Roland Henry, Professor

Closed (1) Deep Learning in Medicine: Monitoring Disability Progression in Multiple Sclerosis Using Fitbit Data

Applications for fall 2021 are now closed for this project.

Walking is the primary form of physical activity for people with multiple sclerosis(MS), and walking impairment is one of the most feared and limiting aspects of the disease. Measures carried out in the clinic to determine multiple sclerosis disability (such as the Expanded Disability Status Scale (EDSS)) are crucial, but suffer from human subjectivity and are insensitive to temporal fluctuations.

Deep Learning has shown an unreasonable level of effectiveness in modeling and prediction given an adequate amount of data. By applying these methods to a new dataset spanning years of Fitbit activity, we aim to develop descriptive measures of physical activity capable crucial to monitoring the disability progression of MS.

An undergraduate working on this project will build tools that will parse, model and visualize minute-by-minute FITBIT step data in order to monitor disease progression of MS. This involves modeling fluctuations of physical activity over time, identifying unique patient subpopulations via unsupervised methods, and predicting disease progression by projecting clinical metrics and physical activity into the future.

There are multiple opportunities for projects that capture and extract information from fitbit data:

(a) building a suite of web applications that enable visualization, analysis and annotation of motion sensor data
(b) developing a data preprocessing and storage pipeline needed to train a range of neural networks
(c) training models to characterize patient behavior and cluster the cohort into subpopulations based on physical activity signatures
(d) formulation, testing and validation of a novel activity metric designed to encapsulate physical activity for patients at varying stages of multiple sclerosis
(e) forecasting patient activity into the future in order to predict disease progression

Day-to-day supervisor for this project: Matthew Waliman, Staff Researcher

Qualifications: We are looking for dedicated software engineers and data scientists eager to contribute to cutting edge research in the fields of deep learning and neuroscience. Students from various majors are encouraged to apply, including but not limited to EECS, BioE, CS, data science, math, and statistics. Required: - Proficiency in python and common libraries (numpy, scipy, scikit-learn, pandas)- Working knowledge of Version Control (such as Github). - Great teamwork (organization, communication skills, punctuality, reliability, etc) - Interest in data science, medical imaging, machine learning, engineering and healthcare research. Desired: - Working knowledge of basic machine learning and deep learning (loss function, cross-validation, overfitting, error analysis, etc). - Experience with Tensorflow/Keras or Pytorch. - Working knowledge of signal processing and image processing. - Experience working with time-series or kinematic data.

Weekly Hours: 9-11 hrs

Off-Campus Research Site: * As this is a data-intensive project, much of the work can be done remotely at any place with a sufficiently fast internet connection
* The day-to-day mentors for the project work at the Sandler Neuroscience Center at UCSF Mission Bay.

COVID-19 Update: We are working with all students remotely until further notice. You will be working off-site.

Closed (2) Monitoring Multiple Sclerosis using Deep Learning

Applications for fall 2021 are now closed for this project.

UCSF’s Department of Radiology and Biomedical Imaging and Department of Neurology are excited to offer a combined educational and research opportunity for motivated undergraduate students in the medical imaging research team. 3D segmentation of structures in the brain and spinal cord is a problem that deep learning is uniquely equipped to solve. We are looking for aspiring data scientists and deep learning engineers to join our team to work on developing next-generation diagnostic techniques to monitor neurodegeneration in multiple sclerosis via deep learning on magnetic resonance imaging data.



We are working with one of the largest clinical imaging datasets for multiple sclerosis in the world with over 10 years of MRI data. Our laboratory specializes in quantitative analysis of images from MRI using image processing and machine learning. We work in close collaboration with the MS Clinic at UCSF Neurology to apply data science and deep learning techniques to uncover imaging biomarkers from clinical neuroimaging studies. We identify features that predict patient survival, therapeutic response, and other clinical outcomes.



We aim to build scalable annotation and segmentation workflows to intelligently compute standard radiological features such as spinal cord areas. We also want to build longitudinal models to analyze the evolution of neurodegeneration. Of particular excitement is building statistical model to quantitatively image the spatial pathology of MS. An undergraduate would help us by (1) building and training deep learning models on NVIDIA GPUs, (2) building scalable annotation platforms to further enrich the terabytes of existing data, (3) building infrastructure for managing the training and visualization of models for image segmentation.



Upon successful progress, it is expected that student submit/present at a national research meeting. Students are encouraged to seek out and apply for undergraduate research grants. Many of our students have went on to produce peer-reviewed publications.

Day-to-day supervisor for this project: Amit Akula, Staff Researcher

Qualifications: Students from various majors are encouraged to apply, including but not limited to EECS, BioE, CS, data science, math, and statistics.

Weekly Hours: 9-11 hrs

Off-Campus Research Site: * As this is a data-intensive project, much of the work can be done remotely at any place with a sufficiently fast internet connection
* The day-to-day mentors for the project work at the Sandler Neuroscience Center at UCSF Mission Bay.

COVID-19 Update: We are working with all students remotely until further notice. You will be working off-site.

Closed (3) Building distributed real time MRI processing tools to analyze the pathology of multiple sclerosis from terabytes of MRI data

Applications for fall 2021 are now closed for this project.

UCSF’s Department of Neurology has some of the largest clinical neuroimaging datasets in the world. As the director of imaging for the multiple sclerosis groups, Dr. Roland Henry’s laboratory is in charge of making sense of this data and applying next generation analytical techniques to translate this raw data into actionable clinical results.



The laboratory is recruiting talented computational and data scientists to help build scalable distributed processing tools to efficiently process, analyze, and visualize data from a unique large cohort of patients to pilot precision medicine with MRI quantitative metrics.



An undergraduate would contribute to the following initiatives

(a) extending the suite of tools to process and understand 3D imaging data, (b) assessing the clinical value of quantitative neuroimaging biomarkers, (c) accelerating and extending the computational advanced clinical analytics on neuroimaging data, (d) building streaming platforms to visualize 3D imaging data annotated with clinical biomarkers, (e) building mobile and other platforms to facilitate human in the loop quality assurance and annotation, and (f) extending our data infrastructure to be able to efficiently store and disseminate clinical results , Staff Researcher

Qualifications: We are looking for talented software engineers who have an interest in building scalable applications. This involves UI/UX designers, software engineers, mobile application developers, and especially people with an interested in distributed systems. There are no hard and fast qualifications for this position but ideally the individual in question has a passion for building and maintaining complex software processing tools and end-user applications. As medicine becomes increasingly data driven, UCSF needs talented programmers who can enable clinicians to be able to provide next-generation care. We have projects to stream analytical results for neuro-surgical applications, segment anatomical structures to build real-time modeling of human systems, compute chemical biomarkers to monitor the progress of disorders, and many more projects all which have bottlenecks due to a lack of programming talent. We hope you’ll be able to help us monitor, diagnose, and hopefully cure neurodegenerative disorders with programming!

Weekly Hours: 9-11 hrs

Off-Campus Research Site: * As this is a data-intensive project, much of the work can be done remotely at any place with a sufficiently fast internet connection
* The day-to-day mentors for the project work at the Sandler Neuroscience Center at UCSF Mission Bay.

COVID-19 Update: We are working with all students remotely until further notice. You will be working off-site.