Transfer learning and feature fusion-based ultrasonic thyroid nodule benign and malignant classification method

Abstract

The invention discloses a transfer learning and feature fusion-based ultrasonic thyroid nodule benign and malignant classification method. The method comprises the following steps of firstly preprocessing an ultrasonic image and zooming the ultrasonic image to a uniform size; extracting traditional low-level features of the ultrasonic image; extracting high-level semantic features of the ultrasonic image by using a model obtained in a natural image through deep neural network training through a transfer learning method; fusing the low-level features with the high-level features; carrying out feature screening by utilizing distinction degree of benign and malignant thyroid nodules so as to obtain a final feature vector which is used for training a support vector machine classifier; and carrying out final thyroid nodule benign and malignant classification. According to the method disclosed by the invention, the low-level features and the high-level features are fused, and salient feature screening is carried out, so that the problem that the ability of single features for describing thyroid nodule features on the level of semantic meaning is insufficient is solved, and the classification precision is effectively improved; and through importing the transfer learning, the problems that the medical sample images are few and the deep features can not be obtained by direct training are solved.

Description

technical field [0001] The invention belongs to the technical field of medical image classification, is suitable for ultrasonic thyroid classification, and specifically relates to a method for classifying benign and malignant ultrasonic thyroid nodules based on migration learning and feature fusion. Background technique [0002] Ultrasonography is one of the most valuable diagnostic methods for thyroid nodules. When ultrasonic waves propagate in the human body, due to the different acoustic impedance and attenuation characteristics of different tissues, they show different echo intensities. Benign and malignant nodules appear differently in ultrasound images, so image recognition and image classification methods can be used to automatically classify and distinguish benign and malignant thyroid nodules. This method can provide doctors with auxiliary diagnostic means, reduce the pressure of doctors' clinical diagnosis, and solve the problem of over-reliance on doctors' subjec...

AI Technical Summary

Problems solved by technology

The difficulty of introducing this feature into ultrasound image classification is that in the medical field, such a large data set cannot be obtained to train a targeted deep network, and a small-scale medical image data set (usually around hundreds) is used to train a network containing With a deep network of millions of parameters, it is foreseeable that the training will fall into overfitting

Images