Computer aided scanning method for medical device, medical device, and readable storage medium
A computer aided scanning method for a medical device is provided in the present invention, comprising step 1 : recognizing and analyzing a pre-scan image through a pre-trained neural network to determine and identify a region of interest in the pre-scan image; and step 2 : determining, according to feature information of the identified region of interest, scanning parameters for further scanning of the region of interest. A medical device employing the above method and a computer readable storage medium for performing the method are further provided in the present invention. The method, the medical device, and the readable storage medium provided by the present invention can automatically identify a region of interest, determine a corresponding auxiliary line and subsequent scanning parameters, and improve the scanning efficiency and accuracy of the medical device.
1. A computer aided scanning method for a medical device, comprising:
recognizing and analyzing a pre-scan image through a pre-trained neural network to determine and identify a region of interest in the pre-scan image;
determining, according to feature information of the identified region of interest, scanning parameters for further scanning of the region of interest; and
determining a feature point in the identified region of interest, and determining the auxiliary line based on at least two of the feature points;
wherein the scanning parameters for further scanning of the region of interest are determined by determining an auxiliary line in the pre-scan image;
wherein the feature point comprises a geometric center point of the identified region of interest, and the auxiliary line is determined by drawing a perpendicular line based on two adjacent geometric center points.
2. The computer aided scanning method for a medical device of claim 1 , wherein theneural network is trained by the following steps:
capturing a plurality of pre-scan images to obtain a pre-scan image set;
marking regions of interest on the pre-scan images to obtain a training set; and
training a neural network by using the pre-scan image set as an input and the training setas an output to obtain the pre-trained neural network.
3. The computer aided scanning method for a medical device of claim 1 , wherein the method further comprises: converting the pre-scan image acquired when pre-scanningof the medical device is performed into a pre-scan image in a red, green, and blue (RGB) format, and the pre-trained neural network recognizes and analyzes the pre-scan image in the red, green, and blue (RGB) format, and outputs a binary image having the identified region of interest.
4. The computer aided scanning method for a medical device of claim 1 , wherein the featurepoint comprises a vertex of the identified region of interest, and the auxiliary line is determined by fitting a straight line based on two adjacent groups of vertexes.
5. A medical device, comprising:
a scanning portion, configured to capture a pre-scan image; and
a computing portion, comprising:
a pre-trained neural network, wherein the pre-trained neural network is configured to recognize and analyze the pre-scan image to determine and identify a region of interest in thepre-scan image; and
the computing portion is configured to determine, according to feature information of the identified region of interest, scanning parameters for further scanning of the region of interest;
wherein the computing portion is configured to determine the scanning parameters for further scanning of the region of interest by determining an auxiliary line in the pre-scan image;
wherein the computing portion is configured to determine a feature point in the identified region of interest, and determine the auxiliary line based on at least two of the feature points; and
wherein the computing portion is configured to determine a geometric center point of the identified region of interest as the feature point, and determine the auxiliary line by drawing a perpendicular line based on two adjacent geometric center points.
6. The medical device of claim 5 , wherein the computing portion further comprises a pre-processing portion, configured to convert the pre-scan image acquired when pre-scanning of the medical device is performed into a pre-scan image in a red, green, and blue (RGB) format, and the pre-trained neural network recognizes and analyzes the pre-scan image in the red, green, andblue (RGB) format, and outputs a binary image having the identified region of interest.
7. The medical device of claim 5 , wherein the computing portion is configured to determine a vertex of the identified region of interest, and determine the auxiliary line by fittinga straight line based on two adjacent groups of vertexes.