Affiliated Faculty - Integrative Biomedical Imaging Informatics at Stanford (IBIIS)
Dr. Olivier Gevaert is an associate professor at Stanford University focusing on developing machine-learning methods for biomedical decision support from multi-scale data. He is an electrical engineer by training with additional training in artificial intelligence, and a PhD in bioinformatics at the University of Leuven, Belgium. He continued his work as a postdoc in radiology at Stanford and then established his lab in the department of medicine in biomedical informatics. The Gevaert lab focuses on multi-scale biomedical data fusion primarily in oncology and neuroscience. The lab develops machine learning methods including Bayesian, kernel methods, regularized regression and deep learning to integrate molecular data or omics. The lab also investigates linking omics data with cellular and tissue data in the context of computational pathology, imaging genomics & radiogenomics.
Rohan Bareja completed his masters in bioinformatics at New York University and an additional masters in data science at Columbia University. He was a bioinformatics analyst at Weill Cornell and most recently a bimoedical software engineer at Case Western Reserve University.
He is now a research engineer in the Gevaert lab working on multi-modal data fusion of biomedical data for complex disseases.
Chris is a data scientist in the Gevaert lab working on the fusion of different biomedical data modalities. His research previously was focused on molecular biology and physics based simulations. He is currently looking into combining different modeling techniques to generate a medical digital twin.
Yuanning "Eric" Zheng
Yuanning has a multidisciplinary background in biomedical science and computer science. He received his Ph.D. in Medical Science in 2021 from Texas A&M University, where his research studied gene and environment interaction and breast cancer prevention. His postdoc work in the lab focuses on developing machine learning approaches to model high-dimensional, multi-modal and multi-omics data, with a goal of improving cancer classification and predicting treatment response. His current work includes (1) integrating histology and genomic data to resolve brain cancer heterogeneity and predict survival outcomes; (2) developing bioinformatic workflows that integrate epigenomic and transcriptomic data to discover biomarkers and therapeutic targets for cancer precision medicine.
Qinmei Xu previously was a student visiting researcher in the Gevaertlab, and now is a postdoctoral scholar. She completed her phd in quantitative imaging at Nanjing University. She now works primarily in quantitative imaging data of complex diseases.
Humaira obtained a Ph.D in Medicine from the University of New South Wales (UNSW), Sydney, Australia in 2022. Her Ph.D research focused on investigating the effects of lower-grade glioma genomic aberrations on patient prognosis and therapeutic response. Previously, she completed M.Phil from the University of Sydney, where she worked on understanding the immunological effects of a naturally derived marine compound. She also taught multiple undergraduate courses at a leading private University in Bangladesh for two years. As a postdoc in the Gevaert Lab, she is working on developing machine learning approaches for brain cancer and other diseases.
Francisco "Paco" Perez
Francisco Carrillo-Perez previously was a Visiting Student Researcher at Stanford and a Ph.D. student at the University of Granada. Now he continues his work as a postdoctoral scholar. His work focus on the fusion of multi-omics and multi-scale data for cancer classification and the use of generative models for multi-modal synthetic data generation and imputation.
Shaimaa was a Ph.D. student in the Department of Electrical Engineering, part of the Gevaert and RIIPL labs. Prior to Stanford, Shaimaa received her B.Sc. (Summa Cum Laude) from the American University in Cairo, where she studied Electronics Engineering and Computer Science. She obtained her MS degree in Electrical Engineering from Rensselaer Polytechnic Institute, working in the Cognitive and Immersive Systems lab, and advised by Professor Richard Radke. Shaimaa now returns as a postdoctoral scholar. She is interested in applying and developing machine learning methods for medical imaging and molecular data.
Marija Pizurica is a visiting student and BAEF fellow from the University of Ghent, Belgium, where she pursues an interdisciplinary doctoral degree in bioinformatics and computer science engineering. She is interested in the development of AI applications for guiding personalized health care. Specifically, her research focuses on developing deep learning methods for digital pathology in cancer research.
Xianghao "Sam" Zhan
Xianghao Zhan is a Ph.D. student in the Department of Bioengineering. He obtained his B. Eng. in control science and engineering and his B. Art in English language and literature with Summa Cum Laude at Chu Kochen Honors College, Zhejiang University, China, in 2019. Under the guidance from Prof. Gevaert and Prof. David B. Camarillo, he mainly focuses on the optimization of computational modeling of traumatic brain injury with machine learning based on biomechanical and radiological data. His research interests and projects also involve the data mining of free-text clinical notes with natural language processing and biomedical data fusion for COVID-19 patient outcome prediction.
Bryce Bagley is an MD candidate at Stanford. Prior to medical school he completed a MS in theoretical biophysics at Stanford, and graduated from the dual-degree program at Washington University in St. Louis summa cum laude with three BS degrees respectively in (bio)physics, systems engineering, and computer science. His research interests are in the use of mathematics, machine learning, and other data methods for improving medical care and studying complex biological systems. He is typically focused on problems relevant to neurological medicine, but is interested in complex biomedical data more generally.
Divya is currently a BS/MS student studying computer science and biology. Her work at the lab focuses on semi-supervised learning, temporal modeling, and information extraction from clinical notes. Divya’s current research work involves modeling using data fusion to predict time to recurrence for brain cancers and studying how federated learning could augment digital twins.
Dr. med. M. Sc. Alexander H. Thieme is a board-certified specialist in Radiation Oncology from Charité - Universitätsmedizin Berlin and fellow and speaker of the Digital Clinician Scientist program of the Berlin Institute of Health (BIH), Germany. His research interests are voxel-based methods to evaluate and optimize radiation treatment plans and assess toxicity using electronic patient-reported outcomes. He is the author of the Open Source application "CovApp" which was used on a large scale by several million users to mitigate the Covid-19 pandemic in Germany and internationally in the USA and Italy. He was also involved to create a GPS-derived contact index to successfully predict new Covid-19 infection cases and the onset of the 2nd surge in Germany. He is currently working at Stanford University as a visiting scholar to develop machine learning models with a focus on clinical application in radiotherapy.
Ahmet Görkem Er
Ahmet Görkem Er is a visiting student researcher as a Fulbright Ph.D. Dissertation Research Grantee at Stanford. He holds an M.D. degree with a double specialty of internal medicine and infectious diseases and clinical microbiology and is pursuing a Ph.D. in medical informatics at Middle East Technical University (Turkey). He is interested in machine learning approaches in healthcare and working on multi-scale data fusion and radiogenomics in Gevaert's Lab.
Internal and External collaborators
Haruka’s research has focused on imaging genomics in brain tumors. She has developed an approach that flips the common analysis framework, by starting from the imaging phenotype of a solid tumor instead of it’s molecular characterization. She has used quantitative characterizations of human brain tumors using their MR images to define subgroups. This led to three brain tumor subgroups that she successfully validated in an external validation data set and was able to match with molecular pathway activities. This result showed thought-provoking implicates with regards to treatment for brain tumors.
Nathalie is an assistant professor at Harvard University and the Broad Institute.
Idoia is an Assistant Professor of Electrical and Computer Engineering.
Mikel is the Director of Computational Genomics at the IGB, University of Illinois
Adrien is an assistant professor at EPFL, Lausanne.
Interns & past interns
Natasha is an undergraduate at University of California Irvine. She is pursuing a B.S. in Biomedical Engineering and a minor in Bioinformatics. She is interested in applying computational skills to model and solve biological problems.
Anika Cheerla is a high school student at Monta Vista High School in Cupertino, CA
Nikhil Cheerla is an undergrad at Stanford university.
Robin was a PhD student at University of Ghent at the time of his visit, and has now transitioned to a postdoc position at the department of applied mathematics, computer science & statistics.
Tina is a PhD student in Engineering Sciences at ESAT-STADIUS, KU Leuven, Belgium
Murilo is a head and neck radiologists visiting from Sao Pualo Brazil. Murilo is interested in modeling head and neck cancers and how quantitative imaging can be used to diagnose and treat patients.
Chao Huang is a visiting student from Zhejiang University in Hangzhou supported by the China Scholarship Council. She is interested in biomedical data fusion and applying advanced statistics on large biomedical data.
Zichen Wang is a visiting student from Zhejiang University in Hangzhou. He is interested in machine learning analysis on quantitative image features and deep learning with applications to healthcare. His research focuses on developing deep learning models on pathology images.
Shuo Wang is a student at the Chinese Academy of Sciences in Beijing.
Dondong Yu is a student at the Chinese Academy of Sciences in Beijing.
Alumni - Graduate students
Lina is a graduate student in electrical engineering.
Majed is an undergrad at Stanford.
Marc is a master student ICME.
Katie finsihed her phd focusing on developing algorithms on meta-analysis of biomedical data. She developed CoINcIDE, a method for meta-clustering across multiple biomedical data sets. She currently is a co-founder & CTO at Mantra Bio.
Alex is a visiting master student.
Guillaume is a master student at Stanford.
Marcos focuses on the statistical analysis of DNA methylation in cancer. He uses and extends, MethylMix, a method which identifies differentially methylated and transcriptionally predictive genes, in samples from single or combined cancer sites. He is currently pursuing a PhD in Buenos Aires, Argentina.
Julie is focusing her medical studies on informatics and data driven medicine. She is intersted in how epigenomics defines subtypes of cancer patients and how this can impact precision medicine. She joined the lab as a Stanford Med Scholar, and after finishing continued her medical studies.
Romain is a master student at Stanford.
Alumni-postdocs, staff & instructors
Sandra received a Master in Bioscience Engineering in 2012 and Doctor of Applied Biological Sciences, cell and gene biotechnology in 2016 from Ghent University in Belgium. She has frequently contributed to books and peer-reviewed research articles on (personal) genomics and epigenetics.
Sandra is now a Research Engineer in the lab. She focuses on biomedical data fusion of complex diseases, primarily oncology and cardiovascular diseases. Using novel AI approaches that digest multi-omics, multi-modal or multi-scale data she aims to enhance disease understanding with applications for precision medicine. Previously, Sandra worked for (bio)tech startups and companies in the US healthcare space deploying the power of biomedical data for next generation diagnostics and therapeutics. In her spare time, Sandra is hooked by the pursuit to optimize human performance and healthy aging. A hobby that became more serious: Sandra is co-founder and CSO of H42, a company exploring topics such as (epi)genetics, external stressors, sleep, lifestyle, diet, micronutrients, types of exercise and their (combined) effect on health/mental status.
Thomas is a postdoctoral scholar with a medical background in Internal Medicine and a degree in Immunology from the University of Lyon (France). As a practitioner in hospital medicine. His main interest is in rare autoimmune diseases such as systemic lupus erythematosus (SLE). His postdoctoral project in the Gevaert lab is focused at developing deep learning tools that take advantage of data fusion procedures to assist clinical decision-making in the management of complex diseases.
Heather Selby was a post-doctoral BD-STEP fellow at the Stanford Center for Biomedical Informatics Research (BMIR) and the Palo Alto VA working with both Dr. Olivier Gevaert and Dr. Rajesh Shah. Heather earned her PhD in Bioinformatics from Boston University in 2020, and her dissertation is entitled “Know Thy Cells: Inferring Phenotype from Genotype”. While her PhD research focus was in genomics, Heather’s post-doctoral research focus is in radiomics. Radiomics is an emerging translational research field of research aiming to extract mineable high-dimensional data from clinical images. Heather worked to (i) classify lung nodules as benign, small cell lung cancer, or non-small cell lung cancer using only radiomic features, (ii) predict immunotherapy response using both radiomic and genomic signatures, and (iii) determine resistance to treatment from follow-up CT imagery using radiomics combined with deep learning. The ultimate aim of this work was to successfully perform multi-scale biomedical data fusion in cancer. Heather is now a postdoc in the Stanford department of surgery.
Yiheng "Terry" Li
Yiheng "Terry" Li was a student in the Biomedical Informatics master program of the Department of Biomedical Data Science, School of Medicine. He obtained his B. Sci. in the Department of Resources and Environment in Shanghai Jiao Tong University, China, in 2019. He is interested in building machine learning models and developing tools for various types of data (tabular, image, free text, time series, etc.) for the optimization of patient health. He is now a part time researcher in the Gevaert lab.
Kevin has a rare combination of skills from his prior undergraduate and PhD training, which encompasses both (wet-lab based) molecular genetic/epigenetic and (dry-lab) bioinformatics and biostatistics expertise. Kevin worked on advanced computational analysis using TCGA data. Kevin is now a principal bioinformatician at Manchester Cancer Research UK.
Pritam received his B. Tech(Hons) with a major in Electronics and Electrical Communication Engineering and a minor in Computer Science and Engineering from Indian Institute of Technology (IIT), Kharagpur in 2010. In 2016, he obtained a Ph.D in Electrical and Computer Engineering at the University of Maryland, College Park under the guidance of Prof. Sennur Ulukus. From January to December 2017, he was a postdoctoral researcher in the Electrical Engineering department at Stanford University with Prof. Tsachy Weissman and Prof. Ayfer Ozgur. From January 2018, he joined the Gevaert lab at BMIR in the Stanford School of Medicine where he focused on research into the application of machine learning and deep learning to medical imaging, primarily focusing on cancer. He also worked on mining electronic health records data for patient stratification and temporal modeling of patient outcomes. He know is a staff scientist at the NIH in the group of Ronald Summers.
Marie obtained her PhD in chemistry from the University of Geneva, Switzerland, in 2017. After a first postdoc in photon science at SLAC simulating photo-properties of fluorescent proteins, she joined the group of Prof. Gevaert at BMIR in October 2019 to work towards solving problems using real-world data. Her research interests included the development of NLP tools for enhanced phenotyping of chronically ill patients. More specifically, the extraction of information such as symptoms, patient reported outcomes, functional status and mental health from clinical notes. She now is working as a Quantitative Scientist at Verana Health.
Hong is a Postdoc in the Gevaert lab. Hong got her PhD from The University of Hong Kong, Department of Clinical Oncology, under the supervision of Prof. Maria Lung. She studied bioinformatics and cancer genomics and her thesis was on Identification of Genetic Susceptibility Genes and Characterization of Somatic Mutations in Nasopharyngeal Carcinoma. Her interests focus on big data in genomics and precision medicine. She works with multiple omics datasets, including whole-genome, whole-exome, transcriptome, methylome, etc. She is proficient in several programming languages (R, Python, Linux/Bash, and Perl), statistical analysis, and machine learning methods. Her research has been focused on understanding the genetic and genomic basic of cancer by integrating and digging into the massive amount of sequencing datasets in cancer genomics. Currently, she works on developing novel algorithms for high throughput sequencing data. She focuses on studying long non coding RNAs and epigenomics.
Jay is a postdoc in computational biology working on developing novel algorithms for multi omics data fusion.
Mu Zhou earned Ph.D. degree in Computer Science and Engineering, advised by Dr. Lawrence Hall and Dr. Dmitry Goldgof at the University of South Florida in 2015. His research interests are focused on the intersection of precision medicine and data mining. During his Ph.D. study, he has been involved in cross-disciplinary research projects, directed by Dr. Robert Gatenby and Dr. Robert Gillies at H. Lee. Moffitt Cancer Research Institute, Tampa. In particular, he worked on the field of quantitative cancer imaging for tumor response assessment in various domains (e.g., brain, breast, sarcoma, and lung cancers). His research aims to develop computational models that integrate clinical information (e.g., imaging, genomic, and clinical records) to predict cancer treatment outcomes and improve personalized healthcare.