Thyroid ultrasound image nodule automatic positioning and identifying method based on USFaster R-CNN

Abstract

The invention discloses a thyroid ultrasound image nodule automatic positioning and identifying method based on USFaster R-CNN, and belongs to the field of artificial intelligence and deep learning. The method comprises the steps of preprocessing a thyroid ultrasound image, building a deep neural network model, and training and optimizing the network model, wherein the deep neural network model comprises a bottom convolution feature extraction network, a candidate box generation network, a feature map pooling layer and a classification and candidate box regression network. A deep learning method is used to realize thyroid ultrasound image feature automatic extraction, candidate box automatic generation, screening and position correction. An automatic positioning and identification functionof thyroid nodules is realized. The method can effectively assist doctors in thyroid ultrasound image diagnosis, improve the objectivity and accuracy of diagnosis, and effectively reduce the workloadof doctors and the omission ratio of small target nodules.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and deep learning, in particular to a method for automatic positioning and recognition of nodules in thyroid ultrasound images based on USFaster R-CNN (a faster regional convolutional neural network for ultrasound images). Background technique [0002] In recent years, with the development of imaging technology, the detection rate of thyroid nodules has increased significantly. Thyroid nodules are very common, and about one-third of adults find thyroid nodules during examination. Although most of them are benign, about 4-5% of thyroid nodules are at risk of becoming malignant. Ultrasound (US) is widely used in the diagnosis of thyroid diseases, but the diagnostician has a lot of subjectivity when evaluating tumors through ultrasound images, which largely depends on the clinical experience of different doctors. Thyroid computer-aided diagnosis system (CAD) using artificial intelligence is an...

AI Technical Summary

Problems solved by technology

For medical images, there are great limitations in terms of training data. The labeling of medical images requires a lot of professional knowledge and energy. The number of medical images of some rare diseases is far from the standard for training.

At the same time, compared with daily images, ultrasound images have fewer features (lack of color features), low contrast, and no obvious difference between benign and malignant nodules, which is a fine-grained classification problem.

Some nodules are small in size, and the diagnostician may miss small nodules due to visual fatigue or lack of experience when working for a long time

Images