Multi-dimensional evaluation method and system for quality of pathological section of dyed nasal polyp and medium

Abstract

The invention discloses a dyed nasal polyp pathological section quality multi-dimensional evaluation method and system and a computer readable storage medium. The method comprises the steps that a nasal polyp digital full-field section image is acquired, and pixel preprocessing and filtering denoising are carried out; performing tissue section integrity scoring on the preprocessed image; the slice thickness uniformity degree of the preprocessed image is scored; performing tool mark and crack scoring on the preprocessed image; performing bubble scoring on the preprocessed image; grading the transparency of the preprocessed image; carrying out cell nucleus and cytoplasm dyeing contrast definition scoring on the preprocessed image; carrying out pollutant scoring on the preprocessed image; performing corrugation and folding scoring on the preprocessed image; and performing weighted summation on the obtained scores to obtain a total quality score of the slice image. According to the method, the quality of the pathological section can be quantified more finely and comprehensively.

Description

technical field [0001] The invention relates to the technical field of quality evaluation of conventional HE stained nasal polyp slices, and more specifically, relates to a multi-dimensional quality evaluation method, system and computer-readable storage medium for dyed nasal polyp pathological slices. Background technique [0002] The production of pathological sections of nasal polyps requires steps such as sampling, fixing, dehydration and transparency, wax immersion, embedding, sectioning, pasting, staining, and sealing. Irregularities or differences in any of these steps may lead to quality problems of pathological slides in the later stage, such as human operation, machine operation mode, quality of reagents, etc. If the quality of pathological slides is poor, it may cause missed diagnosis and misdiagnosis in serious cases. At the same time, with the development and application of digital pathology scanning slices, the requirements for slices are getting higher and hi...

AI Technical Summary

Problems solved by technology

[0004] In the past, the quality evaluation of pathological sections of nasal polyps was mainly based on human evaluation. This method consumes already tight medical resources and is not suitable for the analysis of a large number of sections.

Currently, several types of automated pathological slice quality evaluation methods have been proposed. For example, patent CN112102247A discloses a machine learning method to divide pathological slice images into multiple target quality categories (such as uneven staining, slice thickness, knife vibration, slice Wrinkled, slice wrinkled, collapsed, slice too thick and other quality categories), however, the poor quality of pathological slices should be evaluated from multiple dimensions, and it is inaccurate to judge slices by a single category;

[0005] The above-mentioned evaluation methods have the problems of single evaluation dimension and inaccurate evaluation results. Therefore, there is an urgent need for a multi-dimensional evaluation method for the quality of stained nasal polyp pathological sections.

Images