A method and system for dynamic planning of full-slice scanning path

Abstract

The present invention relates to a method and system for dynamic planning of a full-slice scanning path. The method includes the following steps: i. Processing a low-magnification bird's-eye view image to calculate the range of the scannable area in the bird's-eye view image; ii. The range of the scannable area Select the scanning starting position, iii. Explore the outer boundary of the scannable area by moving the microscope lens step by step, iv. Exhaustively enumerate all the scanning routes starting from the current stop position of the microscope field of view, and the number of moving steps is M ; Select a scanning route according to the preset rules among the several scanning routes exhaustively and execute it; v, re-execute the route planning in the iv step after each step of the microscope lens moving, until the approaching of the microscope field of view Range has no areas to scan. The present invention can use a dynamic programming method instead of a fixed path mode when planning a scanning path, and reduce repeated paths when scanning irregular slices.

Description

technical field [0001] The invention relates to the field of digital pathology, in particular to a system and method for dynamic planning of full-slice scanning paths. Background technique [0002] Automated microscope (motorized microscope) technology has been relatively mature after more than ten years of development. However, the models with the whole slide imaging function are mostly based on the principle of high-precision mechanical positioning, and the cost is extremely high, which limits their wide application in users with low and medium budget needs. In the applicant's invention patent application 201910225913.6, the local field of view positioning control method of the microscope based on feature point matching is solved, and the positioning function is realized; in the applicant's invention patent application 201910225927.8, the focus is solved through the Z-axis control method of the automatic microscope Function. However, when only a single high-magnification...

AI Technical Summary

Problems solved by technology

Due to the huge difference in magnification, the error of the boundary position estimated under the low-magnification bird's-eye view lens may reach as many as several fields of view at high magnification, so the scannable range cannot be determined based on the slices taken by the bird's-eye view lens;

[0006] 2. When relying on high-magnification microscopic images to estimate the scanning boundary, it is necessary to focus first, otherwise it is impossible to distinguish whether there is a slice coverage only by the out-of-focus blurred image

However, the 201910225927.8 scheme cannot be used to focus on areas without slice coverage

If you still use the route of traversing slices and use focus failure as the judgment boundary criterion, the efficiency is extremely low;

[0007] 3. Even if the scannable area is determined, when scanning within this range, there may be a slice hole, which is the unscannable area in the center of the slice, cutting off the traversal route;

[0008] 4. Even if the scannable area and the local unscannable area distributed in it are determined, and several sets of Z-shaped traversal routes can be used to cover the entire irregular scanning area, it is inevitable that there will be a large number of repeated paths, and the efficiency is very low

Images