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

Method for detecting lymph nodes in head and neck CT images

A CT image and lymph node technology, applied in the field of image recognition, can solve the problems of difficult segmentation and poor results, and achieve the effect of improving segmentation accuracy, avoiding interference, and improving accuracy.

Pending Publication Date: 2021-01-15
SHANGHAI NINTH PEOPLES HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the density of lymph nodes is similar to that of muscles, and the CT value is between 20-50 Hu. In addition, the shape and size of lymph nodes in different positions are also quite different, which brings difficulties to segmentation. The effect of direct segmentation using one-step convolutional neural network is not good. good

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
  • Method for detecting lymph nodes in head and neck CT images
  • Method for detecting lymph nodes in head and neck CT images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the present invention.

[0023] see figure 2 As shown, the present invention adopts a two-step method, that is, the first step outlines the location of the lymph node division in the CT image of the head and neck, and the second step performs the segmentation of the lymph node in the lymph node division. The specific steps are as follows:

[0024] Step 1: Recognition and segmentation of lymph node partitions in CT images: Convolutional neural networks including but not limited to U-Net, R-CNN, FCN, DenseNet, etc. are used to identify and segment each lymph node partition in head and neck CT images.

[0025] 1.1 Data acquisition steps: the patient's head and neck CT images are used as input data.

[0026] 1.2 Feature extraction step: use a fully convolutional neural network, including multiple convolutional layers, and...

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 a method for detecting lymph nodes in a head and neck CT (computed tomography) image, which adopts a method of firstly segmenting lymph node partitions and then identifying segmented lymph nodes from the partitions, and makes full use of prior knowledge of head and neck lymph node subsections. The interference of muscle tissues outside lymph node partitions and other tissues with the density close to the lymph node density on lymph node segmentation is reduced; based on the conditions that the lymph node form is relatively smooth and the CT image interlayer change is not obvious, a three-dimensional convolution kernel is adopted in lymph node identification and segmentation, and the segmentation accuracy is improved by virtue of complementary information between image layers; interference of muscle tissue on lymph node identification and segmentation can be avoided, so lymph node segmentation accuracy is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to a method for detecting lymph nodes in head and neck CT images. Background technique [0002] The imaging of CT technology is widely used in the field of clinical medicine because it can better display the organs composed of soft tissues and display lesions on the background of anatomical images. Accurately segmenting the target area from CT images is a key step in computer-aided diagnosis and surgical planning. Inspired by the success of deep learning and convolutional neural networks in computer image understanding and analysis, the researchers applied it to CT / In the processing of medical images such as MR, good results have been achieved in the segmentation of various tissues and organs. For example, Dou Q et al. used 3D convolutional neural networks to realize the recognition and segmentation of pulmonary nodules in LDCT images (Dou Q, Chen H, Jin Y, et al. Automa...

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): G06T7/00G06T7/10
CPCG06T7/0012G06T7/10G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30004
Inventor 朱凌印宏坤陈培倩王晶波陶晓峰邹王忠向诗语
Owner SHANGHAI NINTH PEOPLES HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE