Fabien Scalzo
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
Research Subjects
Fabien Scalzo has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Sean Wu
Pepperdine University
3 shared publications - Eun Sang Cha
Seaver College, Pepperdine University, Malibu, CA 90263, USA
2 shared publications Kouros Nouri-Mahdavi
David Geffen School of Medicine University of California Los Angeles Stein Eye Institute 90095 Los Angeles United States
2 shared publicationsSean Wu
Keck Data Science Insitute Pepperdine University 90263 Malibu United States
2 shared publicationsVahid Mohammadzadeh
David Geffen School of Medicine University of California Los Angeles Stein Eye Institute 90095 Los Angeles United States
2 shared publicationsAlexander R. Carter
Department of Neurology, Washington University School of Medicine, St. Louis, MO, United States
1 shared publication
Latest Publications
- Open Access
- 22 August 2025
- Published by Frontiers Media SA in Frontiers in Rehabilitation Sciences
- Vol. 6, 1448174
Upper limb motor recovery in chronic stroke—longitudinal aggregate analysis from control group outcomes
Introduction: This study examines the effects of regular physical activity on upper extremity motor recovery during the late subacute and chronic phases of stroke.Methods: Data were aggregated from 20 studies comprising 368 participants in control groups receiving usual care or general rehabilitation without specialized interventions. To isolate the impact of non-specific physical activity, studies involving robotics or task-specific therapies were excluded.Results: The primary outcome was the change in Fugl-Meyer Assessment of Upper Extremity (FMA-UE) motor scale. The pooled effect size for FMA-UE change was small and non-significant (Cohen's d = 0.11, 95% CI: −0.05 to 0.26, p > 0.05), indicating that general physical activity alone may result in limited improvements in upper extremity function in chronic stroke. Heterogeneity across studies was low, and no evidence of publication bias was found.Discussion: These findings provide a quantitative benchmark for expected gains from general activity and offer a reference for interpreting outcomes in future stroke rehabilitation trials lacking control groups.
- 22 August 2025
- Published by Frontiers Media SA in Frontiers in Rehabilitation Sciences
- Vol. 6, 1448174
Open AccessUpper limb motor recovery in chronic stroke—longitudinal aggregate analysis from control group outcomes
Introduction: This study examines the effects of regular physical activity on upper extremity motor recovery during the late subacute and chronic phases of stroke.Methods: Data were aggregated from 20 studies comprising 368 participants in control groups receiving usual care or general rehabilitation without specialized interventions. To isolate the impact of non-specific physical activity, studies involving robotics or task-specific therapies were excluded.Results: The primary outcome was the change in Fugl-Meyer Assessment of Upper Extremity (FMA-UE) motor scale. The pooled effect size for FMA-UE change was small and non-significant (Cohen's d = 0.11, 95% CI: −0.05 to 0.26, p > 0.05), indicating that general physical activity alone may result in limited improvements in upper extremity function in chronic stroke. Heterogeneity across studies was low, and no evidence of publication bias was found.Discussion: These findings provide a quantitative benchmark for expected gains from general activity and offer a reference for interpreting outcomes in future stroke rehabilitation trials lacking control groups.
- Open Access
Historical Perspectives in Volatility Forecasting Methods with Machine Learning
Volatility forecasting for financial institutions plays a pivotal role across a wide range of domains, such as risk management, option pricing, and market making. For instance, banks can incorporate volatility forecasts into stress testing frameworks to ensure they are holding sufficient capital during extreme market conditions. However, volatility forecasting is challenging because volatility can only be estimated, and different factors influence volatility, ranging from macroeconomic indicators to investor sentiments. While recent works show promising advances in machine learning and artificial intelligence for volatility forecasting, a comprehensive assessment of current statistical and learning-based methods is lacking. Thus, this paper aims to provide a comprehensive survey of the historical evolution of volatility forecasting with a comparative benchmark of key landmark models, such as implied volatility, GARCH, LSTM, and Transformer. We open-source our benchmark code to further research in learning-based methods for volatility forecasting.
Open AccessHistorical Perspectives in Volatility Forecasting Methods with Machine Learning
Volatility forecasting for financial institutions plays a pivotal role across a wide range of domains, such as risk management, option pricing, and market making. For instance, banks can incorporate volatility forecasts into stress testing frameworks to ensure they are holding sufficient capital during extreme market conditions. However, volatility forecasting is challenging because volatility can only be estimated, and different factors influence volatility, ranging from macroeconomic indicators to investor sentiments. While recent works show promising advances in machine learning and artificial intelligence for volatility forecasting, a comprehensive assessment of current statistical and learning-based methods is lacking. Thus, this paper aims to provide a comprehensive survey of the historical evolution of volatility forecasting with a comparative benchmark of key landmark models, such as implied volatility, GARCH, LSTM, and Transformer. We open-source our benchmark code to further research in learning-based methods for volatility forecasting.
- 22 January 2025
- Published by Springer Nature
- p. 170-181
Real-Time Predictor in Two-Players Fighting Game via Vision Transformer
- 22 January 2025
- Published by Springer Nature
- p. 170-181
Real-Time Predictor in Two-Players Fighting Game via Vision Transformer
- Open Access
Self-supervised denoising of visual field data improves detection of glaucoma progression
Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage from glaucoma. However, visual field data can be noisy, exhibiting high variance, especially with increasing damage. In this study, we demonstrate the utility of self-supervised deep learning in denoising visual field data from over 4000 patients to enhance its signal-to-noise ratio and its ability to detect true glaucoma progression. We deployed both a variational autoencoder (VAE) and a masked autoencoder to determine which self-supervised model best smooths the visual field data while reconstructing salient features that are less noisy and more predictive of worsening disease. Our results indicate that including a categorical p-value at every visual field location improves the smoothing of visual field data. Masked autoencoders led to cleaner denoised data than previous methods, such as variational autoencoders. A 4.7% increase in detection of progressing eyes with pointwise linear regression (PLR) was observed. The masked and variational autoencoders' smoothed data predicted glaucoma progression 2.3 months earlier when p-values were included compared to when they were not. The faster prediction of time to progression (TTP) and the higher percentage progression detected support our hypothesis that masking out visual field elements during training while including p-values at each location would improve the task of detection of visual field progression. Our study has clinically relevant implications regarding masking when training neural networks to denoise visual field data, resulting in earlier and more accurate detection of glaucoma progression. This denoising model can be integrated into future models for visual field analysis to enhance detection of glaucoma progression.
Open AccessSelf-supervised denoising of visual field data improves detection of glaucoma progression
Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage from glaucoma. However, visual field data can be noisy, exhibiting high variance, especially with increasing damage. In this study, we demonstrate the utility of self-supervised deep learning in denoising visual field data from over 4000 patients to enhance its signal-to-noise ratio and its ability to detect true glaucoma progression. We deployed both a variational autoencoder (VAE) and a masked autoencoder to determine which self-supervised model best smooths the visual field data while reconstructing salient features that are less noisy and more predictive of worsening disease. Our results indicate that including a categorical p-value at every visual field location improves the smoothing of visual field data. Masked autoencoders led to cleaner denoised data than previous methods, such as variational autoencoders. A 4.7% increase in detection of progressing eyes with pointwise linear regression (PLR) was observed. The masked and variational autoencoders' smoothed data predicted glaucoma progression 2.3 months earlier when p-values were included compared to when they were not. The faster prediction of time to progression (TTP) and the higher percentage progression detected support our hypothesis that masking out visual field elements during training while including p-values at each location would improve the task of detection of visual field progression. Our study has clinically relevant implications regarding masking when training neural networks to denoise visual field data, resulting in earlier and more accurate detection of glaucoma progression. This denoising model can be integrated into future models for visual field analysis to enhance detection of glaucoma progression.
- Open Access
- 1 August 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (5)
Fourier feature network for 3D vessel reconstruction from biplane angiograms
3D reconstruction of biplane cerebral angiograms remains a challenging, unsolved research problem due to the loss of depth information and the unknown pixelwise correlation between input images. The occlusions arising from only two views complicate the reconstruction of fine vessel details and the simultaneous addressing of inherent missing information. In this paper, we take an incremental step toward solving this problem by reconstructing the corresponding 2D slice of the cerebral angiogram using biplane 1D image data. We developed a coordinate-based neural network that encodes the 1D image data along with a deterministic Fourier feature mapping from a given input point, resulting in a slice reconstruction that is more spatially accurate. Using only one 1D row of biplane image data, our Fourier feature network reconstructed the corresponding volume slices with a peak signal-to-noise ratio (PSNR) of 26.32 ± 0.36, a structural similarity index measure (SSIM) of 61.38 ± 1.79, a mean squared error (MSE) of 0.0023 ± 0.0002, and a mean absolute error (MAE) of 0.0364 ± 0.0029. Our research has implications for future work aimed at improving backprojection-based reconstruction by first examining individual slices from 1D information as a prerequisite.
- 1 August 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (5)
Open AccessFourier feature network for 3D vessel reconstruction from biplane angiograms
3D reconstruction of biplane cerebral angiograms remains a challenging, unsolved research problem due to the loss of depth information and the unknown pixelwise correlation between input images. The occlusions arising from only two views complicate the reconstruction of fine vessel details and the simultaneous addressing of inherent missing information. In this paper, we take an incremental step toward solving this problem by reconstructing the corresponding 2D slice of the cerebral angiogram using biplane 1D image data. We developed a coordinate-based neural network that encodes the 1D image data along with a deterministic Fourier feature mapping from a given input point, resulting in a slice reconstruction that is more spatially accurate. Using only one 1D row of biplane image data, our Fourier feature network reconstructed the corresponding volume slices with a peak signal-to-noise ratio (PSNR) of 26.32 ± 0.36, a structural similarity index measure (SSIM) of 61.38 ± 1.79, a mean squared error (MSE) of 0.0023 ± 0.0002, and a mean absolute error (MAE) of 0.0364 ± 0.0029. Our research has implications for future work aimed at improving backprojection-based reconstruction by first examining individual slices from 1D information as a prerequisite.
- Open Access
- 24 June 2024
- Published by Springer Nature in BioMedical Engineering OnLine
- Vol. 23 (1) , 1-20
Peak detection in intracranial pressure signal waveforms: a comparative study
Background: The monitoring and analysis of quasi-periodic biological signals such as electrocardiography (ECG), intracranial pressure (ICP), and cerebral blood flow velocity (CBFV) waveforms plays an important role in the early detection of adverse patient events and contributes to improved care management in the intensive care unit (ICU). This work quantitatively evaluates existing computational frameworks for automatically extracting peaks within ICP waveforms.Methods: Peak detection techniques based on state-of-the-art machine learning models were evaluated in terms of robustness to varying noise levels. The evaluation was performed on a dataset of ICP signals assembled from 700 h of monitoring from 64 neurosurgical patients. The groundtruth of the peak locations was established manually on a subset of 13, 611 pulses. Additional evaluation was performed using a simulated dataset of ICP with controlled temporal dynamics and noise.Results: The quantitative analysis of peak detection algorithms applied to individual waveforms indicates that most techniques provide acceptable accuracy with a mean absolute error (MAE) $$\le 10$$ ms without noise. In the presence of a higher noise level, however, only kernel spectral regression and random forest remain below that error threshold while the performance of other techniques deteriorates. Our experiments also demonstrated that tracking methods such as Bayesian inference and long short-term memory (LSTM) can be applied continuously and provide additional robustness in situations where single pulse analysis methods fail, such as missing data.Conclusion: While machine learning-based peak detection methods require manually labeled data for training, these models outperform conventional signal processing ones based on handcrafted rules and should be considered for peak detection in modern frameworks. In particular, peak tracking methods that incorporate temporal information between successive periods of the signals have demonstrated in our experiments to provide more robustness to noise and temporary artifacts that commonly arise as part of the monitoring setup in the clinical setting.- 24 June 2024
- Published by Springer Nature in BioMedical Engineering OnLine
- Vol. 23 (1) , 1-20
Open AccessPeak detection in intracranial pressure signal waveforms: a comparative study
Background: The monitoring and analysis of quasi-periodic biological signals such as electrocardiography (ECG), intracranial pressure (ICP), and cerebral blood flow velocity (CBFV) waveforms plays an important role in the early detection of adverse patient events and contributes to improved care management in the intensive care unit (ICU). This work quantitatively evaluates existing computational frameworks for automatically extracting peaks within ICP waveforms.Methods: Peak detection techniques based on state-of-the-art machine learning models were evaluated in terms of robustness to varying noise levels. The evaluation was performed on a dataset of ICP signals assembled from 700 h of monitoring from 64 neurosurgical patients. The groundtruth of the peak locations was established manually on a subset of 13, 611 pulses. Additional evaluation was performed using a simulated dataset of ICP with controlled temporal dynamics and noise.Results: The quantitative analysis of peak detection algorithms applied to individual waveforms indicates that most techniques provide acceptable accuracy with a mean absolute error (MAE) $$\le 10$$ ms without noise. In the presence of a higher noise level, however, only kernel spectral regression and random forest remain below that error threshold while the performance of other techniques deteriorates. Our experiments also demonstrated that tracking methods such as Bayesian inference and long short-term memory (LSTM) can be applied continuously and provide additional robustness in situations where single pulse analysis methods fail, such as missing data.Conclusion: While machine learning-based peak detection methods require manually labeled data for training, these models outperform conventional signal processing ones based on handcrafted rules and should be considered for peak detection in modern frameworks. In particular, peak tracking methods that incorporate temporal information between successive periods of the signals have demonstrated in our experiments to provide more robustness to noise and temporary artifacts that commonly arise as part of the monitoring setup in the clinical setting. - 3 December 2023
- Published by Springer Nature
- p. 109-120
Foil-Net: Deep Wave Classification for Hydrofoil Surfing
- 3 December 2023
- Published by Springer Nature
- p. 109-120
Foil-Net: Deep Wave Classification for Hydrofoil Surfing
- 16 September 2023
- Published by Springer Nature
- p. 21-31
Auxiliary-Domain Learning for a Functional Prediction of Glaucoma Progression
- 16 September 2023
- Published by Springer Nature
- p. 21-31
Auxiliary-Domain Learning for a Functional Prediction of Glaucoma Progression