Arun Seetharaman

Arun Seetharaman has six years of professional experience. In 2020, they began working as a Machine Learning Engineer at HeartVista.AI. From 2019 to 2020, they were a Research Assistant at Stanford University, where they investigated the use of deep learning to predict the presence and aggressiveness of prostate cancer from multi-parametric MRI of the prostate annotated by registration with histopathology slices of excised prostates. Arun created the SPCNet convolutional neural network architecture to use MRI data to detect clinically significant lesions with a ROC AUC of 0.75 on radical prostatectomy patients and 0.80 on biopsy patients. Arun also developed Python code to preprocess MRI data, train neural networks using cross-fold validation, evaluate networks using per-pixel and per-lesion metrics, and produce interactive visual results compatible with 3D Slicer. In 2018, Arun was an FPS/KFT Electrical Engineering Intern at The Johns Hopkins University Applied Physics Laboratory. From 2016 to 2018, they worked as an Intern at HERRICK TECHNOLOGY LABORATORIES, INC., where they developed and tested a MATLAB script for the Keysight N5193A signal generator, evaluated and configured a Analog Devices HMC7043 and HMC7044 Evaluation Board, used the experimental Quartus BluePrint Tool, debugged and repurposed an internally written MATLAB script and an internal Python script, worked in the lab with equipment, and documented all findings and experiences with LaTex documents and uploaded the documents to GitHub. In 2015, Arun was a Teaching Fellow at the University of Maryland - A. James Clark School of Engineering.

Arun Seetharaman received their Bachelor of Science (B.S.) in Electrical and Electronics Engineering from the University of Maryland between 2014 and 2018. Arun then went on to pursue a Master's degree in Electrical and Electronics Engineering at Stanford University, which they completed in 2020.