Ultrasound image hybrid training method based on deep learning

Abstract

The invention relates to the field of medical image processing, and aims to provide an ultrasonic image hybrid training method based on deep learning. Including steps: using the ultrasound image data of different examination parts in the database to prepare training sets, validation sets and test sets; preprocessing each data set; constructing and training a convolutional neural network, using multi-channel output during training, but only A single channel participates in backpropagation; testing on a trained convolutional neural network. The present invention combines multiple ultrasound data sets of different diseases to train together, so that the convolutional neural network model can access more samples, alleviate the problems of few data set samples and single cases, and further improve the training of the model on a single task. Performance. The present invention completes multiple ultrasound tasks through the same convolutional neural network, which can reduce training and deployment costs and improve user experience.

Description

technical field [0001] The present invention relates to the field of medical image processing, in particular to an ultrasonic hybrid training method based on deep learning. Background technique [0002] Ultrasound imaging is a non-invasive examination method. Ultrasound imaging examination has the advantages of cheap, non-destructive, reproducible, and high sensitivity, and is the preferred imaging examination method for disease screening. However, affected by the visual fatigue of medical workers and the level of diagnosis, the results of ultrasound diagnosis have a lot of subjective factors, and the diagnosis process is laborious and time-consuming. [0003] Deep learning can directly process raw data (such as ultrasound images) and automatically learn mid-level and high-level abstract features from it. It can perform various tasks of automatic analysis of ultrasound images, such as lesion / nodule classification, tissue segmentation, and object detection. Using deep lear...

AI Technical Summary

Problems solved by technology

However, the current ultrasound data set is difficult to meet the needs of deep learning

On the one hand, the number of public data sets is often limited; on the other hand, although the hospital has a large amount of ultrasound image data, it is difficult for the outside to obtain a large amount of data from the hospital due to the "data island"

Images