Automatic identification method of thyroid tumor ultrasound image based on faster r-cnn

Abstract

The invention discloses an automatic identification method of a thyroid tumor ultrasound image based on faster r-cnn. The method comprises the following steps: performing data enhancement on a markedthyroid tumor ultrasound image, and increasing the number and scale of training samples; performing feature extraction on an image data set by using a resnet-50 network model; generating a proposal window (proposals) by using a region proposal network RPN, and mapping the proposal window onto a feature map to generate a region proposal box; then causing each RoI to generate a feature map with a fixed size through RoI pooling; and finally performing joint training on a classification probability and border regression by using softmax Loss and softmax L1 Loss. By adoption of the method disclosedby the invention, the tumor ultrasound image does not need to be manually segmented, end-to-end network training can be achieved, and the identification rate is improved by data enhancement.

Description

technical field [0001] The present invention relates to the technical field of medical image recognition, in particular to a faster r-cnn-based automatic recognition method for ultrasound images of thyroid tumors. Background technique [0002] In recent years, with the improvement of hardware, the wave of the rise of artificial intelligence has brought people an intelligent life, and it is deep learning that has brought a breakthrough inflection point for the development of artificial intelligence. Deep learning can greatly reduce the process of artificially extracting features, and is widely used in image processing, natural language processing and other tasks. And deep learning technology is also slowly applied in the medical field. The interpretation of medical images usually depends on doctors, which has strong subjectivity. Under high-intensity work, doctors may miss or misdiagnose a large number of consecutive scans. [0003] Traditional medical image recognition uses...

AI Technical Summary

Problems solved by technology

And deep learning technology is also slowly applied in the medical field. The interpretation of medical images usually depends on doctors, which is highly subjective. Under high-intensity work, doctors may miss or misdiagnose a large number of continuous film readings.

[0003] Traditional medical image recognition uses computer-aided diagnosis system (CAD) to assist doctors in analyzing and judging medical data. It gradually develops into medical image recognition by using image segmentation technology combined with machine learning. Recently, deep learning technology has also been used. Instead of machine learning methods, but still rely on image segmentation technology and then use machine learning or deep learning methods

Images