Biography
I am an Artificial Intelligence and Healthcare enthusiast with a background in machine learning, signal processing and medical imaging. I have worked as a Research Assistant (RA) since 2015 at several laboratories including the UVA Link Lab, MIT Media Lab and HMS Cardiac MR Center. My work has been published to several journals and conferences including JMRI, MRM, Radiology, ISMRM, MobiCom, and UbiComp.
Download my resumé.
Interests
- Artificial Intelligence
- Signal Processing
- Medical Imaging
Education
Master of Science, 2020
Massachusetts Institute of Technology
BS in Computer Science, 2017
University of Virginia
AS in Computer Science, 2015
Northern Virginia Community College
Publications
(2023).
Accelerated Cardiac MRI Cine with Use of Resolution Enhancement Generative Adversarial Inline Neural Network.
In Radiology.
(2022).
An inline deep learning based free-breathing ECG-free cine for exercise cardiovascular magnetic resonance.
In JCMR.
(2022).
Improving accuracy of myocardial T1 estimation in MyoMapNet.
In MRM.
(2022).
Impact of deep learning architectures on accelerated cardiac T1 mapping using MyoMapNet.
In NMR Biomedicine.
(2022).
An Explainable Machine Learning Approach Reveals Prognostic Significance of Right Ventricular Dysfunction in Nonischemic Cardiomyopathy .
In JACC.
(2022).
Accelerated cardiac T1 mapping in four heartbeats with inline MyoMapNet: a deep learning-based T1 estimation approach.
In JCMR.
(2020).
Contactless seismocardiography via deep learning radars.
In MobiCom.
(2018).
Privacy-preserving image processing with binocular thermal cameras.
In UbiComp.
Experience
Research Assistant II
- Became proficient in operating Siemens Vida 3T scanner, with authorization to perform independent scans.
- Contributed to the development of ML models for accelerated imaging, denoising, and heart function analysis.
- Deployed ML models on Siemens scanner for real-time data processing using prototype OpenRecon framework.
Research Assistant
- Developed a novel mmWave sensor capable of contactless cardiovascular activity monitoring.
- Used C++ Boost library to enable the use of multiple sensors concurrently and allow for real-time data evaluation.
- Used MATLAB to filter signal and analyze the cardiac data for signs of heart illnesses.
Machine Learning Engineer
- Worked as full stack developer on a scrum team with C# and JavaScript libraries like AngularJS & Backbone.
- Used Hadoop and Hive to build a scalable distributed data lake on AWS.
- Built a abstractive text summarization tool using TensorFlow, NumPy, Pandas and Pyrouge
Research Assistant
- Introduced a new doorway sensor capable of determine travel direction with 99.7% accuracy.
- Wrote multi-threaded C driver to increase speed of sensor by 3000% & reduced energy consumption by 50%.
- Develop optical flow based tracking algorithm robust to illumination changes & background movement in Python.
Contact
- sassana@bidmc.harvard.edu
- 617 667 2178
- 330 Brookline Ave, Boston, MA 02215
- Enter East Campus and take the Gryzmish Elevators to Floor 4
- DM Me