coefficient of variation (CoV) for estimated tissue volumes with SPIJN-MRF were 10.5% for the myelin water, 6.0% for the white matter, 5.6% for the gray matter, 4.6% for the CSF and 1.1% for the total brain volume. CoVs for CSF and total brain volume measured on the scanned data for SPIJN-MRF were in line with those obtained with SPM12 and FSL. The CoVs for white and gray matter volumes were distinctively higher for SPIJN-MRF than those measured with SPM12 and FSL. In conclusion, the use of SPIJN-MRF provides accurate and precise tissue relaxation parameter estimations taking into account intrinsic partial volume effects. It facilitates obtaining tissue fraction maps of prevalent tissues including myelin water which can be relevant for evaluating diseases affecting the white matter.