CN115861394A - Medical image processing method and device, storage medium and electronic equipment - Google Patents
Medical image processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115861394A CN115861394A CN202310175697.5A CN202310175697A CN115861394A CN 115861394 A CN115861394 A CN 115861394A CN 202310175697 A CN202310175697 A CN 202310175697A CN 115861394 A CN115861394 A CN 115861394A
- Authority
- CN
- China
- Prior art keywords
- sample image
- medical
- target
- medical sample
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application discloses a medical image processing method and device, a storage medium and electronic equipment, and relates to the technical field of image processing, wherein the method comprises the following steps: acquiring a target medical image of a first modality; and registering the target medical image of the first modality through a target registration network to obtain a registered target medical image of a second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolutely same modality. By the method and the device, the problem that the accuracy of the registration of the image by the registration network is low due to the fact that the registration network is trained through existing multi-mode data in the related art is solved.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method and an apparatus for processing a medical image, a storage medium, and an electronic device.
Background
The purpose of multi-modality image registration is to align two images (the movement (M) and target (T) images) with different distributions by distorting the space of the deformation field. One major challenge in multi-modality image registration is that the maps acquired using different imaging machines or different acquisition parameters may differ in several respects. Since the reconstruction and acquisition methods are significantly different, there is no simple one-to-one mapping between different imaging modalities. From the perspective of measuring similarity, mainstream unsupervised multimodal registration methods can be divided into two categories: a similarity operator based registration and an image-to-image transformation based registration.
Similarity operator based registration is the use of multi-modal similarity operators as a loss function of registration, e.g., cross-correlation (NCC), mutual Information (MI), and modality-independent neighborhood descriptor (MIND). The similarity algorithm is based on a priori mathematical knowledge of the researcher and has been elaborated and continuously improved for a long time. They can be applied to both conventional registration processes and neural network registration. The similarity operator has several limitations: one is that it is not possible to design similarity operators that can maintain high accuracy for all data from various imaging modalities. Secondly, the upper limit that these operators can reach cannot be estimated, so it is difficult to find the improvement direction.
Image-to-image conversion based registration first converts multimodal images into single modality images using a generative countermeasure network (GAN), and then evaluates the error per pixel in space using the Mean Absolute Error (MAE) or Mean Square Error (MSE). The registration based on image-to-image conversion skillfully avoids complex multi-mode problems and reduces the difficulty of registration to a certain extent. However, it has significant disadvantages: GAN-based approaches require training using existing multimodal data. If the trained model encounters data that is not visible, it will not work, which greatly limits its applicability scenarios.
Aiming at the problem that the accuracy of the registration network to the image is low due to the fact that the existing multi-modal data training registration network in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The present application mainly aims to provide a medical image processing method and apparatus, a storage medium, and an electronic device, so as to solve the problem in the related art that the accuracy of image registration by a registration network is low due to the fact that the registration network is trained by using existing multi-modal data.
In order to achieve the above object, according to one aspect of the present application, there is provided a method of processing a medical image. The method comprises the following steps: acquiring a target medical image of a first modality; and registering the target medical image of the first modality through a target registration network to obtain a registered target medical image of a second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolutely same modality.
Further, before registering the target medical image of the first modality by the target registration network, the method further comprises: acquiring the first medical sample image and the second medical sample image, and calculating to obtain a real error mapping map between the first medical sample image and the second medical sample image; performing image enhancement processing on the first medical sample image to obtain a processed first medical sample image; determining the processed first medical sample image, the second medical sample image and the true error map as a first medical sample image pair; and training an initial evaluator according to the first medical sample image to obtain the target evaluator.
Further, acquiring the first medical sample image and the second medical sample image comprises: acquiring an original medical sample image; performing first random spatial transformation on the original medical sample image to obtain a first medical sample image; and carrying out second random spatial transformation on the original medical sample image to obtain a second medical sample image.
Further, performing image enhancement processing on the first medical sample image, and obtaining a processed first medical sample image includes: normalizing the pixel points on the first medical sample image to a preset value range to obtain a normalized first medical sample image; randomly generating a plurality of control points in the preset numerical range, and dividing the normalized first medical sample image according to the plurality of control points to obtain a plurality of segmented first medical sample images, wherein the first control point is the starting point of the preset numerical range, and the second control point is the end point of the preset numerical range; numbering the plurality of segmented first medical sample images and randomly scrambling the sequence of the numbering; and mapping the plurality of segmented first medical sample images according to the random scrambled number sequence to obtain the processed first medical sample image.
Further, training an initial evaluator according to the first medical sample image, and obtaining the target evaluator comprises: performing error evaluation on the processed first medical sample image and the second medical sample image through the initial evaluator to obtain a prediction error mapping image; calculating a loss value according to the prediction error mapping map and the real error mapping map; and training the initial evaluator according to the loss value to obtain the target evaluator.
Further, after training an initial evaluator from the first medical sample image to obtain the target evaluator, the method further comprises: acquiring a second medical sample image pair, wherein the second medical sample image pair consists of a third medical sample image of a first modality and a fourth medical sample image of a second modality; and training an initial registration network according to the second medical sample image pair and the target evaluator to obtain the target registration network.
Further, training the initial registration network according to the second medical sample image pair and the target evaluator to obtain a target registration network comprises: inputting the second medical sample image pair into the initial registration network to obtain a deformation field registered from the third medical sample image to the fourth medical sample image, and registering the third medical sample image according to the deformation field to obtain a registered third medical sample image in a second modality; according to the target evaluator, similarity evaluation is carried out on a third medical sample image in the second modality and a fourth medical sample image in the second modality, and an evaluation result is obtained; obtaining a smooth loss function of the deformation field; and training the initial registration network according to the evaluation result and the smooth loss function to obtain the target registration network.
Further, registering the target medical image of the first modality through a target registration network to obtain a registered target medical image of a second modality includes: inputting the target medical image of the first modality into the target registration network, and obtaining a target deformation field for registering the target medical image of the first modality to the target medical image of the second modality through the target registration network; and registering the target medical image in the first modality according to the target deformation field to obtain a registered target medical image in a second modality.
In order to achieve the above object, according to another aspect of the present application, there is provided a processing apparatus of a medical image. The device includes: a first acquisition unit for acquiring a target medical image of a first modality; the registration unit is configured to register the target medical image of the first modality by a target registration network to obtain a registered target medical image of a second modality, where the target registration network is obtained by training a target evaluator, the target evaluator is obtained by training a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolutely same modality.
Further, the apparatus further comprises: a second obtaining unit, configured to obtain the first medical sample image and the second medical sample image before registering the target medical image in the first modality through a target registration network, and calculate a real error map between the first medical sample image and the second medical sample image; the processing unit is used for carrying out image enhancement processing on the first medical sample image to obtain a processed first medical sample image; a confirmation unit for determining the processed first medical sample image, the second medical sample image and the true error map as a first medical sample image pair; and the first training unit is used for training an initial evaluator according to the first medical sample image to obtain the target evaluator.
Further, the second acquisition unit includes: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring an original medical sample image; the first transformation module is used for carrying out first random spatial transformation on the original medical sample image to obtain a first medical sample image; and the second transformation module is used for carrying out second random spatial transformation on the original medical sample image to obtain a second medical sample image.
Further, the processing unit includes: the normalization module normalizes the pixel points on the first medical sample image into a preset value range to obtain a normalized first medical sample image; the dividing module is used for randomly generating a plurality of control points in the preset numerical range and dividing the normalized first medical sample image according to the control points to obtain a plurality of segmented first medical sample images, wherein the first control point is the starting point of the preset numerical range, and the second control point is the end point of the preset numerical range; a numbering module for numbering the plurality of segmented first medical sample images and randomly scrambling the sequence of the numbering; and the mapping module is used for mapping the plurality of segmented first medical sample images according to the random disordered serial number sequence to obtain the processed first medical sample images.
Further, the first training unit comprises: the first evaluation module is used for carrying out error evaluation on the processed first medical sample image and the second medical sample image through the initial evaluator to obtain a prediction error mapping image; the calculation module is used for calculating a loss value according to the prediction error mapping chart and the real error mapping chart; and the first training module is used for training the initial evaluator according to the loss value to obtain the target evaluator.
Further, the apparatus further comprises: a third obtaining unit, configured to obtain a second medical sample image pair after training the initial evaluator according to the first medical sample image to obtain the target evaluator, where the second medical sample image pair is composed of a third medical sample image of the first modality and a fourth medical sample image of the second modality; and the second training unit is used for training the initial registration network according to the second medical sample image pair and the target evaluator to obtain the target registration network.
Further, the second training unit comprises: a first registration module, configured to input the second medical sample image pair into the initial registration network, so as to obtain a deformation field registered from the third medical sample image to the fourth medical sample image, and register the third medical sample image according to the deformation field, so as to obtain a registered third medical sample image in a second modality; the second evaluation module is used for carrying out similarity evaluation on a third medical sample image in the second modality and a fourth medical sample image in the second modality according to the target evaluator to obtain an evaluation result; a second obtaining module, configured to obtain a smooth loss function of the deformation field; and the second training module is used for training the initial registration network according to the evaluation result and the smooth loss function to obtain the target registration network.
Further, the registration unit includes: an input module, configured to input the target medical image in the first modality into the target registration network, and obtain, through the target registration network, a target deformation field for registering the target medical image in the first modality to the target medical image in the second modality; and the second configuration module is used for registering the target medical image in the first modality according to the target deformation field to obtain a registered target medical image in a second modality.
In order to achieve the above object, according to another aspect of the present application, there is also provided a computer-readable storage medium storing a program, wherein when the program runs, a device on which the storage medium is located is controlled to execute the medical image processing method according to any one of the above items.
To achieve the above object, according to one aspect of the present application, there is provided an electronic device including one or more processors and a memory for storing the one or more processors to implement the method of processing a medical image as described in any one of the above.
Through the application, the following steps are adopted: acquiring a target medical image of a first modality; the method comprises the steps of registering a target medical image of a first modality through a target registration network to obtain a registered target medical image of a second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of the first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolute same modality, so that the problem of low accuracy of registration of the registration network to the images due to the fact that the registration network is trained through existing multi-modality data in the related art is solved. According to the scheme, the target evaluator is obtained through absolute homomodal image training, so that the target evaluator only focuses on the difference of spatial positions and does not focus on the difference of multi-modal distribution caused by different image acquisition mechanisms, the registration network is optimized and trained through the target evaluator, the configuration effect of the registration network can be effectively improved, and the effect of improving the registration accuracy of the registration network on images is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a flow chart of a method of processing a medical image provided according to an embodiment of the application;
FIG. 2 is a schematic diagram of a trained target evaluator provided in accordance with an embodiment of the present application;
fig. 3 is a schematic diagram of a trained target registration network provided in accordance with an embodiment of the present application;
FIG. 4 is a schematic diagram of a medical image processing apparatus provided according to an embodiment of the application;
fig. 5 is a schematic diagram of an electronic device provided according to an embodiment of the application.
Detailed Description
It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of description, some terms or expressions referred to in the embodiments of the present application are explained below:
relative to the same modality: for any
If both satisfy a particular and same data distribution rule, i.e.
. Then->
Referred to relative homomorphic data with respect to each other, e.g. MR (magnetic resonance imaging) images taken under different machine parameters.
The absolute same mode: for arbitrary
And j ≠ k, if x j And x k Only through a certain specific spatial transformationφCan be mutually obtained, i.e. <' >>
Or->
. Then->
And are referred to as absolute homomodal data.
Multi-modality images: let x be j And x k Is an image of the same absolute modality
，φLet in x k Generates a random displacement. At this time, x j And x k There is only a spatial difference between them. Next, some noise ε, which we cannot define, is added to x k The method comprises the following steps: />
. This noise will let x k ，x j It is possible to have a large difference in gradation even on the same organ tissue. At this time->
And x k Becomes a multi-modal image relationship.
It should be noted that relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for presentation, analyzed data, medical image data, etc.) referred to in the present disclosure are information and data that are authorized by the user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or organization, before obtaining the relevant information, an obtaining request needs to be sent to the user or organization through the interface, and after receiving the consent information fed back by the user or organization, the relevant information is obtained.
The present invention is described below with reference to preferred implementation steps, and fig. 1 is a flowchart of a medical image processing method provided according to an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:
step S101, acquiring a target medical image of a first modality;
in particular, a target medical image of a first modality is acquired, for example, an MR medical image.
Step S102, registering the target medical image of the first modality through a target registration network to obtain a registered target medical image of the second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of the first medical sample image and the second medical sample image, and the first medical sample image and the second medical sample image are images of the absolute same modality.
Specifically, the obtained target medical image of the first modality is input into a target registration network, and the target medical image of the first modality is registered by using the target registration network, so as to obtain a registered target medical image of the second modality, for example, the medical image of the second modality is a CT medical image.
The target registration network is trained by a target evaluator. Because the target evaluator is obtained by training images in the same absolute mode, the target evaluator only focuses on the difference of spatial positions and does not focus on the difference of multi-mode distribution caused by different image acquisition mechanisms, and further, the target evaluator can more accurately evaluate the difference between the two images. Then, the target evaluator correspondingly trains the registration network, so that the registration accuracy of the target registration network can be effectively improved.
How to obtain the target evaluator is crucial, therefore, in the medical image processing method provided in the embodiment of the present application, before registering the target medical image of the first modality through the target registration network, the method further includes: acquiring a first medical sample image and a second medical sample image, and calculating to obtain a real error mapping map between the first medical sample image and the second medical sample image; performing image enhancement processing on the first medical sample image to obtain a processed first medical sample image; determining the processed first medical sample image, the second medical sample image and the real error map as a first medical sample image pair; and training the initial evaluator according to the first medical sample image to obtain the target evaluator.
Specifically, a first medical sample image and a second medical sample image in the same absolute modality are acquired, an absolute error is calculated for the first medical sample image and the second medical sample image, an error map having the same dimension as the first medical sample image can be accurately obtained, and the error map can be used as a real label between the first medical sample image and the second medical sample image. Since noise epsilon is added to the medical image during generation of the actual medical image, in order to enable the evaluator to accurately evaluate the difference between the first medical sample image with noise and the second medical sample image, a mode of image enhancement of the first medical sample image is adopted. By performing image enhancement on the first medical sample image, the diversity of the training sample can be greatly increased, and therefore the accuracy of the evaluation of the evaluator can be improved.
The processed first medical sample image (i.e. the image enhanced first medical sample image), the second medical sample image and the true error map are determined as a first medical sample image pair. And training the initial evaluator through the first medical sample image pair to obtain the target evaluator.
In the medical image processing method provided by the embodiment of the application, the following steps are adopted to obtain the first medical sample image and the second medical sample image: acquiring an original medical sample image; carrying out first random spatial transformation on an original medical sample image to obtain a first medical sample image; and carrying out second random spatial transformation on the original medical sample image to obtain a second medical sample image.
Specifically, an original medical sample image is acquired, and a first random spatial variation is added to the original medical sample image
Obtaining a first medical sample image, adding a second random spatial variation->
And obtaining a second medical sample image, wherein the random spatial variation operation comprises but is not limited to rotation, translation, scaling of the whole body, random deformation displacement of each pixel and the like. Since the first medical sample image and the second medical sample image are from the same original medical sample image, they satisfy that there is only a spatial error between them and that the absolute homomorphic definition is satisfied.
How to perform image enhancement to increase the diversity of training samples is crucial, and therefore, in the medical image processing method provided in the embodiment of the present application, performing image enhancement processing on a first medical sample image to obtain a processed first medical sample image includes: normalizing pixel points on the first medical sample image to a preset value range to obtain a normalized first medical sample image; randomly generating a plurality of control points in a preset numerical range, and dividing the normalized first medical sample image according to the plurality of control points to obtain a plurality of segmented first medical sample images, wherein the first control point is a starting point of the preset numerical range, and the second control point is an end point of the preset numerical range; numbering the segmented first medical sample images, and randomly disordering the numbering sequence; and mapping the plurality of segmented first medical sample images according to the random disordered serial number sequence to obtain a processed first medical sample image.
Specifically, pixel points on the first medical sample image are normalized to be within a preset value range, and a normalized first medical sample image is obtained. For example, pixel points on the first medical sample image are normalized to between [ -1,1 ]. A plurality of control points are randomly generated within a preset numerical range. For example, P0 to PN control points are randomly generated between [ -1,1], where P0, PN are the endpoints-1 and 1, and the positions of the remaining Pn points are completely random. Dividing the normalized first medical sample image into a plurality of segmented first medical sample images through the control points, numbering the segmented first medical sample images according to a sequence from small to large, randomly disordering the numbers, and remapping according to the disordering sequence to obtain the processed first medical sample image. For example, a pixel x in the range of (Pi, pi + 1) remaps to the range of (Pj, pj + 1):
wherein, x' is a pixel point after mapping, a pixel point before x mapping,p i for the control point of the i-th order,p j for the jth control point, the control point,p i+1 for the (i + 1) th control point,p j+1 for the j +1 th control point, the above formula maps the pixels x in the range of (Pi, pi + 1) into the range of (Pj, pj + 1) randomly, so as to realize the image enhancement of the first medical sample image.
Through the steps, the diversity of the first medical sample images is effectively improved, the first medical sample images in any modality can be obtained, and the practicability and the robustness of the target evaluator can be effectively improved.
Optionally, in the medical image processing method provided in the embodiment of the present application, training an initial evaluator according to a first medical sample image, and obtaining a target evaluator includes: carrying out error evaluation on the processed first medical sample image and the processed second medical sample image through an initial evaluator to obtain a prediction error mapping chart; calculating according to the prediction error mapping chart and the real error mapping chart to obtain a loss value; and training the initial evaluator according to the loss value to obtain the target evaluator.
Specifically, the processed first medical sample image and the processed second medical sample image are input into an initial evaluator, a prediction error map is obtained through the initial evaluator, the prediction error map is calculated, then a loss value between the prediction error map and a real error map is calculated, and the initial evaluator is trained by minimizing the loss value, so that a target evaluator is obtained. In an alternative embodiment, the loss function may be as follows:
wherein the content of the first and second substances,
for the prediction error map, | x1-x2| is the true error map described above. x1 is the first medical sample image, x2 is the second medical sample image, and x1+ epsilon is the processed first medical sample image.
In an alternative embodiment, the target estimator can be obtained by using the schematic diagram shown in fig. 2, and two random spatial transformations are applied to an original image x respectively
And &>
And transformed x1 and x2 are obtained. The spatial transformation operation includes rotation, translation, scaling of the whole body and random deformation displacement of each pixel. Since x1 and x2 are from the same image x, there is only a spatial error between them, andthe absolute homomorphic definition is satisfied. Then, an absolute error calculation is performed on x1 and x2, so that an error map with the same dimension as x can be accurately obtained and taken as a label. And adding random noise epsilon to x1 to change the modal distribution relation between x1 and x2, and completing the data preparation before training. And then stacking x1+ epsilon and x2 and using the stacked x1+ epsilon and x2 as the input of an initial evaluator E, and finally performing loss calculation on the output predicted by the initial evaluator and the label manufactured before to realize the calculation of the initial evaluator and obtain the target evaluator.
After obtaining the target evaluator, obtaining the target registration network through training of the target evaluator comprises: acquiring a second medical sample image pair, wherein the second medical sample image pair is composed of a third medical sample image of the first modality and a fourth medical sample image of the second modality; and training the initial registration network according to the second medical sample image pair and the target evaluator to obtain the target registration network.
Training the initial registration network according to the second medical sample image pair and the target evaluator to obtain a target registration network, wherein the training comprises the following steps: inputting the second medical sample image pair into an initial registration network to obtain a deformation field from the third medical sample image to the fourth medical sample image in registration, and registering the third medical sample image according to the deformation field to obtain a registered third medical sample image in a second mode; according to the target evaluator, similarity evaluation is carried out on a third medical sample image in the second mode and a fourth medical sample image in the second mode, and an evaluation result is obtained; obtaining a smooth loss function of the deformation field; and training the initial registration network according to the evaluation result and the smooth loss function to obtain the target registration network.
Specifically, a second medical sample image pair is obtained by a third medical sample image of a first modality and a fourth medical sample image of a second modality, then the second medical sample image pair is input into an initial registration network, a deformation field from the third medical sample image to the fourth medical sample image is obtained through registration, the third medical sample image is registered according to the deformation field, the registered third medical sample image of the second modality is obtained, then the registered third medical sample image of the second modality and the registered fourth medical sample image are input into a target evaluator, and similarity evaluation is carried out on the third medical sample image of the second modality and the fourth medical sample image of the second modality by the target evaluator, and an evaluation result is obtained. And finally, training the initial registration network through the evaluation result and the smooth loss function to obtain the target registration network.
In an alternative embodiment, the schematic diagram shown in fig. 3 may be used to train to obtain the target registration network, which has a real moving image x (registration image) and a fixed image y (fixed image). Using x and y as input of registration network R and obtaining deformation field phi from x to y x2y Warping x with a deformation field to obtain a registered image xo phi x2y . Next, xo φ x2y And inputting the fixed image y into a target evaluator to carry out error similarity evaluation. Finally, only the error needs to be minimized and the weight of the registration network R needs to be updated.
In an alternative embodiment, the optimization function of the error similarity evaluation result is as follows:
where E (x o R (x, y), y) is the above error similarity.
In an alternative embodiment, the smoothing loss function is as follows:
wherein ∑ represents a gradient operator, R (x, y) is the degree of correlation between x and y.
Optionally, in the medical image processing method provided in the embodiment of the present application, registering the target medical image in the first modality through the target registration network, and obtaining the registered target medical image in the second modality includes: inputting a target medical image in a first modality into a target registration network, and obtaining a target deformation field for registering the target medical image in the first modality to a target medical image in a second modality through the target registration network; and registering the target medical image of the first modality according to the target deformation field to obtain a registered target medical image of the second modality.
Specifically, a target medical image of a first modality is input into a target registration network, a target deformation field for registering the target medical image of the first modality to a target medical image of a second modality is obtained by using the target registration network, and then the target medical image of the first modality is registered by using the target deformation field, so that a registered target medical image of the second modality is obtained.
According to the medical image processing method provided by the embodiment of the application, a target medical image in a first modality is obtained; the method comprises the steps of registering a target medical image of a first modality through a target registration network to obtain a registered target medical image of a second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of the first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolute same modality, so that the problem of low accuracy of registration of the registration network to the images due to the fact that the registration network is trained through existing multi-modality data in the related art is solved. According to the scheme, the target evaluator is obtained through absolute homomodal image training, so that the target evaluator only focuses on the difference of spatial positions and does not focus on the difference of multi-modal distribution caused by different image acquisition mechanisms, the registration network is optimized and trained through the target evaluator, the configuration effect of the registration network can be effectively improved, and the effect of improving the registration accuracy of the registration network on images is achieved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
The embodiment of the present application further provides a processing apparatus for a medical image, and it should be noted that the processing apparatus for a medical image according to the embodiment of the present application may be used to execute the processing method for a medical image according to the embodiment of the present application. The following describes a medical image processing apparatus provided in an embodiment of the present application.
Fig. 4 is a schematic diagram of a medical image processing apparatus according to an embodiment of the application. As shown in fig. 4, the apparatus includes: a first acquisition unit 401 and a registration unit 402.
A first acquisition unit 401 for acquiring a target medical image of a first modality;
a registration unit 402, configured to register a target medical image in a first modality through a target registration network to obtain a registered target medical image in a second modality, where the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images in an absolutely same modality.
In the medical image processing apparatus provided in the embodiment of the present application, a first obtaining unit 401 obtains a target medical image in a first modality; the registration unit 402 registers a target medical image of a first modality through a target registration network to obtain a registered target medical image of a second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolutely same modality, so that the problem that the registration accuracy of the registration network to the images is low due to the fact that the registration network is trained through existing multi-modality data in the related art is solved. According to the scheme, the target evaluator is obtained through absolute homomodal image training, so that the target evaluator only focuses on the difference of spatial positions and does not focus on the difference of multi-modal distribution caused by different image acquisition mechanisms, the registration network is optimized and trained through the target evaluator, the configuration effect of the registration network can be effectively improved, and the effect of improving the accuracy of the registration network on images is achieved.
Optionally, in the medical image processing apparatus provided in the embodiment of the present application, the apparatus further includes: the second acquisition unit is used for acquiring the first medical sample image and the second medical sample image before the target medical image of the first modality is registered through the target registration network, and calculating to obtain a real error mapping map between the first medical sample image and the second medical sample image; the processing unit is used for carrying out image enhancement processing on the first medical sample image to obtain a processed first medical sample image; a confirming unit, configured to determine the processed first medical sample image, the second medical sample image, and the true error map as a first medical sample image pair; and the first training unit is used for training the initial evaluator according to the first medical sample image to obtain the target evaluator.
Optionally, in the medical image processing apparatus provided in the embodiment of the present application, the second obtaining unit includes: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring an original medical sample image; the first transformation module is used for carrying out first random spatial transformation on the original medical sample image to obtain a first medical sample image; and the second transformation module is used for carrying out second random spatial transformation on the original medical sample image to obtain a second medical sample image.
Optionally, in a medical image processing apparatus provided in an embodiment of the present application, a processing unit includes: the normalization module is used for normalizing pixel points on the first medical sample image into a preset value range to obtain a normalized first medical sample image; the dividing module is used for randomly generating a plurality of control points in a preset numerical range and dividing the normalized first medical sample image according to the control points to obtain a plurality of segmented first medical sample images, wherein the first control point is a starting point of the preset numerical range, and the second control point is an end point of the preset numerical range; the numbering module is used for numbering the segmented first medical sample images and randomly disordering the numbering sequence; and the mapping module is used for mapping the plurality of segmented first medical sample images according to the random disordered serial number sequence to obtain the processed first medical sample images.
Optionally, in the medical image processing apparatus provided in the embodiment of the present application, the first training unit includes: the first evaluation module is used for carrying out error evaluation on the processed first medical sample image and the processed second medical sample image through the initial evaluator to obtain a prediction error mapping image; the calculation module is used for calculating to obtain a loss value according to the prediction error mapping chart and the real error mapping chart; and the first training module is used for training the initial evaluator according to the loss value to obtain the target evaluator.
Optionally, in the medical image processing apparatus provided in the embodiment of the present application, the apparatus further includes: the third acquisition unit is used for acquiring a second medical sample image pair after the initial evaluator is trained according to the first medical sample image to obtain the target evaluator, wherein the second medical sample image pair consists of a third medical sample image in the first modality and a fourth medical sample image in the second modality; and the second training unit is used for training the initial registration network according to the second medical sample image pair and the target evaluator to obtain the target registration network.
Optionally, in the medical image processing apparatus provided in the embodiment of the present application, the second training unit includes: the first registration module is used for inputting the second medical sample image pair into the initial registration network to obtain a deformation field from the third medical sample image to the fourth medical sample image in registration, and registering the third medical sample image according to the deformation field to obtain a registered third medical sample image in a second modality; the second evaluation module is used for carrying out similarity evaluation on a third medical sample image in the second modality and a fourth medical sample image in the second modality according to the target evaluator to obtain an evaluation result; the second acquisition module is used for acquiring a smooth loss function of the deformation field; and the second training module is used for training the initial registration network according to the evaluation result and the smooth loss function to obtain the target registration network.
Optionally, in a medical image processing apparatus provided in an embodiment of the present application, the registration unit includes: the input module is used for inputting the target medical image of the first modality into the target registration network, and obtaining a target deformation field for registering the target medical image of the first modality to the target medical image of the second modality through the target registration network; and the second configuration module is used for registering the target medical image in the first modality according to the target deformation field to obtain a registered target medical image in the second modality.
The medical image processing apparatus comprises a processor and a memory, wherein the first acquisition unit 401, the registration unit 402, and the like are stored in the memory as program units, and the program units stored in the memory are executed by the processor to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to one or more, and the registration of the image is realized by adjusting the kernel parameters.
The memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present invention provides a computer-readable storage medium on which a program is stored, the program implementing a method of processing a medical image when executed by a processor.
As shown in fig. 5, an embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor executes the program to implement the following steps: acquiring a target medical image of a first modality; the method comprises the steps of registering a target medical image in a first modality through a target registration network to obtain a registered target medical image in a second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images in the absolute same modality.
Acquiring a first medical sample image and a second medical sample image, and calculating to obtain a real error mapping map between the first medical sample image and the second medical sample image; performing image enhancement processing on the first medical sample image to obtain a processed first medical sample image; determining the processed first medical sample image, the second medical sample image and the real error map as a first medical sample image pair; and training the initial evaluator according to the first medical sample image to obtain the target evaluator.
Optionally, the acquiring the first medical sample image and the second medical sample image comprises: acquiring an original medical sample image; performing first random spatial transformation on an original medical sample image to obtain a first medical sample image; and carrying out second random spatial transformation on the original medical sample image to obtain a second medical sample image.
Optionally, performing image enhancement processing on the first medical sample image, and obtaining the processed first medical sample image includes: normalizing pixel points on the first medical sample image to a preset value range to obtain a normalized first medical sample image; randomly generating a plurality of control points in a preset numerical range, and dividing the normalized first medical sample image according to the plurality of control points to obtain a plurality of segmented first medical sample images, wherein the first control point is a starting point of the preset numerical range, and the second control point is an end point of the preset numerical range; numbering the segmented first medical sample images, and randomly disordering the numbering sequence; and mapping the plurality of segmented first medical sample images according to the random disordered serial number sequence to obtain a processed first medical sample image.
Optionally, training the initial evaluator according to the first medical sample image, and obtaining the target evaluator comprises: carrying out error evaluation on the processed first medical sample image and the processed second medical sample image through an initial evaluator to obtain a prediction error mapping chart; calculating according to the prediction error mapping chart and the real error mapping chart to obtain a loss value; and training the initial evaluator according to the loss value to obtain the target evaluator.
Optionally, after training the initial evaluator according to the first medical sample image to obtain the target evaluator, the method further includes: acquiring a second medical sample image pair, wherein the second medical sample image pair is composed of a third medical sample image of the first modality and a fourth medical sample image of the second modality; and training the initial registration network according to the second medical sample image pair and the target evaluator to obtain the target registration network.
Optionally, training the initial registration network according to the second medical sample image pair and the target evaluator, and obtaining the target registration network includes: inputting the second medical sample image pair into an initial registration network to obtain a deformation field registered from the third medical sample image to the fourth medical sample image, and registering the third medical sample image according to the deformation field to obtain a registered third medical sample image in a second modality; according to the target evaluator, similarity evaluation is carried out on a third medical sample image in the second mode and a fourth medical sample image in the second mode, and an evaluation result is obtained; obtaining a smooth loss function of the deformation field; and training the initial registration network according to the evaluation result and the smooth loss function to obtain the target registration network.
Optionally, registering the target medical image of the first modality through a target registration network, and obtaining the registered target medical image of the second modality includes: inputting a target medical image of a first modality into a target registration network, and obtaining a target deformation field for registering the target medical image of the first modality to a target medical image of a second modality through the target registration network; and registering the target medical image of the first modality according to the target deformation field to obtain a registered target medical image of the second modality.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: acquiring a target medical image of a first modality; the target medical image of the first modality is registered through a target registration network to obtain a registered target medical image of the second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolute same modality.
Optionally, a first medical sample image and a second medical sample image are obtained, and a real error mapping map between the first medical sample image and the second medical sample image is obtained through calculation; performing image enhancement processing on the first medical sample image to obtain a processed first medical sample image; determining the processed first medical sample image, the second medical sample image and the real error map as a first medical sample image pair; and training the initial evaluator according to the first medical sample image to obtain the target evaluator.
Optionally, the acquiring the first medical sample image and the second medical sample image comprises: acquiring an original medical sample image; performing first random spatial transformation on an original medical sample image to obtain a first medical sample image; and carrying out second random spatial transformation on the original medical sample image to obtain a second medical sample image.
Optionally, performing image enhancement processing on the first medical sample image, and obtaining the processed first medical sample image includes: normalizing pixel points on the first medical sample image to a preset value range to obtain a normalized first medical sample image; randomly generating a plurality of control points in a preset numerical range, and dividing the normalized first medical sample image according to the plurality of control points to obtain a plurality of segmented first medical sample images, wherein the first control point is a starting point of the preset numerical range, and the second control point is an end point of the preset numerical range; numbering the segmented first medical sample images, and randomly disordering the numbering sequence; and mapping the plurality of segmented first medical sample images according to the random disordered serial number sequence to obtain a processed first medical sample image.
Optionally, training the initial evaluator according to the first medical sample image, and obtaining the target evaluator comprises: carrying out error evaluation on the processed first medical sample image and the processed second medical sample image through an initial evaluator to obtain a prediction error mapping chart; calculating according to the prediction error mapping chart and the real error mapping chart to obtain a loss value; and training the initial evaluator according to the loss value to obtain the target evaluator.
Optionally, after training the initial evaluator according to the first medical sample image to obtain the target evaluator, the method further includes: acquiring a second medical sample image pair, wherein the second medical sample image pair is composed of a third medical sample image of the first modality and a fourth medical sample image of the second modality; and training the initial registration network according to the second medical sample image pair and the target evaluator to obtain the target registration network.
Optionally, training the initial registration network according to the second medical sample image pair and the target evaluator, and obtaining the target registration network includes: inputting the second medical sample image pair into an initial registration network to obtain a deformation field from the third medical sample image to the fourth medical sample image in registration, and registering the third medical sample image according to the deformation field to obtain a registered third medical sample image in a second mode; according to the target evaluator, similarity evaluation is carried out on a third medical sample image in the second mode and a fourth medical sample image in the second mode, and an evaluation result is obtained; obtaining a smooth loss function of the deformation field; and training the initial registration network according to the evaluation result and the smooth loss function to obtain the target registration network.
Optionally, registering the target medical image in the first modality by using a target registration network, and obtaining the registered target medical image in the second modality includes: inputting a target medical image of a first modality into a target registration network, and obtaining a target deformation field for registering the target medical image of the first modality to a target medical image of a second modality through the target registration network; and registering the target medical image of the first modality according to the target deformation field to obtain a registered target medical image of the second modality.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (11)
1. A method of processing a medical image, comprising:
acquiring a target medical image of a first modality;
and registering the target medical image of the first modality through a target registration network to obtain a registered target medical image of a second modality, wherein the target registration network is obtained through training of a target evaluator, the target evaluator is obtained through training of a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolutely same modality.
2. The method of processing medical images of claim 1, wherein prior to registering the target medical image of the first modality through a target registration network, the method further comprises:
acquiring the first medical sample image and the second medical sample image, and calculating to obtain a real error mapping map between the first medical sample image and the second medical sample image;
performing image enhancement processing on the first medical sample image to obtain a processed first medical sample image;
determining the processed first medical sample image, the second medical sample image and the true error map as a first medical sample image pair;
and training an initial evaluator according to the first medical sample image to obtain the target evaluator.
3. The method of processing a medical image according to claim 2, wherein acquiring the first medical sample image and the second medical sample image comprises:
acquiring an original medical sample image;
performing first random spatial transformation on the original medical sample image to obtain a first medical sample image;
and carrying out second random spatial transformation on the original medical sample image to obtain a second medical sample image.
4. The method for processing medical images according to claim 2, wherein the performing image enhancement processing on the first medical sample image to obtain the processed first medical sample image comprises:
normalizing the pixel points on the first medical sample image to a preset value range to obtain a normalized first medical sample image;
randomly generating a plurality of control points in the preset numerical range, and dividing the normalized first medical sample image according to the plurality of control points to obtain a plurality of segmented first medical sample images, wherein the first control point is the starting point of the preset numerical range, and the second control point is the end point of the preset numerical range;
numbering the plurality of segmented first medical sample images and randomly scrambling the sequence of numbering;
and mapping the plurality of segmented first medical sample images according to the random scrambled serial number sequence to obtain the processed first medical sample image.
5. The method of claim 2, wherein training an initial evaluator based on the first medical sample image to obtain the target evaluator comprises:
performing error evaluation on the processed first medical sample image and the second medical sample image through the initial evaluator to obtain a prediction error mapping chart;
calculating a loss value according to the prediction error mapping map and the real error mapping map;
and training the initial evaluator according to the loss value to obtain the target evaluator.
6. The method of processing medical images according to claim 1, wherein after training an initial evaluator from the first medical sample image to obtain the target evaluator, the method further comprises:
acquiring a second medical sample image pair, wherein the second medical sample image pair consists of a third medical sample image of a first modality and a fourth medical sample image of a second modality;
and training an initial registration network according to the second medical sample image pair and the target evaluator to obtain the target registration network.
7. The method of claim 6, wherein training an initial registration network according to the second medical sample image pair and the target evaluator to obtain a target registration network comprises:
inputting the second medical sample image pair into the initial registration network to obtain a deformation field from a third medical sample image to a fourth medical sample image, and registering the third medical sample image according to the deformation field to obtain a registered third medical sample image in a second mode;
according to the target evaluator, similarity evaluation is carried out on the third medical sample image in the second modality and the fourth medical sample image in the second modality to obtain an evaluation result;
obtaining a smooth loss function of the deformation field;
and training the initial registration network according to the evaluation result and the smooth loss function to obtain the target registration network.
8. The medical image processing method according to claim 1, wherein registering the target medical image of the first modality through a target registration network to obtain a registered target medical image of the second modality comprises:
inputting the target medical image of the first modality into the target registration network, and obtaining a target deformation field for registering the target medical image of the first modality to the target medical image of the second modality through the target registration network;
and registering the target medical image in the first modality according to the target deformation field to obtain a registered target medical image in a second modality.
9. A medical image processing apparatus, comprising:
a first acquisition unit for acquiring a target medical image of a first modality;
the registration unit is configured to register the target medical image of the first modality by a target registration network to obtain a registered target medical image of a second modality, where the target registration network is obtained by training a target evaluator, the target evaluator is obtained by training a first medical sample image pair, the first medical sample image pair is composed of a first medical sample image and a second medical sample image, and the first medical sample image and the second medical sample image are images of the absolutely same modality.
10. A computer-readable storage medium characterized in that the storage medium stores a program, wherein the program executes the method of processing a medical image according to any one of claims 1 to 8.
11. An electronic device, comprising one or more processors and memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of processing a medical image of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310175697.5A CN115861394B (en) | 2023-02-28 | 2023-02-28 | Medical image processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310175697.5A CN115861394B (en) | 2023-02-28 | 2023-02-28 | Medical image processing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115861394A true CN115861394A (en) | 2023-03-28 |
| CN115861394B CN115861394B (en) | 2023-05-05 |
Family
ID=85659301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310175697.5A Active CN115861394B (en) | 2023-02-28 | 2023-02-28 | Medical image processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115861394B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103948432A (en) * | 2014-04-30 | 2014-07-30 | 深圳先进技术研究院 | Algorithm for augmented reality of three-dimensional endoscopic video and ultrasound image during operation |
| CN110298871A (en) * | 2019-06-10 | 2019-10-01 | 东软医疗系统股份有限公司 | Method for registering images and device |
| CN111862175A (en) * | 2020-07-13 | 2020-10-30 | 清华大学深圳国际研究生院 | Cross-modal medical image registration method and device based on cyclic canonical training |
| US20200402237A1 (en) * | 2017-10-13 | 2020-12-24 | Beijing Keya Medical Technology Co., Ld. | Interactive clinical diagnosis report system |
| CN113822792A (en) * | 2021-06-15 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Image registration method, device, equipment and storage medium |
-
2023
- 2023-02-28 CN CN202310175697.5A patent/CN115861394B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103948432A (en) * | 2014-04-30 | 2014-07-30 | 深圳先进技术研究院 | Algorithm for augmented reality of three-dimensional endoscopic video and ultrasound image during operation |
| US20200402237A1 (en) * | 2017-10-13 | 2020-12-24 | Beijing Keya Medical Technology Co., Ld. | Interactive clinical diagnosis report system |
| CN110298871A (en) * | 2019-06-10 | 2019-10-01 | 东软医疗系统股份有限公司 | Method for registering images and device |
| CN111862175A (en) * | 2020-07-13 | 2020-10-30 | 清华大学深圳国际研究生院 | Cross-modal medical image registration method and device based on cyclic canonical training |
| CN113822792A (en) * | 2021-06-15 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Image registration method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115861394B (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rohlfing et al. | Shape-based averaging | |
| US20230021661A1 (en) | Forgery detection of face image | |
| JP2009520558A (en) | Point-based adaptive elasticity image registration | |
| EP4009278A1 (en) | Method for producing labeled image from original image while preventing private information leakage of original image and server using the same | |
| CN112884820B (en) | Image initial registration and neural network training method, device and equipment | |
| CN112862738B (en) | Method and device for synthesizing multi-mode image, storage medium and processor | |
| Laddi et al. | An augmented image gradients based supervised regression technique for iris center localization | |
| Hu et al. | Domain-adaptive 3d medical image synthesis: An efficient unsupervised approach | |
| CN116563096B (en) | Method and device for determining deformation field for image registration and electronic equipment | |
| Kelenyi et al. | SAM-Net: self-attention based feature matching with spatial transformers and knowledge distillation | |
| CN105190689A (en) | Image processing including adjoin feature based object detection, and/or bilateral symmetric object segmentation | |
| Han et al. | GPU-accelerated, gradient-free MI deformable registration for atlas-based MR brain image segmentation | |
| CN115861394A (en) | Medical image processing method and device, storage medium and electronic equipment | |
| Saygili | Predicting medical image registration error with block-matching using three orthogonal planes approach | |
| CN110310314A (en) | Method for registering images, device, computer equipment and storage medium | |
| Molnár et al. | Representation learning for point clouds with variational autoencoders | |
| Almogadwy et al. | A deep learning approach for slice to volume biomedical image integration | |
| CN113012204B (en) | Registration method, registration device, storage medium and processor for multi-mode image | |
| Hoegele | A Stochastic-Geometrical Framework for Object Pose Estimation Based on Mixture Models Avoiding the Correspondence Problem | |
| Zhang et al. | A comparative study for non-rigid image registration and rigid image registration | |
| Siddiqi et al. | A Network Analysis for Correspondence Learning via Linearly-Embedded Functions | |
| Wang | Cross-domain microscopy cell counting by disentangled transfer learning | |
| Hu et al. | Manifold‐based feature point matching for multi‐modal image registration | |
| Hosny et al. | CUDAQuat: new parallel framework for fast computation of quaternion moments for color images applications | |
| CN116013475B (en) | Method and device for sketching multi-mode medical image, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |