An automatic detection system for children's intussusception based on deep learning
An automatic detection and deep learning technology, applied in the field of medical artificial intelligence, can solve problems such as no relevant records, detection models are difficult to achieve detection results, etc., and achieve the effect of improving expression ability
Active Publication Date: 2022-05-17
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] However, for the detection of "concentric circles" in abdominal ultrasound images, there is no relevant record in the prior art, and it is difficult to achieve better detection results by using existing detection models
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
[0035] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be noted that the following embodiments are intended to facilitate the understanding of the present invention, but do not limit it in any way.
[0036] An automatic detection system for children's intussusception based on deep learning, including a computer memory, a computer processor and a computer program stored in the computer memory and executable on the computer processor, the computer memory has trained concentric circle detection phantom; the concentric circle detection phantom is used to detect concentric circles in abdominal ultrasound images of children.
[0037] The invention designs a model that is more suitable for the detection of "concentric circle" signs in ultrasonic images. In order to better distinguish the standard "concentric circle" phenomenon from the non-standard "concentric circle" phenomenon, the method of the ...
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 discloses an automatic detection system for children's intussusception based on deep learning, which includes a trained concentric circle detection model, and uses the concentric circle detection model to detect concentric circles in children's abdominal ultrasound images; the concentric circle detection model includes a feature extraction network , region generation network RPN and ROI Pooling layer; the feature extraction network adopts VGG16 convolutional neural network, and a skip connection layer is added in the convolutional neural network, and the shallow layer features and deep layers of the convolutional neural network are combined through the skip connection layer feature union. The model constructed by the invention realizes automatic detection of "concentric circle" signs in children's abdominal intussusception ultrasound images, assists doctors to identify them, reduces the time for manual evaluation, and improves the diagnosis speed of children's intussusception patients.
Description
technical field [0001] The invention belongs to the field of medical artificial intelligence, in particular to an automatic detection system for children's intussusception based on deep learning. Background technique [0002] Intussusception is a pediatric surgical emergency, which is relatively common in clinical practice, and the main patients are children under 2 years old. Intussusception mainly refers to the phenomenon that two connected intestines overlap each other. Early diagnosis and active correct treatment can prevent intestinal necrosis and reduce the suffering of children. [0003] Ultrasound diagnosis, as a non-invasive and painless examination method, is easy to be accepted by children and their families. Typical children’s intussusception ultrasound images can be summarized into two signs: one is the “concentric circle” sign on the cross section The second is the "sleeve sign" on the longitudinal section. Doctors usually judge whether patients have intussusc...
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 Patents(China)
IPC IPC(8): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/08G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/10132G06T2207/30028G06T2207/30204G06N3/047G06N3/045
Inventor 李哲明黄坚沈忱俞刚李竞黄寿奖宋春泽柴象飞郭娜左盼莉钱宝鑫
Owner ZHEJIANG UNIV