Evelio Gonzalez-Dalmau
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Evelio Gonzalez-Dalmau has a total of 115 co-authors. Here are the top co-authors by number of shared publications:
Carmen Valenzuela
Institute of Cybernetics, Mathematics and Physics (ICIMAF), Vedado, Cuba
3 shared publications- Eduardo Garea-Llano
Neuroinformatic Department. Cuban Neuroscience Center, Havana 16600, Cuba
3 shared publications Giosmany Bringas
National Institute of Neurology (INN), Vedado, Cuba
3 shared publicationsJuan M. Parra Robles
Univ. de Oriente (Cuba)
3 shared publications- Leslie Pérez Ruiz
Center of Molecular Immunology Havana Cuba
3 shared publications Nelky Urrutia
Hospital Iván Portuondo, San Antonio de los Baños, Cuba
3 shared publications
Latest Publications
- 3 February 2026
- Published by Springer Nature
- p. 3-14
From Pixels to Prognosis: An AI Framework for Volumetric RALE Scoring in Post-COVID Chest CT
- 3 February 2026
- Published by Springer Nature
- p. 3-14
From Pixels to Prognosis: An AI Framework for Volumetric RALE Scoring in Post-COVID Chest CT
- Open Access
Deep Learning-Based Assessment of Brainstem Volume Changes in Spinocerebellar Ataxia Type 2 (SCA2): A Study on Patients and Preclinical Subjects
Spinocerebellar ataxia type 2 (SCA2) is a neurodegenerative disorder marked by progressive brainstem and cerebellar atrophy, leading to gait ataxia. Quantifying this atrophy in magnetic resonance imaging (MRI) is critical for tracking disease progression in both symptomatic patients and preclinical subjects. However, manual segmentation of brainstem subregions (mesencephalon, pons, and medulla) is time-consuming and prone to human error. This work presents an automated deep learning framework to assess brainstem atrophy in SCA2. Using T1-weighted MRI scans from patients, preclinical carriers, and healthy controls, a U-shaped convolutional neural network (CNN) was trained to segment brainstem subregions and quantify volume loss. The model achieved strong agreement with manual segmentations, significantly outperforming four U-Net-based benchmarks (mean Dice scores: whole brainstem 0.96 vs. 0.93–0.95, pons 0.96 vs. 0.91–0.94, mesencephalon 0.96 vs. 0.89–0.93, and medulla 0.95 vs. 0.91–0.93). Results revealed severe atrophy in preclinical and symptomatic cohorts, with pons volumes reduced by nearly 50% compared to controls (p < 0.001). The mesencephalon and medulla showed milder degeneration, underscoring regional vulnerability differences. This automated approach enables rapid, precise assessment of brainstem atrophy, advancing early diagnosis and monitoring in SCA2.
Open AccessDeep Learning-Based Assessment of Brainstem Volume Changes in Spinocerebellar Ataxia Type 2 (SCA2): A Study on Patients and Preclinical Subjects
Spinocerebellar ataxia type 2 (SCA2) is a neurodegenerative disorder marked by progressive brainstem and cerebellar atrophy, leading to gait ataxia. Quantifying this atrophy in magnetic resonance imaging (MRI) is critical for tracking disease progression in both symptomatic patients and preclinical subjects. However, manual segmentation of brainstem subregions (mesencephalon, pons, and medulla) is time-consuming and prone to human error. This work presents an automated deep learning framework to assess brainstem atrophy in SCA2. Using T1-weighted MRI scans from patients, preclinical carriers, and healthy controls, a U-shaped convolutional neural network (CNN) was trained to segment brainstem subregions and quantify volume loss. The model achieved strong agreement with manual segmentations, significantly outperforming four U-Net-based benchmarks (mean Dice scores: whole brainstem 0.96 vs. 0.93–0.95, pons 0.96 vs. 0.91–0.94, mesencephalon 0.96 vs. 0.89–0.93, and medulla 0.95 vs. 0.91–0.93). Results revealed severe atrophy in preclinical and symptomatic cohorts, with pons volumes reduced by nearly 50% compared to controls (p < 0.001). The mesencephalon and medulla showed milder degeneration, underscoring regional vulnerability differences. This automated approach enables rapid, precise assessment of brainstem atrophy, advancing early diagnosis and monitoring in SCA2.
- Open Access
- 28 July 2025
- Published by MDPI AG in Preprints.org
Deep Learning-Based Assessment of Brainstem Volume Changes in Spinocerebellar Ataxia Type 2 (SCA2): A Study on Patients and Preclinical Subjects
Spinocerebellar ataxia type 2 (SCA2) is a neurodegenerative disorder marked by progressive brainstem and cerebellar atrophy, leading to gait ataxia. Quantifying this atrophy in magnetic resonance imaging (MRI) is critical for tracking disease progression in both symptomatic patients and preclinical subjects. However, manual segmentation of brainstem subregions (mesencephalon, pons, and medulla) is time-consuming and prone to human error. This work presents an automated deep learning framework to assess brainstem atrophy in SCA2. Using T1-weighted MRI scans from patients, preclinical carriers, and healthy controls, an U-shape convolutional neural network (CNN) was trained to segment brainstem subregions and quantify volume loss. The model achieved strong agreement with manual segmentations (min DSC: 0.93), and significantly reduced processing time from hours to minutes. Results revealed severe atrophy in preclinical and symptomatic cohorts, with pons volumes reduced by nearly 50% compared to controls (p< 0.001). The mesencephalon and medulla showed milder degeneration, underscoring regional vulnerability differences. This automated approach enables rapid, precise assessment of brainstem atrophy, advancing early diagnosis and monitoring in SCA2. By streamlining analysis, deep learning bridges translational gaps in neurodegenerative disease research.
- 28 July 2025
- Published by MDPI AG in Preprints.org
Open AccessDeep Learning-Based Assessment of Brainstem Volume Changes in Spinocerebellar Ataxia Type 2 (SCA2): A Study on Patients and Preclinical Subjects
Spinocerebellar ataxia type 2 (SCA2) is a neurodegenerative disorder marked by progressive brainstem and cerebellar atrophy, leading to gait ataxia. Quantifying this atrophy in magnetic resonance imaging (MRI) is critical for tracking disease progression in both symptomatic patients and preclinical subjects. However, manual segmentation of brainstem subregions (mesencephalon, pons, and medulla) is time-consuming and prone to human error. This work presents an automated deep learning framework to assess brainstem atrophy in SCA2. Using T1-weighted MRI scans from patients, preclinical carriers, and healthy controls, an U-shape convolutional neural network (CNN) was trained to segment brainstem subregions and quantify volume loss. The model achieved strong agreement with manual segmentations (min DSC: 0.93), and significantly reduced processing time from hours to minutes. Results revealed severe atrophy in preclinical and symptomatic cohorts, with pons volumes reduced by nearly 50% compared to controls (p< 0.001). The mesencephalon and medulla showed milder degeneration, underscoring regional vulnerability differences. This automated approach enables rapid, precise assessment of brainstem atrophy, advancing early diagnosis and monitoring in SCA2. By streamlining analysis, deep learning bridges translational gaps in neurodegenerative disease research.
- 20 December 2023
- Published by Springer Nature
- p. 202-214
A Comparative Study of Deep Learning Methods for Brain Magnetic Resonance Image Reconstruction
- 20 December 2023
- Published by Springer Nature
- p. 202-214
A Comparative Study of Deep Learning Methods for Brain Magnetic Resonance Image Reconstruction
- Open Access
- 13 December 2023
- Published by Springer Nature in Alzheimer's Research & Therapy
- Vol. 15 (1) , 1-15
NeuroEPO plus (NeuralCIM®) in mild-to-moderate Alzheimer’s clinical syndrome: the ATHENEA randomized clinical trial
Background: NeuroEPO plus is a recombinant human erythropoietin without erythropoietic activity and shorter plasma half-life due to its low sialic acid content. NeuroEPO plus prevents oxidative damage, neuroinflammation, apoptosis and cognitive deficit in an Alzheimer’s disease (AD) models. The aim of this study was to assess efficacy and safety of neuroEPO plus. Methods: This was a double-blind, randomized, placebo-controlled, phase 2–3 trial involving participants ≥ 50 years of age with mild-to-moderate AD clinical syndrome. Participants were randomized in a 1:1:1 ratio to receive 0.5 or 1.0 mg of neuroEPO plus or placebo intranasally 3 times/week for 48 weeks. The primary outcome was change in the 11-item cognitive subscale of the AD Assessment Scale (ADAS-Cog11) score from baseline to 48 weeks (range, 0 to 70; higher scores indicate greater impairment). Secondary outcomes included CIBIC+, GDS, MoCA, NPI, Activities of Daily Living Scales, cerebral perfusion, and hippocampal volume. Results: A total of 174 participants were enrolled and 170 were treated (57 in neuroEPO plus 0.5 mg, 56 in neuroEPO plus 1.0 mg and 57 in placebo group). Mean age, 74.0 years; 121 (71.2%) women and 85% completed the trial. The median change in ADAS-Cog11 score at 48 weeks was −3.0 (95% CI, −4.3 to −1.7) in the 0.5 mg neuroEPO plus group, −4.0 (95% CI, −5.9 to −2.1) in the 1.0 mg neuroEPO plus group and 4.0 (95% CI, 1.9 to 6.1) in the placebo group. The difference of neuroEPO plus 0.5 mg vs. placebo was 7.0 points (95% CI, 4.5–9.5) P = 0.000 and between the neuroEPO plus 1.0 mg vs. placebo was 8.0 points (95% CI, 5.2–10.8) P = 0.000. NeuroEPO plus treatment induced a statistically significant improvement in some of clinical secondary outcomes vs. placebo including CIBIC+, GDS, MoCA, NPI, and the brain perfusion. Conclusions: Among participants with mild-moderate Alzheimer’s disease clinical syndrome, neuroEPO plus improved the cognitive evaluation at 48 weeks, with a very good safety profile. Larger trials are warranted to determine the efficacy and safety of neuroEPO plus in Alzheimer’s disease. Trial registration: https://rpcec.sld.cu Identifier: RPCEC00000232.
- 13 December 2023
- Published by Springer Nature in Alzheimer's Research & Therapy
- Vol. 15 (1) , 1-15
Open AccessNeuroEPO plus (NeuralCIM®) in mild-to-moderate Alzheimer’s clinical syndrome: the ATHENEA randomized clinical trial
Background: NeuroEPO plus is a recombinant human erythropoietin without erythropoietic activity and shorter plasma half-life due to its low sialic acid content. NeuroEPO plus prevents oxidative damage, neuroinflammation, apoptosis and cognitive deficit in an Alzheimer’s disease (AD) models. The aim of this study was to assess efficacy and safety of neuroEPO plus. Methods: This was a double-blind, randomized, placebo-controlled, phase 2–3 trial involving participants ≥ 50 years of age with mild-to-moderate AD clinical syndrome. Participants were randomized in a 1:1:1 ratio to receive 0.5 or 1.0 mg of neuroEPO plus or placebo intranasally 3 times/week for 48 weeks. The primary outcome was change in the 11-item cognitive subscale of the AD Assessment Scale (ADAS-Cog11) score from baseline to 48 weeks (range, 0 to 70; higher scores indicate greater impairment). Secondary outcomes included CIBIC+, GDS, MoCA, NPI, Activities of Daily Living Scales, cerebral perfusion, and hippocampal volume. Results: A total of 174 participants were enrolled and 170 were treated (57 in neuroEPO plus 0.5 mg, 56 in neuroEPO plus 1.0 mg and 57 in placebo group). Mean age, 74.0 years; 121 (71.2%) women and 85% completed the trial. The median change in ADAS-Cog11 score at 48 weeks was −3.0 (95% CI, −4.3 to −1.7) in the 0.5 mg neuroEPO plus group, −4.0 (95% CI, −5.9 to −2.1) in the 1.0 mg neuroEPO plus group and 4.0 (95% CI, 1.9 to 6.1) in the placebo group. The difference of neuroEPO plus 0.5 mg vs. placebo was 7.0 points (95% CI, 4.5–9.5) P = 0.000 and between the neuroEPO plus 1.0 mg vs. placebo was 8.0 points (95% CI, 5.2–10.8) P = 0.000. NeuroEPO plus treatment induced a statistically significant improvement in some of clinical secondary outcomes vs. placebo including CIBIC+, GDS, MoCA, NPI, and the brain perfusion. Conclusions: Among participants with mild-moderate Alzheimer’s disease clinical syndrome, neuroEPO plus improved the cognitive evaluation at 48 weeks, with a very good safety profile. Larger trials are warranted to determine the efficacy and safety of neuroEPO plus in Alzheimer’s disease. Trial registration: https://rpcec.sld.cu Identifier: RPCEC00000232.
- Open Access
- 7 November 2023
- Published by Wiley
Measuring Working Memory in Aphasic Individuals with Electroencephalography and N-Back Tasks
Aphasia is a neurological condition that manifests itself through deficiencies in linguistic functions, which are essential for social interaction and activities of daily living. This deficiency is associated with a loss of working memory capacity, which is responsible for the temporary storage of information. This work sought to develop an approach to aid professionals involved in aphasia treatment and rehabilitation programs, aiming to improve the manner in which evidences of rehabilitation are obtained. The methodology is based on an electroencephalography device, which captures brain signals from individuals while they execute a task that stimulates verbal working memory. The signals are processed using an approach based on event-related potentials, which are then used as input to a statistical model trained with a scientifically validated measurement of working memory. The results indicated that the error of the model was slightly larger than expected, but diminished proportionally to the amount of training samples. We conclude the study suggesting research paths to reduce the error of the model and investigate the feasibility of this approach in a clinical context.
- 7 November 2023
- Published by Wiley
Open AccessMeasuring Working Memory in Aphasic Individuals with Electroencephalography and N-Back Tasks
Aphasia is a neurological condition that manifests itself through deficiencies in linguistic functions, which are essential for social interaction and activities of daily living. This deficiency is associated with a loss of working memory capacity, which is responsible for the temporary storage of information. This work sought to develop an approach to aid professionals involved in aphasia treatment and rehabilitation programs, aiming to improve the manner in which evidences of rehabilitation are obtained. The methodology is based on an electroencephalography device, which captures brain signals from individuals while they execute a task that stimulates verbal working memory. The signals are processed using an approach based on event-related potentials, which are then used as input to a statistical model trained with a scientifically validated measurement of working memory. The results indicated that the error of the model was slightly larger than expected, but diminished proportionally to the amount of training samples. We conclude the study suggesting research paths to reduce the error of the model and investigate the feasibility of this approach in a clinical context.
- 15 September 2023
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 39 (4) , 843-851
Semi-automated methodology for determination of contrast agent relaxivity using MRI
- 15 September 2023
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 39 (4) , 843-851
Semi-automated methodology for determination of contrast agent relaxivity using MRI
- 9 June 2023
- Published by Springer Nature
- p. 211-220
Chest X-Ray Imaging Severity Score of COVID-19 Pneumonia
- 9 June 2023
- Published by Springer Nature
- p. 211-220
Chest X-Ray Imaging Severity Score of COVID-19 Pneumonia
- Open Access
- 15 May 2023
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 59 (10)
An open‐source tool for evaluating calibration techniques used in low‐cost air pollutant monitors
Low‐cost air pollutant sensors suffer several interferences due to the variation of climatic elements. Recent studies look for calibration solutions based on different regression and classification machine learning algorithms. The present work brings together the implementation and extraction of performance metrics from these algorithms in a single open‐source tool. Both the input data and parameters for each algorithm are automatically configured. This feature makes the tool compatible with any input dataset and removes the need to interact with complex codes.
- 15 May 2023
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 59 (10)
Open AccessAn open‐source tool for evaluating calibration techniques used in low‐cost air pollutant monitors
Low‐cost air pollutant sensors suffer several interferences due to the variation of climatic elements. Recent studies look for calibration solutions based on different regression and classification machine learning algorithms. The present work brings together the implementation and extraction of performance metrics from these algorithms in a single open‐source tool. Both the input data and parameters for each algorithm are automatically configured. This feature makes the tool compatible with any input dataset and removes the need to interact with complex codes.
- Open Access
- 6 January 2023
- Published by Wiley
An open-source tool for evaluating calibration techniques used in low-cost air pollutant monitors
Low-cost air pollutant sensors suffer several interferences due to the variation of climatic elements. Recent studies look for calibration solutions based on different regression and classification machine learning algorithms. The present work brings together the implementation and extraction of performance metrics from these algorithms in a single open-source tool. Both the input data and parameters for each algorithm are automatically configured. This feature makes the tool compatible with any input dataset and removes the need to interact with complex codes.
- 6 January 2023
- Published by Wiley
Open AccessAn open-source tool for evaluating calibration techniques used in low-cost air pollutant monitors
Low-cost air pollutant sensors suffer several interferences due to the variation of climatic elements. Recent studies look for calibration solutions based on different regression and classification machine learning algorithms. The present work brings together the implementation and extraction of performance metrics from these algorithms in a single open-source tool. Both the input data and parameters for each algorithm are automatically configured. This feature makes the tool compatible with any input dataset and removes the need to interact with complex codes.