PhD, Biomedical Engineering - University of Iowa
2019 — 2023Thesis: Deep Learning and Explainable AI in Medical Image Segmentation
Advisor: Milan Sonka
Resume
Education
M.S., Computer Science - University of Iowa
2017 — 2019B.A., Computer Science - Carleton College
2012 — 2016Minor: Cognitive Science
Comprehensive Exam: Genetic Programming for Stock Forcasting
Experience
Graduate Research Assistant - University of Iowa, Dept. of Biomedical Engineering
2018 — 2023In my role as an AI/ML researcher, I've specialized in developing and implementing innovative deep learning models for medical image segmentation, enhancing accuracy across various imaging modalities. I've also pioneered a novel visual explanation method for these models, significantly advancing the fields of explainable AI and reliable model validation in healthcare.
Graduate Research Assistant - University of Iowa, Dept. of Computer Science
2017 — 2018Working as a researcher in the Computer Science Department, I created innovative wearable technologies and computer vision algorithms to aid the visually impaired, and conducted extensive analysis of these technologies in various settings. Additionally, I developed a machine learning pipeline for diabetic foot ulcer segmentation and an assisted annotation tool, streamlining the annotation process for a large-scale diabetic foot ulcer dataset.
Test Automation Engineer - Quality Consulting Inc.
2016 — 2017"In my test automation role, I created and managed automated feature testing scripts, developing TypeScript and Protractor-based test suites for DuPont Pioneer's Encirca web services. I actively collaborated within a development team, contributing to issue resolution and enhancing the continuous development pipeline."
Most Recent Publications
Mullan, S., Zhang, L., Zhang, H., & Sonka, M. (2024). Deep learning medical image segmentation. In A. Frangi, J. Prince, & M. Sonka (Eds.), Medical Image Analysis (1st ed., pp. 475-500). Elsevier
https://doi.org/10.1016/b978-0-12-813657-7.00042-xMullan, S., & Sonka, M. (2023). Kernel-weighted contribution: a method of visual attribution for 3D deep learning segmentation in medical imaging. In Journal of Medical Imaging (Vol. 10, Issue 05). SPIE-Intl Soc Optical Eng.
https://doi.org/10.1117/1.jmi.10.5.054001Mullan, S. M., Evans, N. J., Sewell, D. K., Francis, S. L., Polgreen, L. A., Segre, A. M., & Polgreen, P. M. (2023). Predicting use of a gait-stabilizing device using a Wii Balance Board. In M. Błaszczyszyn (Ed.), PLOS ONE (Vol. 18, Issue 10, p. e0292548). Public Library of Science (PLoS).
https://doi.org/10.1371/journal.pone.0292548Vecchi, J. T., Mullan, S., Lopez, J. A., Rhomberg, M., Yamamoto, A., Hallam, A., Lee, A., Sonka, M., & Hansen, M. R. (2023). Sensitivity of CNN image analysis to multifaceted measurements of neurite growth. In BMC Bioinformatics (Vol. 24, Issue 1). Springer Science and Business Media LLC.
https://doi.org/10.1186/s12859-023-05444-4Hyer, D. E., Caster, J., Smith, B., St-Aubin, J., Snyder, J., Shepard, A., Zhang, H., Mullan, S., Geoghegan, T., George, B., Byrne, J., Smith, M., Buatti, J. M., & Sonka, M. (2023). A Technique to Enable Efficient Adaptive Radiation Therapy: Automated Contouring of Prostate and Adjacent Organs. In Advances in Radiation Oncology (p. 101336). Elsevier BV.
https://doi.org/10.1016/j.adro.2023.101336