Deep learning-based grape embryo image processing method and device
An image processing device and deep learning technology, applied in the field of hydatidiform mole slice image processing, can solve the problems of low efficiency of clinical diagnosis and detection of hydatidiform mole, and achieve the effect of reducing excessive dependence and improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0044]A method for image processing of hydatidiform mole slices based on deep learning, the steps are as follows:
[0045] S1, put the hydatidiform mole slice into the microscope stage, focus the microscope, and obtain the hydatidiform hydatidiform slice scan picture under the microscope;
[0046] In this step, firstly, the hydatidiform hydatidiform slices need to be he-stained first, and then put the hydatidiform hydatidiform hydatidiform mole slices into the stage of the digital microscope after the he-stained hydatidiform mole slices, and the microscope is a digital microscope; Clear hydatidiform mole slices can be seen in the field of view of the microscope; finally, the slice scanning module obtains the hydatidiform hydatidiform mole slice scanning image under the microscope.
[0047] S2, because the acquired hydatidiform mole slice scan image has a large size, and the existing network input has requirements for the image size, so it is necessary to segment the image inpu...
Embodiment 2
[0079] The present embodiment also provides a mole slice image processing device based on deep learning, including:
[0080] A microscope, to magnify the tiny structures in slices of hydatidiform hydatidiform mole;
[0081] The slice scanning module is used to obtain the hydatidiform hydatidiform section scan map under the microscope;
[0082] The slice edema label map generation module is used to slice the mole slice scan image to obtain the scan image slice 2, and input the scan image slice 2 into the edema network b-net to obtain the slice edema label map of the mole slice, and All slice edema label maps are fused to obtain a slice edema label map;
[0083] A distribution map generating module, configured to obtain a slice edema distribution map according to the slice edema label map;
[0084] Additionally, you can include:
[0085] The section fluff label map generation module is used to cut the mole slice scan image into pieces to obtain the scan image slice one, and i...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More