6/23/2026 Illinois Physics
NVIDIA will provide an RTX PRO 6000 Server Edition GPU to support Neubauer's project, ‘Early Cancer Detection through Extreme-Scale Anomaly Detection via Quantum ML.’
Written by Illinois Physics
Illinois Physics Professor Mark Neubauer has received an award from the NVIDIA Academic Grant Program to support his project, “Early Cancer Detection through Extreme-Scale Anomaly Detection via Quantum ML.” NVIDIA will provide an RTX PRO 6000 Server Edition GPU to support the project, valued at upwards of $15,000.
The project explores quantum artificial intelligence (quantum AI), an emerging interdisciplinary field that combines quantum computing and artificial intelligence to develop new algorithms for analyzing complex, high-dimensional data.
Unlike classical computation using binary bits, quantum computation exploits quantum bits (qubits) that can exist in superpositions of states and exhibit entanglement, enabling new ways of representing and manipulating information. Although practical fault-tolerant quantum computers remain a long-term goal, current quantum AI research, including Neubauer’s project, investigates hybrid quantum-classical algorithms that leverage quantum circuits alongside powerful classical AI models and GPU-accelerated quantum simulations.
Neubauer's project aims to develop a novel hybrid quantum-classical AI framework that provides transparent, actionable insights into subtle anomalies detected in high-dimensional data. Traditional anomaly detection methods often struggle when anomalies are weak, high-dimensional, or poorly represented in training data. Quantum AI approaches to anomaly detection aim to address these challenges.
“By encoding data into high-dimensional quantum feature spaces, complex correlations and subtle distinctions in data become more separable,” said Neubauer. “Integrating quantum algorithms—such as quantum kernels, variational quantum circuits, and quantum autoencoders—with classical AI techniques into hybrid systems could lead to ultra-sensitive anomaly detectors for a variety of applications.”
Neubauer's project will focus initially on identifying subtle patterns in medical image data that may indicate the earliest stages of cancer. While modern AI systems have demonstrated remarkable capabilities in image analysis, detecting small or diffuse early-stage abnormalities remains a major challenge due to weak signals, limited training examples, and the need for transparent predictions that clinicians can trust.
“Early detection is one of the most powerful tools we have for reducing cancer mortality, but the earliest signs of disease can be extremely difficult to distinguish from normal biological variation and imaging noise,” said Neubauer. “Our goal is to investigate whether quantum AI techniques can provide new ways to identify these weak signatures while producing interpretable insights that can ultimately help clinicians make more informed decisions.”
Beyond medical applications, these approaches hold promise for addressing the challenge of rare event identification common in fundamental science and engineering, such as particle physics research and confinement of high-temperature plasmas for nuclear fusion.
This project builds on Neubauer’s broader research program at the intersection of AI, high-performance computing, and scientific discovery.