A lung lobe segmentation method based on digital human technology
A digital human and lung lobe technology, applied in image analysis, image data processing, image enhancement and other directions to achieve the effect of improving accuracy and stability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] Such as figure 1 It is a schematic diagram of a lung lobe segmentation method based on digital human technology, and the method includes the following steps:
[0030] Step 1: Generate a lung digital human model containing lung lobe mask information through registration and data statistics of lung CT images, specifically including the following sub-steps:
[0031] (1.1) Each collected lung CT image was preprocessed with threshold division for lung lobe segmentation, and then the interactive segmentation software was used for precise lung lobe segmentation.
[0032] (1.2) Surface registration is performed between each segmented lung CT image and the template, and the registered boundary point cloud data is obtained as a sample set. This process often uses non-rigid point cloud registration algorithms, such as TPS-RPM and non-rigid ICP.
[0033] (1.3) Construct a digital demographic map and set a sample set:
[0034] Ω={ X 1 , X 2 ,…, X N} (1)
[0035] i-th sampl...
Embodiment 2
[0066] As a preferred solution, the present invention can also adopt the elastix function in the Elastix toolkit to obtain the deformation field of the digital human image and the clinical patient's lung CT image and the deformed digital human image, specifically:
[0067] A lung lobe segmentation method based on digital human technology, the method comprises the following steps:
[0068] Step 1: Using the elastix function in the Elastix toolkit, the digital human image generated by the digital human model constructed in Example 1 and the clinical lung CT image of the patient are used as input to obtain the deformation field and the deformed digital human image.
[0069] Step 2: Using the digital human image deformed in Step 1, use the trained encoding network ( Figure 4 ) to fit the shape parameters of the digital human, and generate a new digital human image according to the shape parameters of the digital human.
[0070] Step 3: Repeat step 1 and step 2 multiple times unt...
Embodiment 3
[0074] As another preferred solution, the present invention can also connect the trained non-rigid registration model to the encoding network, and output the fitted shape parameters in one step, as follows:
[0075] A lung lobe segmentation method based on digital human technology, the method comprises the following steps:
[0076] Step 1: The digital human image generated by the digital human model constructed in Example 1 and the clinical lung CT image of the patient are used as the input of the joint network composed of the non-rigid registration model and the encoding network connection to obtain the deformed digital human shape parameters, and generate a new digital human image according to the shape parameters of the digital human.
[0077] Step 2: Repeat step 1 for several times until the iteration threshold is reached or the shape parameters of the digital human converge, and a new digital human image generated after final fitting is obtained.
[0078] Step 3: The new...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


