G-band chromosome HDR image reconstruction method

An image reconstruction and chromosome technology, applied in the field of image processing, can solve the problems of artifacts, failure to use a single LDR image, HDR image reconstruction, etc., to achieve the effect of reducing difficulty, avoiding chromosome artifacts, and high quality

Inactive Publication Date: 2021-03-02
SHANGHAI BEION MEDICAL TECH CO LTD
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the disadvantages in the prior art that a single LDR image cannot be used to complete HDR image reconstruction and will cause artifacts, the present invention provides a G-banded chromosome HDR image reconstruction method, which can use a single G-banded chromosome with a low dynamic range Image reconstruction of high dynamic range images, while avoiding the problem of chromosomal artifacts when compositing HDR images

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
  • G-band chromosome HDR image reconstruction method
  • G-band chromosome HDR image reconstruction method
  • G-band chromosome HDR image reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043] G-banded chromosome HDR image reconstruction method, LDR image is G-banded chromosome LDR image, HDR image is G-banded chromosome HDR image, such as figure 1 As shown, it includes the model training steps of the three sub-networks of the dequantization network, the linearization network, and the detail reconstruction network, and the steps of reconstructing the HDR image using the trained model.

[0044] The model training steps are as follows:

[0045] S01: The dequantization network adopts a 6-level U-Net network structure. Each level of U-Net network structure is composed of two convolutional layers activated by the leaky ReLU function (α=0.1), and the Tanh activation layer is used to convert The result of the dequantization network output is normalized to [-1.0,1.0], and finally the output of the dequantization network is fused to the input LDR image I (real image) to generate a dequantization LDR image and minimize the LDR image by and the corresponding true LD...

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 relates to the technical field of image processing, and discloses a G-band chromosome HDR image reconstruction method, which comprises the training steps of a dequantization network model, a linearization network model and a detail reconstruction network model, and the step of reconstructing an HDR image by using the trained models. According to the method, three neural network models, namely a de-quantization network, a linearization network and a detail reconstruction network, are designed, and a training set is formed by utilizing an actual G-band chromosome HDR image and a corresponding real LDR image, so that the training of the three neural network models is completed; performing three steps of de-quantization, linearization and overexposure region detail reconstructionon a real LDR image by using the trained model, and finally completing a task of G-band chromosome HDR image reconstruction; according to the method, reconstruction of the HDR image is completed onlythrough one LDR image, so that G-banding chromosome characteristics are more obvious, subsequent analysis is facilitated, artifacts do not appear in the reconstructed HDR image, and the quality of the image is higher.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for reconstructing HDR images of G-banded chromosomes. Background technique [0002] The quality of G-banded chromosome images will seriously affect the effect of chromosome G-banded karyotype analysis. Usually, higher-quality G-banded chromosome images can provide more chromosome structure information and texture information, and have more important clinical application value. [0003] In order to obtain a higher-quality G-banded chromosome image, a better-effect preparation method is usually used to prepare a G-banded chromosome sample, and the high-resolution chromosome preparation method is usually better than the low-resolution chromosome preparation method. Obtain more pronounced chromosomal details. With the advancement of digital image technology, digital images of G-banded chromosome samples collected by digital cameras can be processed more convenient...

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): G06T11/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06T11/005G06T11/008G06N3/08G06V10/443G06V10/50G06N3/045G06F18/2135
Inventor 崔玉峰
Owner SHANGHAI BEION MEDICAL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products