Sadhana Ravikumar, PhD

I am a Postdoctoral Researcher in the Penn Image Computing and Science Lab (PICSL), Department of Radiology at the Perelman School of Medicine, University of Pennsylvania. I recently completed my doctoral training in Bioengineering, under the mentorship of Prof. Paul Yushkevich. I am broadly interested in the application of computer vision and machine learning methods in healthcare, with a focus on medical imaging solutions to help improve disease detection and treatment.

I grew up in Gaborone, Botswana for the first 18 years of my life. Living in Botswana, a developing nation that suffers from an acute shortage of advanced medical services, I became aware of the immense promise that technology holds for improving access to reliable healthcare. In the future, I am interested in leveraging my skills which lie at the intersection of medicine, computer science, and engineering to explore the potential of healthcare technologies in countries with limited resources.

I obtained an M.Sc in Biomedical Engineering from Carnege Mellon University where I worked with Prof. Steven Chase. Before that, I received a B.Sc in Electrical Engineering from the University of Cape Town, South Africa.
profile picture

Research

Present

My PhD dissertation work focused on the development of image analysis techniques applied to MRI for quantifying early neurodegeneration in Alzheimer’s disease (AD). AD diagnosis is significantly challenged by the fact that multiple pathologic processes frequently co-occur in the brains of patients with AD. My work aims to disentangle this pathological heterogeneity by combining information from high resolution ex vivo MRI data, and serial digital histopathology to isolate changes in the brain associated specifically with AD. Such analyses will be used to develop MRI biomarkers that will empower clinical trials in early AD to detect therapeutic effects earlier and with greater precision than current methods allow.

More specifically, my project focuses on the construction of a computational atlas of the medial temporal lobe, one of the earliest brain regions affected by AD, using machine learning and computer vision techniques applied 3D ex vivo MRI and histology data. The template provides a common reference space across specimens which can be used to characterize anatomical variability and effects of AD-related pathology on MTL structure. Conventional approches for atlas construction fail to handle ultra-high resolution MRI and geometric variability in the medial temporal lobe. Therefore, to address these challenges, I develop and validate customized image segmentation and registration pipelines using classical image analysis and deep learning techniques and concepts such as shape awareness and geometric modelling.

Past

During the summer of 2021, I had the opportunity to work as a Data Science Imaging Intern with the Personalized Health Care (Product Development) team at Genentech. I designed, implemented and evaluated deep learning methods for end-to-end image classification and segmentation applied to clinical brain MRI data for the detection of amyloid-related imaging abnormalities (ARIA), a common radiological finding associated with amyloid-targeting therapies developed to treat Alzheimer's Disease.

Prior to starting my doctoral studies, I completed a Masters in Biomedical Engineering from Carnegie Mellon University, where I was supervised by Prof. Steven Chase. For my thesis, I developed an algorithm for the identification of stable neurons across multiple neural recording sessions, based on a pairwise cross-correlogram similarity metric. The ability to record from the same subset of neurons over extended periods when conducting Brain Computer Interface (BCI) studies has the advantage of improving BCIs through reliable decoding, and is important when looking at neural activity changes associated with learning.

Select Publications & Conference Proceedings

Postmortem imaging reveals patterns of medial temporal lobe vulnerability to tau pathology in Alzheimer’s disease (2024)
S Ravikumar, LEM Wisse, R Ityerrah, S Lim, ..., P Yushkevich
Nature Communications 15(1), 4803

Improved Segmentation of Deep Sulci in Cortical Gray Matter Using a Deep Learning Framework Incorporating Laplace’s Equation (2023)
S Ravikumar, LEM Wisse, R Ityerrah, S Lim, ..., P Yushkevich
IPMI 2023 | Information Processing in Medical Imaging

Ex vivo MRI atlas of the human medial temporal lobe: characterizing neurodegeneration due to tau pathology (2021)
S Ravikumar, LEM Wisse, R Ityerrah, S Lim, ..., P Yushkevich
Acta neuropathologica communications 9 (1), 1-14

Downstream effects of polypathology on neurodegeneration of medial temporal lobe subregions (2021)
LEM Wisse*, S Ravikumar*, R Ityerrah, S Lim, ..., P Yushkevich (* = co-first authors)
Acta neuropathologica communications 9 (1), 1-11

Unfolding the medial temporal lobe cortex to characterize neurodegeneration due to Alzheimer’s disease pathology using ex vivo imaging (2021)
S Ravikumar, LEM Wisse, R Ityerrah, S Lim, ..., P Yushkevich
MLCN 201 | International Workshop on Machine Learning in Clinical Neuroimaging
talk

Three-dimensional mapping of neurofibrillary tangle burden in the human medial temporal lobe (2021)
P Yushkevich, MMI de Onzoño Martin, R Ittyerah, S Lim,..., S Ravikumar,...,R Insausti
Brain. 144(9):2784-2797

Novel ex vivo MRI atlas of the medial temporal lobe can be used to characterize structural changes due to Alzheimer’s Disease pathology (2020)
S Ravikumar, LEM Wisse, R Ityerrah, S Lim, ..., P Yushkevich
AAIC'20 | Alzheimer's Association International Conference
talk

Building an Ex Vivo Atlas of the Earliest Brain Regions Affected by Alzheimer's Disease Pathology (2020)
S Ravikumar, LEM Wisse, R Ityerrah, S Lim, ..., P Yushkevich
ISBI'20 | International Symposium on Biomedical Imaging
talk

Facilitating Manual Segmentation of 3D Datasets Using Contour And Intensity Guided Interpolation (2019)
S Ravikumar, LEM Wisse, Y Gao, G Gerig, P Yushkevich
ISBI'19 | International Symposium on Biomedical Imaging
poster

Distinct types of neural reorganization during long-term learning (2018)
X Zhou, RN Tien, S Ravikumar, SM Chase
Journal of neurophysiology 121 (4), 1329-134

Service & Community

Teaching and mentoring have played a formative role through all my academic experiences, from working as a teaching asssitant, to contributing to and organizing peer mentorship programs for students. Throughout my high school and college years I volunteered to teach at multiple after-school education programs offered in underserved communities, such as The Students' Health and Welfare Centres Organisation (SHAWCO) in Cape Town, and the "Homework Help Zone" through iPraxis, Philadelphia. My experiences teaching and mentoring in Southern Africa and the US have made me more aware of the role that historical and economic inequities play in limiting access to education and science for some communities. I believe that science and technology stand to benefit from bringing in people with diverse viewpoints and backgrounds.