Image segmentation method based on cascade convolution

Abstract

The invention discloses an image segmentation method based on cascade convolution, and relates to the technical field of image segmentation. The image segmentation method based on cascade convolutioncomprises the following steps of step S1, collecting medical image information of a plurality of lesion areas; step S2, performing artificial edge labeling on the lesion area of the collected medicalimage information layer by layer to obtain label information; step S3, carrying out standardized preprocessing on the label information to obtain a two-dimensional data set; step S4, establishing a multi-layer two-dimensional convolutional neural network based on cascade convolution, and training the multi-layer two-dimensional convolutional neural network by using a two-dimensional data set to obtain a neural network model; step S5, inputting medical image information of a patient to be segmented, and performing standardized preprocessing to obtain a two-dimensional data set to be processed;and step S6, inputting a to-be-processed two-dimensional data set into the neural network model, and automatically segmenting the medical image information of the to-be-segmented patient to obtain a lesion area of the patient.

Description

technical field [0001] The present invention relates to the technical field of image segmentation, in particular to an image segmentation method based on cascade convolution. Background technique [0002] The segmentation of medical images has always been highly valued by people, and the segmentation algorithm is the key factor affecting the segmentation effect. Therefore, scholars continue to study the segmentation algorithm. According to the characteristics of medical images, many excellent algorithms have emerged, such as boundary-based Segmentation methods, region-based segmentation methods, etc., and in the corresponding era, assisted medical diagnosticians in diagnosis and produced positive results. [0003] However, with the gradual enhancement of people's health awareness and the continuous development of medical level, higher requirements are put forward for the accuracy and efficiency of seeing a doctor. It is hoped that computers can be used to read CT (Computed ...

AI Technical Summary

Problems solved by technology

[0011] The end-to-end image semantic segmentation method is based on a supervised machine learning algorithm, which requires a large number of pixel-level labeled samples. According to the existing literature research, the time-consuming of pixel-level labeling of images is the cost of calibrating the position of objects in the image. 15 times that of time, therefore, it is difficult to obtain a large number of pixel-level annotated images, which limits the application range of end-to-end methods

Images