Left atrium and atrial scar segmentation method based on artificial neural network and device thereof
An artificial neural network and left atrium technology, applied in the field of medical detection, can solve problems such as accumulation of segmentation errors and incorrect quantification of atrial scars, and achieve the effects of eliminating manual intervention, accurate segmentation results, and improving efficiency
Pending Publication Date: 2020-06-16
SUN YAT SEN UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, it is prone to the problem of accumulation of segmentation errors, which may further lead to incorrect quantification of atrial scar
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
[0081] In order to make the purpose, features and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Apparently, the described embodiments are some of the embodiments of the present application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.
[0082] It should be noted that, in any embodiment of the present invention, cascading is an effective structure that can be used to automatically associate tasks, and can improve the performance of the multi-task model. For the multi-task problem, the cascade operation designs the tasks as a cascade mode, the previous tasks transmit valid information to the subsequent tasks, and the subsequent tasks are m...
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 left atrium and atrial scar segmentation method based on an artificial neural network and a device thereof, and the method comprises the steps: building the corresponding relation between the image features of a cardiac medical image and a left atrium and atrial scar segmentation result through the self-learning capability of the artificial neural network; obtaining current image features of the current cardiac medical image of the patient; and determining a current left atrium and atrial scar segmentation result corresponding to the current image feature through the corresponding relationship; specifically, determining a current left atrium and atrial scar segmentation result corresponding to the image feature, which is characterized by including that the left atrium and atrial scar segmentation result corresponding to the image feature the same as the current image feature in the corresponding relation is determined as the current left atrium and atrial scarsegmentation result. The left atrium and atrial scar segmentation efficiency is improved, and the segmentation result is more accurate.
Description
technical field [0001] The present application relates to the field of medical detection, in particular to a method and device for segmenting left atrium and atrial scar based on artificial neural network. Background technique [0002] Quantification of atrial scar can grade AF patients before and after radiofrequency catheter ablation, so it is very important to formulate effective diagnosis and treatment plans for AF patients. Quantification of atrial scar usually requires left atrium and atrial scar segmentation information. Clinically, because late gadolinium-enhanced cardiac magnetic resonance (LGE CMR) technology can non-invasively detect and localize atrial scar, LGE CMR has been effectively used for accurate quantification of atrial scar. But the clinical practice process relies on physicians to manually segment the left atrium and atrial scar on LGE CMR images. This process is time consuming and inefficient. [0003] Since the atrial scar is small and discretely ...
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): A61B5/055A61B5/00G06T7/11
CPCA61B5/055A61B5/0044A61B5/7264A61B5/7267G06T7/11A61B2576/023G06T2207/20081G06T2207/20084G06T2207/30048
Inventor 张贺晔陈军张冬
Owner SUN YAT SEN UNIV