Dr. Antonio Porras is an Assistant Professor at the Department of Biostatistics and Informatics, where he teaches courses on machine learning and biomedical image analysis. He also directs the Medical Image Phenotyping lab and serves as Director of Research in the Department of Pediatric Plastic and Reconstructive Surgery at Children’s Hospital Colorado. His research interest is the development of computational and machine learning methods and tools to improve the understanding, diagnosis and treatment of pathology.
Dr. Porras holds two undergraduate degrees in Computer Science and Engineering, a MS degree in Biomedical Engineering and a PhD in Medical Image Computing. Before moving to Colorado, he worked for five years as a scientist at Children’s National Hospital in Washington, DC, where he developed several technologies to improve the diagnosis and treatment of diverse pediatric diseases. During that time, he also received postdoctoral training in embryology, developmental biology and human malformations by the Foundation for Advanced Education in the Sciences at the National Institutes of Health, which complemented his mentored clinical training in the Neurosurgery department of Children’s National.
Areas of Expertise
- Medical image computing: computer aided diagnosis, segmentation, registration, discovery of image biomarkers, etc.
- Machine learning methods with biomedical applications (e.g., diagnosis, phenotyping, risk estimation) including both traditional modeling approaches and modern convolutional and Bayesian deep learning methods
Education, Licensure & Certifications
- PhD, Medical Image Computing, Pompeu Fabra University (Spain), 2015
- MSc, Biomedical Engineering, University of Barcelona and Polytechnique University of Catalonia (Spain), 2010
- BSc, Computer Engineering, University of Cordoba (Spain), 2008
- BSc, Technical Engineering in Computer Systems, University of Cordoba (Spain), 2006
Resumes/CV:
Research
- Development of CT image-based cranial bone markers of intra-cranial hypertension
Funding source: National Institute of Dental and Craniofacial Research - National Institutes of Health
Funding identifier: R21DE031824. Funding period: 08/01/2023 - 07/31/2025.
- Data-driven quantification and prediction of pre-surgical local head volume distributions and post-surgical development in patients with craniosynostosis
Funding source: National Institute of Dental and Craniofacial Research - National Institutes of Health
Funding identifier: R01DE032681. Funding period: 03/01/2023 - 02/28/2028
- Early joint cranial and brain development from fetal and pediatric imaging
Funding source: National Institute of Dental and Craniofacial Research - National Institutes of Health
Funding identifier: R01DE030286. Funding period: 15/09/2020 - 05/31/2026
- Quantitative characterization and predictive modeling of cranial bone development in patients with craniosynostosis
Funding source: National Institute of Dental and Craniofacial Research - National Institutes of Health
Funding identifier: R00DE027993. Funding period: 01/07/2020 - 06/30/2024
Publications and Presentations
- Liu, J., Xing, F., Shaikh, A., French, B., Linguraru, M.G., Porras, A.R., 2023. Joint Cranial Bone Labeling and Landmark Detection in Pediatric CT Images using Context Encoding. IEEE Transactions on Medical Imaging (early access online).
- Elkhill, C., Liu, J., Linguraru, M.G., LeBeau, S., Khechoyan, D., French, B., Porras, A.R., 2023. Geometric learning and statistical modeling for surgical outcomes evaluation in craniosynostosis using 3D photogrammetry. Computer Methods and Programs in Biomedicine 240, 107689.
- Liu, J., Elkhill, C., LeBeau, S., French, B., Lepore, N., Linguraru, M.G., Porras, A.R., 2022. Data-driven normative reference of pediatric cranial bone development. Plastic and Reconstructive Surgery Global Open 10(8), e4457.
- Porras, A.R., Keating, R., Lee, J., Linguraru, M.G., 2022. Predictive statistical model of early cranial development. IEEE Transactions in Biomedical Engineering 69(2), 537-546.
- Porras, A.R., Rosenbaum, K., Tor-Diez, C., Summar, M., Linguraru, M.G., 2021. Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: a multinational retrospective study. Lancet Digital Health 3(10), 635-e643.