Automated tumor identification during surgery using machine-learning
摘要:
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 the acquired 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 ROI of 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 superimposed.
信息查询
0/0