I-Corps: Translation Potential of a Quantum Machine Learning Framework for Multimodal Neuroimaging and Neurophysiological Data Analysis

This I-Corps project is based on the development of a technology that merges quantum computing with artificial intelligence designed to analyze complex medical data and images. Healthcare providers and clinical researchers struggle to accurately identify diseases when dealing with highly complex data that lacks labeled, abnormal examples. This limitation restricts the ability of the wider medical community to efficiently process neurological data, increasing manual workloads and delaying crucial discoveries in large-scale clinical research. This technology provides an advanced software platform that identifies abnormal structures and latent patterns in complex scans without relying heavily on massive, pre-labeled datasets. Users may include research hospitals, imaging centers, and health technology companies, without focusing on a single diagnostic application, and can be delivered through a software-as-a-service or analysis-as-a-service model. This may provide faster, more accessible, and more accurate medical data analysis, ultimately accelerating disease discovery and improving public health research capabilities. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of a multimodal quantum machine learning (qML) framework for unsupervised anomaly detection in medical imaging. This technology is designed to process magnetic resonance imaging (MRI), functional MRI (fMRI), and electroencephalography (EEG) data using quantum entropy deviations, quantum vision transformers, and quantum feature extractors. Unlike traditional classical artificial intelligence systems that require extensive task-specific training and massive labeled datasets, this qML method leverages deterministic quantum computation to estimate quantum entropy and perform similarity-based learning. The technology has been used to demonstrate that grouping image regions by entropy deviations reveals latent structures and isolates anomalies from healthy reference clusters. Users benefit by receiving interpretable outputs, such as anomaly maps, cluster-based summaries, and anomaly distribution reports that reduce manual analysis time and support exploratory multimodal research workflows. In addition, this technology contributes to the field of quantum computing in healthcare by providing scalable decision-support tools for neuroimaging and neurophysiological data analysis. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.