Automatic classification method and device for mammary gland medical ultrasonic images

Abstract

The invention provides an automatic classification method and device for mammary gland medical ultrasonic images. The method comprises the steps of preprocessing an obtained target mammary gland medical ultrasonic image; performing HSV color space conversion on the preprocessed target breast medical ultrasonic image to obtain a hue H channel feature corresponding to the target breast medical ultrasonic image; and taking the hue H channel feature corresponding to the preprocessed target breast medical ultrasonic image as a prediction sample, inputting the prediction sample into a preset targetdeep convolutional neural network, and taking the output of the target deep convolutional neural network as a classification result of the target breast medical ultrasonic image. The breast medical ultrasonic image classification method and device can effectively improve the accuracy and efficiency of feature recognition of the breast medical ultrasonic image, can effectively and reliably improvethe high efficiency and intelligent degree of the classification process of the breast medical ultrasonic image, and can improve the accuracy of the classification result of the breast medical ultrasonic image.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an automatic classification method and device for breast medical ultrasound images. Background technique [0002] With the rapid development of science and technology in the medical field, artificial breast medical image segmentation, feature extraction and classification techniques can no longer meet the automation needs of modern breast medicine. Therefore, in order to effectively adapt to the current development trend of medical imaging big data intelligent diagnosis, how to classify breast medical images with a higher degree of intelligence has become an important medical topic. [0003] In the prior art, the method of classifying breast medical images is to use a restricted Boltzmann machine (RBM) to design a two-layer feature extractor to extract and learn task-related features, and then use a support vector machine (SVM) to output breast Image data feat...

AI Technical Summary

Problems solved by technology

[0004] However, because the two-layer feature extractor is not a deep learning model in the strict sense, the existing classification methods for breast medical images are not intelligent enough, and its shallower network results also lead to poor quality and quantity of extracted features. Therefore, the existing classification methods of breast medical images have the problems of low classification accuracy and poor performance

Images