U of T Technology & Startup Explorer

Machine learning architecture offers a novel, high-fidelity means of assessing lung physiology during the performance of (monofrequency) oscillometry tests.

Pulmonary Embolism (PE) diagnosis using machine learning (ML) techniques on CT pulmonary angiography (CTPA) is transforming the field of medical imaging. PE is a life-threatening condition where blood clots block the pulmonary arteries, requiring timely and accurate detection to improve patient outcomes. Traditional training and development of ML models for PE diagnosis involve extensive annotation, which is resource-intensive. To make these applications practical, the team has developed optimized training strategies, model architectures, and deployment pipelines for efficient PE detection.

Machine-learning based methods to improve traffic flow through adaptive signal control.

AI-powered cyber threat detection honeypot technologies for ICS, CPS, and IoT that actively engage attackers and draw out more information about their tactics, providing organizations with the intelligence they need to better defend their systems.

This technology includes a suite of inventions, including a fully-functional coded-exposure-pixel (CEP) camera prototype, a novel programmable CMOS sensor, and a method for adaptive adjustment of exposure of every pixel, based on changes in the brightness of the scene for that pixel to extend dynamic range at native sensor resolution.

Toronto Annotation Suite (TORAS) is a web-based AI-powered annotation platform.

Based on thermal and optical sensing analysis of digital imaging, this technology allows for rapid measurement of photoplethysmogram (PPG), temperature, respiratory rate, and heart rate beyond conventional distance limitations (e.g. at distances more than 1m), with the ability to add other components (e.g. tissue oxygenation and blood pressure) in the future.

A DCE-MRI acquisition and reconstruction package that enables more accurate quantification of physiological parameters in larger volumes than any state-of-the-art method. By first performing a high-temporal (rapid), high spatial (hifi) acquisition of anatomical details in the image set, each time frame is reconstructed with a high degree of precision and accuracy.

SiMLQ is a process mining solution that uses event data and machine learning to automate the representation, analysis, and optimization of business processes. This enables better allocation of resources, increased productivity, and reduced costs in service systems.

The platform allows for clinical-grade data analysis from wearable sensors (e.g. smartwatches, mobile devices) through proprietary machine learning (ML)-based algorithms that extract clinically relevant data and filter out unreliable sensor data. This platform can provide real-time feedback on patient health, generate more accurate predictions, and enable actionable insights and recommendations to improve care.

This technology is an optimized version of the Ring-Learning-With-Errors (RLWE) Fully Homomorphic Encryption (FHE) system. This proprietary system maintains encrypted data privacy of communications while still allowing cloud operations to be carried out on the encrypted data, such as Secure Search and Spam-Filter Applications.

A software platform that leverages statistical inference and machine learning to make more informed decisions.

Hippocamera is a memory augmentation technology that aides in the recall and storage of memories. The technology features novel methods to tag and replay recorded moments to promote rich reliving and storage of experiences.

JALI provides products and services for the complete automation of high-end lip sync and facial animation for ultimate animator directorial control.

This invention is a platform to improve the functionality of the conventional surface plasmon resonance-based sensors.

This invention is a system that presents an original contribution in the form of a knowledge base implemented as an Web Ontology Language (OWL). This system also combines customized wayfinding and recommender systems to support this knowledge base and automate the communication process.

A clinically-relevant stimulation system can induce directed migration (translocation) of neural precursor cells using asymmetric balanced biphasic electric fields.

This invention builds around an online system/service that tries to leverage advancements in Building Information Models (BIM), energy-efficiency simulation tools and online social network analysis methods to enable a data-driven approach to building design, planning, construction and maintenance.

CrossShade allows the creation of 3D-looking shaded production drawings from initial concept sketches.

The technology uses a combination of sensor information, such as the accelerometer and gyroscope (e.g. from mobile phones or wearable inertial sensors), in addition to WiFi signal strength, to build a system that can achieve accurate location estimation technique for indoor environment.

iTest is a turn-key and modular software and hardware platform for testing physical motors remotely over the Internet.

Monte Carlo Lights is a novel ATSC approach that combines state-of-the-art reinforcement learning and Monte Carlo tree search to optimize traffic flow.

Rhea is a rehabilitation platform and startup grounded in science that active recovery to heal and care for the brain.

PhenoTips is a B2B digital health spinout from U of T and SickKids, helping healthcare systems prepare for a future when genetics is a critical part of every patient's routine care. Healthcare workers use PhenoTips through their existing EHRs to manage critical data for genomic medicine,

ODAIA is business intelligence software that enables organizations to understand, predict, and optimize their customer's journeys. The technology leverages AI to facilitate the exploration, analysis, summarization, and optimization of a customer's journey, from awareness to purchase.

This opportunity is a portfolio of hardware and software techniques that seamlessly accelerate AI/ML applications, while saving on-chip and off-chip memory, bandwidth, and processing power. These compute and compression methods have been shown to deliver a 3x boost in processing speed with 2x-4x increase in storage capabilities (up to 10x for natural language processing).

High-performance software solutions and advanced algorithms for cryo-EM data processing.

AutoScribe uses hands-free speech recognition and Artificial Intelligence to help reduce time consuming manual clinical documentation, freeing clinicians to place their focus where it should be – on their patients.

Invasive and non-invasive hardware and software for vital signs monitoring

Treatment of overactive bladder and other disorders via non-invasive electrical neurostimulation.

A method and model for simulating general multi-phase network growth, inspired by the simplified, stepwise behaviours of a unicellular slime mould.

Quantum-proof cybersecurity products and enabling technologies for the Quantum Internet. These technologies offer quantum-safe communication products ready for today's infrastructure, while building key components of the Quantum Internet, including Quantum Repeaters, Quantum Communication Protocols, and Quantum Network Simulators.

A method to extract, assess, and visualize information from electroencephalography (EEG) readings.

Electronic Systems for Monitoring, Diagnosis, and Control of Physiological Disorders

Centivizer is a modular system that physically, cognitively, and socially stimulates individuals with dementia by providing self-initiated, reward-based activities that can be used 24/7 without needing caregiver support.

BinPro combines static analysis, graph matching and ML to detect and mitigate the threat of maliciously inserted backdoors by conducting binary source code audits.

The two inventions captured in this technology allow for the representation, learning, and interactive editing of color palettes through a novel interface for creating color themes.