José Marcio Luna, Ph.D

Research Associate

José Marcio LunaComputational Biomarker Imaging Group  (CBIG)
Center for Biomedical Image Computing & Analytics (CBICA)
Department of Radiology
Perelman School of Medicine
University of Pennsylvania

Richards Labs, Suite 700D
3700 Hamilton Walk
Philadelphia, PA 19104


Educational Qualifications

PhD in Engineering, PhD Minor in Applied Mathematics, University of New Mexico (2010-2014)
MS in Electrical Engineering, University of New Mexico (2007-2009)
BSc in Electronics Engineering, District University of Bogota (1999-2004)

Research Summary

My research objective is to reduce the burden of cancer patients and families through improved medical attention, with focus on cancer prognosis and treatment based on rigorous data analysis. In particular, my current research seeks to implement precision medicine approaches to reduce morbidity and improve outcomes in lung cancer patients. I have experience in the development and application of mathematical methods for modeling and predicting treatment response using clinical and tissue-based data, as well as medical images of lung cancer patients undergoing chemoradiotherapy. I have strong background in machine learning, medical imaging, optimization theory, digital signal processing, discrete event systems and control systems theory.

Publications/ Journals

Google Scholar

Representative Publications:

Luna JM, Chao HH, Shinohara RT, Ungar LH, Cengel KA, Pryma DA, Chinniah C, Berman AT, Katz SI, Kontos D, Simone CB, Diffenderfer ES. Machine learning highlights the deficiency of conventional dosimetric constraints for prevention of high-grade radiation esophagitis in non-small cell lung cancer treated with chemoradiation. ctRO Clin Transl Radiat Oncol 2020;22:69–75. doi:10.1016/j.ctro.2020.03.007.

Gennatas ED, Friedman JH, Ungar LH, Pirracchio R, Eaton E, Reichmann LG, Interian Y, Luna JM, Simone CB, Auerbach A, Delgado E, van der Laan MJ, Solberg TD, Valdes G. Expert-augmented machine learning. PNAS Proc Natl Acad Sci 2020;117:4571–7. doi:10.1073/pnas.1906831117.

Luna JM, Gennatas ED, Ungar LH, Eaton E, Diffenderfer ES, Jensen ST, Simone CD, Friedman JH, Solberg TD, Valdes G. Building more accurate decision trees with the additive tree. PNAS Proc Natl Acad Sci 2019;116:19887–93. doi:10.1073/pnas.1816748116.

* Press coverage by Penn Today and Health IT Analytics

Luna JM, Chao HH, Diffenderfer ES, Valdes G, Chinniah C, Ma G, Cengel KA, Solberg TD, Berman AT, Simone CB. Predicting radiation pneumonitis in locally advanced stage II–III non-small cell lung cancer using machine learning. Radiother Oncol 2019;133:106–12. doi:10.1016/j.radonc.2019.01.003.

Yousefi B, Jahani N, LaRiviere M., Luna JM, Thompson JC, Aggarwal C, Carpenter EL, Katz SI, Kontos D. Correlation-Incorporated Hierarchical Clustering of High-Dimensional Radiomic Features for Prognostic Phenotype Identification of EGFR-mutaed Non-Small Cell Lung Cancer. Proc. RSNA Medical Imaging, 2019.

Chao HH, Valdes G, Luna JM, Heskel M, Berman AT, Solberg TD, Simone CB. Exploratory analysis using machine learning to predict for chest wall pain in patients with stage I non-small-cell lung cancer treated with stereotactic body radiation therapy. J Appl Clin Med Phys 2018;19:539–46. doi:10.1002/acm2.12415.

Luna JM, Kontos D, Cengel K, Simone C, Diffenderfer E. Prediction of Tumor Progression in Locally Advanced Non-Small Cell Lung Cancer Using Standardized Uptake Values From Thoracic PET/CT Images. AAPM 2018 Am. Assoc. Phys. Med. Meet. Annu. Meet., 2018.

Chao H-H, Luna JM, Valdes G, Diffenderfer E, Chinniah C, Ma G, Solberg TD, Berman AT, Simone CB. Novel Use of Machine Learning for Predicting Radiation Pneumonitis in Locally Advanced Stage II-III Non-Small Cell Lung Cancer. ARS 2018 Am. Radium Soc. Annu. Meet., 2018. doi:10.1016/j.ijrobp.2018.02.127.

Luna JM, Valdes G, Berman AT, Diffenderfer ES, Chinniah C, Ma G, Chao HH, Solberg TD, Simone CB. Novel Use of Machine Learning for Predicting Radiation Esophagitis in Locally Advanced Stage II-III Non–small Cell Lung Cancer. ASTRO 2017 Am. Soc. Radiat. Oncol. Meet., 2017. doi:10.1016/j.ijrobp.2017.06.1743.

Luna JM, Eaton E, Ungar LH, Diffenderfer E, Jensen ST, Gennatas ED, Wirth M, Simone CB, Solberg TD, Valdes G. Tree-Structured Boosting: Connections Between Gradient Boosted Stumps and Full Decision Trees. Proc. NeurIPS 2017 Conf. Neural Inf. Process. Syst., 2017, p. 1–8.

O’Reilly S, Teo B-K, Xie Y, Yin L, Diffenderfer E, Luna JM, Dong L, Xiao Y, Wei Z. Validation of dual energy CT atomic composition extraction using proton Monte Carlo. AAPM 2017 Am. Assoc. Phys. Med. Annu. Meet., 2017. doi:10.1016/j.ejmp.2017.09.099.

Luna JM, Ungar L, Zou J, Weimer J, Diffenderfer E. Towards Modeling Proton Pencil Beam Scanning for Accurate Simulated QA. AAPM 2017 Am. Assoc. Phys. Med. Annu. Meet., 2017.

Luna JM, Valdes G, Simone CB, Ungar L, Diffenderfer E, Solberg TD. MediBoost: An automated and interpretable tool for accurate patient stratification. Proc. SPIE 2017 Live Demo Wrkshp. Imaging Informatics Heal. Res. Appl., 2017.

Valdes G, Luna JM, Eaton E, Simone CB, Ungar LH, Solberg TD. MediBoost: A Patient Stratification Tool for Interpretable Decision Making in the Era of Precision Medicine. Nat Sci Reports 2016;6:1–8. doi:10.1038/srep37854.

Luna JM, Abdallah CT, Heileman GL. Probabilistic Optimization of Resource Distribution and Encryption for Data Storage in the Cloud. IEEE Trans Cloud Comput 2016;6:428–39. doi:10.1109/TCC.2016.2543728.