Iterative correction-based histopathologic image cell nucleus detection method and device

A detection method and cell nucleus technology, applied in the fields of image processing and pattern recognition, can solve the problem of positioning inaccuracy and non-maximum inhibition scale, and achieve the effect of easy selection of inhibition range, high nuclear positioning accuracy, and enhanced distinguishability.

Pending Publication Date: 2022-03-15
SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem mainly solved by the present invention is to provide a histopathological image based on iterative correction for the inaccuracy of positioning in the detection of cell nuclei in the current pathological image and the difficulty in selecting the non-maximum inhibitory effect scale in eliminating redundant candidates. Cell nucleus detection method and device

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Iterative correction-based histopathologic image cell nucleus detection method and device
  • Iterative correction-based histopathologic image cell nucleus detection method and device
  • Iterative correction-based histopathologic image cell nucleus detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0051]The nuclei detection model used in the iterative correction-based method for detecting nuclei in histopathological images provided in this embodiment consists of two parts, namely, a location generation network (LPN) and an iterative correction network (ICN). The location generation network selects CNN as the backbone network, and adds a side output layer under the deep supervision mechanism to generate candidate locations. The iterative rectification network refines locations by iteratively incorporating difference cues and feedback error predictions.

[0052] The nuclei detection method of histopathological images can be used for the detection of nuclei in various histopathological images, such as figure 1 As s...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a histopathology image cell nucleus detection method and device based on iterative correction. Comprising the following steps: firstly, generating candidate objects and initial positions thereof; and then refining and positioning. A novel block learning method is designed to obtain high-quality kernel candidates, in addition to categories, position expressions are added in image block information, the multi-task learning process of cell nucleus classification and positioning is achieved, meanwhile, a deep supervision mechanism is introduced into tasks, and rich hierarchical expressions are provided. In order to improve the positioning precision of the cell nucleus, an iterative correction strategy is provided, so that the prediction is gradually close to the real situation, the positioning precision of the center of the cell nucleus is remarkably improved, and convenience is provided for selection of the inhibition range in the non-maximum inhibition step. Experimental results show that the method is applied to Hamp; the nuclear detection performance on an E-dyed histopathologic image data set is superior to that of the conventional method, and a better detection effect can be obtained particularly in multi-clutter nuclear detection.

Description

technical field [0001] The present invention relates to the technical fields of image processing and pattern recognition, and more specifically, to a method and device for detecting nuclei in histopathological images based on iterative correction. Background technique [0002] Histopathology images, the examination of microscopic sections composed of cells, tissues, etc., play a vital role in the diagnosis of various cancers and are widely used in clinical practice and pathological research. Accurate analysis of breast histopathological images is important for pathologists to grade breast cancer and assess prognostic factors. For example, the Nottingham histology scoring system correlates with tubule formation, nuclear pleomorphism, which can indicate the evolution of breast cancer, and mitotic count, which can assess the aggressiveness of breast tumors. For quantitative analysis of histopathological images, features are usually quantified based on the appearance and shape ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06N3/04G06N3/08
CPCG06T7/0012G06N3/084G06T2207/20081G06T2207/20084G06T2207/30024G06T2207/30068G06T2207/30096G06T2207/30204G06N3/045
Inventor 唐奇伶蔡玉刘子仪
Owner SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap