About

I am an Advanced Scientific Application Developer at the Department of Medical Physics, Memorial Sloan Kettering Cancer Center (MSKCC), with 10+ years of experience in Bioinformatics, Image Analysis, and Statistical Modeling.

I was previously a Research Assistant at Purdue University, where I earned a Master's degree in Electrical and Computer Engineering. The first sparks of my interest in Signal and Image Processing were lit at Anna University, where I earned my Bachelor's degree.

Projects

Research software

  • CERR (Key contributor, MSKCC)
    • The Computational Environment for Radiological Research is a free, open-source research platform, used worldwide to prototype radiotherapy and image analysis algorithms (peer-review cited 700+ times). I've served as a core member of CERR's development team for 7+ years, leading the development of key components including for radiomics and radiotherapy outcomes analyses, building and deploying auto-segmentation models, and Python compatibility.

  • ROE (Lead developer, MSKCC)
    • The Radiotherapy Outcomes Estimator, a plugin to CERR for patient-specific prescription selection, using published NTCP and TCP models to quantify the risks and benefits of different treatment protocols.

Radiomics (Lead developer, MSKCC)

  • I represent CERR in the Image Biomarker Standardization Initiative (IBSI), and adapted CERR's radiomics toolbox to meet its proposed standards, incorporating unit tests and cross-software comparisons for ongoing compliance.

Image segmentation

  • Machine learning models (Lead engineer, MSKCC
    • The deep-learning auto-segmentation tools I developed have been adopted for clinical use at MSKCC. As a result, we have revised guidelines for limiting induced complications through RT for head and neck cancer treatment, and improved clinical efficiency, accuracy, and consistency.

  • Statistical models (Graduate Research Asst., Purdue University)
    • I formulated the task of estimating a group-representative functional network from a cohort of fMRIs as a MAP-MRF estimation problem. The approach was validated on simulations as well as real-world fMRI recordings of individuals suffering depression vs. a control group.

All publications

Selected publications

  • Iyer, A., ... & Jackson, A. (2023). ROE (Radiotherapy Outcomes Estimator): An Open-Source Tool for Optimizing Radiotherapy Prescriptions. Computer Methods and Programs in Biomedicine, 107833. | PDF
  • Iyer, A., ... & Apte, A. P. (2022). Prospectively-validated deep learning model for segmenting swallowing and chewing structures in CT. Physics in Medicine & Biology, 67(2), 024001. | Open Access
  • Chen, I., Iyer, A*., ... & Jackson, A. (2023). Simulating the potential of model-based individualized prescriptions for ultracentral lung tumors. Advances in Radiation Oncology, 101285. | Open Access
  • Apte, A. P., Iyer, A*., ... & Deasy, J. O. (2020). Library of deep-learning image segmentation and outcomes model-implementations. Physica Medica, 73, 190-196. | Open Access
  • (Cover page article) Apte, A. P., Iyer, A.*, ... & Deasy, J. O. (2018). Extension of CERR for computational radiomics: a comprehensive MATLAB platform for reproducible radiomics research. Medical physics, 45(8), 3713-3720. | Open Access

*co-first author

    Selected talks

  • Deep Learning-Based Auto-Segmentation of Swallowing and Chewing Structures. American Association of Physicists in Medicine, 2020.
  • Machine Learning-Based Post-Processing Method for Improved Segmentation of Parotid Glands. American Association of Physicists in Medicine, 2018.

    Selected poster presentations

  • IBSI-Compatible Scalar Radiomics and Texture Filters in CERR. American Association of Physicists in Medicine, 2023.
  • Simulating Clinical Protocol Accrual in the Radiotherapy Outcomes Estimator (ROE). American Association of Physicists in Medicine, 2022.
  • Deploying Deep Learning-Based Image Segmentation Models Via CERR. American Association of Physicists in Medicine, 2021.
  • Personalized Optimization of TCP Using NTCP Based Constraints for Ultracentral Lung Tumors. World Conference on Lung Cancer, 2021.
  • Standardizing Patient Orientation to Improve Generalization of Radiomics Models. American Association of Physicists in Medicine, 2019.

  • Painting

  • Photography