CN112802032A - Training and image processing method, device, equipment and medium for image segmentation network - Google Patents
Training and image processing method, device, equipment and medium for image segmentation network Download PDFInfo
- Publication number
- CN112802032A CN112802032A CN202110068613.9A CN202110068613A CN112802032A CN 112802032 A CN112802032 A CN 112802032A CN 202110068613 A CN202110068613 A CN 202110068613A CN 112802032 A CN112802032 A CN 112802032A
- Authority
- CN
- China
- Prior art keywords
- image
- training
- segmentation network
- imaging
- processing
- 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.)
- Withdrawn
Links
- 238000012549 training Methods 0.000 title claims abstract description 130
- 238000003709 image segmentation Methods 0.000 title claims abstract description 117
- 238000003672 processing method Methods 0.000 title claims abstract description 9
- 238000003384 imaging method Methods 0.000 claims abstract description 123
- 238000000034 method Methods 0.000 claims abstract description 83
- 238000007781 pre-processing Methods 0.000 claims abstract description 39
- 238000012545 processing Methods 0.000 claims description 59
- 238000007408 cone-beam computed tomography Methods 0.000 claims description 50
- 238000002591 computed tomography Methods 0.000 claims description 44
- 230000011218 segmentation Effects 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 15
- 210000004373 mandible Anatomy 0.000 claims description 15
- 210000000214 mouth Anatomy 0.000 claims description 14
- 238000012952 Resampling Methods 0.000 claims description 8
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 28
- 230000009466 transformation Effects 0.000 description 17
- 238000004891 communication Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000002050 maxilla Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present disclosure relates to a training and image processing method, apparatus, device and medium for an image segmentation network, the training method comprising: performing first preprocessing on a first sample image imaged in a first imaging mode to obtain a training image; and training the image segmentation network through the first sample image and the training image. According to the training method of the image segmentation network, the first sample image which does not meet the preset second imaging mode can be preprocessed to obtain the training image, the training image has the characteristics of the medical image obtained through the preset imaging mode and is more suitable for the specified human body part, therefore, the number of the training images suitable for the specified part is increased, and the precision of the image segmentation network is improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for training an image segmentation network and image processing.
Background
During image processing, in particular medical three-dimensional images, segmentation of a target region is often required, for example, in CT (Computed Tomography) or CBCT (Cone Beam Computed Tomography) to facilitate diagnosis. In the related art, manual segmentation consumes a large amount of time and cost, a threshold segmentation method is adopted, time consumption is long, reconstruction errors are large, and if the segmentation is performed by methods such as a neural network, the accuracy of the neural network is low due to reasons such as insufficient training sample amount.
Disclosure of Invention
The disclosure provides a training and image processing method, device, equipment and medium for an image segmentation network.
According to an aspect of the present disclosure, there is provided a training method for an image segmentation network for segmenting a medical image of a specified human body part, including: performing first preprocessing on a first sample image imaged in a first imaging mode to obtain a training image, wherein the training image has the characteristics of a medical image obtained in a predetermined second imaging mode, and the predetermined second imaging mode is suitable for imaging the specified human body part; training the image segmentation network by the first sample image and the training image.
According to the training method of the image segmentation network, the first sample image which does not meet the preset second imaging mode can be preprocessed to obtain the training image, the training image has the characteristics of the medical image obtained through the preset second imaging mode, so that the training image is more suitable for the specified human body part compared with the first sample image before preprocessing, the number of the training images suitable for the specified human body part is increased, the accuracy of the image segmentation network is improved, the image segmentation network can be trained together through the first sample image and the training image, the adaptability of the image segmentation network to different training samples is improved, and the trained image segmentation network can be suitable for segmentation processing of various images.
In one possible implementation, the first preprocessing is performed on a first sample image imaged in a first imaging mode, and includes: randomly transforming gray values of pixels in a first sample image imaged in a first imaging mode; and/or performing mask segmentation processing on the first sample image.
In this way, the gray scale characteristics (e.g., contrast) of the first image can be made closer to the medical image that satisfies the predetermined imaging modality.
In one possible implementation, the mask segmentation process employs a cylindrical mask.
By the method, the first sample image which does not meet the preset second imaging mode can be preprocessed, so that the imaging characteristics of the training image which meets the preset imaging mode are obtained after preprocessing, the number of the training images can be expanded, and the training effect is improved.
In one possible implementation, the method further includes training the image segmentation network with a second sample image imaged in a second imaging modality.
In one possible implementation, the first sample image comprises a computed tomography image, the predetermined imaging modality comprises a cone-beam computed tomography imaging modality, and the designated body part comprises an oral cavity.
According to an aspect of the present disclosure, there is provided an image processing method including: performing second preprocessing on the image to be processed to obtain a third image; inputting a third image into an image segmentation network for image segmentation processing to obtain a first region, wherein the image segmentation network is obtained by training through a training method of the image segmentation network; and obtaining a target area where a target object in the image to be processed is located according to the first area.
In a possible implementation manner, performing a second preprocessing on the image to be processed to obtain a third image includes: and performing resampling processing on the image to be processed to obtain a third image with a preset resolution.
In a possible implementation manner, obtaining a target region where a target object in the image to be processed is located according to the first region includes: processing the first area by taking the maximum connected domain to obtain a second area where the target object in the third image is located; and determining a target area in the image to be processed according to the second area.
In one possible implementation, the target object includes a mandible.
According to an aspect of the present disclosure, there is provided a training apparatus for an image segmentation network, including: a first preprocessing module, configured to perform first preprocessing on a first sample image imaged in a first imaging manner to obtain a training image, where the training image has characteristics of a medical image obtained in a predetermined second imaging manner, and the predetermined second imaging manner is suitable for imaging the specified human body part; and the training module is used for training the image segmentation network through the first sample image and the training image.
In a possible implementation manner, the first preprocessing module is further configured to randomly transform a gray value of a pixel in a first sample image imaged in a first imaging manner; and/or performing mask segmentation processing on the first sample image.
In one possible implementation, the mask segmentation process employs a cylindrical mask.
In one possible implementation, the apparatus further includes: and the second training module is used for training the image segmentation network by utilizing a second sample image imaged in a second imaging mode.
In one possible implementation, the first sample image comprises a computed tomography image, the predetermined imaging modality comprises a cone-beam computed tomography imaging modality, and the designated body part comprises an oral cavity.
According to an aspect of the present disclosure, there is provided an image processing apparatus, the apparatus including: the second preprocessing module is used for performing second preprocessing on the image to be processed to obtain a third image; the segmentation module is used for inputting a third image into an image segmentation network for image segmentation processing to obtain a first region, wherein the image segmentation network is obtained by training through a training method of the image segmentation network; and the target area module is used for acquiring a target area where a target object in the image to be processed is located according to the first area.
In one possible implementation, the second preprocessing module is further configured to: and performing resampling processing on the image to be processed to obtain a third image with a preset resolution.
In one possible implementation, the target area module is further configured to: processing the first area by taking the maximum connected domain to obtain a second area where the target object in the third image is located; and determining a target area in the image to be processed according to the second area.
In one possible implementation, the target object includes a mandible.
According to an aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.
According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.
FIG. 1 shows a flow diagram of an image segmentation network method according to an embodiment of the present disclosure;
FIG. 2 shows a schematic diagram of a first sample image according to an embodiment of the present disclosure;
FIG. 3 shows a schematic diagram of a linear transformation of gray values according to an embodiment of the present disclosure;
FIG. 4 shows a schematic diagram of a mask segmentation process according to an embodiment of the present disclosure;
FIG. 5 shows a flow diagram of an image processing method according to an embodiment of the present disclosure;
FIG. 6 shows a schematic diagram of an application of a training method of an image segmentation network according to an embodiment of the present disclosure;
FIG. 7 shows a block diagram of a training apparatus of an image segmentation network according to an embodiment of the present disclosure;
fig. 8 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure;
FIG. 9 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure;
fig. 10 shows a block diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.
Fig. 1 shows a flow chart of an image segmentation network method according to an embodiment of the present disclosure, as shown in fig. 1, the method comprising:
in step S11, performing a first preprocessing on a first sample image imaged in a first imaging mode to obtain a training image having characteristics of a medical image obtained in a predetermined second imaging mode adapted to image the designated human body part;
in step S12, the image segmentation network is trained by the first sample image and the training image.
According to the training method of the image segmentation network, the first sample image in the first imaging mode can be preprocessed to obtain the training image, and the training image has the characteristics of the medical image obtained through the second imaging mode. The second imaging mode is different from the first imaging mode, and when the specified human body part is imaged through the second imaging mode, the effect is better than that of other imaging modes (including the first imaging mode); therefore, compared with the first sample image before preprocessing, the training image is more suitable for the specified human body part, so that the number of the training images suitable for the specified human body part is increased, the accuracy of the image segmentation network is improved, the image segmentation network can be trained through the first sample image and the training image together, the adaptability of the image segmentation network to different training samples is improved, and the trained image segmentation network can be suitable for the segmentation processing of various images.
In a possible implementation manner, the training method of the image segmentation network may be performed by an electronic device such as a terminal device or a server, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, or the like, and the method may be implemented by a processor calling a computer readable instruction stored in a memory. Alternatively, the method may be performed by a server.
In one possible implementation, the medical image specifying the human body part may include an image captured by a medical instrument, for example, a CT (Computed Tomography) image or a CBCT (Cone Beam Computed Tomography) image. In an example, the designated human body part may include a mandible, an oral cavity, a tooth, and the like. The present disclosure does not limit the medical images and the human body parts.
The predetermined second imaging method may be used to image a designated body part, which may have a better effect than other imaging methods, and the designated body part may be different, and the corresponding predetermined second imaging method may also be different. In an example, the first sample image comprises a Computed Tomography (CT) image, the second imaging mode comprises a Cone Beam Computed Tomography (CBCT) imaging mode, and the designated human body part comprises an oral cavity, wherein the CBCT is an oral cavity three-dimensional digital imaging technology, has the characteristics of high resolution, high imaging speed, low radiation quantity and the like, and has advantages in the aspect of oral cavity part imaging.
In an example, a CT image of a specified human body part, i.e., a medical image imaged by a computed tomography method, may be used for diagnosis of various human body parts, and the imaging method is widely used in medical diagnosis and has a large number of sample images. CBCT images of a designated human body part, i.e., medical images imaged by cone beam computed tomography, are generally used for diagnosis of human body parts such as oral cavity, and CBCT imaging is more suitable for oral cavity parts than other imaging methods such as CT, but the application range of imaging is smaller than CT images, and the number of obtained sample images is smaller.
In one possible implementation, the image segmentation network may be a neural network capable of segmenting the target region from the image, such as a convolutional neural network, and the like, and the present disclosure does not limit the type of the image segmentation network. The image segmentation network may segment a target region from a medical image of a designated body part, for example, a target region in which a mandible is located from a CT image or CBCT image of an oral cavity.
In one possible implementation, the segmentation capability of the image segmentation network may be trained, for example, by training the image segmentation network with sample images of a predetermined imaging modality, for example, medical images (CBCT images) obtained by cone beam computed tomography imaging, and training the image segmentation network with the CBCT images, so that the image segmentation network can segment a target region in the CBCT images, for example, a region in which a mandible is located. In an example, the small number of CBCT images may result in insufficient training precision of the image segmentation network and a small applicability of the image segmentation network, for example, not applicable to target region segmentation processing of CT images.
In a possible implementation manner, in step S11, the number of medical images obtained by the second imaging manner is small, and the first sample image that does not satisfy the predetermined second imaging manner (e.g., the sample image that satisfies the first imaging manner) may be preprocessed to obtain a training image, where the training image has imaging characteristics of the medical image obtained by the predetermined imaging manner, and the imaging characteristics include, for example, the field of view, the contrast, and other attributes of imaging, so that the medical image obtained by the second imaging manner may be simulated by the first sample image imaged by the first imaging manner. For example, a CT image (a first sample image satisfying the first imaging method) is preprocessed, and a CBCT image (an image satisfying the second imaging method) is simulated using the CT image, so that the preprocessed CT image has the imaging characteristics of the CBCT image. The number of images meeting the preset imaging mode can be increased through the mode, the number of training images is expanded, and the training effect is improved.
The preprocessing mode for the first sample image (e.g., CT image) that does not satisfy the predetermined imaging mode may be determined according to the imaging characteristics of the medical image (e.g., imaging characteristics of CBCT image) obtained by the predetermined imaging mode, so that the training image obtained after the preprocessing has the above-mentioned imaging characteristics.
In one possible implementation, step S11 may include: and carrying out random transformation on the gray value of the pixel in the first sample image imaged in the first imaging mode, and/or carrying out mask segmentation processing on the first sample image to obtain the training image.
Fig. 2 shows a schematic diagram of a first sample image according to an embodiment of the present disclosure. Taking the CBCT image as an image satisfying the predetermined imaging mode and the CT image as a first sample image not satisfying the predetermined imaging mode as an example, the CT image may be preprocessed to obtain a first image, that is, a CT image having the imaging characteristics of the CBCT image.
In an example, the gray values of the pixels of the first sample image may be randomly transformed. For example, a linear relationship exists between a gray value of a pixel of the CT image and a gray value of a pixel of the CBCT image, for example, x is a gray value of a certain pixel of the CT image, and y is a gray value of a corresponding pixel in the CBCT image, then a linear relationship exists between x and y, for example, y is ax + b, where a and b are preset linear transformation parameters. In an example, a and b may be linear transformation parameters randomly set for a certain first sample image, that is, in a first sample image, the same linear transformation parameters may be used for performing linear transformation processing on the gray values of all the pixels. And in another first sample image, another random set of linear transformation parameters may be used for the linear transformation process.
Fig. 3 shows a schematic diagram of a linear transformation of gray values according to an embodiment of the present disclosure. As shown in fig. 3, the image obtained by the linear transformation (e.g., a CT image having pixel gradations of a CBCT image) has a sharper contour and a higher contrast in a target region (e.g., a region where a mandible is located).
In an example, other random transformation processes, such as exponential transformation, logarithmic transformation, trigonometric function transformation, and the like, may also be performed on the gray-scale values of the pixels of the first sample image, and the transformation parameters may all be randomly set. The present disclosure does not limit the type of random transformations.
In an example, the CT image may also be used as an image satisfying the second imaging mode, the CBCT image is a first sample image of the first imaging mode, and the CBCT image is randomly transformed, and the selection of the first sample image is not limited in the present disclosure.
In this way, the gray scale characteristics (e.g., contrast) of the first image can be made closer to the medical image that satisfies the predetermined imaging modality.
In one possible implementation, the first sample image may be subjected to a mask segmentation process to obtain a training image. Taking the CBCT image as an image satisfying the predetermined imaging mode, the CT image is a first sample image not satisfying the predetermined imaging mode as an example, the CBCT image is a medical image obtained by cone beam computed tomography, a computed tomography image with a cylindrical field of view can be obtained, and the CT image obtains a medical image of a three-dimensional cube, so that the mask segmentation processing can be performed on the CT image to obtain a cylindrical medical image, thereby simulating the imaging characteristics of the CBCT image.
In one possible implementation, the mask segmentation process employs a cylindrical mask. For example, the first sample image is subjected to mask segmentation processing through a cylindrical mask, the content of the cylindrical inner region is retained, and the content of the cylindrical outer region is removed to obtain a training image.
Fig. 4 shows a schematic diagram of a mask segmentation process according to an embodiment of the present disclosure. The training image (e.g., CT image having imaging characteristics of CBCT image) obtained by performing mask segmentation processing on the first sample image through the cylindrical mask as shown in fig. 4 only retains the content in the cylindrical region, and is closer to the imaging characteristics of CBCT image.
In one possible implementation, the process of randomly transforming the gray-scale values of the pixels and the process of dividing the mask do not conflict with each other, that is, both processes may be performed while the first preprocessing is performed. For example, the gray-scale values of the pixels of the first sample image may be first randomly transformed, and then the transformed first sample image may be subjected to a mask segmentation process to obtain a training image.
By the method, the first sample image which does not meet the preset imaging mode can be preprocessed, so that the imaging characteristics of the training image which meets the preset imaging mode are obtained after preprocessing, the number of the training images can be expanded, and the training effect is improved.
In one possible implementation, in step S12, the training image obtained in step S11 may be used to train the image segmentation network, so that the image segmentation network can segment the target region in the simulated image with the predetermined imaging characteristics. In an example, the image segmentation network may be trained by a training image with imaging features of a CBCT image obtained by preprocessing the CT image.
In one possible implementation, the image segmentation network may also be trained using the first sample image, that is, using an image without predetermined imaging features to train the image segmentation network, so that the image segmentation network can segment the target region in the image without predetermined imaging features. In an example, the image segmentation network may be trained using CT images.
In one possible implementation, the segmentation network may be trained using the first sample image and the training image, which may enable the segmentation network to adapt to images of both imaging modalities, i.e., the segmentation network may segment the target region regardless of the imaging modality of the image input to the segmentation network. The adaptability of the segmentation network to various images can be improved.
In one possible implementation, the method further includes: training the image segmentation network using a second sample image imaged in a predetermined imaging modality. Enabling the image segmentation network to segment a target region in an image having predetermined imaging characteristics. In an example, the image segmentation network can be trained using true CBCT images, further improving the adaptability of the segmentation network to a variety of images.
In a possible implementation manner, the image segmentation network can be trained by using the three images, so that the image segmentation network can be applied to a plurality of images, and the adaptability of the image segmentation network is improved. For example, the image segmentation network may be adapted to both CT images and CBCT images, i.e. the target region may be segmented in both CT and CBCT images.
In one possible implementation, in the training process, the image may be input into the image segmentation network after being subjected to pre-processing such as resampling (e.g., resampling to a resolution of 1mm × 1mm × 1 mm), normalization, and the like, to obtain a prediction target region, and a network loss of the image segmentation network is determined according to the prediction target region and an annotation of the image, for example, a cross entropy loss of the image segmentation network may be determined. Further, the network loss may be back-propagated to adjust network parameters of the image segmentation network, for example, by adjusting the network parameters by a gradient descent method to minimize the network loss.
In one possible implementation, the training step may be performed iteratively, i.e., inputting an image to the image segmentation network a plurality of times, where the input image may include the training image and the first sample image, or the training image, the first sample image, and the second sample image. And completes training when a training condition is satisfied, wherein the training condition may include a training number condition, for example, completing training when the training number reaches a predetermined number. The training condition may include a network loss condition, for example, when the network loss is less than or equal to a preset threshold, or converges to a preset interval, the training is completed. The present disclosure does not limit the training conditions.
According to the training method of the image segmentation network, the gray scale of a first sample image which does not meet a preset second imaging mode can be randomly transformed, the gray scale features of the obtained first image are closer to medical images which meet the preset imaging mode, a training image is obtained through the segmentation processing of the cylindrical mask, the training image meets the imaging features of the preset second imaging mode, the number of the training images is increased, the accuracy of the image segmentation network is improved, the image segmentation network can be trained through the first sample image, the training image and the second sample image together, the adaptability of the image segmentation network to different training samples is improved, and the trained image segmentation network can be suitable for the segmentation processing of various images.
In one possible implementation, after the training of the image segmentation network is completed, the medical image may be processed by the image segmentation network to segment the target region. For example, the oral medical image is processed to segment the area of the mandible.
In one possible implementation, the present disclosure also provides an image processing method.
Fig. 5 shows a flow chart of an image processing method according to an embodiment of the present disclosure, as shown in fig. 5, the method comprising:
in step S21, performing a second preprocessing on the image to be processed to obtain a third image;
in step S22, a third image is input into an image segmentation network, which is trained by the above-mentioned training method of the image segmentation network, and image segmentation processing is performed to obtain a first region;
in step S23, a target area where a target object in the image to be processed is located is obtained according to the first area.
In one possible implementation, in step S21, the image to be processed may be a medical image (e.g., CBCT image) satisfying the predetermined imaging modality or a medical image (e.g., CT image) not satisfying the predetermined imaging modality. Both images can be processed by the trained image segmentation network. The second preprocessing may be performed on the image to be processed to meet the processing requirement of the segmentation network, and step S21 may include performing resampling processing on the image to be processed to obtain a third image with a preset resolution. In an example, the image to be processed may be resampled to a resolution of 1mm x 1mm resulting in a third image. In addition, preprocessing such as normalization can be performed, and the preprocessing mode is not limited by the disclosure. The third image complies with the input criteria of the image segmentation network, i.e. enables the image segmentation network to process the third image.
In one possible implementation manner, in step S22, the trained image segmentation network may process the input third image to segment the first region where the target object is located. In an example, the target object may include a first region of the mandible where the object is located, and the image segmentation network may segment the contour of the mandible. In an example, the target object may further include teeth, maxilla, and the like, and the present disclosure does not limit the target object.
In one possible implementation manner, in step S23, if the target object is a plurality of target objects such as teeth, the first area may be a plurality of discontinuous areas, that is, the first area is a target area where the target object is located.
In one possible implementation, if the target object is an entire area of the mandible and the like, and the image segmentation network obtains a plurality of first areas, the target area where the target object is located can be obtained according to the plurality of first areas. Step S23 may include: processing the first area by taking the maximum connected domain to obtain a second area where the target object in the third image is located; and determining a target area in the image to be processed according to the second area.
In one possible implementation, a maximum connected component of the plurality of first regions may be obtained, and the maximum connected component may be determined as a second region in which the target object is located in the third image. In an example, a first region having the largest area or volume may be determined as the second region.
Furthermore, the third image can be restored to the resolution which is the same as that of the image to be processed in a resampling mode, and the region where the target object is located in the restored image is the target region. Or, the target area where the target object in the image to be processed is located may be determined according to the position where the second area in the third image is located and the image to be processed.
Fig. 6 shows an application diagram of a training method of an image segmentation network according to an embodiment of the present disclosure. The image segmentation network may be trained by specifying a medical image of a body part, e.g. a CT image and/or CBCT image of an oral cavity part, and a target region in which a target object is located may be marked in the medical image, e.g. a region in which a mandible is located.
In a possible implementation manner, the number of CBCT images is small, and the imaging characteristics of the CBCT images can be simulated through the CT images, for example, the gray-scale values of the pixels of the CT images can be subjected to random linear transformation, and the transformed first sample image is subjected to mask segmentation through a cylindrical mask, so as to obtain a training image with the imaging characteristics of the CBCT images, thereby expanding the number of images with the imaging characteristics of the CBCT images and improving the training effect.
In one possible implementation, the image segmentation network may be trained by the CT image, the CBCT image, and the training image, such that the image segmentation network is applicable to both the CT image and the CBCT image, i.e., the image segmentation network may segment the target region from the image regardless of whether the image segmentation network is the CT image or the CBCT image.
In one possible implementation, after training, the trained image segmentation network may be used to segment the target region in the medical image. In an example, an image to be processed (e.g., a CT image or CBCT image of an oral cavity region) may be first resampled and input into a trained image segmentation network that may determine a target region in which a target object (e.g., a mandible) is located.
In a possible implementation manner, the image segmentation network training method can be used in the field of medical image processing, and if the number of samples meeting the predetermined imaging mode is small or the labeling cost is high, the predetermined imaging mode can be simulated by using other common sample images to enlarge the number of samples, improve the training effect, and improve the adaptability of the image segmentation network to different training samples. The trained image segmentation network can be used in medical image processing of parts such as oral cavity and the like to segment the region of a target object such as mandible. The application field of the image segmentation network training method is not limited by the disclosure.
Fig. 7 shows a block diagram of a training apparatus of an image segmentation network, the apparatus comprising: a first preprocessing module 11, configured to perform first preprocessing on a first sample image imaged in a first imaging manner to obtain a training image, where the training image has characteristics of a medical image obtained in a predetermined second imaging manner, and the predetermined second imaging manner is suitable for imaging the specified human body part; a training module 12, configured to train the image segmentation network through the first sample image and the training image.
In a possible implementation manner, the first preprocessing module is further configured to randomly transform a gray value of a pixel in a first sample image imaged in a first imaging manner; and/or performing mask segmentation processing on the first sample image.
In one possible implementation, the mask segmentation process employs a cylindrical mask.
In one possible implementation, the apparatus further includes: and the second training module is used for training the image segmentation network by utilizing a second sample image imaged in a second imaging mode.
In one possible implementation, the first sample image comprises a computed tomography image, the predetermined imaging modality comprises a cone-beam computed tomography imaging modality, and the designated body part comprises an oral cavity.
Fig. 8 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure, the apparatus including: the second preprocessing module 21 is configured to perform second preprocessing on the image to be processed to obtain a third image; a segmentation module 22, configured to input a third image into an image segmentation network to perform image segmentation processing, so as to obtain a first region, where the image segmentation network is trained by the training method of the image segmentation network according to any one of claims 1 to 5; and a target area module 23, configured to obtain, according to the first area, a target area where a target object in the image to be processed is located.
In one possible implementation, the second preprocessing module is further configured to: and performing resampling processing on the image to be processed to obtain a third image with a preset resolution.
In one possible implementation, the target area module is further configured to: processing the first area by taking the maximum connected domain to obtain a second area where the target object in the third image is located; and determining a target area in the image to be processed according to the second area.
In one possible implementation, the target object includes a mandible.
It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.
In addition, the present disclosure also provides a training apparatus, an electronic device, a computer-readable storage medium, and a program for an image segmentation network, which can be used to implement any one of the training methods for an image segmentation network provided by the present disclosure, and the corresponding technical solutions and descriptions and corresponding descriptions in the method section are not repeated.
In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.
Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.
An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.
The disclosed embodiments also provide a computer program product comprising computer readable code which, when run on a device, executes instructions for implementing a method as provided by any of the above embodiments.
Embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which when executed, cause a computer to perform the operations of the method provided by any of the above embodiments.
The electronic device may be provided as a terminal, server, or other form of device.
Fig. 9 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.
Referring to fig. 9, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.
The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.
The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense an edge of a touch or slide action, but also detect a duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.
Fig. 10 shows a block diagram of an electronic device 1900 according to an embodiment of the disclosure. For example, the electronic device 1900 may be provided as a server. Referring to fig. 10, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.
The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system, such as Windows Server, stored in memory 1932TM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTMOr the like.
In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.
The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, 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/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (13)
1. A method for training an image segmentation network, the image segmentation network being used for segmenting a medical image of a specified part of a human body, the method comprising:
performing first preprocessing on a first sample image imaged in a first imaging mode to obtain a training image, wherein the training image has the characteristics of a medical image obtained in a predetermined second imaging mode, and the predetermined second imaging mode is suitable for imaging the specified human body part;
training the image segmentation network by the first sample image and the training image.
2. The method of claim 1, wherein performing a first pre-processing on a first sample image imaged in a first imaging modality comprises:
randomly transforming gray values of pixels in a first sample image imaged in a first imaging mode; and/or the presence of a gas in the gas,
and carrying out mask segmentation processing on the first sample image.
3. The method of claim 2, wherein the mask segmentation process employs a cylindrical mask.
4. The method according to any one of claims 1 to 3, further comprising,
training the image segmentation network with a second sample image imaged in a second imaging modality.
5. The method of any of claims 1-4, wherein the first sample image comprises a computed tomography image, the predetermined imaging modality comprises a cone-beam computed tomography imaging modality, and the designated body part comprises an oral cavity.
6. An image processing method, comprising:
performing second preprocessing on the image to be processed to obtain a third image;
inputting a third image into an image segmentation network to perform image segmentation processing to obtain a first region, wherein the image segmentation network is obtained by training through the training method of the image segmentation network according to any one of claims 1 to 5;
and obtaining a target area where a target object in the image to be processed is located according to the first area.
7. The method of claim 6, wherein performing a second pre-processing on the image to be processed to obtain a third image comprises:
and performing resampling processing on the image to be processed to obtain a third image with a preset resolution.
8. The method according to claim 6, wherein obtaining a target region where a target object is located in the image to be processed according to the first region comprises:
processing the first area by taking the maximum connected domain to obtain a second area where the target object in the third image is located;
and determining a target area in the image to be processed according to the second area.
9. The method of claim 6, wherein the target object comprises a mandible.
10. An apparatus for training an image segmentation network, comprising:
a first preprocessing module, configured to perform first preprocessing on a first sample image imaged in a first imaging manner to obtain a training image, where the training image has characteristics of a medical image obtained in a predetermined second imaging manner, and the predetermined second imaging manner is suitable for imaging the specified human body part;
and the training module is used for training the image segmentation network through the first sample image and the training image.
11. An image processing apparatus characterized by comprising:
the second preprocessing module is used for performing second preprocessing on the image to be processed to obtain a third image;
a segmentation module, configured to input a third image into an image segmentation network for image segmentation processing to obtain a first region, where the image segmentation network is obtained by training through the training method of the image segmentation network according to any one of claims 1 to 5;
and the target area module is used for acquiring a target area where a target object in the image to be processed is located according to the first area.
12. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 9.
13. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110068613.9A CN112802032A (en) | 2021-01-19 | 2021-01-19 | Training and image processing method, device, equipment and medium for image segmentation network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110068613.9A CN112802032A (en) | 2021-01-19 | 2021-01-19 | Training and image processing method, device, equipment and medium for image segmentation network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112802032A true CN112802032A (en) | 2021-05-14 |
Family
ID=75810429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110068613.9A Withdrawn CN112802032A (en) | 2021-01-19 | 2021-01-19 | Training and image processing method, device, equipment and medium for image segmentation network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112802032A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663714A (en) * | 2022-05-23 | 2022-06-24 | 阿里巴巴（中国）有限公司 | Image classification and ground object classification method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537794A (en) * | 2018-04-19 | 2018-09-14 | 上海联影医疗科技有限公司 | Medical image processing method, device and computer readable storage medium |
| CN109242865A (en) * | 2018-09-26 | 2019-01-18 | 上海联影智能医疗科技有限公司 | Medical image auto-partition system, method, apparatus and storage medium based on multichannel chromatogram |
| CN109360210A (en) * | 2018-10-16 | 2019-02-19 | 腾讯科技（深圳）有限公司 | Image partition method, device, computer equipment and storage medium |
| CN109754394A (en) * | 2018-12-28 | 2019-05-14 | 上海联影智能医疗科技有限公司 | 3 d medical images processing unit and method |
| CN109784255A (en) * | 2019-01-07 | 2019-05-21 | 深圳市商汤科技有限公司 | Neural network training method and device and recognition methods and device |
| CN109949309A (en) * | 2019-03-18 | 2019-06-28 | 安徽紫薇帝星数字科技有限公司 | A kind of CT image for liver dividing method based on deep learning |
| CN110599505A (en) * | 2019-09-17 | 2019-12-20 | 上海微创医疗器械（集团）有限公司 | Organ image segmentation method and device, electronic equipment and storage medium |
| CN111898324A (en) * | 2020-08-13 | 2020-11-06 | 四川大学华西医院 | Segmentation task assistance-based nasopharyngeal carcinoma three-dimensional dose distribution prediction method |
| CN112150569A (en) * | 2020-09-24 | 2020-12-29 | 北京羽医甘蓝信息技术有限公司 | Method and device for generating CBCT image into CT image and terminal equipment |
| US20210004984A1 (en) * | 2018-09-25 | 2021-01-07 | Tsinghua University | Method and apparatus for training 6d pose estimation network based on deep learning iterative matching |
-
2021
- 2021-01-19 CN CN202110068613.9A patent/CN112802032A/en not_active Withdrawn
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537794A (en) * | 2018-04-19 | 2018-09-14 | 上海联影医疗科技有限公司 | Medical image processing method, device and computer readable storage medium |
| US20210004984A1 (en) * | 2018-09-25 | 2021-01-07 | Tsinghua University | Method and apparatus for training 6d pose estimation network based on deep learning iterative matching |
| CN109242865A (en) * | 2018-09-26 | 2019-01-18 | 上海联影智能医疗科技有限公司 | Medical image auto-partition system, method, apparatus and storage medium based on multichannel chromatogram |
| CN109360210A (en) * | 2018-10-16 | 2019-02-19 | 腾讯科技（深圳）有限公司 | Image partition method, device, computer equipment and storage medium |
| CN109754394A (en) * | 2018-12-28 | 2019-05-14 | 上海联影智能医疗科技有限公司 | 3 d medical images processing unit and method |
| CN109784255A (en) * | 2019-01-07 | 2019-05-21 | 深圳市商汤科技有限公司 | Neural network training method and device and recognition methods and device |
| CN109949309A (en) * | 2019-03-18 | 2019-06-28 | 安徽紫薇帝星数字科技有限公司 | A kind of CT image for liver dividing method based on deep learning |
| CN110599505A (en) * | 2019-09-17 | 2019-12-20 | 上海微创医疗器械（集团）有限公司 | Organ image segmentation method and device, electronic equipment and storage medium |
| CN111898324A (en) * | 2020-08-13 | 2020-11-06 | 四川大学华西医院 | Segmentation task assistance-based nasopharyngeal carcinoma three-dimensional dose distribution prediction method |
| CN112150569A (en) * | 2020-09-24 | 2020-12-29 | 北京羽医甘蓝信息技术有限公司 | Method and device for generating CBCT image into CT image and terminal equipment |
Non-Patent Citations (2)
| Title |
|---|
| Y. TAKAYAMA ET AL.: "Evaluation of the performance of deformable image registration between planning CT and CBCT images for the pelvic region: comparison between hybrid and intensity-based DIR", JOURNAL OF RADIATION RESEARCH, vol. 58, no. 4, pages 567 - 571 * |
| 吴志坚;王博亮;黄晓阳;鞠颖;胡丽玲;: "一种基于BP网络的CT图像肝实质分割算法", 中国数字医学, no. 08, pages 18 - 20 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663714A (en) * | 2022-05-23 | 2022-06-24 | 阿里巴巴（中国）有限公司 | Image classification and ground object classification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310764B (en) | Network training method, image processing device, electronic equipment and storage medium | |
| CN109978886B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN109816764B (en) | Image generation method and device, electronic equipment and storage medium | |
| CN111899268B (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN107692997B (en) | Heart rate detection method and device | |
| CN109584362B (en) | Three-dimensional model construction method and device, electronic equipment and storage medium | |
| TWI718631B (en) | Method, device and electronic apparatus for face image processing and storage medium thereof | |
| CN109145970B (en) | Image-based question and answer processing method and device, electronic equipment and storage medium | |
| CN113012166A (en) | Intracranial aneurysm segmentation method and device, electronic device, and storage medium | |
| CN111640114B (en) | Image processing method and device | |
| CN111860388A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN112785672A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN111583142A (en) | Image noise reduction method and device, electronic equipment and storage medium | |
| CN111815750A (en) | Method and device for polishing image, electronic equipment and storage medium | |
| CN111882558A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN113506229B (en) | Neural network training and image generating method and device | |
| CN112308867B (en) | Tooth image processing method and device, electronic equipment and storage medium | |
| CN112613447B (en) | Key point detection method and device, electronic equipment and storage medium | |
| CN113660531A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN112802032A (en) | Training and image processing method, device, equipment and medium for image segmentation network | |
| CN112200820A (en) | Three-dimensional image processing method and device, electronic device and storage medium | |
| CN112102300A (en) | Counting method and device, electronic equipment and storage medium | |
| CN109978759B (en) | Image processing method and device and training method and device of image generation network | |
| CN115457024A (en) | Method and device for processing cryoelectron microscope image, electronic equipment and storage medium | |
| CN112734015B (en) | Network generation method and device, electronic equipment and storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210514 |