Automatic identification method and system for pathogenic phases in fungus microscopic image
A microscopic image and automatic identification technology, applied in the field of medical image technology processing, can solve the problems of high degree of subjective judgment of results and high labor intensity of personnel, and achieve the effect of reducing time, improving efficiency and improving recognition degree.
Active Publication Date: 2020-02-14
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a method and system for automatic identification of pathogenic phases in fungal microscopic images, thereby solving the problem of high labor intensity and subjective judgment of results in traditional manual fungal microscopic examination. High degree of technical problems
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0040] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following further describes the present invention in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0041] The image analysis method proposed by the present invention is not intended to completely replace medical staff in disease diagnosis, but to provide doctors with objective and accurate evaluation suggestions through scientific analysis methods, and assist in diagnosis, thereby improving the doctor’s work efficiency and getting better results. Accurate diagnosis results.
[0042] Such as figure 1 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
Login to View More Abstract
The invention discloses an automatic identification method and system for pathogenic phases in fungus microscopic images, and the method comprises the steps: carrying out the binarization of each fungus microscopic image, and obtaining a foreground image of each fungus microscopic image; extracting hypha characteristics and non-hypha characteristics in each foreground image, and obtaining sample data required by SVM training; and training the sample data by using an SVM (Support Vector Machine) learning algorithm to obtain a target recognition model, recognizing a microscopic image of the to-be-detected fungus by using the target recognition model, and marking hyphae in the image of the to-be-detected fungus. According to the invention, the hypha structure of the pathogenic phase can be detected from the image and accurately positioned.
Description
Technical field [0001] The invention belongs to the technical processing field of medical images, and more specifically, relates to a method and system for automatically identifying pathogenic phases in fungal microscopic images. Background technique [0002] Fungal infections are already a major disease that seriously affects people's health in my country. Medical units need to improve their diagnosis and treatment capabilities for fungal infections. In particular, new scientific and technological methods are urgently needed to accurately and efficiently detect pathogens. [0003] At present, the main techniques for fungal detection include direct microscopy, fungal culture, and culture inspection. Among them, direct microscopy, as one of the classic fungal testing methods, has the advantages of high positive rate and quick reporting. Medical staff need to observe and judge the sample in the field of view of the microscope. If pathogenic hyphae are found in the microscopic image,...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/698G06F18/2135
Inventor 曾绍群吕晓华刘越田靓程胜华
Owner HUAZHONG UNIV OF SCI & TECH