I am Francisco Gimenez, a Ph.D. student in the Biomedical Informatics Training Program at Stanford University. I am a member of Daniel Rubin's Lab. My current research area is using statistical machine learning to improve radiological care.

Honors & Awards

  • National Hispanic Scholar, College Board (2004)
  • California Alumni Scholar, California Alumni Association (2005)
  • Graduate Student Teaching Award, Stanford School of Medicine (2011)
  • National Research Service Award, NIH (2012)
  • Best Student Paper and Martin Epstein Award, American Medical Informatics Association (2014)

Education & Certifications

  • Bachelor of Science, University of California Berkeley, EECS (2009)

Service, Volunteer and Community Work

  • Biomedical Computation At Stanford (BCATS) Symposium Organizer, Stanford University (6/1/2011 - 11/12/2011)

    I was one of the core organizers of the 12th annual Biomedical Computation at Stanford (BCATS) Symposium. BCATS is the largest student-run biomedical conference at Stanford and attracts presenters from all over the bay area. As one of the organizers, my responsibilities included:

    - Funding our conference by soliciting donations
    - Publicizing our conference to promote high quality scientific applicants
    - Selecting applications for acceptance into the conference
    - Identifying and inviting keynote speakers
    - Inviting the local student community to attend
    - Organizing conference venue and food


    Stanford, CA

  • Biomedical Informatics Training Program Student Czar, Stanford University (January 2013 - December 2013)

    Student Czars act as the liaison between students and faculty in the Biomedical Informatics Training Program (BMI). Czars are expected to organize all social events in the program. In addition, czars also act as the student admissions officers. They are tasked with interviewing all applicants invited to the interview process at BMI, shepherding the interviewees during admissions week, and present student comments about interviewees to the faculty during the admissions meetings.


    Stanford, CA

Research & Scholarship

Current Research and Scholarly Interests

My main research interests lie in computational image analysis of biomedical data. Specifically, I use computers to perform biomedical image analysis more efficiently and accurately.

Lab Affiliations


Work Experience

  • Data Scientist in Residence, Formation 8 (6/2014 - Present)

    I work to help startups in the Formation 8 portfolio make meaningful use of their data.


    San Francisco, CA

  • Staff Data Scientist, Radius Intelligence (June 2014 - January 2015)

    Created predictive analytics products to evaluate and discover market segments in CRM data.


    San Francisco, CA

  • Teaching Assistant for BIOMEDIN 210: Modeling Biomedical Systems: Ontology, Terminology, Problem Solving, Stanford University (1/2013 - 3/2013)

    - Wrote homework and exam
    - Graded homework and projects
    - Taught section on probability and classification evaluation


    Stanford CA

  • Teaching Assistant for GENE 218: Computational Analysis of Biological Information: Introduction to Python for Biologists, Stanford University (6/2012 - 8/2012)

    - Wrote and graded homework
    - Taught weekly interactive section on programming
    - Provided input and evaluated final projects


    Stanford CA

  • Teaching Assistant for BMI260: Computational Methods for Biomedical Image Analysis and Interpretation, Stanford University (4/1/2012 - 6/12/2012)

    - Graded homeworks and exams,
    - Taught sections on MATLAB, image processing, and machine learning
    - Taught lecture on image segmentation


    Stanford CA

  • Course Content Creator for BMI260: Computational Methods for Biomedical Image Analysis and Interpretation, Stanford University (1/2011 - 6/2011)

    I was part of student team to design the new biomedical image analysis class at Stanford. There were three students (including myself) and two professors designing this course from scratch. My responsibilities included:

    - Determining meaningful materials to cover in the class
    - Identifying readings (publications and textbook).
    - Designing projects to enforce class concepts
    - Designing lesson plans for weekly sections


    Stanford CA

  • Programmer/Analyst in Bankiewicz Lab, University of California, San Francisco (1/7/2008 - 5/31/2010)

    Performed computational image analysis at the Bankiewicz lab at UCSF. My work helped to optimize parameters for image-guided delivery of therapeutic agents into the brain in order to treat neurodegenerative disorders.


    1855 Folsom St., San Francisco, CA


All Publications

  • Automated segmentation tool for brain infusions. PloS one Rosenbluth, K. H., Gimenez, F., Kells, A. P., Salegio, E. A., Mittermeyer, G. M., Modera, K., Kohal, A., Bankiewicz, K. S. 2013; 8 (6)


    This study presents a computational tool for auto-segmenting the distribution of brain infusions observed by magnetic resonance imaging. Clinical usage of direct infusion is increasing as physicians recognize the need to attain high drug concentrations in the target structure with minimal off-target exposure. By co-infusing a Gadolinium-based contrast agent and visualizing the distribution using real-time using magnetic resonance imaging, physicians can make informed decisions about when to stop or adjust the infusion. However, manual segmentation of the images is tedious and affected by subjective preferences for window levels, image interpolation and personal biases about where to delineate the edge of the sloped shoulder of the infusion. This study presents a computational technique that uses a Gaussian Mixture Model to efficiently classify pixels as belonging to either the high-intensity infusate or low-intensity background. The algorithm was implemented as a distributable plug-in for the widely used imaging platform OsiriX®. Four independent operators segmented fourteen anonymized datasets to validate the tool's performance. The datasets were intra-operative magnetic resonance images of infusions into the thalamus or putamen of non-human primates. The tool effectively reproduced the manual segmentation volumes, while significantly reducing intra-operator variability by 67±18%. The tool will be used to increase efficiency and reduce variability in upcoming clinical trials in neuro-oncology and gene therapy.

    View details for DOI 10.1371/journal.pone.0064452

    View details for PubMedID 23755125

  • Automatic annotation of radiological observations in liver CT images. AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium Gimenez, F., Xu, J., Liu, Y., Liu, T., Beaulieu, C., Rubin, D., Napel, S. 2012; 2012: 257-263


    We aim to predict radiological observations using computationally-derived imaging features extracted from computed tomography (CT) images. We created a dataset of 79 CT images containing liver lesions identified and annotated by a radiologist using a controlled vocabulary of 76 semantic terms. Computationally-derived features were extracted describing intensity, texture, shape, and edge sharpness. Traditional logistic regression was compared to L(1)-regularized logistic regression (LASSO) in order to predict the radiological observations using computational features. The approach was evaluated by leave one out cross-validation. Informative radiological observations such as lesion enhancement, hypervascular attenuation, and homogeneous retention were predicted well by computational features. By exploiting relationships between computational and semantic features, this approach could lead to more accurate and efficient radiology reporting.

    View details for PubMedID 23304295

  • T2 Imaging in Monitoring of Intraparenchymal Real-Time Convection-Enhanced Delivery NEUROSURGERY Richardson, R. M., Gimenez, F., Salegio, E. A., Su, X., Bringas, J., Berger, M. S., Bankiewicz, K. S. 2011; 69 (1): 154-163


    Real-time convection-enhanced delivery (RCD) of adeno-associated viral vectors by co-infusion of gadoteridol allows T1 magnetic resonance imaging (T1 MRI) prediction of areas of subsequent gene expression. The use of T2 MRI in RCD is less developed. In addition, the effect of flushing a dead-space volume on subsequent distribution of a therapeutic agent is not known.The value of T2 MRI in RCD was investigated by comparing distribution volumes of saline with immediately after T1 RCD of gadoteridol and by comparing T2, T1, and transgene distribution patterns after viral vector RCD.Adult nonhuman primates underwent saline infusion/T2 acquisition, immediately followed by gadoteridol infusion/T1 acquisition in the putamen and brainstem. Distribution volumes and spatial patterns were analyzed. Gadoteridol and adeno-associated virus encoding human aromatic l-amino acid decarboxylase (AAV2-hAADC) were co-infused under alternating T2/T1 acquisition in the thalamus, and hyperintense areas were compared with areas of subsequent transgene expression.Ratios of distribution volume to infusion volume were similar between saline and gadoteridol RCD. Spatial overlap correlated well between T2 and T1 images. The second infusate followed a spatiotemporal pattern similar to that of the first, filling the target area before developing extra-target distribution. Areas of human L-amino acid decarboxylase expression correlated well with areas of both T1 and T2 hyperintensity observed during RCD.Accuracy of cannula placement and initial infusate distribution may be safely determined by saline infusion without significantly altering the subsequent distribution of the tracer agent. T2 RCD provides detection of intraparenchymal convection- enhanced delivery in the uninjured brain and may predict subsequent distribution of a transgene after viral vector infusion.

    View details for DOI 10.1227/NEU.0b013e318217217e

    View details for Web of Science ID 000291344700055

    View details for PubMedID 21430597

  • Optimal region of the putamen for image-guided convection-enhanced delivery of therapeutics in human and non-human primates NEUROIMAGE Yin, D., Valles, F. E., Fiandaca, M. S., Bringas, J., Gimenez, F., Berger, M. S., Forsayeth, J., Bankiewicz, K. S. 2011; 54: S196-S203


    Optimal results in the direct brain delivery of brain therapeutics such as growth factors or viral vector into primate brain depend on reproducible distribution throughout the target region. In the present study, we retrospectively analyzed MRI of 25 convection-enhanced delivery (CED) infusions with MRI contrast into the putamen of non-human primates (NHP). Infused volume (V(i)) was compared to total volume of distribution (V(d)) versus V(d) within the target putamen. Excellent distribution of contrast agent within the putamen was obtained in eight cases that were used to define an optimal target volume or "green" zone. Partial or poor distribution with leakage into adjacent anatomical structures was noted in 17 cases, defining "blue" and "red" zones, respectively. Quantitative containment (99±1%) of infused gadoteridol within the putamen was obtained when the cannula was placed in the green zone, 87±3% in the blue zone and 49±0.05% in the red zone. These results were used to determine a set of 3D stereotactic coordinates that define an optimal site for putaminal infusions in NHP and human putamen. We conclude that cannula placement and definition of optimal (green zone) stereotactic coordinates have important implications in ensuring effective delivery of therapeutics into the putamen utilizing routine stereotactic MRI localization procedures and should be considered when local therapies such as gene transfer or protein administration are being translated into clinical therapy.

    View details for DOI 10.1016/j.neuroimage.2009.08.069

    View details for Web of Science ID 000294408600024

    View details for PubMedID 19761848

  • Image-guided convection-enhanced delivery of GDNF protein into monkey putamen NEUROIMAGE Gimenez, F., Krauze, M. T., Valles, F., Hadaczek, P., Bringas, J., Sharma, N., Forsayeth, J., Bankiewicz, K. S. 2011; 54: S189-S195


    Recently, we developed an MRI-based method that enables tracking of parenchymal infusions of therapeutic agents by inclusion of a contrast reagent in the infusate. We show that both liposomal Gadoteridol (GDL) and free Gadoteridol (Gd) can be used for MRI-monitored infusions into the non-human primate (NHP) putamen to predict the distribution of GDNF protein after convection-enhanced delivery (CED). GDNF and both MRI tracers showed good co-distribution within the putamen and other brain regions. Although the CED infusion technique can distribute GDNF protein over large brain regions, continuous administration of GDNF could cause undesired effects that could counteract the benefits of CED as demonstrated in this study when large volumes of GDNF were delivered that lead to GDNF leakage into CSF. These limitations can be addressed by employing an intermittent CED schedule that permits consistent target coverage without GDNF leakage into CSF or white matter. We present an approach intracranial GDNF infusions that can be optimized by means of real-time monitoring via MRI. Adoption of this new standard, along with advanced, reflux-resistant cannulae, may permit reconsideration of direct GDNF infusion into parenchyma as a clinical strategy, since previous clinical studies involving chronic infusion of recombinant glial cell line-derived neurotrophic factor (GDNF) to the putamen for the treatment of Parkinson's disease have yielded mixed results, a state of affairs that may in part be attributed to suboptimal infusion parameters.

    View details for DOI 10.1016/j.neuroimage.2010.01.023

    View details for Web of Science ID 000294408600023

    View details for PubMedID 20080195

Footer Links:

Stanford Medicine Resources: