Acute cerebral apoplexy lesion segmentation method based on small sample learning

Abstract

The invention discloses an acute cerebral apoplexy lesion segmentation method based on small sample learning. The method comprises the steps of training a convolutional neural network by a data samplewith an image-level label, and using the classification accuracy of an image as a measurement index; constructing a new convolutional neural network by using the trained convolutional neural network,and constructing an end-to-end convolutional neural network by using a feature map obtained by the trained network from the input image; fixing trained convolutional layer parameters, training a newly constructed convolutional neural network by using a small number of data samples of pixel-level tags, and taking the segmentation precision of the image as a measurement index; and after the training is finished, verifying the segmentation effect of the network on the test set of the pixel-level label. According to the method, only a small number of pixel-level label data samples and a small number of image-level label data samples are used, so that the cost of labeling data is greatly reduced, the engineering operability is enhanced to a certain extent, and doctors are assisted in clinicaldiagnosis of acute cerebral stroke patients.

Description

technical field [0001] The invention relates to an acute cerebral apoplexy lesion segmentation method based on small sample learning proposed for the clinical diagnosis of acute cerebral apoplexy patients. Background technique [0002] Acute ischemic stroke is an acute cerebrovascular disease that seriously threatens human health. According to the latest epidemiological studies, the age-standardized prevalence, annual incidence and mortality of stroke in China are 1114.8 / 100,000 and 246.8 / 100,000 and 114.8 / 100,000, the high morbidity and disability rate caused heavy economic burden to the government. Early diagnosis and treatment of acute ischemic stroke can significantly improve the prognosis of patients. Magnetic resonance examination is crucial for its early diagnosis. Quantitative information such as lesion size, signal, and location have great guiding significance for subsequent treatment plans. Rapid and accurate analysis of the above image information will help clin...

AI Technical Summary

Problems solved by technology

[0005] At present, the acute stroke lesion segmentation methods based on small-sample learning are still relatively scarce, and most of them are still segmented in a supervised manner based on deep learning. Therefore, it is necessary to study a data sample that only needs a small number of pixel-level labels and some image-level labels. A method for effectively segmenting acute stroke lesions with just a few data samples

Images