Reads Light's Polarization to Spot Cancer Left Behind in Dog Tumors

A study in Veterinary Oncology from researchers at The Ohio State University explores faster margin assessment for dogs undergoing surgery for soft tissue sarcomas. When surgeons remove a tumor, it’s critical to know if cancer touches the surgical edge—so that a “positive” margin can mean a higher risk of recurrence and a possible second operation. The researchers report a deep learning system that reads polarization-sensitive optical coherence tomography (PS-OCT) images of excised tumor margins and flags residual cancer within minutes of surgery, with an area under the ROC curve of 0.989 and 91% accuracy. The approach builds on OCT’s near-infrared, micrometer-resolution imaging and adds polarization contrast tied to tissue birefringence.