AUTOMATED TUMOR IDENTIFICATION DURING SURGERY USING MACHINE-LEARNING

• Main Authors: ERKAMP RAMON Q, MERAL FAIK C, BHARAT SHYAM
• Format: Patent
• Language: Chinese; English
• Published: 01.01.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

An ultrasound (US) system (10) includes a US scanner (14) and a US probe (12) operatively connected to the US scanner. At least one electronic processor (20) is programmed to: control the US scanner and US probe to acquire a series of preoperative images of a tumor and surrounding blood vessels in a region of interest (ROI) of a patient; provide a graphical user interface (GUI) (26) via which theacquired preoperative images are labeled with contours of the tumor and the surrounding blood vessels in the ROI; tune a trained neural network (30) for the patient using the labeled preoperative images to generate a patient-tuned trained neural network; perform live imaging by controlling the US scanner and US probe to acquire live images of the tumor and the surrounding blood vessels in the ROIof the patient; input the live images to the patient-tuned trained NN to output live contours of the tumor and the surrounding blood vessels; and control a display device (24) to display the live images with the live contours