Ultrasonic medical image AI-assistance labelling system

A technology of medical imaging and ultrasound, applied in the fields of medical images, healthcare informatics, instruments, etc., can solve the problems of complicated processing process, large manpower and material resources, and heavy tasks, so as to reduce investment, save costs, and improve labeling accuracy. and efficiency effects

Pending Publication Date: 2019-11-15
苏州米特希赛尔人工智能有限公司 +1
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, a large amount of labeled data is a very heavy task and complicated process
In particular, the machine learning of medical images requires a large number of medical experts to

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
  • Ultrasonic medical image AI-assistance labelling system
  • Ultrasonic medical image AI-assistance labelling system
  • Ultrasonic medical image AI-assistance labelling system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will now be described in further detail in conjunction with the accompanying drawings and preferred embodiments. These drawings are all simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, so they only show the configurations related to the present invention.

[0033] Such as figure 1 , as shown in the schematic diagram of the medical image AI medical image labeling system of the preferred embodiment of the present invention: 1 is the labeling terminal, here, the PC is preferably used as the labeling terminal, and the client is run and called to complete machine labeling, result inspection, comparison and labeling results Functions such as classified storage (correct result classification storage and incorrect result pictures are stored separately); 2 is the Internet, connect 1 and 3 through the Internet, send the data and instructions of 1 to 3, and send the marked result of 3 bac...

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 discloses an ultrasonic medical image AI-assistance labelling system. According to the system, firstly, a limited medical image training set labelled by a doctor is utilized for trainingan AI target detection system, then the trained AI target detection system is utilized for labelling a corresponding medical image, the labelled medical image is compared with a diagnosis conclusionwritten on a medical record and corrected, or is determined or corrected by a medical expert, and therefore a new medical image training set is obtained. The training set and an original medical imagetraining set are mixed at random to obtain a new medical image training set, the new medical image training set is utilized for training the AI target detection system anew, in this way, the operation is repeated many times, training data is constantly added, and the labelling precision of the system is improved. The system solves the problems that lots of expert resources required by medical image labelling need to be input, and the cost is quite high.

Description

technical field [0001] The present invention relates to artificial intelligence, medical images and deep learning, in particular to an AI (artificial intelligence) auxiliary labeling system for ultrasonic medical images. Background technique [0002] At present, more than 90% of medical data comes from medical images, and medical image data has become one of the indispensable "evidences" for doctors' diagnosis. The combination of artificial intelligence and medical imaging can provide assistance and reference for doctors to read and outline images, greatly saving doctors' time and improving diagnostic efficiency and accuracy. In particular, it can provide high-quality medical imaging diagnosis services for primary hospitals, and solve the problems of low-quality or unavailable imaging diagnosis and treatment. [0003] Big data has promoted the rapid development and wide application of machine learning. In machine learning, a large amount of labeled data is required to trai...

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
IPC IPC(8): G16H30/20G06K9/62
CPCG16H30/20G06F18/241G06F18/214
Inventor 周琦秦绮玲刘亚平
Owner 苏州米特希赛尔人工智能有限公司
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