KR20220056892A - Method for segmentation based on medical image - Google Patents

Abstract

A medical image-based segmentation method performed by a computing device according to one embodiment of the present disclosure is disclosed. The method includes the steps of: receiving a medical image including at least one brain region; and parcellating the at least one brain region included in the medical image by using the neural network model learned as a 3D feature of an input image.

Description

Segmentation method based on medical images

The present invention relates to a method of processing a medical image, and more particularly, to a method of segmenting a body organ existing in a medical image by region using a neural network.

Medical images are data that enable us to understand the physical state of various organs of the human body. Medical images include digital radiographic imaging (X-ray), computed tomography (CT), or magnetic resonance imaging (MRI).

For effective analysis of body organs included in medical images, research on a method of segmenting body organs into each area has been continuously conducted. However, conventional methods have a problem in that a considerable amount of computation is required for segmentation of a body organ including numerous detailed regions, such as the brain. In addition, in order to perform accurate segmentation through the conventional method, there is a problem that a considerable amount of accurately captured medical images must be secured so that the target organ is expressed in a certain shape.

US Patent Publication No. 2020/0275838 discloses a method for determining the location or properties of a target for transcranial magnetic stimulation treatment of a patient.

The present disclosure has been made in response to the above-mentioned background art, and an object of the present disclosure is to provide a segmentation method for a medical body image.

Disclosed is a medical image-based segmentation method performed by a computing device according to an embodiment of the present disclosure for realizing the above-described problem. The method comprises: receiving a medical image comprising at least one brain region; and partitioning at least one brain region included in the medical image using a neural network model learned as a 3D feature of the input image.

In an alternative embodiment, the medical image may include a mask of a cortical region of a brain generated based on a 3D image.

In an alternative embodiment, the medical image may include a mask of a brain cortex region that is generated based on output data of a neural network model trained as a two-dimensional feature of an input image. In this case, the neural network model learned with the two-dimensional feature uses at least one two-dimensional slice generated from a three-dimensional image as input data to partition at least one brain region included in the input data. can

In an alternative embodiment, the neural network model trained with the 3D feature may learn the 3D feature based on an active region based on a predetermined brain region with respect to the input image.

In an alternative embodiment, the neural network model trained with the three-dimensional feature learns the three-dimensional feature by training a convolutional neural network on only the active region based on the brain cortical region in the input image. can learn

A medical image-based segmentation method performed by a computing device according to another embodiment of the present disclosure for realizing the above-described problems is disclosed. The method includes: receiving a first medical image including at least one brain region; segmenting at least one brain region included in the first medical image by using a first model learned as a two-dimensional feature of the input image; and at least one brain region included in the second medical image by using a second model learned as a 3D feature of an input image based on a second medical image generated based on the output data of the first model. It may include the step of partitioning.

In an alternative embodiment, the first medical image may include at least one slice of a 2D shape generated from a 3D image.

In an alternative embodiment, the first model may include: a first operation of training a convolutional neural network by randomly sampling an input image having a label; and by performing a second operation of learning the convolutional neural network by applying both an input image in which the label exists and an input image in which the label does not exist, the two-dimensional feature may be learned.

In an alternative embodiment, the first operation and the second operation may be performed based on different loss functions.

In an alternative embodiment, the first operation is performed based on a dice loss function, and the second operation is performed based on a cross-entropy loss function after the first operation. can

In an alternative embodiment, the second medical image may include a mask of a brain cortex region generated based on output data of a first model receiving the first medical image.

A computer program stored in a computer-readable storage medium is disclosed according to an embodiment of the present disclosure for realizing the above-described problems. When the computer program is executed in one or more processors, the computer program performs the following operations for performing segmentation based on a medical image, the operations comprising: receiving a medical image including at least one brain region; and segmenting at least one brain region included in the medical image by using the neural network model learned as the 3D feature of the input image.

An apparatus for performing segmentation based on a medical image is disclosed according to an embodiment of the present disclosure for realizing the above-described problem. The apparatus includes: a processor including at least one core; a memory containing program codes executable by the processor; and a network unit for receiving a medical image including at least one brain region, wherein the processor detects at least one brain region included in the medical image by using a neural network model learned as a three-dimensional feature of the input image. can be partitioned.

The present disclosure may provide a segmentation method for a medical body image.

1 is a block diagram of a computing device for performing segmentation based on a medical image according to an embodiment of the present disclosure.
2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure;
3 is a block diagram illustrating a process of performing segmentation of a computing device according to an embodiment of the present disclosure.
4 is a conceptual diagram illustrating one of learning methods of a neural network model of a computing device according to an embodiment of the present disclosure.
5 is a flowchart of a segmentation method based on a medical image according to an embodiment of the present disclosure.
6 is a block diagram illustrating a process of performing segmentation of a computing device according to another embodiment of the present disclosure.
7 is a flowchart of a segmentation method based on a medical image according to another embodiment of the present disclosure.
8 is a block diagram of a computing device according to an embodiment of the present disclosure.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments may be practiced without these specific descriptions.

The terms “component,” “module,” “system,” and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or execution of software. For example, a component can be, but is not limited to being, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored therein. Components may communicate via a network such as the Internet with another system, for example, via a signal having one or more data packets (eg, data and/or signals from one component interacting with another component in a local system, distributed system, etc.) may communicate via local and/or remote processes depending on the data being transmitted).

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean one of the natural implicit substitutions. That is, X employs A; X employs B; or when X employs both A and B, "X employs A or B" may apply to either of these cases. It should also be understood that the term “and/or” as used herein refers to and includes all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the feature and/or element in question is present. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, elements and/or groups thereof. Also, unless otherwise specified or unless it is clear from context to refer to a singular form, the singular in the specification and claims should generally be construed to mean “one or more”.

And, the term "at least one of A or B" should be interpreted as meaning "when including only A", "when including only B", and "when combined with the configuration of A and B".

Those skilled in the art will further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or combinations of both. It should be recognized that they can be implemented with To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Descriptions of the presented embodiments are provided to enable those skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art of the present disclosure. The generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present invention is not limited to the embodiments presented herein. This invention is to be interpreted in its widest scope consistent with the principles and novel features presented herein.

In the present disclosure, a network function, an artificial neural network, and a neural network may be used interchangeably.

On the other hand, the term "image" or "image data" as used throughout the detailed description and claims of the present invention refers to multidimensional data composed of discrete image elements (eg, pixels in a two-dimensional image), in other words , a term that refers to a visible object (eg, displayed on a video screen) or a digital representation of that object (eg, a file corresponding to a pixel output of a CT, MRI detector, etc.).

For example, "image" or "image" can be defined by computed tomography (CT), magnetic resonance imaging (MRI), ultrasound or any other medical imaging system known in the art. It may be a medical image of a collected subject. The image does not necessarily have to be provided in a medical context, but may be provided in a non-medical context, for example, there may be X-ray imaging for security screening.

Throughout the detailed description and claims of the present invention, the 'DICOM (Digital Imaging and Communications in Medicine)' standard is a generic term for various standards used for digital image expression and communication in medical devices. The DICOM standard is published by a joint committee formed by the American Society of Radiological Medicine (ACR) and the National Electrical Engineers Association (NEMA).

In addition, throughout the detailed description and claims of the present invention, 'Picture Archiving and Communication System (PACS)' is a term that refers to a system that stores, processes, and transmits in accordance with the DICOM standard, X-ray, CT , medical imaging images acquired using digital medical imaging equipment such as MRI are stored in DICOM format and transmitted to terminals inside and outside the hospital through a network, to which reading results and medical records can be added.

1 is a block diagram of a computing device for performing segmentation based on a medical image according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In an embodiment of the present disclosure, the computing device 100 may include other components for performing the computing environment of the computing device 100 , and only some of the disclosed components may configure the computing device 100 .

The computing device 100 may include a processor 110 , a memory 130 , and a network unit 150 .

The processor 110 may include one or more cores, and a central processing unit (CPU) of a computing device, a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU). unit) and the like, and may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 to perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning the neural network. The processor 110 for learning of the neural network, such as processing input data for learning in deep learning (DL), extracting features from the input data, calculating an error, updating the weight of the neural network using backpropagation calculations can be performed. At least one of a CPU, a GPGPU, and a TPU of the processor 110 may process learning of a network function. For example, the CPU and the GPGPU can process learning of a network function and data classification using the network function. Also, in an embodiment of the present disclosure, learning of a network function and data classification using the network function may be processed by using the processors of a plurality of computing devices together. In addition, the computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, GPGPU or TPU executable program.

The processor 110 may perform segmentation of body organs present in the medical image through the neural network model learned as the two-dimensional feature of the medical image. For example, the processor 110 may partition each detailed region constituting the brain based on a 3D T1 magnetic resonance (MR) image of the brain as a target organ using a neural network model. In this case, the processor 110 may divide the 3D T1 MR image, which is the input image, into 2D slices for learning the 2D feature of the neural network model. The processor 110 may use some of the adjacent slices among the slices divided from the 3D T1 MR image to input the neural network model. However, the processor 110 does not directly perform the above-described operation of generating the slices, but may receive the slices in the two-dimensional form already divided and processed from another terminal.

The processor 110 may perform segmentation of body organs present in the medical image through the neural network model learned as the 3D feature of the medical image. The processor 110 may increase the accuracy and precision of segmentation for a large amount of organ regions by using the neural network model learned as a 3D feature. For example, the processor 110 uses a neural network model to determine each sub-region of a brain cortical region that can be divided into about 60 based on a three-dimensional T1 MR image targeting a cortical region among brain regions. can be partitioned. In this case, the input image of the neural network model learned with the three-dimensional feature may be a mask extracted from the output data of the neural network model learned with the aforementioned two-dimensional feature. The input image of the neural network model learned with the three-dimensional feature may be a mask processed from the extracted data of the neural network model learned with the two-dimensional feature.

The processor 110 may partition a brain region into a cortical region and a subcortical region using the neural network model learned as a two-dimensional feature. Then, the processor 110 uses the medical image of the cortical region partitioned through the neural network model learned with the two-dimensional feature as an input to the neural network model learned with the three-dimensional feature, and the brain cortex region is divided into about 60 detailed regions. can be partitioned into

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150 .

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, SD or XD memory, etc.), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read (PROM) -Only Memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. The computing device 100 may operate in relation to a web storage that performs a storage function of the memory 130 on the Internet. The description of the above-described memory is only an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure includes a Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), VDSL ( A variety of wired communication systems such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and Local Area Network (LAN) can be used.

In addition, the network unit 150 presented herein is CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA ( A variety of wireless communication systems can be used, such as Single Carrier-FDMA) and other systems.

In the present disclosure, the network unit 150 may use any type of wired/wireless communication system.

The techniques described herein may be used in the networks mentioned above, as well as in other networks.

The network unit 150 may receive a medical image representing a body organ from a medical imaging system. For example, a medical image in which a body organ is expressed may be data for training or inference of a neural network model learned with a 2D feature or a 3D feature. The medical image representing the body organs may be a 3D T1 MR image including at least one brain region. The medical image expressing body organs is not limited to the above-described examples, and may include all images related to body organs acquired through imaging, such as X-ray images and CT images.

2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure;

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is configured to include at least one or more nodes. Nodes (or neurons) constituting the neural networks may be interconnected by one or more links.

In the neural network, one or more nodes connected through a link may relatively form a relationship between an input node and an output node. The concepts of an input node and an output node are relative, and any node in an output node relationship with respect to one node may be in an input node relationship in a relationship with another node, and vice versa. As described above, an input node-to-output node relationship may be created around a link. One or more output nodes may be connected to one input node through a link, and vice versa.

In the relationship between the input node and the output node connected through one link, the value of the data of the output node may be determined based on data input to the input node. Here, a link interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node sets values input to input nodes connected to the output node and links corresponding to the respective input nodes. An output node value may be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and an output node relationship in the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the correlation between the nodes and the links, and the value of a weight assigned to each of the links. For example, when the same number of nodes and links exist and there are two neural networks having different weight values of the links, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes constituting the neural network may constitute a layer. Some of the nodes constituting the neural network may configure one layer based on distances from the initial input node. For example, a set of nodes having a distance of n from the initial input node may constitute n layers. The distance from the initial input node may be defined by the minimum number of links that must be passed to reach the corresponding node from the initial input node. However, the definition of such a layer is arbitrary for description, and the order of the layer in the neural network may be defined in a different way from the above. For example, a layer of nodes may be defined by a distance from the final output node.

The initial input node may mean one or more nodes to which data is directly input without going through a link in a relationship with other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. In addition, the hidden node may mean nodes constituting the neural network other than the first input node and the last output node.

The neural network according to an embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as progresses from the input layer to the hidden layer. can Also, in the neural network according to another embodiment of the present disclosure, the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes may be reduced as the number of nodes progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as the number of nodes progresses from the input layer to the hidden layer. can The neural network according to another embodiment of the present disclosure may be a neural network in a combined form of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to identify the latent structures of data. In other words, it can identify the potential structure of photos, texts, videos, voices, and music (e.g., what objects are in the photos, what the text and emotions are, what the texts and emotions are, etc.) . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted boltzmann machines (RBMs). machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, and a Generative Adversarial Network (GAN). The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

In an embodiment of the present disclosure, the network function may include an autoencoder. The auto-encoder may be a kind of artificial neural network for outputting output data similar to input data. The auto encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between the input/output layers. The number of nodes in each layer may be reduced from the number of nodes of the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically with reduction from the bottleneck layer to the output layer (symmetrically with the input layer). The auto-encoder can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to a dimension after preprocessing the input data. In the auto-encoder structure, the number of nodes of the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, a sufficient amount of information may not be conveyed, so a certain number or more (e.g., more than half of the input layer, etc.) ) may be maintained.

The neural network may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Learning of the neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

A neural network can be trained in a way that minimizes output errors. In the training of a neural network, iteratively input the training data into the neural network, calculate the output of the neural network and the target error for the training data, and calculate the error of the neural network from the output layer of the neural network to the input layer in the direction to reduce the error. It is a process of updating the weight of each node in the neural network by backpropagation in the direction. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (ie, labeled learning data), and in the case of comparative learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of teacher learning related to data classification may be data in which categories are labeled in each of the learning data. Labeled training data is input to the neural network, and an error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of comparison learning related to data classification, an error may be calculated by comparing the input training data with the neural network output. The calculated error is back propagated in the reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back propagation. The change amount of the connection weight of each node to be updated may be determined according to a learning rate. The computation of the neural network on the input data and the backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of repetitions of the learning cycle of the neural network. For example, in the early stage of learning of a neural network, a high learning rate can be used to enable the neural network to quickly obtain a certain level of performance, thereby increasing efficiency, and using a low learning rate at a later stage of learning can increase accuracy.

In the training of neural networks, in general, the training data may be a subset of real data (that is, data to be processed using the trained neural network), and thus, the error on the training data is reduced, but the error on the real data is reduced. There may be increasing learning cycles. Overfitting is a phenomenon in which errors on actual data increase by over-learning on training data as described above. For example, a phenomenon in which a neural network that has learned a cat by seeing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing errors in machine learning algorithms. In order to prevent such overfitting, various optimization methods can be used. In order to prevent overfitting, methods such as increasing the training data, regularization, and dropout that deactivate some of the nodes of the network in the process of learning, and the use of a batch normalization layer are applied. can

3 is a block diagram illustrating a process of performing segmentation of a computing device according to an embodiment of the present disclosure.

Referring to FIG. 3 , the processor 110 of the computing device 100 according to an embodiment of the present disclosure uses a medical image 10 including at least one brain region as a 3D feature of an input image to learn a neural network model. (200) can be used as an input. In this case, the processor 110 uses the medical image 10 received through the network unit 150 as it is as an input to the neural network model 200 , or pre-processes the medical image 10 (e.g., a mask of a specific brain region is generated). etc.) may be used as an input of the neural network model 200 . For example, the input data, which is a medical image 10 corresponding to the input of the neural network model 200 trained as a three-dimensional feature, is a 3D image for a brain cortex region generated based on a three-dimensional image (e.g. T1 MR image, etc.) It may be a dimensional image. The input data of the neural network model 200 that is the medical image 10 may be a binary mask in which a brain cortex region is displayed. In addition, the input data of the neural network model 200, which is the medical image 10, is a mask including the intensity of the brain cortex region extracted by synthesizing the above-described binary mask and a medical image (e.g. 3D T1 MR image, etc.) it may be

The processor 110 may receive the medical image 10 corresponding to the 3D image of the brain cortex from the medical imaging system through the network unit 150 . In this case, the received medical image 10 itself may be used as input data of the neural network model 200 . In addition, the processor 110 uses a mask for the brain cortex region extracted or generated from the output data of the neural network model 400 (refer to FIG. 6 ) trained as a two-dimensional feature of an input image, which will be described later, as the input data of the neural network model 200 . can also be used as

The processor 110 may partition at least one brain region included in the medical image 10 into detailed regions using the neural network model 200 . The neural network model 200 receives input data based on the medical image 10 and divides at least one brain region included in the medical image 10 into detailed regions to obtain a plurality of segment data 21 , 22 , 23 , 24) may be generated.

For example, the neural network model 200 may divide the brain cortex region into about 60 cortical detailed regions based on the medical image 10 corresponding to the mask of the brain cortex region. The first segment data 21 may be data representing the entorhinal. The second segment data 22 may be data representing an insula. The third segment data 23 may be data representing the posterior cingulate. The N-th segment data 24 may be data representing a cuneus. A detailed description of each of the segment data 21 , 22 , 23 , and 24 is only an example, and the order and content may vary according to the segmentation result.

4 is a conceptual diagram illustrating one of learning methods of a neural network model of a computing device according to an embodiment of the present disclosure.

3 and 4 , the neural network model 200 according to an embodiment of the present disclosure is based on active regions 311 and 312 based on a predetermined brain region with respect to input data 300 . can learn 3D features. The neural network model 200 may learn a three-dimensional feature by learning the neural network from only the active regions 311 and 312 based on the brain cortex in the input data 300 . In this case, the input data 300 may be a medical image selected, extracted, or generated for learning the neural network model 200 . For example, the input data 300 may be a binary mask indicating a brain cortex region or a mask indicating an intensity of an MR image generated based on the binary mask.

The active regions 311 and 312 according to an embodiment of the present disclosure include input data 300 representing a specific brain region, such as a set of data structural units (e.g. pixels, etc.) of the input data 300 based on the specific brain region. It can mean the data part of For example, when the input data 300 is a binary mask for the brain cortex region, the active regions 311 and 312 may mean a set of data constituting the input image 300 having a data value greater than 0. . That is, when the input data 300 is a binary mask of a brain cortex region, the active regions 311 and 312 may be brain cortical regions of the input data 300 in which the data value is 1 instead of 0. When the input data 300 is a mask indicating the intensity of the MR image for the brain cortex region, the active regions 311 and 312 may mean a set of data existing in the brain cortex region of the input data 300 . That is, when the input data 300 is a mask indicating the intensity of the MR image for the brain cortex region, the active regions 311 and 312 are input data 300 in which the data value is not a binary value but an intensity value of the MR image. of the brain cortex. Meanwhile, the neural network model 200 may include a convolution layer.

For example, referring to FIGS. 3 and 4 , the neural network model 200 does not train the convolutional layer for all regions constituting the input data 300 . The neural network model 200 convolves the active region 311 corresponding to the initially given brain cortex region except for the inactive region 321 that does not correspond to the brain cortex region from the input data 300 . layers can be trained. Thereafter, the neural network model 200 may train only the initially given active region 312 , excluding the inactive region 322 , for the next convolutional layer. The neural network model 200 does not perform a convolution operation on the inactive regions 321 and 322 of the input data 300 . Through this learning method, memory can be used efficiently, computational efficiency can be increased, and segmentation accuracy and precision can be improved.

5 is a flowchart of a segmentation method based on a medical image according to an embodiment of the present disclosure.

Referring to FIG. 5 , in operation S110 , the computing device 100 may receive a medical image including at least one brain region. Receiving the medical image may mean receiving the medical image from the medical imaging system. For example, the computing device 100 may receive a medical image representing the entire brain through the network unit 150 . The computing device 100 may receive a medical image representing the brain cortex region through the network unit 150 . In this case, the computing device 100 may use the medical image itself received through the network unit 150 as data for input of a neural network model learned as a 3D feature. In addition, the computing device 100 may generate a medical image by processing the medical image received through the network unit 150 , and use the generated medical image as input data of a neural network model learned as a 3D feature. there is. The computing device 100 may use data generated by extraction or processing from output data generated from the neural network model learned with the two-dimensional feature as input data of the neural network model learned with the three-dimensional feature.

In operation S120 , the computing device 100 may divide the brain region included in the medical image into detailed regions through the neural network model learned as the 3D feature. For example, if the input data of the neural network model is a mask for the brain cortex region, the neural network model that trains the convolutional neural network only for the active region based on a predetermined brain region (e.g. brain cortical region) is the brain cortical region. It can be divided into about 60 cortical subregions (e.g. olfactory cortex, insula, etc.). The data, which are learned as three-dimensional features and divided through the neural network model, can be used as masks for each cortical subregion.

6 is a block diagram illustrating a process of performing segmentation of a computing device according to another embodiment of the present disclosure.

Referring to FIG. 6 , the processor 110 of the computing device 100 according to another embodiment of the present disclosure converts the first medical image 30 including at least one brain region as a two-dimensional feature of the input image. It can be used as an input of the learned first model 400 . For example, the processor 110 may receive two-dimensional slices generated based on a three-dimensional image (e.g. T1 MR image) as the first medical image 30 corresponding to the input of the first model 400 . can In this case, the processor 110 may receive the first medical image 30 representing the brain region including both the cortical region and the subcortical region from the medical imaging system through the network unit 150 .

The processor 110 may receive the 3D medical image as the first medical image 30 through the network unit 150 , and may generate 2D slices by itself through a preprocessing process. The preprocessing process may include the following examples. For example, the processor 110 may receive the 3D T1 MR image and normalize the intensity of each voxel to have a value within a predetermined range. In this case, the predetermined range may represent a value of 0 to 1. The processor 110 may perform augmentation on the leveled 3D T1 MR image. In this case, the augmentation may include a method of randomly rotating the leveled image at a predetermined angle (e.g. 15 degrees, etc.), a method of adding a randomly extracted intensity to the leveling image, and the like.

The processor 110 may use one reference slice and slices adjacent to the reference slice as input data to be input to the first model 400 . An input of the first model 400 may be a medical image having a plurality of channels. For example, the processor 110 uses i-1 th, i th and i+1 th (i is a natural number) axial slices among a plurality of slices generated from the 3D MR T1 image as the first model ( 400) can be input to the channel. The first model 400 may receive a total of three slices based on the i-th and output the slice at the i-th position including segment data.

The processor 110 may partition at least one brain region included in the first medical image 30 into detailed regions by using the first model 400 . The first model 400 divides at least one brain region included in the first medical image 30 into detailed regions based on the first medical image 30 to obtain a plurality of segment data 41 , 42 , and 43 . ), the first output data 40 including

For example, the first model 400 may divide a brain region into detailed regions including a cortical region and a subcortical region based on the first medical image 30 representing the entire brain region. The first segment data 41 may be data representing the hippocampus. The second segment data 42 may be data representing the amygdala. The N-th segment data 43 may be data representing the cortex. In this case, the N-th segment data 43 may be data representing the entire cortical region, or a set of segment data representing each of the cortical subregions (e.g. olfactory cortex, insula, etc.). A detailed description of each of the segment data 41 , 42 , and 43 is only an example, and the order and content may vary according to the segmentation result.

The processor 110 may generate a second medical image 50 that is an input image of the second model 500 based on one of the segment data 41 , 42 , and 43 of the first output data 40 . . In this case, the generation of the second medical image 50 may mean extracting one of the segment data 41 , 42 , and 43 of the first output data 40 and using it as it is or performing additional processing. For example, the processor 110 may extract the N-th segment data 43 representing the brain cortex region from the first output data 40 to generate a mask for the brain cortical region that is the second medical image 50 . there is. The processor 110 extracts and merges segment data representing the detailed regions (e.g. olfactory cortex, insula, etc.) of the brain cortex from the first output data 40 , thereby merging the brain cortex region as the second medical image 50 . You can also create a mask for Also, the processor 110 may generate a mask as the second medical image 50 by synthesizing the N-th segment data 43 and the first medical image 30 to extract the intensity of the cortical region.

The processor 110 may generate second output data 60 including a plurality of segment data 61 , 62 , 63 , and 64 using the second model 500 based on the second medical image 50 . can For example, when the second medical image 50 is a mask of the brain cortex region generated from the first output data 40 , the processor 110 uses the second model 500 learned as a 3D feature to The brain cortex region included in the second medical image 50 may be divided into detailed regions.

On the other hand, in the first model 400 according to an embodiment of the present disclosure, a first operation of learning a neural network by random sampling of an input image having a label and an input image having a label and a label are not present. By performing the second operation of learning the neural network by applying all of the input images that are not, two-dimensional features can be learned. The first model 400 may learn two-dimensional features of a medical image through a two-step learning process of the neural network.

For example, the first model 400 may train the convolutional neural network by selecting only a slice having a label among a plurality of slices generated from the 3D MR T1 image. The first model 400 may perform an operation of randomly sampling slices irrespective of a subject in the process of selecting only slices with labels. In this case, the first model 400 may use a dice loss function and an adam optimizer to learn the first motion.

The first model 400 may train the convolutional neural network using all of the plurality of slices generated from the 3D MR T1 image after the first operation described above. In the second operation, an input image including both a slice with a label and a slice without a label may be used. In this case, the first model 400 may use a cross entropy loss function and stochastic gradient descent to learn the second motion.

Referring to the above-described example, in the learning process of the first model 400, the first operation and the second operation are sequentially performed, and at the same time, the first operation and the second operation may be performed based on different loss functions. The first model 400 may learn to improve the dice score by using the dice loss function in the first operation. Also, the first model 400 may use a cross entropy loss function that is stable compared to the die loss function while performing the second operation after the first operation. This two-step learning method may reduce a learning rate in the second operation. In addition, in the second operation process, false positives can be effectively reduced without significantly changing the parameter learned by the second neural network through the first operation.

7 is a flowchart of a segmentation method based on a medical image according to another embodiment of the present disclosure.

When the computing device 100 uses the neural network model learned with the three-dimensional feature and the neural network model learned with the two-dimensional feature together, segmentation of the brain region may be performed through the following steps. In operation S210 , the computing device 100 may receive a first medical image including at least one brain region. In this case, the reception of the first medical image may mean receiving the medical image from the medical imaging system. For example, the first medical image may be a three-dimensional T1 MR image representing the entire brain region or a two-dimensional slice generated from the image.

In operation S220 , the computing device 100 may divide the brain region included in the first medical image into detailed regions through the first model learned as the two-dimensional feature. When the first medical image is an image representing the entire brain region and is used as an input to the first model, the first model that performs two-step learning based on different input data and loss functions is a first model that shows the entire brain region in the cortical region and the subcortical region. It can be divided into regions (e.g. hippocampus, etc.). In this case, the first model may further subdivide the cortical region into cortical detailed regions (eg, olfactory brain cortex, etc.). The image segmented through the first model may be used as a mask for each of the cortical region or subcortical regions. The first medical image may be a 3D T1 MR image or a 2D slice image generated based on the 3D T1 MR image. When the 3D T1 MR image is received by the computing device 100 as the first medical image, the computing device 100 may perform a preprocessing process of generating a 2D slice image as input data of the first model.

In operation S230 , the computing device 100 may use the second medical image generated from the output data of the first model as the input image of the second model. The computing device 100 may extract or generate a second medical image from segment data for each brain region generated by the first model. The computing device 100 may use the second medical image extracted or generated through the above-described process as an input image of the second model. For example, when a mask for the cortical region is generated through the first model, the computing device 100 may receive the mask for the cortical region as a second medical image and use it as an input image of the second model. The second medical image may be a binary mask indicating a brain cortex region generated from one of the segments of the first medical image. In addition, the second medical image may be a mask generated by matching a binary mask extracted from one of the segments of the first medical image with an original medical image (e.g., the first medical image, etc.) and extracting the intensity for the brain cortex region. .

Since step S240 may be interchangeably performed with step S120 described above by the computing device 100 , a detailed description thereof will be omitted.

On the other hand, a computer-readable medium storing a data structure according to an embodiment of the present disclosure is disclosed.

The data structure may refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure may refer to an organization of data to solve a specific problem (eg, data retrieval, data storage, and data modification in the shortest time). A data structure may be defined as a physical or logical relationship between data elements designed to support a particular data processing function. The logical relationship between data elements may include a connection relationship between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements physically stored on a computer-readable storage medium (eg, persistent storage). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to data. Through an effectively designed data structure, the computing device can perform an operation while using the resource of the computing device to a minimum. Specifically, the computing device may increase the efficiency of operations, reads, insertions, deletions, comparisons, exchanges, and retrievals through effectively designed data structures.

A data structure may be classified into a linear data structure and a non-linear data structure according to the type of the data structure. The linear data structure may be a structure in which only one piece of data is connected after one piece of data. The linear data structure may include a list, a stack, a queue, and a deck. A list may mean a set of data in which an order exists internally. The list may include a linked list. The linked list may be a data structure in which data is linked in such a way that each data is linked in a line with a pointer. In a linked list, a pointer may contain information about a link with the next or previous data. A linked list may be expressed as a single linked list, a doubly linked list, or a circularly linked list according to a shape. A stack can be a data enumeration structure with limited access to data. A stack can be a linear data structure in which data can be manipulated (eg, inserted or deleted) at only one end of the data structure. The data stored in the stack may be a data structure (LIFO-Last in First Out). A queue is a data listing structure that allows limited access to data, and unlike a stack, it may be a data structure that is stored later (FIFO-First in First Out). A deck can be a data structure that can process data at either end of the data structure.

The non-linear data structure may be a structure in which a plurality of data is connected after one data. The nonlinear data structure may include a graph data structure. A graph data structure may be defined as a vertex and an edge, and the edge may include a line connecting two different vertices. A graph data structure may include a tree data structure. The tree data structure may be a data structure in which one path connects two different vertices among a plurality of vertices included in the tree. That is, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, the neural network is unified and described. The data structure may include a neural network. And the data structure including the neural network may be stored in a computer-readable medium. Data structures, including neural networks, also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and neural networks. It may include a loss function for learning of . A data structure comprising a neural network may include any of the components disclosed above. That is, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation function associated with each node or layer of the neural network, and neural network It may be configured to include all or any combination thereof, such as a loss function for learning of . In addition to the above-described configurations, a data structure including a neural network may include any other information that determines a characteristic of a neural network. In addition, the data structure may include all types of data used or generated in the operation process of the neural network, and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is configured by including at least one or more nodes.

The data structure may include data input to the neural network. A data structure including data input to the neural network may be stored in a computer-readable medium. The data input to the neural network may include learning data input in a neural network learning process and/or input data input to the neural network in which learning is completed. Data input to the neural network may include pre-processing data and/or pre-processing target data. The preprocessing may include a data processing process for inputting data into the neural network. Accordingly, the data structure may include data to be pre-processed and data generated by pre-processing. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weight and parameter may be used interchangeably.) And the data structure including the weight of the neural network may be stored in a computer-readable medium. The neural network may include a plurality of weights. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node sets values input to input nodes connected to the output node and links corresponding to the respective input nodes. A data value output from the output node may be determined based on the weight. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

By way of example and not limitation, the weight may include a weight variable in a neural network learning process and/or a weight in which neural network learning is completed. The variable weight in the neural network learning process may include a weight at a time point at which a learning cycle starts and/or a weight variable during the learning cycle. The weight for which neural network learning is completed may include a weight for which a learning cycle is completed. Accordingly, the data structure including the weights of the neural network may include a data structure including the weights that vary in the neural network learning process and/or the weights on which the neural network learning is completed. Therefore, it is assumed that the above-described weights and/or combinations of weights are included in the data structure including the weights of the neural network. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer-readable storage medium (eg, memory, hard disk) after being serialized. Serialization can be the process of converting a data structure into a form that can be reconstructed and used later by storing it on the same or a different computing device. The computing device may serialize the data structure to send and receive data over the network. A data structure including weights of the serialized neural network may be reconstructed in the same computing device or in another computing device through deserialization. The data structure including the weight of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure to increase computational efficiency while using the resources of the computing device to a minimum (e.g., B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree). The foregoing is merely an example, and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network. In addition, the data structure including the hyperparameters of the neural network may be stored in a computer-readable medium. The hyper parameter may be a variable variable by a user. Hyperparameters are, for example, learning rate, cost function, number of iterations of the learning cycle, weight initialization (e.g., setting the range of weight values to be initialized for weights), Hidden Unit The number (eg, the number of hidden layers, the number of nodes of the hidden layer) may be included. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

8 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above as being generally capable of being implemented by a computing device, those skilled in the art will appreciate that the present disclosure may be implemented in hardware and software in combination with computer-executable instructions and/or other program modules and/or in combination with computer-executable instructions and/or other program modules that may be executed on one or more computers. It will be appreciated that it can be implemented as a combination.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will appreciate that the methods of the present disclosure can be applied to single-processor or multiprocessor computer systems, minicomputers, mainframe computers as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like. It will be appreciated that each of these may be implemented in other computer system configurations, including those capable of operating in connection with one or more associated devices.

The described embodiments of the present disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Any medium accessible by a computer can be a computer-readable medium, and such computer-readable media includes volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. including removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer readable storage media includes volatile and nonvolatile media, temporary and non-transitory media, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media. A computer-readable storage medium may be RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device, or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store the desired information.

Computer readable transmission media typically embodies computer readable instructions, data structures, program modules or other data, etc. in a modulated data signal such as a carrier wave or other transport mechanism, and Includes any information delivery medium. The term modulated data signal means a signal in which one or more of the characteristics of the signal is set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 implementing various aspects of the disclosure is shown including a computer 1102 , the computer 1102 including a processing unit 1104 , a system memory 1106 , and a system bus 1108 . do. A system bus 1108 couples system components, including but not limited to system memory 1106 , to the processing device 1104 . The processing device 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as processing unit 1104 .

The system bus 1108 may be any of several types of bus structures that may further interconnect a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112 . A basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, EEPROM, etc., the BIOS is the basic input/output system (BIOS) that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

The computer 1102 may also include an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) - this internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes—a magnetic floppy disk drive (FDD) 1116 (eg, for reading from or writing to removable diskette 1118), and an optical disk drive 1120 (eg, a CD-ROM) for reading from, or writing to, disk 1122, or other high capacity optical media, such as DVD. The hard disk drive 1114 , the magnetic disk drive 1116 , and the optical disk drive 1120 are connected to the system bus 1108 by the hard disk drive interface 1124 , the magnetic disk drive interface 1126 , and the optical drive interface 1128 , respectively. ) can be connected to The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will use zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other tangible computer-readable media such as etc. may also be used in the exemplary operating environment and any such media may include computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in the drive and RAM 1112 , including an operating system 1130 , one or more application programs 1132 , other program modules 1134 , and program data 1136 . All or portions of the operating system, applications, modules, and/or data may also be cached in RAM 1112 . It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 via one or more wired/wireless input devices, for example, a pointing device such as a keyboard 1138 and a mouse 1140 . Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are connected to the processing unit 1104 through an input device interface 1142 that is often connected to the system bus 1108, parallel ports, IEEE 1394 serial ports, game ports, USB ports, IR interfaces, It may be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also coupled to the system bus 1108 via an interface, such as a video adapter 1146 . In addition to the monitor 1144, the computer typically includes other peripheral output devices (not shown), such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148 via wired and/or wireless communications. Remote computer(s) 1148 may be workstations, computing device computers, routers, personal computers, portable computers, microprocessor-based entertainment devices, peer devices, or other common network nodes, and are typically connected to computer 1102 . Although it includes many or all of the components described for it, only memory storage device 1150 is shown for simplicity. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, eg, a wide area network (WAN) 1154 . Such LAN and WAN networking environments are common in offices and companies, and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, for example, the Internet.

When used in a LAN networking environment, the computer 1102 is coupled to the local network 1152 through a wired and/or wireless communication network interface or adapter 1156 . Adapter 1156 may facilitate wired or wireless communication to LAN 1152 , which LAN 1152 also includes a wireless access point installed therein for communicating with wireless adapter 1156 . When used in a WAN networking environment, the computer 1102 may include a modem 1158, be connected to a communication computing device on the WAN 1154, or establish communications over the WAN 1154, such as over the Internet. have other means. A modem 1158 , which may be internal or external and a wired or wireless device, is coupled to the system bus 1108 via a serial port interface 1142 . In a networked environment, program modules described for computer 1102 , or portions thereof, may be stored in remote memory/storage device 1150 . It will be appreciated that the network connections shown are exemplary and other means of establishing a communication link between the computers may be used.

The computer 1102 may be associated with any wireless device or object that is deployed and operates in wireless communication, for example, a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communication satellite, wireless detectable tag. It operates to communicate with any device or place, and phone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network or may simply be an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet, etc. without a wired connection. Wi-Fi is a wireless technology such as cell phones that allows these devices, eg, computers, to transmit and receive data indoors and outdoors, ie anywhere within range of a base station. Wi-Fi networks use a radio technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks may operate in unlicensed 2.4 and 5 GHz radio bands, for example at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band). .

One of ordinary skill in the art of this disclosure will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols, and chips that may be referenced in the above description are voltages, currents, electromagnetic waves, magnetic fields or particles, optical field particles or particles, or any combination thereof.

Those of ordinary skill in the art of the present disclosure will recognize that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein include electronic hardware, (convenience For this purpose, it will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. A person skilled in the art of the present disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be interpreted as a departure from the scope of the present disclosure.

The various embodiments presented herein may be implemented as methods, apparatus, or articles of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash drives. memory devices (eg, EEPROMs, cards, sticks, key drives, etc.). Also, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. Based on design priorities, it is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure. The appended method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the embodiments presented herein, but is to be construed in the widest scope consistent with the principles and novel features presented herein.

Claims (13)

A medical image-based segmentation method performed by a computing device including at least one processor, comprising:
receiving a medical image including at least one brain region; and
partitioning at least one brain region included in the medical image using a neural network model learned as a three-dimensional feature of the input image;
containing,
Way.
The method of claim 1,
The medical image is
Which includes a mask (mask) of the brain cortical region (cortical region) generated based on the three-dimensional image,
Way.
The method of claim 1,
The medical image is
It includes a mask of the brain cortex region generated based on the output data of the neural network model learned with the two-dimensional features of the input image,
The neural network model trained with the two-dimensional features,
At least one two-dimensional slice generated from a three-dimensional image is used as input data to partition at least one brain region included in the input data,
Way.
The method of claim 1,
The neural network model trained with the three-dimensional features,
Learning the three-dimensional feature based on an active region based on a predetermined brain region with respect to the input image,
Way.
5. The method of claim 4,
The neural network model trained with the three-dimensional features,
By learning a convolutional neural network for only an active region based on a brain cortical region in the input image, the three-dimensional feature is learned,
Way.
A medical image-based segmentation method performed by a computing device including at least one processor, comprising:
receiving a first medical image including at least one brain region;
partitioning at least one brain region included in the first medical image using a first model learned as a two-dimensional feature of the input image; and
At least one brain region included in the second medical image is calculated using a second model learned as a 3D feature of an input image based on a second medical image generated based on the output data of the first model. partitioning;
containing,
Way.
7. The method of claim 6,
The first medical image is
Containing at least one two-dimensional slice (slice) generated from a three-dimensional image,
Way.
7. The method of claim 6,
The first model is
a first operation of training a convolutional neural network by random sampling an input image having a label; and
a second operation of learning the convolutional neural network by applying both an input image with the label and an input image without the label;
By performing the to learn the two-dimensional features,
Way.
9. The method of claim 8,
The first operation and the second operation are
which is performed based on different loss functions,
Way.
10. The method of claim 9,
The first operation is
It is performed based on the dice loss function,
The second operation is
Which is performed based on a cross-entropy loss function after the first operation,
Way.
7. The method of claim 6,
The second medical image is
which includes a mask of a brain cortex region generated based on output data of a first model receiving the first medical image,
Way.
A computer program stored in a computer readable storage medium, wherein the computer program, when executed on one or more processors, performs the following operations for performing segmentation based on a medical image, the operations comprising:
receiving a medical image including at least one brain region; and
partitioning at least one brain region included in the medical image by using a neural network model learned as a three-dimensional feature of the input image;
containing,
A computer program stored on a computer-readable storage medium.
A computing device that performs segmentation based on a medical image, comprising:
a processor including at least one core;
a memory containing program codes executable by the processor; and
a network unit for receiving a medical image including at least one brain region;
including,
The processor is
Partitioning at least one brain region included in the medical image using a neural network model learned as a three-dimensional feature of the input image,
Device.

Images