Knowledge graph fusion method for doctor experience knowledge and ultrasonic image information
A technology of knowledge map and empirical knowledge, which is applied in the field of knowledge map fusion of doctor's experience knowledge and ultrasound image information, and can solve the problem that ultrasound-assisted diagnosis cannot effectively integrate doctor's experience and knowledge
Active Publication Date: 2020-11-17
NORTHWESTERN POLYTECHNICAL UNIV
View PDF5 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In order to solve the problem that the existing data-driven ultrasound-assisted diagnosis cannot effectively integrate the doctor's experience and knowledge, the present invention provides a knowledge map fusion method of doctor's experience knowledge and ultrasound image information
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
[0027] The present invention will be further described below in conjunction with the accompanying drawings and embodiments, and the present invention includes but not limited to the following embodiments.
[0028] Such as figure 1 and 2 As shown, the present invention provides a knowledge map fusion method of doctor's experience knowledge and ultrasound image information, and its specific implementation process is as follows:
[0029] 1. Representation of triplets of doctor experience annotation information
[0030] The index of breast ultrasound diagnosis is taken as entity, and the necessary, sufficient or related relationship between entities marked by doctors is taken as labeling relationship, and the entity and labeling relationship are expressed as a triplet form of entity 1-relation type-entity 2. The indicators mentioned are common conceptual indicators listed by sonographers, including shape, orientation, edge, lesion border, internal echo type, rear echo characteri...
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 a knowledge graph fusion method for doctor experience knowledge and ultrasonic image information. The method comprises the following steps: firstly, narrating doctor experienceannotation information as triple regularized knowledge one by one, and constructing each regularized knowledge into a doctor experience knowledge graph; secondly, performing semantic ontology query onentities in the doctor experience knowledge graph and the ultrasonic image knowledge graph, and performing alignment processing and knowledge graph embedding representation; and finally, solving theconstructed fusion target function to obtain joint spatial embedding vectors of different maps, and combining distance judgment to realize fusion of the doctor experience knowledge map and the ultrasonic image knowledge map. Doctor experience is fused into an ultrasonic image in a knowledge graph mode, the limitation that only medical image data driving is adopted in a computer-aided diagnosis method can be broken through, and the aided diagnosis process better conforms to the doctor experience.
Description
technical field [0001] The invention belongs to the field of medical information processing, and in particular relates to a knowledge map fusion method of doctor's experience knowledge and ultrasonic image information. Background technique [0002] In clinical practice, medical ultrasound is the most frequent medical imaging diagnosis. In order to effectively alleviate the work intensity of doctors during large-scale screening, hospitals mainly use computer-aided diagnosis technology to assist doctors in diagnosis. The existing research on computer-aided diagnosis technology mainly focuses on the medical images collected by clinics. The potential correlation between images and diseases is mined through data-driven methods, and the diagnosis results of diseases are predicted. [0003] Since the information only from medical image data is often of limited reference value for auxiliary diagnosis, other medical information can be further fused on the basis of medical images to s...
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): G06F16/36G06F16/33G06K9/62G16H70/20
CPCG06F16/367G06F16/3344G16H70/20G06F18/25Y02A90/10
Inventor 习佳宁黄庆华
Owner NORTHWESTERN POLYTECHNICAL UNIV