How a $400,000 University Fund Is Fast-Tracking AI That Reads Cancer Slides and Diagnoses Burns in Seconds

The State University of New York has committed $400,000 to eight faculty-led technology projects that could reshape how clinicians diagnose cancer and assess burn injuries. Among the recipients are two artificial intelligence platforms designed to eliminate diagnostic delays and improve accuracy in high-stakes clinical decisions: an AI system that predicts cancer molecular biomarkers directly from pathology images, and a handheld terahertz scanner that diagnoses burn depth with up to 95% accuracy—far exceeding the 60-65% accuracy of current methods.

The funding comes through SUNY's Technology Accelerator Fund, a commercialization bridge program that has invested $5.1 million since 2011 and catalyzed $41 million in follow-on investment across 99 innovations. The awards span five campuses—Albany, Binghamton, Buffalo, Stony Brook, and Upstate Medical University—and target technologies with established intellectual property protection, clear market potential, and technical feasibility.

AI Platform Aims to Eliminate Cancer Testing Delays

Dr. Nancy Guo at Binghamton University is developing ClinSegAI, a secure artificial intelligence platform that extracts molecular biomarker predictions from standard pathology imaging. The technology addresses a persistent bottleneck in oncology: the wait time between tissue biopsy and molecular test results that guide targeted therapy selection. By analyzing pathology slides with AI, ClinSegAI could accelerate treatment decisions without requiring separate molecular testing workflows, potentially shortening the interval between diagnosis and therapy initiation for cancer patients.

The platform's design emphasizes security and integration with existing clinical pathology systems, positioning it as a workflow enhancement rather than a replacement technology. This approach may ease adoption barriers in hospital laboratories already managing high slide volumes under tight turnaround requirements.

Terahertz Imaging Tackles Burn Depth Diagnostic Gap

At Stony Brook University, Dr. M. Hassan Arbab has developed a handheld terahertz imaging scanner that achieves 93-95% accuracy in determining burn depth—a critical assessment that dictates whether patients require surgical intervention. Current clinical methods achieve only 60-65% accuracy, often leading to unnecessary reconstructive surgeries or delayed treatment of deeper burns that require immediate grafting.

The device's portability and precision could transform triage in emergency departments and burn units, where rapid, accurate depth assessment directly impacts patient outcomes and resource allocation. Reducing surgical overtreatment also carries significant cost and recovery time implications for burn patients, who face prolonged rehabilitation when procedures exceed clinical necessity.

Broader Portfolio Targets Pediatric and Critical Care

The funding round also supports CurrentView, a non-invasive 3D monitoring system from the University at Albany that tracks pulmonary perfusion and ventilation in neonatal and pediatric cardiopulmonary patients, and an acute respiratory distress syndrome formulation from SUNY Upstate Medical University designed to target sepsis-induced lung injury affecting approximately 3 million patients annually. Additional awards went to RNA therapeutic delivery systems and quantum sensor technologies.

The Technology Accelerator Fund's 8:1 leverage ratio—$41 million in follow-on investment generated from $5.1 million in seed funding—suggests that university translational programs serve as validated deal flow for commercial partners seeking de-risked early-stage medical technologies. Projects are selected based on intellectual property protection, marketability, commercial potential, technical feasibility, and impact breadth.

Sources

1. SUNY Invests $400,000 in Quantum Sensors, AI Cancer Diagnostics and Burn Scanning Tech — Scienmag.com