Unlock instant, AI-driven research and patent intelligence for your innovation.

Attention-enhanced brain tumor auxiliary intelligent detection and recognition method

A technology of intelligent detection and identification method, applied in the fields of image processing and medical imaging, can solve the problems involving less, and achieve the effect of improving the diagnosis ability

Active Publication Date: 2020-04-21
BEIHANG UNIV
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The current application of deep learning on brain MRI images, especially other related patents, is focused on the field of brain tumor segmentation, and less involved in areas directly related to diagnosis and treatment, such as classification and grading of brain tumors, which are clinical It is more concerned about and it is difficult for the human eye to do non-invasive image inspection

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
  • Attention-enhanced brain tumor auxiliary intelligent detection and recognition method
  • Attention-enhanced brain tumor auxiliary intelligent detection and recognition method
  • Attention-enhanced brain tumor auxiliary intelligent detection and recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] See attached Figure 1-2 , the present invention proposes an analysis method that combines medical images with deep learning and computer vision methods, uses computer vision to analyze and process three-dimensional brain MRI images, and performs segmentation and segmentation of glioma lesion regions on brain MRI images. Classification and diagnosis tasks based on images. Aiming at the small amount of data in medical image datasets, serious category imbalance, and the existing methods focus on the segmentation of lesion regions while ignoring the classification and diagnosis tasks, an improved 3D U-Net convolutional neural network is proposed to increase the classification and diagnosis. The branch obtains segmentation and classification results at the same time through multi-task joint training. figure 1It is the algorithm design process proposed by the present invention. First, preprocess the MRI image and its corresponding segmentation result of manual annotation an...

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

According to the invention, a set of attention-enhanced brain tumor auxiliary intelligent detection and identification method is realized; according to the technical scheme, improvement is carried outon the basis of a U-Net model; training of segmentation tasks is used as an attention enhancement mechanism of classification tasks; by paying attention to the segmentation tasks, a focus area and the edge information, the accuracy of the classification task is improved, the segmentation tasks and the classification task are optimized at the same time through adoption of a multi-task loss measurement and training method, the expected effect on the segmentation task and the classification task is achieved, and the design purpose and the application target are achieved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an attention-enhanced brain tumor-assisted intelligent detection and recognition method in the fields of medical imaging and computer-aided diagnosis. Background technique [0002] Tumors that grow in the brain are collectively referred to as brain tumors, which refer to nervous system tumors that occur in the cranial cavity, including tumors originating from neuroepithelium, peripheral nerves, meninges, and germ cells, tumors of lymphoid and hematopoietic tissues, and craniopharynx in the sella region. Tumors and granular cell tumors, and metastatic tumors. Tumors that originate from the brain parenchyma are called primary intracranial tumors, and those that metastasize from malignant tumors in other organs and tissues of the body are called secondary intracranial tumors. Intracranial tumors can occur at any age, with the most common being 20-50 years old. In recent years, with...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/084G06T2207/10088G06T2207/30016G06T2207/30096G06N3/045
Inventor 李建欣张帅于金泽周号益邰振赢
Owner BEIHANG UNIV