Auxiliary diagnosis system and method for artificial intelligence in nuclide myocardial perfusion imaging and application
A technology of myocardial perfusion and artificial intelligence, applied in the field of medical image processing, can solve problems such as no technical route for myocardial nuclear perfusion imaging diagnosis, low efficiency of clinical medical image diagnosis, and inability to be directly applied to the medical field, so as to improve diagnosis The effect of service ability, development and patient comfort promotion and improvement of treatment efficiency
Pending Publication Date: 2022-04-15
GENERAL HOSPITAL OF TIANJIN MEDICAL UNIV
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] (1) For the application of nuclear medicine myocardial perfusion and AI in medical image processing, the existing technology does not provide a comprehensive myocardial nuclear perfusion imaging diagnostic technology route
[0007] (2) In prior art image processing in the medical field, the traditional neural learning network has its limitations, making the accuracy of image processing lower
[0008] (3) In the image processing in the medical field of the prior art, the efficiency of clinical medical image diagnosis is low and the labor cost is high
Due to the particularity of images in the medical field, the traditional neural learning network has its limitations, so it cannot be directly applied to the medical field, but it needs to be improved
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
[0062] The present invention provides an image processing method for an auxiliary diagnosis system of artificial intelligence in nuclide myocardial perfusion imaging comprising:
[0063] (1) Document preparation
[0064] Through retrospective screening of 500 cases of patients who received myocardial nuclide perfusion imaging, the artificial intelligence network was trained, and 70% of the cases were positive cases (including mild sparseness, moderate sparseness, and severe myocardial uptake). Sparse and defective, such as image 3 ), 30% of cases were negative cases. Patient information is collected and obtained through different SPECT devices in four centers. The device models are: Discovery NM / CT 670 CZT (GE Company), Discovery NM / CT670 (GE Company), Discovery NM530c (GE Company), Symbia T16 (Siemens company). There are no special restrictions on image acquisition parameters, and the acquisition is performed according to the default parameters of each device. The image ...
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 belongs to the technical field of medical image processing, and discloses an auxiliary diagnosis system and method for artificial intelligence in nuclide myocardial perfusion imaging and application. The marked image is put into a deep learning network for feature extraction, so that an auxiliary diagnosis model is trained; judging different lesion positions and different lesion degrees of the input detected image based on the auxiliary diagnosis model after feature extraction training; meanwhile, an improved segmentation network is applied to carry out target map detection, and the area proportion of the myocardial ischemia part is counted; and carrying out visual display on a statistical result. The artificial intelligence network is gradually improved to improve the diagnosis accuracy, and then the artificial intelligence network is expanded to auxiliary diagnosis of images of other examination parts in nuclear medicine and popularized to the cloud for auxiliary diagnosis, so that support is provided for primary hospitals and hospitals with large examination amount or other third-party institutions; and a brand new means is provided for auxiliary diagnosis of nuclide myocardial perfusion imaging.
Description
technical field [0001] The invention belongs to the technical field of medical image processing, and in particular relates to an auxiliary diagnosis system, method and application of artificial intelligence in nuclide myocardial perfusion imaging. Background technique [0002] At present, myocardial nuclear perfusion imaging is the most commonly used non-invasive imaging diagnostic method for coronary heart disease. It can more accurately evaluate the degree, area and location of myocardial ischemia. With the maturity of myocardial nuclear perfusion imaging in recent years, it has accumulated a large amount of clinical data in the risk classification of coronary heart disease, various levels of prevention, treatment options and prognosis assessment, which has good reference significance. [0003] The application of learning network based on artificial intelligence in medicine has certain difficulties in the past, which limits its application in the field of medicine. In rec...
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): G06K9/62G06N3/02G06T3/40G06T7/00G16H30/40G06V10/774
Inventor 孟召伟张如意张为谭建贾强王澎李剑明边艳珠刘雪辉王赫王淼王深申一鸣徐凌云张雪梅范岩胡玉敬廖栩鹤
Owner GENERAL HOSPITAL OF TIANJIN MEDICAL UNIV