Software Embedding-Space Harmonization for Robust Foundation Model Deployment University of Chicago researchers have developed FEATMAP, a computational framework that improves the reliability and interoperability of foundation-model embeddings by reducing unwanted technical or… Reference ID: 26-T-208
Hardware Quantum Sciences Software AI-Enhanced Single-Photon Quantum Detectors This technology uses advanced machine learning algorithms to extract significantly more information from single-photon detector signals than conventional approaches. By analyzing full detector waveforms… Reference ID: 24-T-206 Desired Partnership: Co-development, Licensing IP: Patent Pending
Diagnostics Software Computational Framework For Unraveling Single-Cell Transcriptional Dynamics Novel system using statistical topic modeling and a bursty transcriptional model to analyze spliced and unspliced RNA, revealing precise cell state transitions and dynamics… Reference ID: 22-T-208 Desired Partnership: Co-development, Licensing IP: Patent Pending
Diagnostics Software AI Pipeline For Predicting Oral Cancer Progression An AI-driven system analyzes histopathology images of oral lesions using deep learning, self-supervised learning, and attention methods to predict cancer progression risk with explainable… Interests: Bioinformatics, Biomarker, Pathology, Point-of-Care Reference ID: 24-T-144 Desired Partnership: Co-development, Licensing IP: Patent Pending
Diagnostics Software Deep Learning Uncertainty Quantification System For Reliable Cancer Histopathology Diagnosis Deep learning and uncertainty estimation (via Monte Carlo dropout and cross-validation) to classify digital pathology images by confidence, improving reliability in cancer diagnostics and… Interests: Pathology Reference ID: 24-T-142 Desired Partnership: Co-development, Licensing IP: Patent Pending
Diagnostics Software Deep Learning-Based Diagnostic System For Differentiating Thyroid Tumor Genetic And Histologic Profiles A deep learning system analyzes high-resolution pathology images to predict thyroid tumor subtypes and gene expression patterns, helping distinguish less aggressive cancers from those… Interests: Pathology Reference ID: 24-T-091 Desired Partnership: Co-development, Licensing IP: Patent Pending
Medical Devices Software DeMaND (Decoding using Manifold Neural Dynamics) This method enables high fidelity decoding of neural activity in an interpretable manner with a small training data set. The Unmet Need: Measuring neural… Interests: Neurology Reference ID: 23-T-075 Desired Partnership: Co-development, Licensing IP: Patent Pending
Software Therapeutics Data-Driven Discovery Of Innate Immunomodulators Via Machine Learning-Guided High Throughput Screening Novel machine learning-enable platform to guide in vitro experimental screening and discovery of small molecule immunomodulators to improve immune responses The unmet need:… Interests: Drug Development Tool, Immunotherapy, Machine Learning/Artificial Intelligence, Small Molecules, Vaccines Reference ID: 24-T-043 Desired Partnership: Co-development, Licensing IP: Patent Pending
Hardware Medical Devices Other Software Treatment Adherence Tracking For Sleep Apnea A new mobile health tool for patients with obstructive sleep apnea (OSA) using a novel CPAP adherence metric and enables tracking of lifestyle features… Interests: Cardiovascular Reference ID: 22-T-198 Desired Partnership: Co-development, Licensing IP: Patent Pending
Hardware Software Grace: A Data Scalable Real-Time Video Communication System Real-time video communications are essential to the daily routine of users for online meetings, cloud gaming, and interactive virtual reality. Retransmitting data packets that… Interests: Communications, Communications Reference ID: 23-T-070 Desired Partnership: Co-development, Licensing IP: Patent Pending
Quantum Sciences Research Tools Software Computational-Guided Spin Defect Systems This method enables predictive growth of qubit host materials without the limitations of iterative measurements. The Unmet Need: Proper characterization of qubit host substrate… Interests: Electronic Reference ID: 23-T-065 Desired Partnership: Co-development, Licensing IP: Patent Pending
Diagnostics Medical Devices Software Automatic Prediction of Cancer Recurrence through Machine Learning Deep learning tools are becoming increasingly popular for histologic analyses and have been used to predict tumor biomarker status, clinical variables, tumor subtypes, and… Interests: Machine Learning/Artificial Intelligence, Pathology Reference ID: 21-T-118 Desired Partnership: Co-development, Licensing IP: Patent Pending
