Smart analysis method for liver tumors based on ultrasonic scanned images and deep learning algorithms

• Main Authors: LIN, DA-XIANG, ZHOU, PEI-LIAN, NIAN, XIAO-JING
• Format: Patent
• Language: Chinese; English
• Published: 01.06.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION; TESTING

A smart analysis method for liver tumors uses ultrasonic detection in combination with a deep learning algorithm to determine a risk of benignancy and malignancy of a liver tumor. The smart analysis method for liver tumors relies on experienced abdominal ultrasound specialists marking ultrasound images with liver tumor imaging points. Parameters and coefficients of such experience data are used, through training with the deep learning algorithm, to establish an inference model of which accuracy rate can be up to 86%. As such, a reference basis is provided to a physician for diagnosis of liver tumors by subjecting an ultrasonic inspection scanning image to the smart analysis method for liver tumors to provide immediate assistance for the physician or an ultrasound technician in determining risks of benignancy and malignancy of the liver tumor.