Artificial intelligence identification and analysis method for chromosome aberration
A technology of artificial intelligence and analysis method, applied in the field of artificial intelligence identification and analysis of chromosomal aberrations, can solve the problems of low accuracy rate of automatic identification of chromosomal aberrations, and achieve accurate large-area and large-scale personnel detection with high accuracy and fast speed Effect
Pending Publication Date: 2020-11-17
厦门汉舒捷医疗科技有限公司
View PDF0 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In order to solve the problem of low accuracy of automatic identification of chromosomal aberrations in the prior art, an artificial intelligence identification and analysis method for chromosomal aberrations provided by the present invention can solve the problem of low accuracy of automatic identification of chromosomal aberrations, making the process of identification and classification Full automation, fast speed and high accuracy
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 1
[0045] The invention provides an artificial intelligence identification and analysis method for chromosomal aberrations, such as figure 1 shown, including:
[0046] S100: Input the original historical chromosome distortion image data, mark the data according to the geometric figure and make a type mark to complete the learning and training, and store the marked data in the database;
[0047] S200: Input the chromosomal aberration target image to be identified into the backbone network model, so as to locate the position of the candidate object;
[0048] S300: continue to classify and identify the objects through the positioning of the objects in S200, input the image processed in S200 into the local pre-selection frame model, and classify and identify the actual situation of the target objects with different sizes;
[0049] S400: Outputting an automatic analysis result of chromosome aberration form according to the classified and identified data.
[0050] The collected images ...
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 provides an artificial intelligence identification and analysis method for chromosome aberration, and the method comprises the steps: inputting original historical chromosome aberrationform image data, carrying out the data marking according to a geometric figure, making a type mark, so as to complete the learning training, and storing the marked data into a database; inputting a chromosome aberration form target image to be identified into the backbone network backbone model to realize positioning of the candidate object; continuously classifying and identifying the object by positioning the object, inputting the processed image into a local pre-selection frame model, and classifying and identifying the actual situation that the target object is different in size; and outputting a chromosome aberration form automatic analysis result according to the classified and identified data. In the prior art, the accuracy of automatically identifying chromosome aberration is low,and the method can solve the problem, so that the identifying and classifying process is full-automatic, high in speed and high in accuracy. The difference with the accuracy of manual identification is small.
Description
technical field [0001] The invention relates to the field of chromosomal aberration identification, in particular to an artificial intelligence identification and analysis method for chromosomal aberrations. Background technique [0002] Chromosome is a deeply stained structure that can be observed in dividing cells, usually in spherical cells, and can only be observed and studied during cell division (mitosis or meiosis). The number of chromosomes in a cell is constant and the morphological characteristics are stable. Chromosomal aberrations are structural aberrations resulting from chromosome breaks and rejoining of the broken ends, resulting in abnormal chromosome lengths, chromosome locations, and new structures of genetic composition in an illegitimate manner, including: centromeres, secondary constrictions, long arms, short arm and body. In view of the characteristics of chromosomes, the chromosomal aberrations induced by radiation include: acentric fragments, micros...
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 IPC IPC(8): G06T7/00G06T7/70G06T5/00G06N3/04
CPCG06T7/0012G06T7/70G06T2207/20032G06T2207/10056G06T2207/30072G06N3/045G06T5/73G06T5/70
Inventor 李刚赖冬商向群周颖
Owner 厦门汉舒捷医疗科技有限公司