CN110838139A - Training method of image registration model, image registration method and computer equipment - Google Patents

Training method of image registration model, image registration method and computer equipment Download PDF

Info

Publication number
CN110838139A
CN110838139A CN201911064283.5A CN201911064283A CN110838139A CN 110838139 A CN110838139 A CN 110838139A CN 201911064283 A CN201911064283 A CN 201911064283A CN 110838139 A CN110838139 A CN 110838139A
Authority
CN
China
Prior art keywords
image
deformation field
loss
image registration
training sample
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
Application number
CN201911064283.5A
Other languages
Chinese (zh)
Other versions
CN110838139B (en
Inventor
马姗姗
曹晓欢
薛忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai United Imaging Intelligent Healthcare Co Ltd
Original Assignee
Shanghai United Imaging Intelligent Healthcare Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai United Imaging Intelligent Healthcare Co Ltd filed Critical Shanghai United Imaging Intelligent Healthcare Co Ltd
Priority to CN201911064283.5A priority Critical patent/CN110838139B/en
Publication of CN110838139A publication Critical patent/CN110838139A/en
Application granted granted Critical
Publication of CN110838139B publication Critical patent/CN110838139B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Abstract

The application relates to a training method of an image registration model, an image registration method and computer equipment. The training method of the image registration model comprises the following steps: acquiring a first training sample image and a second training sample image; inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field; calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field; calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model. The method ensures the precision of the image registration model, and simultaneously enables the deformation field obtained according to the image registration model to be reversible.

Description

Training method of image registration model, image registration method and computer equipment
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a training method for an image registration model, an image registration method, and a computer device.
Background
The image registration is a process of performing spatial matching on the two images, and if the image A is to be registered to the image B, the image B is used as a reference image, the image A is used as a floating image, and a deformation field of the image A registered to the image B is obtained. The medical image registration technology is the basis of medical image processing, and plays an important role in the fields of image information fusion, auxiliary diagnosis, surgical planning, basic theory research of medicine and the like. The early medical image registration method is mainly a gray level-based registration method, and uses an image to be registered as two frames of a continuously moving image sequence according to an optical flow field theory, and then calculates the size of a deformation field, thereby realizing the registration of the image. However, under the conditions of poor medical image quality and large deformation, the registration accuracy is obviously reduced.
With the continuous development of artificial intelligence technology, a medical image registration method based on deep learning also comes, and a large number of training samples are needed to learn the characteristics of data in a continuous iteration mode. In the conventional technology, the first-order gradient of a deformation field is generally used as a regularized loss function to guide the update of network parameters in the training process of an image registration network so as to train and obtain a converged image registration network.
However, the conventional technology only considers local smoothness of a deformation field, and the obtained image registration network has low precision, so that the result of image registration by using the image registration network has low accuracy and does not have good inverse consistency.
Disclosure of Invention
Based on this, it is necessary to provide a training method of an image registration model, an image registration method, and a computer device for solving the problems that the result of image registration in the conventional technology is also low in accuracy and does not have good inverse consistency.
In a first aspect, an embodiment of the present application provides a training method for an image registration model, including:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
In one embodiment, the method further includes:
calculating the smooth loss of the deformation field according to the second deformation field;
and calculating the network loss according to the image registration loss, the inverse consistency loss and the deformation field smoothing loss.
In one embodiment, inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field, including:
inputting the first training sample image as a floating image and the second training sample image as a reference image into an initial image registration network for image registration to obtain a first deformation field;
and taking the second training sample image as a floating image, taking the first training sample image as a reference image, inputting the first training sample image into an initial image registration network for image registration, and obtaining a second deformation field.
In one embodiment, calculating an image registration loss from the second deformation field, the first training sample image, and the second training sample image comprises:
performing image space transformation on the second training sample image by using the second deformation field to obtain a registration image;
and calculating a difference value between the registration image and the first training sample image, and taking the difference value as an image registration loss.
In one embodiment, calculating an inverse conformity loss based on the first deformation field and the second deformation field comprises:
carrying out deformation field spatial transformation on the first deformation field by using the second deformation field to obtain a deformation field after spatial transformation;
and calculating the inverse consistency loss according to the deformation field after the space transformation and the second deformation field.
In one embodiment, calculating an inverse conformity loss from the spatially transformed deformation field and the second deformation field comprises:
summing the pixel point values of the corresponding positions in the space-transformed deformation field and the second deformation field to obtain a summation result;
the sum of squares of the summed results is calculated as the inverse consistency loss.
In one embodiment, performing deformation field spatial transformation on the first deformation field by using the second deformation field to obtain a spatially transformed deformation field, includes:
determining the pointing position of a pixel point in the second deformation field, and calculating the value of the first deformation field at the pointing position by using an interpolation algorithm;
and taking the value of the pointing position as the value of the deformation field after the space transformation at the pixel point to obtain the deformation field after the space transformation.
In one embodiment, calculating the deformation field smoothing loss from the second deformation field comprises:
and calculating the square sum of all pixel point values of the first-order gradient of the second deformation field, and taking the square sum as the deformation field smoothing loss.
In a second aspect, an embodiment of the present application provides an image registration method, including:
acquiring an image to be registered and a reference image;
inputting the image to be registered and the reference image into an image registration model for image registration to obtain a registration result of the image to be registered; the training mode of the image registration model comprises the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
In a third aspect, an embodiment of the present application provides a training apparatus for an image registration model, including:
the first acquisition module is used for acquiring a first training sample image and a second training sample image;
the first image registration module is used for inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
the calculation module is used for calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image and calculating inverse consistency loss according to the first deformation field and the second deformation field;
the training module is used for calculating network loss according to the image registration loss and the inverse consistency loss and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
In a fourth aspect, an embodiment of the present application provides an image registration apparatus, including:
the second acquisition module is used for acquiring the image to be registered and the reference image;
and the second image registration module is used for inputting the image to be registered and the reference image into the image registration model for image registration to obtain a registration result of the image to be registered.
In a fifth aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the following steps when executing the computer program:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
In a sixth aspect, an embodiment of the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the following steps when executing the computer program:
acquiring an image to be registered and a reference image;
inputting the image to be registered and the reference image into an image registration model for image registration to obtain a registration result of the image to be registered; the training mode of the image registration model comprises the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
In an eighth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following steps:
acquiring an image to be registered and a reference image;
inputting the image to be registered and the reference image into an image registration model for image registration to obtain a registration result of the image to be registered; the training mode of the image registration model comprises the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
Firstly, acquiring a first training sample image and a second training sample image; inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field; then, calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field; finally, calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model. In the method, besides the registration loss during image registration, the accuracy of an image registration model is ensured, and the inverse consistency loss between deformation fields obtained by mutual registration of images is also considered, namely f is consideredABAnd fBAEqual and opposite properties between the deformation fields, thereby making the deformation field obtained from the image registration model reversible, i.e. from fABCan be converted into fBAAnd the calculation by the network model is not needed.
Drawings
Fig. 1 is a schematic flowchart of a training method of an image registration model according to an embodiment;
fig. 2 is a schematic flowchart of a training method of an image registration model according to another embodiment;
fig. 3 is a schematic flowchart of a training method of an image registration model according to yet another embodiment;
FIG. 3a is a schematic diagram of a deformation field spatial transformation process provided by an embodiment;
FIG. 3b is a diagram illustrating a training process of an image registration model according to an embodiment;
FIG. 4 is a flowchart illustrating an image registration method according to an embodiment;
FIG. 5 is a schematic structural diagram of a training apparatus for an image registration model according to an embodiment;
fig. 6 is a schematic structural diagram of an image registration apparatus according to an embodiment;
fig. 7 is a schematic internal structural diagram of a computer device according to an embodiment.
Detailed Description
The training method of the image registration model provided by the embodiment of the application can be suitable for the training process of the network model for image registration, and the image can be a medical image or an image in other fields. The image registration mainly comprises rigid and non-rigid types, and the rigid registration mainly solves the problems of simple integral image movement, such as translation, rotation and the like; the non-rigid registration mainly solves the problem of elastic transformation of images, and allows the corresponding relation between any two pixel points to change in the transformation process. The medical image registration technology is the basis and the premise in the aspects of operation plan customization, image-guided radiotherapy, medical image fusion treatment and the like, and has important clinical application value; meanwhile, most tissues and organs of the human body have non-rigid characteristics, so that the method has important significance for the research of non-rigid medical images.
Medical image registration refers to seeking one or a series of spatial transformations for one medical image to bring it into spatial correspondence with corresponding points on another medical image or images. The correspondence is established for matching anatomical structures in the two images. The general strategy of the registration algorithm is to define an objective function (also called energy function) E ═ E (M, T (F)) assuming that two images to be registered are M and F, respectively, where T represents the spatial transformation of the image F, and the size of the value of E is generally considered to represent the degree of registration of the images, and for a particular registration task, the images M and F are determined, and therefore E is a function of the spatial transformation T, i.e., E ═ E (T). The problem of registration thus translates into the problem of finding a certain spatial transformation T that optimizes E ═ E (T). According to the definition of E, the optimal value corresponds to the maximum value or the minimum value, and after E is defined, a problem must be solved, namely how to find the spatial transformation T so that E obtains the optimal value. In theory, there is a one-to-one transformation relationship between the points of the image a and the image B, and ideally, the spatial position correspondence is mutual, that is, the spatial transformation relationship from the image a to the image B can be changed into the spatial transformation relationship from the image B to the image a through some conversion. For the task of non-rigid registration, the spatial transformation relationship is embodied in the deformation field obtained by the non-rigid registration model, i.e. the deformation field should have inverse consistency.
In recent years, with the great enhancement of computer computing capability, the method has the capability of processing mass data, the artificial intelligent neural network technology plays a great role in practical application, and meanwhile, deep learning also becomes a core topic in the field of artificial intelligence. In the field of medical health, the application of deep learning in medical images is mainly expressed as auxiliary diagnosis or image detection. The deep learning-based medical image registration directly learns the characteristics of data from a large number of training samples in a continuous iteration mode, and forms more abstract high-level characteristics by combining low-level characteristics, so that a network model is obtained to realize the image registration. For the deep learning-based medical image registration, T is a network structure, E is a loss function, and the optimization problem of E is that the related parameters of the network structure are updated iteratively through a back propagation algorithm according to the loss value of the loss function.
Non-rigid medical image registration methods based on deep learning are mainly classified into two categories: supervised learning and unsupervised learning. However, the supervised learning method requires a large amount of labeled data, and the medical image registration task has difficulty in acquiring gold standard data. Therefore, an unsupervised method based on deep learning becomes the first choice of a non-rigid registration task of a medical image, a commonly used network structure is a UNet network structure based on a convolutional neural network, and the mapping of the image to be registered to a deformation field is realized through regression learning. In addition, in order to obtain a smoother deformation field, the conventional technology generally takes the first-order gradient of the deformation field as a regular loss function to guide the updating of parameters in the network training process, so that the learned deformation field is smoother. However, the method for controlling the smoothness of the deformation field only considers the local smoothness of the deformation field, cannot avoid the crossing of the deformation field, has low accuracy of the result of image registration, and cannot fundamentally ensure that the deformation field obtained by the non-rigid registration model has inverse consistency. The application provides a training method of an image registration model, an image registration method and computer equipment, and aims to solve the technical problems.
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application are further described in detail by the following embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that the execution subject of the method embodiments described below may be a training apparatus of an image registration model, and the apparatus may be implemented as part of or all of a computer device by software, hardware, or a combination of software and hardware. The following method embodiments take an execution subject as a computer device for example, where the computer device may be a terminal, may also be a server, may be a separate computing device, or may be integrated on a medical imaging device, as long as the training of the image registration model can be completed, and this embodiment is not limited thereto.
Fig. 1 is a schematic flowchart of a training method of an image registration model according to an embodiment. The embodiment relates to a specific process of training an initial image registration network by using a first training sample image and a second training sample image to obtain an image registration model by using computer equipment. As shown in fig. 1, the method includes:
s101, a first training sample image and a second training sample image are obtained.
Specifically, the computer device needs to acquire a large number of training sample images, in this embodiment, the training sample images are divided into a first training sample image and a second training sample image, and an image is required to be used as a reference image and an image is required to be used as a floating image in the image registration process, which is not substantially different. The training sample images may be divided into two groups, one group being a first training sample image and the other group being a second training sample image, or the training sample images may be combined arbitrarily two by two as the first training sample and the second training sample image.
Alternatively, the training sample image may be Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), Computed Tomography (CT), and the like, and may be a brain image, a chest image, an abdomen image, and the like, but it should be noted that two training sample images for performing image registration need to be the same type of image. Optionally, the manner of acquiring the training sample image by the computer device may be directly retrieved from a memory of the computer device, or may be acquired from a Picture Archiving and Communication System (PACS), which is not limited in this embodiment.
S102, inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field.
Specifically, the computer device inputs the first training sample image and the second training sample image into an initial image registration network for mutual image registration, so as to obtain a first deformation field and a second deformation field. Optionally, the computer device may input the first training sample image a as a floating image and the second training sample image B as a reference image into the initial image registration network for image registration to obtain the first deformation field fAB(ii) a Inputting the second training sample image B as a floating image and the first training sample image A as a reference image into an initial image registration network for image registration to obtain a second deformation field fBA. Optionally, the computer device may also perform image registration by using the second training sample image B as a floating image and the first training sample image a as a reference image, and then perform image registration by using the first training sample image a as a floating image and the second training sample image B as a reference imageThis embodiment is not limited to this order.
Optionally, the initial image registration network may be a Neural network model, may be a Convolutional Neural Network (CNN), a Full Convolutional Network (FCN), or may be another network model. Optionally, the initial image registration network is a UNet network, and the entire network structure is divided into two parts, namely a compression path and an uncompressed path, that is, feature mapping of the reduced and expanded images, and the low-level features of the reduced end are sent to the corresponding positions of the expanded end, so that more effective information is provided for model training, and convergence of the model in the training process is accelerated.
S103, calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field.
Specifically, the computer device may calculate the image registration loss according to the second deformation field, the first training sample image, and the second training sample image, where the second deformation field is a deformation field obtained by performing image registration for the last time by the initial image registration network, and may be fABMay also be fBAIt is not specified which deformation field is based on the processing order thereof. Assuming that the second deformation field is fBAThen according to fBAAnd the second training sample image may result in an image after registration, and then the image after registration may be compared to the first training sample image resulting in an image registration loss. Alternatively, the Loss function of the image registration Loss may be a mean square error Loss (MSE Loss) or a normalized cross correlation Loss (NCC Loss).
Then, the computer device further calculates an inverse consistency loss from the first deformation field and the second deformation field, assuming the first deformation field as fABThe second deformation field is fBAThe computer device will fABConversion to fBAObtaining f under a space coordinate systemAB', theoretically fAB' and fBAShould have equal and opposite relationships, i.e. fAB’+fBA0. But since the initial image registration network at this time has not converged, fAB' and fBAThe sum of (a) and (b) is different from 0 to some extent, and the difference is used to obtain a corresponding inverse consistency loss.
S104, calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
Specifically, the computer device may calculate the network loss according to the image registration loss and the inverse consistency loss, and optionally, may directly sum the image registration loss and the inverse consistency loss, or average sum, or weighted sum, to obtain the network loss. When the loss is weighted and summed, each loss has a different weight, and the weight represents the importance degree of the loss; the greater the weight, the greater the contribution of this loss in the training process. And then the computer equipment adjusts the network parameters of the initial image registration network by using the obtained network loss, and optionally, the network parameters can be adjusted by adopting a reverse gradient propagation method.
The initial image registration network is iteratively trained in the above manner, and when the network loss in a certain iterative process meets a preset condition, the training of the initial image registration network is represented to be completed, so that a convergent image registration model is obtained. Optionally, the preset condition may be that the network loss reaches convergence, or that the network loss is less than or equal to a preset threshold, which is not limited in this embodiment.
In the training method of the image registration model provided by this embodiment, the computer device inputs the acquired first training sample image and second training sample image into the initial image registration network to perform mutual image registration, so as to obtain a first deformation field and a second deformation field; then, calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field; finally, calculating the network loss according to the image registration loss and the inverse consistency loss, training the initial image registration network by using the network loss,until a converged image registration model is obtained. In the method, besides the registration loss during image registration, the accuracy of an image registration model is ensured, and the inverse consistency loss between deformation fields obtained by mutual registration of images is also considered, namely f is consideredABAnd fBAEqual and opposite properties between the deformation fields, thereby making the deformation field obtained from the image registration model reversible, i.e. from fABCan be converted into fBAAnd the calculation by the network model is not needed.
Optionally, in some embodiments, the method further includes: calculating the smooth loss of the deformation field according to the second deformation field; and calculating the network loss according to the image registration loss, the inverse consistency loss and the deformation field smoothing loss.
Alternatively, the computer device may calculate a sum of squares of all pixel points of the first order gradient of the second deformation field, and take the sum of squares as the deformation field smoothing loss. Optionally, the computer device may directly sum the image registration loss, the inverse consistency loss, and the deformation field smoothing loss, or average sum, or weighted sum, to obtain the network loss. Therefore, local smoothness of the deformation field is considered, and the accuracy of the obtained image registration model is further improved.
Fig. 2 is a schematic flowchart of a training method of an image registration model according to another embodiment. The embodiment relates to a specific process of calculating the image registration loss by the computer device according to the second deformation field, the first training sample image and the second training sample image. On the basis of the foregoing embodiment, optionally, as shown in fig. 2, S103 may include:
s201, image space transformation is carried out on the second training sample image by using the second deformation field, and a registration image is obtained.
Specifically, the computer device performs image space transformation on the second training sample image (i.e., the floating image) by using the second deformation field, that is, calculates the second training sample image by using an interpolation algorithm according to the coordinate position corresponding relationship provided by the second deformation field, so as to obtain the registration image. The second deformation field of this embodiment is made for the second training sample image BInputting the floating image and the first training sample image A as reference images into an initial image registration network for image registration to obtain a deformation field fBABut is not limited to fBA。
S202, calculating a difference value between the registration image and the first training sample image, and taking the difference value as an image registration loss.
Specifically, the computer device calculates a difference value between the registration image and the first training sample image (i.e., the reference image), and optionally, may calculate a pixel difference value of the registration image and the first training sample image at the corresponding coordinate position, and use the difference value as an image registration loss.
In the training method of the image registration model provided in this embodiment, the computer device performs image space transformation on the second training sample image by using the second deformation field to obtain the registration image, then calculates a difference value between the registration image and the first training sample image, and uses the difference value as an image registration loss. By calculating the image registration loss between the reference image and the registration image and taking the image registration loss as partial loss to carry out gradient return in the updating process of the initial image registration network, the registration accuracy of the obtained image registration model can be further improved.
Fig. 3 is a flowchart illustrating a training method of an image registration model according to yet another embodiment. The present embodiment relates to a specific process in which a computer device calculates an inverse conformity loss from a first deformation field and a second deformation field. On the basis of the above embodiment, optionally, as shown in fig. 3, S103 may include:
and S301, performing deformation field space transformation on the first deformation field by using the second deformation field to obtain a deformation field after space transformation.
S302, calculating the inverse consistency loss according to the deformation field after the space transformation and the second deformation field.
In particular, the computer device may perform a deformation field spatial transformation on the first deformation field using the second deformation field, assuming that the first deformation field is fABThe second deformation field is fBAOptionally, using fBATo fABCarrying out deformation field space transformation to obtain space transformationThe deformation field of (a) may be: determining a second deformation field fBAThe pointing position b (x + dx, y + dy) of the middle pixel point a (x, y) is used for calculating a first deformation field f by utilizing an interpolation algorithmABA value c at the pointing position b; using the value of c as the deformation field f after space transformationAB' at the value of pixel point a, the deformation field f after space transformation can be obtainedAB’。
Then, the computer device transforms the deformation field f according to the spaceAB' and a second deformation field fBACalculating the inverse consistency loss, optionally, the spatially transformed deformation field fAB' with a second deformation field fBAThe pixel point values of the corresponding positions in the image are summed to obtain a summation result, the sum of squares of the summation result is calculated, and the sum of squares is used as the inverse consistency loss. Alternatively, the computer device may be based on
Figure BDA0002258841440000151
Calculating the inverse consistency loss, where i is the pixel point position, fiIs' fAB' Pixel value of Point i, giIs fBAPixel point values of the intermediate i point. A schematic diagram of the deformation field spatial transformation process can be seen in fig. 3 a. The training process for the image registration model can be seen in the schematic diagram shown in fig. 3 b.
In the training method of the image registration model provided in this embodiment, the computer device performs deformation field spatial transformation on the first deformation field by using the second deformation field to obtain a deformation field after spatial transformation, and calculates the inverse consistency loss according to the deformation field after spatial transformation and the second deformation field. The inverse consistency loss between the first deformation field and the second deformation field is calculated by transforming the first deformation field to a second deformation field space coordinate system, so that the accuracy of the calculated inverse consistency loss can be improved, and the inverse consistency loss is used as partial loss to carry out gradient pass-back in the updating process of the initial image registration network, so that the reversibility of the deformation field of the image registration model can be greatly improved.
After the training of the image registration model is completed, image registration may be performed by using the model, and fig. 4 is a schematic flow chart of an image registration method according to an embodiment, where the method includes:
s401, an image to be registered and a reference image are obtained.
S402, inputting the image to be registered and the reference image into an image registration model for image registration to obtain a registration result of the image to be registered; the training mode of the image registration model comprises the following steps: acquiring a first training sample image and a second training sample image; inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field; calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field; calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
Specifically, after the computer device obtains the image to be registered and the reference image, the image to be registered is input into the image registration model as the floating image and the reference image for image registration, and a registration result of the image to be registered can be obtained. Alternatively, the registration result may be a deformation field of the image to be registered to the reference image. For the training process of the image registration model, reference may be made to the method shown in the above embodiment, and the implementation process is similar to the principle and is not described herein again.
According to the image registration method provided by the embodiment, the adopted image registration model has certain reversibility of a deformation field and higher precision, so that the registration result of the obtained image to be registered is higher in accuracy and also has inverse consistency.
It should be understood that although the various steps in the flowcharts of fig. 1-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
Fig. 5 is a schematic structural diagram of a training apparatus for an image registration model according to an embodiment. As shown in fig. 5, the apparatus includes: a first acquisition module 11, a first image registration module 12, a calculation module 13 and a training module 14.
Specifically, the first obtaining module 11 is configured to obtain a first training sample image and a second training sample image.
The first image registration module 12 is configured to input the first training sample image and the second training sample image into an initial image registration network to perform mutual image registration, so as to obtain a first deformation field and a second deformation field.
And a calculating module 13, configured to calculate an image registration loss according to the second deformation field, the first training sample image, and the second training sample image, and calculate an inverse consistency loss according to the first deformation field and the second deformation field.
The training module 14 is used for calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
The training device for the image registration model provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the calculating module 13 is further configured to calculate a deformation field smoothing loss according to the second deformation field; and the training module 14 is further used for calculating network loss according to the image registration loss, the inverse consistency loss and the deformation field smoothing loss.
In one embodiment, the first image registration module 12 is specifically configured to use the first training sample image as a floating image, and use the second training sample image as a reference image to be input into an initial image registration network for image registration, so as to obtain a first deformation field; and taking the second training sample image as a floating image, taking the first training sample image as a reference image, inputting the first training sample image into an initial image registration network for image registration, and obtaining a second deformation field.
In one embodiment, the calculation module 13 includes an image space transformation unit and a calculation unit; the image space transformation unit is used for carrying out image space transformation on the second training sample image by utilizing the second deformation field to obtain a registration image; and the calculating unit is used for calculating a difference value between the registration image and the first training sample image and taking the difference value as an image registration loss.
In one embodiment, the calculation module 13 further comprises a deformation field transformation unit; the deformation field transformation unit is used for carrying out deformation field space transformation on the first deformation field by utilizing the second deformation field to obtain a deformation field after space transformation; and the calculation unit is also used for calculating the inverse consistency loss according to the deformation field after the space transformation and the second deformation field.
In one embodiment, the calculation unit is specifically configured to sum the pixel point values of the corresponding positions in the spatially transformed deformation field and the second deformation field to obtain a sum result; the sum of squares of the summed results is calculated as the inverse consistency loss.
In one embodiment, the deformation field transformation unit is specifically configured to determine a pointing position of a pixel point in the second deformation field, and calculate a value of the first deformation field at the pointing position by using an interpolation algorithm; and taking the value of the pointing position as the value of the deformation field after the space transformation at the pixel point to obtain the deformation field after the space transformation.
In one embodiment, the calculation module 13 is specifically configured to calculate a sum of squares of all pixel point values of the first order gradient of the second deformation field, and to use the sum of squares as the deformation field smoothing loss.
Fig. 6 is a schematic structural diagram of an image registration apparatus according to an embodiment. As shown in fig. 6, the apparatus includes: a second acquisition module 21 and a second image registration module 22.
Specifically, the second obtaining module 21 is configured to obtain an image to be registered and a reference image.
And the second image registration module 22 is configured to input the image to be registered and the reference image into the image registration model for image registration, so as to obtain a registration result of the image to be registered. The training process of the image registration model may refer to the implementation process of the above training apparatus embodiment of the image registration model.
The image registration apparatus provided in this embodiment may implement the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
For specific limitations of the training apparatus and the image registration apparatus of the image registration model, reference may be made to the above limitations of the training method and the image registration method of the image registration model, which are not described herein again. The above-mentioned training device of the image registration model and each module in the image registration device may be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of training an image registration model or a method of image registration. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
The implementation principle and technical effect of the computer device provided in this embodiment are similar to those of the method embodiments described above, and are not described herein again.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
calculating the smooth loss of the deformation field according to the second deformation field;
and calculating the network loss according to the image registration loss, the inverse consistency loss and the deformation field smoothing loss.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
inputting the first training sample image as a floating image and the second training sample image as a reference image into an initial image registration network for image registration to obtain a first deformation field;
and taking the second training sample image as a floating image, taking the first training sample image as a reference image, inputting the first training sample image into an initial image registration network for image registration, and obtaining a second deformation field.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
performing image space transformation on the second training sample image by using the second deformation field to obtain a registration image;
and calculating a difference value between the registration image and the first training sample image, and taking the difference value as an image registration loss.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out deformation field spatial transformation on the first deformation field by using the second deformation field to obtain a deformation field after spatial transformation;
and calculating the inverse consistency loss according to the deformation field after the space transformation and the second deformation field.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
summing the pixel point values of the corresponding positions in the space-transformed deformation field and the second deformation field to obtain a summation result;
the sum of squares of the summed results is calculated as the inverse consistency loss.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining the pointing position of a pixel point in the second deformation field, and calculating the value of the first deformation field at the pointing position by using an interpolation algorithm;
and taking the value of the pointing position as the value of the deformation field after the space transformation at the pixel point to obtain the deformation field after the space transformation.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and calculating the square sum of all pixel point values of the first-order gradient of the second deformation field, and taking the square sum as the deformation field smoothing loss.
In one embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the following steps when executing the computer program:
acquiring an image to be registered and a reference image;
inputting the image to be registered and the reference image into an image registration model for image registration to obtain a registration result of the image to be registered; the training mode of the image registration model comprises the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
The implementation principle and technical effect of the computer device provided in this embodiment are similar to those of the method embodiments described above, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
The implementation principle and technical effect of the computer-readable storage medium provided by this embodiment are similar to those of the above-described method embodiment, and are not described herein again.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating the smooth loss of the deformation field according to the second deformation field;
and calculating the network loss according to the image registration loss, the inverse consistency loss and the deformation field smoothing loss.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting the first training sample image as a floating image and the second training sample image as a reference image into an initial image registration network for image registration to obtain a first deformation field;
and taking the second training sample image as a floating image, taking the first training sample image as a reference image, inputting the first training sample image into an initial image registration network for image registration, and obtaining a second deformation field.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing image space transformation on the second training sample image by using the second deformation field to obtain a registration image;
and calculating a difference value between the registration image and the first training sample image, and taking the difference value as an image registration loss.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out deformation field spatial transformation on the first deformation field by using the second deformation field to obtain a deformation field after spatial transformation;
and calculating the inverse consistency loss according to the deformation field after the space transformation and the second deformation field.
In one embodiment, the computer program when executed by the processor further performs the steps of:
summing the pixel point values of the corresponding positions in the space-transformed deformation field and the second deformation field to obtain a summation result;
the sum of squares of the summed results is calculated as the inverse consistency loss.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the pointing position of a pixel point in the second deformation field, and calculating the value of the first deformation field at the pointing position by using an interpolation algorithm;
and taking the value of the pointing position as the value of the deformation field after the space transformation at the pixel point to obtain the deformation field after the space transformation.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and calculating the square sum of all pixel point values of the first-order gradient of the second deformation field, and taking the square sum as the deformation field smoothing loss.
In one embodiment, there is also provided a computer readable storage medium having a computer program stored thereon, the computer program when executed by a processor implementing the steps of:
acquiring an image to be registered and a reference image;
inputting the image to be registered and the reference image into an image registration model for image registration to obtain a registration result of the image to be registered; the training mode of the image registration model comprises the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating image registration loss according to the second deformation field, the first training sample image and the second training sample image, and calculating inverse consistency loss according to the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training an initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the initial image registration network training to obtain an image registration model.
The implementation principle and technical effect of the computer-readable storage medium provided by this embodiment are similar to those of the above-described method embodiment, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A training method of an image registration model is characterized by comprising the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating an image registration loss from the second deformation field, the first training sample image, and the second training sample image, and calculating an inverse consistency loss from the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training the initial image registration network by using the network loss; and when the network loss meets a preset condition, finishing the initial image registration network training to obtain an image registration model.
2. The method of claim 1, further comprising:
calculating the smooth loss of the deformation field according to the second deformation field;
calculating the network loss according to the image registration loss, the inverse consistency loss and the deformation field smoothing loss.
3. The method according to claim 1 or 2, wherein the inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field comprises:
taking the first training sample image as a floating image, taking the second training sample image as a reference image, inputting the reference image into the initial image registration network for image registration, and obtaining the first deformation field;
and taking the second training sample image as a floating image, and taking the first training sample image as a reference image to be input into the initial image registration network for image registration to obtain the second deformation field.
4. The method of claim 1, wherein the calculating an image registration loss from the second deformation field, the first training sample image, and the second training sample image comprises:
performing image space transformation on the second training sample image by using the second deformation field to obtain a registration image;
calculating a difference value between the registered image and the first training sample image, and taking the difference value as the image registration loss.
5. The method of claim 1, wherein said calculating an inverse conformity loss from said first deformation field and said second deformation field comprises:
carrying out deformation field spatial transformation on the first deformation field by using the second deformation field to obtain a deformation field after spatial transformation;
and calculating the inverse consistency loss according to the deformation field after the spatial transformation and the second deformation field.
6. The method of claim 5, wherein said calculating the inverse conformity loss from the spatially transformed deformation field and the second deformation field comprises:
summing the pixel point values of the corresponding positions in the space-transformed deformation field and the second deformation field to obtain a summation result;
and calculating the sum of squares of the summation results, and taking the sum of squares as the inverse consistency loss.
7. The method according to claim 5 or 6, wherein said transforming the first deformation field with the second deformation field to obtain a spatially transformed deformation field comprises:
determining the pointing position of a pixel point in the second deformation field, and calculating the value of the first deformation field at the pointing position by using an interpolation algorithm;
and taking the value of the pointing position as the value of the space-transformed deformation field at the pixel point to obtain the space-transformed deformation field.
8. The method of claim 2, wherein said calculating a deformation field smoothing loss from said second deformation field comprises:
calculating the sum of squares of all pixel point values of the second deformation field first order gradient, and taking the sum of squares as the deformation field smoothing loss.
9. An image registration method, comprising:
acquiring an image to be registered and a reference image;
inputting the image to be registered and the reference image into an image registration model for image registration to obtain a registration result of the image to be registered; the training mode of the image registration model comprises the following steps:
acquiring a first training sample image and a second training sample image;
inputting the first training sample image and the second training sample image into an initial image registration network for mutual image registration to obtain a first deformation field and a second deformation field;
calculating an image registration loss from the second deformation field, the first training sample image, and the second training sample image, and calculating an inverse consistency loss from the first deformation field and the second deformation field;
calculating network loss according to the image registration loss and the inverse consistency loss, and training the initial image registration network by using the network loss; and when the network loss meets the preset condition, finishing the training of the initial image registration network to obtain an image registration model.
10. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of claim 9 when executing the computer program.
CN201911064283.5A 2019-11-04 2019-11-04 Training method of image registration model, image registration method and computer equipment Active CN110838139B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911064283.5A CN110838139B (en) 2019-11-04 2019-11-04 Training method of image registration model, image registration method and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911064283.5A CN110838139B (en) 2019-11-04 2019-11-04 Training method of image registration model, image registration method and computer equipment

Publications (2)

Publication Number Publication Date
CN110838139A true CN110838139A (en) 2020-02-25
CN110838139B CN110838139B (en) 2022-10-25

Family

ID=69576141

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911064283.5A Active CN110838139B (en) 2019-11-04 2019-11-04 Training method of image registration model, image registration method and computer equipment

Country Status (1)

Country Link
CN (1) CN110838139B (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111768436A (en) * 2020-06-17 2020-10-13 哈尔滨理工大学 Improved image feature block registration method based on fast-RCNN
CN111862174A (en) * 2020-07-08 2020-10-30 清华大学深圳国际研究生院 Cross-modal medical image registration method and device
CN112200788A (en) * 2020-10-16 2021-01-08 清华大学 High-temperature deformation measuring device and method
CN112802073A (en) * 2021-04-08 2021-05-14 之江实验室 Fusion registration method based on image data and point cloud data
CN113112534A (en) * 2021-04-20 2021-07-13 安徽大学 Three-dimensional biomedical image registration method based on iterative self-supervision
WO2021238171A1 (en) * 2020-05-29 2021-12-02 上海商汤智能科技有限公司 Image registration method and related model training method, device and apparatus
CN114332181A (en) * 2021-12-29 2022-04-12 中国人民解放军国防科技大学 Remote sensing image automatic registration method and device based on non-rigid bidirectional registration network
CN114359356A (en) * 2021-12-28 2022-04-15 上海联影智能医疗科技有限公司 Training method of image registration model, image registration method, device and medium
CN114511599A (en) * 2022-01-20 2022-05-17 推想医疗科技股份有限公司 Model training method and device, medical image registration method and device
CN115393402A (en) * 2022-08-24 2022-11-25 北京医智影科技有限公司 Training method of image registration network model, image registration method and equipment
CN116503453A (en) * 2023-06-21 2023-07-28 福建自贸试验区厦门片区Manteia数据科技有限公司 Image registration method, image registration device, computer-readable storage medium and electronic device

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101887525A (en) * 2010-07-09 2010-11-17 北京师范大学 Grading-based positive and inverse reversing three-dimensional dense point set rapid registering method
US20110081066A1 (en) * 2009-10-07 2011-04-07 Marie-Pierre Jolly System and method for cardiac segmentation in mr-cine data using inverse consistent non-rigid registration
US20120121200A1 (en) * 2010-11-11 2012-05-17 Siemens Corporation Symmetric and Inverse-Consistent Deformable Registration
CN103914847A (en) * 2014-04-10 2014-07-09 西安电子科技大学 SAR image registration method based on phase congruency and SIFT
CN107403446A (en) * 2016-05-18 2017-11-28 西门子保健有限责任公司 Method and system for the image registration using intelligent human agents
CN109272443A (en) * 2018-09-30 2019-01-25 东北大学 A kind of PET based on full convolutional neural networks and CT method for registering images
CN109598745A (en) * 2018-12-25 2019-04-09 上海联影智能医疗科技有限公司 Method for registering images, device and computer equipment
CN110021037A (en) * 2019-04-17 2019-07-16 南昌航空大学 A kind of image non-rigid registration method and system based on generation confrontation network
CN110070935A (en) * 2019-03-20 2019-07-30 中国科学院自动化研究所 Medical image synthetic method, classification method and device based on confrontation neural network
CN110246488A (en) * 2019-06-14 2019-09-17 苏州思必驰信息科技有限公司 Half optimizes the phonetics transfer method and device of CycleGAN model

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110081066A1 (en) * 2009-10-07 2011-04-07 Marie-Pierre Jolly System and method for cardiac segmentation in mr-cine data using inverse consistent non-rigid registration
CN101887525A (en) * 2010-07-09 2010-11-17 北京师范大学 Grading-based positive and inverse reversing three-dimensional dense point set rapid registering method
US20120121200A1 (en) * 2010-11-11 2012-05-17 Siemens Corporation Symmetric and Inverse-Consistent Deformable Registration
CN103914847A (en) * 2014-04-10 2014-07-09 西安电子科技大学 SAR image registration method based on phase congruency and SIFT
CN107403446A (en) * 2016-05-18 2017-11-28 西门子保健有限责任公司 Method and system for the image registration using intelligent human agents
CN109272443A (en) * 2018-09-30 2019-01-25 东北大学 A kind of PET based on full convolutional neural networks and CT method for registering images
CN109598745A (en) * 2018-12-25 2019-04-09 上海联影智能医疗科技有限公司 Method for registering images, device and computer equipment
CN110070935A (en) * 2019-03-20 2019-07-30 中国科学院自动化研究所 Medical image synthetic method, classification method and device based on confrontation neural network
CN110021037A (en) * 2019-04-17 2019-07-16 南昌航空大学 A kind of image non-rigid registration method and system based on generation confrontation network
CN110246488A (en) * 2019-06-14 2019-09-17 苏州思必驰信息科技有限公司 Half optimizes the phonetics transfer method and device of CycleGAN model

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
BOAH KIM等: "Unsupervised Deformable Image Registration Using Cycle-Consistent CNN", 《INTERNATIONAL CONFERENCE ON INFORMATION PROCESSING IN MEDICAL IMAGING MICCAI 2019》 *
JUN ZHANG: "Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration", 《COMPUTER VISION AND PATTERN RECOGNITION》 *
杨晓梅: "几何变分方法在图像配准中的应用", 《中国优秀博硕士学位论文全文数据库(硕士)基础科学辑》 *
陈琳琳: "心脏CT-TEE图像配准", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 *

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102450931B1 (en) 2020-05-29 2022-10-06 상하이 센스타임 인텔리전트 테크놀로지 컴퍼니 리미티드 Image registration method and associated model training method, apparatus, apparatus
WO2021238171A1 (en) * 2020-05-29 2021-12-02 上海商汤智能科技有限公司 Image registration method and related model training method, device and apparatus
KR20220006654A (en) * 2020-05-29 2022-01-17 상하이 센스타임 인텔리전트 테크놀로지 컴퍼니 리미티드 Image registration method and associated model training method, apparatus, apparatus
JP7241933B2 (en) 2020-05-29 2023-03-17 シャンハイ センスタイム インテリジェント テクノロジー カンパニー リミテッド Image registration method and related model training method, device, apparatus
TWI785588B (en) * 2020-05-29 2022-12-01 中國商上海商湯智能科技有限公司 Image registration method and related model training methods, equipment and computer readable storage medium thereof
JP2022534123A (en) * 2020-05-29 2022-07-27 シャンハイ センスタイム インテリジェント テクノロジー カンパニー リミテッド Image registration method and related model training method, device, apparatus
CN111768436A (en) * 2020-06-17 2020-10-13 哈尔滨理工大学 Improved image feature block registration method based on fast-RCNN
CN111862174A (en) * 2020-07-08 2020-10-30 清华大学深圳国际研究生院 Cross-modal medical image registration method and device
CN111862174B (en) * 2020-07-08 2023-10-03 清华大学深圳国际研究生院 Cross-modal medical image registration method and device
CN112200788A (en) * 2020-10-16 2021-01-08 清华大学 High-temperature deformation measuring device and method
CN112200788B (en) * 2020-10-16 2021-03-26 清华大学 High-temperature deformation measuring device and method
CN112802073A (en) * 2021-04-08 2021-05-14 之江实验室 Fusion registration method based on image data and point cloud data
CN113112534A (en) * 2021-04-20 2021-07-13 安徽大学 Three-dimensional biomedical image registration method based on iterative self-supervision
CN113112534B (en) * 2021-04-20 2022-10-18 安徽大学 Three-dimensional biomedical image registration method based on iterative self-supervision
CN114359356A (en) * 2021-12-28 2022-04-15 上海联影智能医疗科技有限公司 Training method of image registration model, image registration method, device and medium
CN114332181A (en) * 2021-12-29 2022-04-12 中国人民解放军国防科技大学 Remote sensing image automatic registration method and device based on non-rigid bidirectional registration network
CN114332181B (en) * 2021-12-29 2024-02-20 中国人民解放军国防科技大学 Remote sensing image automatic registration method and device based on non-rigid bidirectional registration network
CN114511599A (en) * 2022-01-20 2022-05-17 推想医疗科技股份有限公司 Model training method and device, medical image registration method and device
CN115393402A (en) * 2022-08-24 2022-11-25 北京医智影科技有限公司 Training method of image registration network model, image registration method and equipment
CN116503453A (en) * 2023-06-21 2023-07-28 福建自贸试验区厦门片区Manteia数据科技有限公司 Image registration method, image registration device, computer-readable storage medium and electronic device
CN116503453B (en) * 2023-06-21 2023-09-26 福建自贸试验区厦门片区Manteia数据科技有限公司 Image registration method, image registration device, computer-readable storage medium and electronic device

Also Published As

Publication number Publication date
CN110838139B (en) 2022-10-25

Similar Documents

Publication Publication Date Title
CN110838139B (en) Training method of image registration model, image registration method and computer equipment
CN109767461B (en) Medical image registration method and device, computer equipment and storage medium
CN110827331B (en) Training method of image registration model, image registration method and computer equipment
US11741605B2 (en) Method and system for image registration using an intelligent artificial agent
Zhou et al. Deep reinforcement learning in medical imaging: A literature review
Liao et al. An artificial agent for robust image registration
JP7433297B2 (en) Deep learning-based coregistration
CN109598745B (en) Image registration method and device and computer equipment
EP3488381A1 (en) Method and system for artificial intelligence based medical image segmentation
CN110599526A (en) Image registration method, computer device, and storage medium
CN110866909A (en) Training method of image generation network, image prediction method and computer equipment
JP2023524252A (en) Generative nonlinear human shape model
CN110473241A (en) Method for registering images, storage medium and computer equipment
CN114881930A (en) 3D target detection method, device, equipment and storage medium based on dimension reduction positioning
CN112150404B (en) Global-to-local non-rigid image registration method and device based on joint saliency map
CN113850710A (en) Cross-modal medical image accurate conversion method
Velázquez-Durán et al. Multimodal 3D rigid image registration based on expectation maximization
Zhang Image registration
Hu et al. Attention guided policy optimization for 3d medical image registration
CN114782624B (en) 3D image projection fusion method and device, computer equipment and storage medium
US20230099906A1 (en) Image registration method, computer device, and storage medium
Polo et al. Improving hybrid image and structure-based deformable image registration for large internal deformations
Zou Unsupervised learning for deformable medical image registration
CN117727086A (en) Image processing method, device, computer equipment and image processing system
SANONGSIN et al. A New Deep Learning Model for Diffeomorphic Deformable Image Registration Problems

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