Francisco Javier Alvarez-Padilla

Dr. Francisco Javier Alvarez-Padilla

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 November 2025 in BMC Medical Imaging
Verified
Journal Article
Open access
PDF file
ELErick Eduardo López-Ríos
Erick Eduardo López-Ríos
FAFrancisco Javier Alvarez-Padilla
Francisco Javier Alvarez-Padilla
Multiple sclerosis (MS) radiomics is hindered by multicenter variability and limited sample sizes. We evaluated whether GAN-based augmentation (GBA) improves MS classification versus traditional data augmentation (TDA) under center-wise external testing. A conditional GAN generated T1-weighted brain MRIs conditioned on class labels. Ten subcortical regions (including thalamus, putamen, caudate) were segmented with a 3D U-Net; radiomic features (shape, first-order, and texture families) were extracted and selected with LASSO. We used a leave-one-center-out (LOCO) design. All model development, segmentation, cGAN training, feature engineering, and tuning, were performed within the training centers only using inner 5-fold (subject-level 80/20) splits; the entire held-out center was reserved for a single external test. Across centers, GBA yielded small but consistent gains over TDA and real-only training, most evident for a tabular ResNet (average F1 up to 0.957), while confidence intervals overlapped for some metrics. SHAP analyses preserved the salience of basal-ganglia features, supporting biological plausibility. Limitations include a single-country cohort and no public external validation, which constrains generalizability. AI-augmented training provides incremental improvements for MS radiomics under site-held-out testing and motivates broader, international validation and clinically oriented utility analyses.

4 July 2024 in International Journal for Numerical Methods in Biomedical Engineering
Verified
Journal Article
Closed access
FAFrancisco Javier Alvarez-Padilla
Francisco Javier Alvarez-Padilla
JFJorge L. Flores‐Nunez
Jorge L. Flores‐Nunez
JAJuan R. Alvarez‐Padilla
Juan R. Alvarez‐Padilla
FGFrancisco J. Gonzalez
Francisco J. Gonzalez
AOAntonio Oceguera‐Villanueva
Antonio Oceguera‐Villanueva
BGBrian A. Gutierrez‐Quiroz
Brian A. Gutierrez‐Quiroz

Verified
Journal Article
Open access
PDF file
JMJazmin Marquez-Pedroza
Jazmin Marquez-Pedroza
MPMartha Rocio Hernández Preciado
Martha Rocio Hernández Preciado
EVEdgar Ricardo Valdivia-Tangarife
Edgar Ricardo Valdivia-Tangarife
FAFrancisco Javier Alvarez-Padilla
Francisco Javier Alvarez-Padilla
MMMario Alberto Mireles-Ramírez
Mario Alberto Mireles-Ramírez
BTBlanca Miriam Torres-Mendoza
Blanca Miriam Torres-Mendoza
Multiple sclerosis (MS) is a common disease in young women of reproductive age, characterized by demyelination of the central nervous system (CNS). Understanding how genes related to MS are expressed during pregnancy can provide insights into the potential mechanisms by which pregnancy affects the course of this disease. This review article presents evidence-based studies on these patients’ gene expression patterns. In addition, it constructs interaction networks using bioinformatics tools, such as STRING and KEGG pathways, to understand the molecular role of each of these genes. Bioinformatics research identified 25 genes and 21 signaling pathways, which allows us to understand pregnancy patients’ genetic and biological phenomena and formulate new questions about MS during pregnancy.

11 September 2025 in IEEE Access
Verified
Journal Article
Open access
JRJorge Ramos-Frutos
Jorge Ramos-Frutos
OROscar Ramos-Soto
Oscar Ramos-Soto
Israel Miguel-AndrésIsrael Miguel-Andrés
Israel Miguel-Andrés
Diego OlivaDiego Oliva
Diego Oliva
OAOmar Alvarez
Omar Alvarez
FAFrancisco Javier Alvarez-Padilla
Francisco Javier Alvarez-Padilla
Early detection of diseases allows for timely interventions that can reduce the risk of severe health complications; using Machine Learning (ML) tools to support medical specialists aids in early detection. Flatfoot is a musculoskeletal disorder that affects the biomechanical structure of the foot and the distribution of pressure while walking or running, often resulting in pain or injuries in the lower extremities. This work presents a methodology for classifying foot types using ML algorithms, requiring minimal information to be effective. Ten algorithms were trained on a dataset of 626 images and evaluated using a test set of 268 images. Hyper-parameter tuning of ten algorithms is achieved through Bayesian Optimization (BO), utilizing a descriptor based on the attention mechanism of a vision transformer. The results obtained by optimizing the Radial Basis Function Support Vector Machine (RBF-SVM) with BO are promising for flatfoot disease, achieving an accuracy greater than 95% in foot type classification. The methodology is also implemented in biomedical datasets to compare the results obtained with Flatfoot and define a methodology that provides good results for the type of flatfoot images analyzed.

8 January 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
FAFrancisco Javier Alvarez-Padilla
Francisco Javier Alvarez-Padilla
MAMayelin V Argudin-Ferran
Mayelin V Argudin-Ferran
JFJorge Flores
Jorge Flores
JAJuan Rodolfo Alvarez-Padilla
Juan Rodolfo Alvarez-Padilla
Breast cancer remains the most prevalent cancer among women worldwide, underscoring the critical need for effective early detection methods. Thermography presents a non-invasive and radiation-free alternative, offering significant potential in breast cancer screening; however, challenges such as noise, low resolution, and anatomical variability limit its potential. The aim of this project is to propose a method for segmenting the breast in thermograms to analyze thermal variations that might be associated with medical pathologies. To address these issues, we developed a hybrid segmentation approach that combines traditional computer vision techniques with a Dense Multiscale U-Net architecture, leveraging anatomical references extracted directly from thermographic images. Our method integrates the adaptability of deep learning with the domain-specific precision of traditional computer vision techniques, creating a hybrid framework designed to overcome individual limitations and enhance segmentation robustness. Our method demonstrated substantial advancements in segmentation performance, achieving a Dice Similarity Coefficient (DSC) of 0.987 and an Intersection over Union (IoU) of 0.963. These results not only surpassed those of standalone computer vision methods (DSC: 0.983, IoU: 0.934) and neural networks (DSC: 0.972, IoU: 0.922), but also highlighted the robustness, reproducibility, and precision of the hybrid approach in addressing critical challenges. Notably, the method effectively delineates the weak supramammary boundary, a common limitation of other techniques, thereby enhancing its clinical relevance and reliability in diverse imaging scenarios. This approach enhances the precision and robustness of breast segmentation, particularly in challenging regions such as the supramammary boundary. By bridging the gap between traditional and deep learning methods, this hybrid framework represents a significant advancement in thermography-based breast segmentation and lays the foundation for improving diagnostic accuracy in breast cancer screening.

20 October 2026 in Frontiers in Human Neuroscience
Verified
Journal Article
Open access
PDF file
ETEdgar A. Toscano-Flores
Edgar A. Toscano-Flores
MMMario Alberto Mireles-Ramírez
Mario Alberto Mireles-Ramírez
JGJosé de Jesús Guerrero-García
José de Jesús Guerrero-García
FAFrancisco Javier Alvarez-Padilla
Francisco Javier Alvarez-Padilla
Introduction: Magnetic resonance imaging (MRI) reveals macroscopic lesion burden in multiple sclerosis (MS) but correlates poorly with clinical phenotype, a phenomenon known as the clinico-radiological paradox. While diffusion tensor imaging (DTI) metrics assess microstructural damage, standard whole-lesion averaging may obscure microstructurally spared white matter within heterogeneous plaques. Methods: We propose a fully automated, multimodal pipeline to identify and quantify reference-like intralesional segments (RLIS) within MS lesions (i.e., the cluster exhibiting maximum feature-space similarity to subject-specific, lesion-spared reference tissue). A modified 2.5D U-Net, developed and evaluated on a cohort of 75 MS patients (115 series), performed automated FLAIR lesion segmentation. In an independent cohort of 100 MS subjects, intralesional DTI metrics (FA and MD) were extracted along streamlines reconstructed via Constrained Spherical Deconvolution tractography. Unsupervised clustering algorithms, validated against a subject-specific, lesion-spared reference CST streamlines (internal capsule), identified operationally defined reference-like segments. Results: The 2.5D U-Net achieved robust segmentation performance (DSC: 0.732, VC: 0.954), exhibited higher nominal metrics in a contextual benchmark comparison (DSC: 0.682, VC: 0.864). Across the clinical cohort, lesion count (11–131) and volume (0.54–57.3 mL) varied widely. Among the evaluated clustering methods, K-Means and Gaussian Mixture Models proved to be the most conservative, identifying median reference-like segment proportions of 26% and 22%, respectively. Crucially, the proportion of reference-like intralesional segments showed no significant monotonic association with macroscopic lesion volume or count. Conclusion: This automated framework successfully integrates robust deep learning-based lesion segmentation with tract-specific analysis to quantify the proportion of reference-like intralesional segments. The observed dissociation between overall lesion burden and RLIS suggests that this index serves as a promising candidate metric for exploring microstructural features that may contribute to the clinico-radiological paradox.