Fernando Collado-Mesa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fernando Collado-Mesa has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Jose Net
Department of Radiology, University of Miami Miller School of Medicine, Miami, Florida
12 shared publications - Monica Yepes
Department of Radiology, Division of Breast Imaging, Miller School of Medicine, University of Miami, Miami, Florida
12 shared publications - Alexandra E. Hernandez
University of Miami Miller School of Medicine
11 shared publications - Aristeidis G. Telonis
Department of Biochemistry and Molecular Biology, University of Miami Miller School of Medicine, Miami, FL 33136, USA
11 shared publications - Elizabeth D. Reguero Hernandez
Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, Florida
11 shared publications - Erin N. Kobetz
Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, Florida
11 shared publications
Latest Publications
- Open Access
- 17 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 7 (2) , 1-15
Multi-Level Volumetric Transformer for Early Prediction of Response to Neoadjuvant Chemotherapy in Locally Advanced Breast Cancer
Neoadjuvant Chemotherapy (NAC) is a standard treatment for locally advanced breast cancer, where achieving a Pathological Complete Response (pCR) is the primary goal. Early identification of patient response is vital for personalizing treatment and avoiding unnecessary toxicity. Recent advances in deep learning have produced models predicting NST effectiveness using breast MRI scans. However, many of these models rely on time-consuming tumor segmentation, requiring expert involvement. To address these challenges and enhance clinical applicability, we propose a Multi-Level Volumetric Transformer (MVT-Former), a novel model that predicts NAC response directly from non-segmented, full-field breast MRI data combined with relevant clinical information. The primary novelty of this work lies in its specialized dual-transformer design: (1) the Multi-Level Convolutional Spatial Transformer (MLCS-Former), which utilizes multi-scale convolutions and a Global Convolutional Attention (GCA) mechanism to extract fine-grained textural and morphological features from 2D MRI slices without manual annotations; and (2) the Volume Feature Learning Transformer (VFL-Former), which captures 3D structural changes and long-range dependencies across the entire MRI volume. We evaluated the MVT-Former on the I-SPY-1 TRIAL dataset and results demonstrate that the proposed model outperforms state-of-the-art methods, achieving superior performance across key metrics, including area under the curve, accuracy, sensitivity, and specificity.
- 17 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 7 (2) , 1-15
Open AccessMulti-Level Volumetric Transformer for Early Prediction of Response to Neoadjuvant Chemotherapy in Locally Advanced Breast Cancer
Neoadjuvant Chemotherapy (NAC) is a standard treatment for locally advanced breast cancer, where achieving a Pathological Complete Response (pCR) is the primary goal. Early identification of patient response is vital for personalizing treatment and avoiding unnecessary toxicity. Recent advances in deep learning have produced models predicting NST effectiveness using breast MRI scans. However, many of these models rely on time-consuming tumor segmentation, requiring expert involvement. To address these challenges and enhance clinical applicability, we propose a Multi-Level Volumetric Transformer (MVT-Former), a novel model that predicts NAC response directly from non-segmented, full-field breast MRI data combined with relevant clinical information. The primary novelty of this work lies in its specialized dual-transformer design: (1) the Multi-Level Convolutional Spatial Transformer (MLCS-Former), which utilizes multi-scale convolutions and a Global Convolutional Attention (GCA) mechanism to extract fine-grained textural and morphological features from 2D MRI slices without manual annotations; and (2) the Volume Feature Learning Transformer (VFL-Former), which captures 3D structural changes and long-range dependencies across the entire MRI volume. We evaluated the MVT-Former on the I-SPY-1 TRIAL dataset and results demonstrate that the proposed model outperforms state-of-the-art methods, achieving superior performance across key metrics, including area under the curve, accuracy, sensitivity, and specificity.
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Data from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Background:Social adversity from neighborhood disadvantage (ND) is associated with shorter breast cancer survival. Although studies have identified associations between ND and DNA methylation (DNAme) or gene expression (mRNA), a study integrating DNAme and mRNA to understand how the epigenome regulates key biological pathways in ND merits further inquiry.Methods:DNAme-, mRNA-, miRNA-, and tRNA-derived fragment data were analyzed from 80 estrogen receptor+/HER2− breast cancer samples. We analyzed the association among ND, DNAme, coding, and noncoding data to understand how the epigenome regulates biological pathways.Results:Twenty-five patients lived in ND and 55 in neighborhood advantage. In patients from ND, calcium signaling and cell adhesion pathways were hypermethylated, immune-related pathways hypomethylated, immune response genes upregulated, and estrogen response genes downregulated. Small RNA analysis showed differential expression of miRNA isoforms and tRNA-derived fragments related to ND. Subjective ND further correlated with epigenetic changes in calcium signaling, cell adhesion, and metabolic pathways, along with upregulation of proliferative and stemness pathways.Conclusions:We discovered novel associations between ND and epigenomic regulation of clinically relevant oncogenesis pathways associated with aggressive biology, such as estrogen response pathways. These findings lay the foundation for multi-institutional studies to validate our findings.Impact:This study demonstrates that ND, which is associated with shorter breast cancer survival, is also associated with epigenetic reprogramming of key oncogenesis pathways. These findings highlight pathways through which ND may affect tumor biology and lay the foundation for cancer control policy and behavioral interventions that may reverse the negative effects of ND on cancer biology.
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessData from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Background:Social adversity from neighborhood disadvantage (ND) is associated with shorter breast cancer survival. Although studies have identified associations between ND and DNA methylation (DNAme) or gene expression (mRNA), a study integrating DNAme and mRNA to understand how the epigenome regulates key biological pathways in ND merits further inquiry.Methods:DNAme-, mRNA-, miRNA-, and tRNA-derived fragment data were analyzed from 80 estrogen receptor+/HER2− breast cancer samples. We analyzed the association among ND, DNAme, coding, and noncoding data to understand how the epigenome regulates biological pathways.Results:Twenty-five patients lived in ND and 55 in neighborhood advantage. In patients from ND, calcium signaling and cell adhesion pathways were hypermethylated, immune-related pathways hypomethylated, immune response genes upregulated, and estrogen response genes downregulated. Small RNA analysis showed differential expression of miRNA isoforms and tRNA-derived fragments related to ND. Subjective ND further correlated with epigenetic changes in calcium signaling, cell adhesion, and metabolic pathways, along with upregulation of proliferative and stemness pathways.Conclusions:We discovered novel associations between ND and epigenomic regulation of clinically relevant oncogenesis pathways associated with aggressive biology, such as estrogen response pathways. These findings lay the foundation for multi-institutional studies to validate our findings.Impact:This study demonstrates that ND, which is associated with shorter breast cancer survival, is also associated with epigenetic reprogramming of key oncogenesis pathways. These findings highlight pathways through which ND may affect tumor biology and lay the foundation for cancer control policy and behavioral interventions that may reverse the negative effects of ND on cancer biology.
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Table S3 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S3: Differentially expressed small non-coding RNAs.
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S3 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S3: Differentially expressed small non-coding RNAs.
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S4 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Figure S4: Architectural Parameters of Genes
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S4 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Figure S4: Architectural Parameters of Genes
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Table S1 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S1: Differentially methylated pathways.
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S1 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S1: Differentially methylated pathways.
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Table S4 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S4: Correlation results
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S4 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S4: Correlation results
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S2 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Figure S2: Heatmap of Perceived Disadvantage and ADI
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S2 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Figure S2: Heatmap of Perceived Disadvantage and ADI
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Table S2 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S2: Differentially expressed pathways.
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S2 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Table S2: Differentially expressed pathways.
- Open Access
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S1 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Figure S1: Blood cytokine levels in ADI-High Compared to ADI-Low Patients
- 3 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S1 from Molecular Portraits of Social Adversity in Breast Cancer: Neighborhood Disadvantage Is Associated with Epigenetic Deregulation of Key Oncogenic Pathways
Supplementary Figure S1: Blood cytokine levels in ADI-High Compared to ADI-Low Patients