Method for typing chronic sinusitis based on digital pathological slide and system thereof

A technology of chronic sinusitis and digital pathology, applied in the field of medical treatment methods, can solve the problems of measurement deviation, lack of accuracy and timeliness of auxiliary diagnosis method and its system, and high time cost, achieve strong social benefits, and improve the pathology of nasal polyps. Diagnostic level, high efficiency

CN110728666AActive Publication Date: 2020-01-24THE THIRD AFFILIATED HOSPITAL OF SUN YAT SEN UNIV +1
8 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2020-01-24

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a method for typing chronic nasosinusitis based on a digital pathological slide. The method comprises the following steps: acquiring an image, namely acquiring a digital pathological image from the chronic nasosinusitis nasal polyp slide, and sketching to generate a large mask image; preprocessing the image to obtain a small pathological image and a small mask image; establishing training set data; establishing a deep learning quantitative prediction module; training on an ImageNet data set by adopting an Inception V3 model to obtain model parameters; removing the lastfull-connection layer FC of the model, adding a full-connection layer FC, only one neuron being arranged in the full-connection layer FC, not using activation function, setting a loss function to adopt a mean square error MSE, and setting a learning rate lr; integrating the eosinophilic granulocyte proportion values of all the small pathological pictures on the slide to obtain a final auxiliary diagnosis result. The invention also discloses a system thereof. According to the method, the eosinophilic granulocyte proportion on the pathological picture is rapidly obtained through learning and training, and an objective and high-accuracy auxiliary diagnosis result is given.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of medical treatment means, in particular to a method for typing chronic sinusitis based on digital pathological slides and a system technology thereof. Background technique

[0002] Chronic rhinosinusitis (CRS) can be clinically divided into two types: without nasal polyps (CRSsNP) and with nasal polyps (CRSwNP). Chronic sinusitis with nasal polyps (CRSwNP) is subdivided into two subtypes: eosinophilic nasal polyps (eCRSwNP) and non-eosinophilic nasal polyps (neCRSwNP). Eosinophilic nasal polyps (eCRSwNP) were sensitive to steroid therapy, whereas non-eosinophilic nasal polyps (neCRSwNP) were sensitive to macrolide antibiotics. Clinically, for how to define eosinophilic nasal polyps (eCRSwNP) and non-eosinophilic nasal polyps (neCRSwNP), pathologists usually randomly take 10 high-power fields of eosinophilic nasal polyp slide specimens from patients The average percentage of granulocytes, and using 10% as...

Examples

Embodiment Construction

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0041] The present invention carries out the typing method of chronic sinusitis based on the digital pathology slide, mainly comprises the following technical measures:

[0042] (1) The processing of pathological pictures comprises the following steps:

[0043] Image Acquisition:

[0044] 1) Complete scanning of chronic sinusitis nasal polyp slides to obtain digital pathological images;

[0045] 2) Outlining the lesion area with the digitalized pathological ...