Javier Murgoitio-Esandi

I am Ph.D student with more than 4 years of experience specializaing in the theory and application of generative deep learning methods. I am part of the Computation and Data Driven Discovery Group at the Aerospace and Mechanical Engineeirng Department of the University of Southern California, where I started my Ph.D. studies in the Fall of 2020 as part of Professor Assad Oberai’s research group. During the 2023-2024 academic year, I worked as an intern researcher at Sandia National Labs conducting research on uncertainty quantification in deep learning.

My research focuses on developing generative deep learning methods applied to anomaly detection and uncertainty quantification in medical imaging. My work on anomaly detection includes the study and development of methods such as autoencoders and energy-based models to identify rare biological events in immunofluorescent liquid biopsy images, with the end goal of aiding cancer diagnosis. As part of this project, I have also developed a foundation model for immunofluorescent microscopy images. Additionally, my research on uncertainty quantification involves the development and application of techniques such as generative adversarial networks and diffusion models to solve inverse problems in the context of elastography imaging.

As a consequence of my research and studies I am expert in Generative AI, and have extensive knowledge on foundation models and large language models.

selected publications

Unsupervised Detection of Rare Events in Liquid Biopsy Assays

Javier Murgoitio-Esandi, Dean Tessone, Amin Naghdloo, and 9 more authors

bioRxiv, 2025

Abs

The use of liquid biopsies in the detection, diagnosis and treatment monitoring of different types of cancers and other diseases often requires identifying and enumerating instances of analytes that are rare. Most current techniques that aim to computationally isolate these rare instances or events first learn the signature of the event, and then scan the appropriate biological assay for this signature. While such techniques have proven to be very useful, they are limited because they must first establish what signature to look for, and only then identify events that are consistent with this signature. In contrast to this, in this study, we present an automated approach that does not require the knowledge of the signature of the rare event. It works by breaking the assay into a sequence of components, learning the probability distribution of these components, and then isolating those that are rare. This is done with the help of deep generative algorithms in an unsupervised manner, meaning without a-priori knowledge of the rare event associated with an analyte. In this study, this approach is applied to immunofluorescence microscopy images of peripheral blood, where it is shown that it successfully isolates biologically relevant events in blood from normal donors spiked with cancer-related cells and in blood from patients with late-stage breast cancer.Competing Interest StatementThe authors have declared no competing interest.
CMAME

Solution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty

Deep Ray, Javier Murgoitio-Esandi, Agnimitra Dasgupta, and 1 more author

Computer Methods in Applied Mechanics and Engineering, 2023
CMAME

Conditional score-based diffusion models for solving inverse elasticity problems

Agnimitra Dasgupta, Harisankar Ramaswamy, Javier Murgoitio-Esandi, and 5 more authors

Computer Methods in Applied Mechanics and Engineering, 2025