KR102505539B1 - Method for providing information on segmentation of liver and device for using the same - Google Patents

Abstract

The present invention provides a method for providing liver segmentation information, implemented by a processor, and a device for providing liver segmentation information using the same. The method comprises the steps of: receiving a CT image including an abdominal image; obtaining a mask of a liver region based on the received CT image by using an artificial neural network-based first segmentation model configured to output the mask of the liver region using the CT images as an input; obtaining a mask of the liver vascular area based on the received CT image by using an artificial neural network-based second segmentation model configured to output the mask of the liver vascular area; generating a three-dimensional liver based on segmented masks of the liver region; generating a three-dimensional liver vascular area on segmented masks of the liver vascular area; and segmenting the three-dimensional liver into a plurality of regions using the three-dimensional liver vascular system. According to the present invention, information on the liver and blood vessels necessary for diagnosis of lesions or surgery can be provided in a three-dimensional and spatial manner.

Description

Liver segmentation information providing method and device for providing information on liver segmentation using the same

The present invention relates to a method for providing information on liver segmentation and an apparatus using the same.

The liver is anatomically divided into eight compartments. The liver is three-dimensional, so it cannot be seen in one section. Conventionally, when checking the liver or blood vessels, it is insufficient to view a CT image as a flat 2D image or directly view a 3D image generated by a computer for imaging a CT device to check it in a three-dimensional sense of space.

As the accuracy of diagnosis is further demanded for the improvement of medical services, etc., the development of a new method for obtaining liver and blood vessel information necessary for diagnosis of lesions and surgery is required.

The background description of the invention has been prepared to facilitate understanding of the present invention. It should not be construed as an admission that matters described in the background art of the invention exist as prior art.

The segmentation method of the existing image processing technique has a problem in that the segmentation result is not accurate depending on the captured image.

Therefore, by introducing an artificial intelligence algorithm-based system, we tried to improve the reading and surgical planning environment by quickly and accurately segmenting the liver and liver blood vessel regions in the CT image.

The inventors of the present invention attempted to reconstruct a region segmentation model learned to divide a liver region and a liver blood vessel region for a liver segmentation system, and the divided liver region and blood vessel region into a three-dimensional volume.

More specifically, the inventors of the present invention tried to create a three-dimensional liver and three-dimensional liver blood vessels based on a segmentation model learned from CT images and a mask of the liver and liver blood vessels region extracted therefrom. An attempt was made to divide the three-dimensional liver into a plurality of regions using the generated inter-dimensional blood vessels.

In particular, the inventors of the present invention tried to divide based on the location of two blood vessels, the hepatic vein and the portal vein, which pass through the liver.

Therefore, the problem to be solved by the present invention is to obtain a mask of the liver and liver blood vessel region for the received CT image using a segmentation model, and based on this, create a three-dimensional liver and three-dimensional inter-vascular volume, and create a three-dimensional image. It is to provide a liver segmentation information providing method for segmenting a three-dimensional liver using liver blood vessels and an apparatus using the same.

The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above problems, a method for providing segmentation information according to an embodiment of the present invention is provided. The method, as a method for providing liver segmentation information implemented by a processor, includes receiving a CT image including an abdominal image, first segmentation based on an artificial neural network configured to output a mask of the liver region using the CT image as an input Obtaining a mask of the liver region based on the received CT image using a model, using a second segmentation model based on an artificial neural network configured to output a mask for the liver blood vessel region, based on the received CT image Obtaining a mask of the liver blood vessel region, generating a three-dimensional liver based on the divided liver region mask, generating a three-dimensional liver blood vessel based on the divided liver blood vessel region mask, and using the three-dimensional liver blood vessel and dividing the three-dimensional space into two regions.

According to a feature of the present invention, after receiving the CT image, the size of the CT image is changed and sampled into several predetermined fields, or the CT image is converted into a CT image by applying window values to the liver region and liver blood vessels. or applying histogram equalization and normalization.

According to another feature of the present invention, the step of generating a three-dimensional liver comprises: detecting a pixel having the same value as a specific pixel in a slice including a liver region mask and a slice adjacent to each other in an adjacent predetermined direction; The method may further include generating a plurality of graphs in which pixels having the same value are connected to each other, and detecting a graph having the largest number of connected nodes among the plurality of graphs.

According to another feature of the present invention, the step of segmenting the three-dimensional space is the step of dividing the three-dimensional space into a plurality of regions by using the three-dimensional liver corresponding to the graph with the largest number of detected connected nodes and using the inter-dimensional blood vessels. may further include.

According to another feature of the present invention, the dividing of the three-dimensional space into a plurality of regions includes extracting inter-dimensional blood vessels as dotted lines, and dividing the three-dimensional space into a plurality of regions using the positions and directions of the extracted dotted lines. Further steps may be included.

According to another feature of the present invention, the method may further include measuring volumes between three-dimensional regions divided into a plurality of regions.

According to another feature of the present invention, after the step of dividing the three-dimensional body into a plurality of regions, a step of generating a single volume by merging the plurality of divided liver regions may be further included.

In order to solve the above problems, an apparatus for providing information on liver segmentation according to another embodiment of the present invention is provided. The apparatus includes a communication unit configured to receive a CT image including an abdominal image, and a processor connected to the communication unit. At this time, the processor obtains a mask of the liver region based on the received CT image by using an artificial neural network-based first segmentation model configured to output a mask of the liver region by taking the CT image as an input, and A mask of the liver blood vessel region is obtained based on the received CT image using an artificial neural network network-based second segmentation model configured to output a mask for , a stereoscopic liver is generated based on the segmented liver region mask, and segmentation is performed. A three-dimensional liver blood vessel is generated based on the obtained liver blood vessel region mask, and the three-dimensional liver is divided into a plurality of regions using the three-dimensional liver blood vessel.

According to a feature of the present invention, the processor, after receiving the CT image, changes the size of the CT image and samples it into several predetermined fields, or applies a window value to the liver region and liver blood vessels. , or to apply histogram smoothing and normalization.

According to another feature of the present invention, the processor detects a pixel having the same value as a specific pixel in a slice including a liver region mask and a slice adjacent to each other in an adjacent predetermined direction, and detects a pixel having the same value as the specific pixel. It may be further configured to generate a plurality of graphs connected to each other and detect a graph having the greatest number of connected nodes among the plurality of graphs.

According to another feature of the present invention, when dividing a three-dimensional space, the processor divides the three-dimensional space into a plurality of regions using the three-dimensional space corresponding to the graph with the largest number of detected connected nodes and using the inter-dimensional blood vessels. It can be further configured to do.

According to another feature of the present invention, the processor may be further configured to extract inter-dimensional blood vessels as dotted lines and divide the inter-dimensions into a plurality of regions using the positions and directions of the extracted dotted lines.

According to another feature of the present invention, the processor may be further configured to measure volumes between solids divided into a plurality of regions, respectively.

According to another feature of the present invention, the processor may be further configured to create a single volume by combining the divided plurality of liver regions after dividing the three-dimensional liver into a plurality of regions.

The present invention provides a system for dividing the liver into a plurality of regions by dividing the liver and liver blood vessels based on a segmentation model, thereby providing information on the liver and blood vessels necessary for diagnosis or surgery of lesions in a three-dimensional and spatial sense. there is.

Accordingly, the present invention provides a liver segmentation system based on a deep learning model, so that highly accurate reading and surgical planning can be established.

In particular, the present invention uses a deep learning-based liver and liver blood vessel segmentation algorithm, rather than a segmentation method of image processing techniques, to automatically segment the liver region and liver blood vessel region without user input, thereby dividing the divided regions into a plurality of regions. Liver can be served quickly and accurately.

Furthermore, by providing a visualized image to a hologram device connected to a computer, it is possible to improve a medical staff's workflow in surgery or treatment.

Effects according to the present invention are not limited by the contents exemplified above, and more various effects are included in the present invention.

1 illustrates a liver segmentation system based on an apparatus for providing information on liver segmentation according to an embodiment of the present invention.
FIG. 2 illustratively illustrates the configuration of an apparatus for providing information on liver segmentation according to an embodiment of the present invention.
FIG. 3 illustratively illustrates the configuration of a medical device for receiving and outputting information on liver segmentation from a device for providing information on liver segmentation according to an embodiment of the present invention.
4 illustrates a procedure of a liver segmentation information providing method according to an embodiment.
5A to 5D illustrate a liver segmentation information providing method according to an exemplary embodiment.
6 illustrates liver segmentation results according to an embodiment.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various forms different from each other, only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention pertains. It is provided to completely inform the person who has the scope of the invention, and the present invention is only defined by the scope of the claims. In connection with the description of the drawings, like reference numerals may be used for like elements.

In this document, expressions such as "has," "may have," "includes," or "may include" indicate the existence of a corresponding feature (eg, numerical value, function, operation, or component such as a part). , which does not preclude the existence of additional features.

In this document, expressions such as “A or B,” “at least one of A and/and B,” or “one or more of A or/and B” may include all possible combinations of the items listed together. . For example, “A or B,” “at least one of A and B,” or “at least one of A or B” (1) includes at least one A, (2) includes at least one B, Or (3) may refer to all cases including at least one A and at least one B.

Expressions such as “first,” “second,” “first,” or “second,” used in this document may modify various elements, regardless of order and/or importance, and refer to one element as It is used only to distinguish it from other components and does not limit the corresponding components. For example, a first user device and a second user device may represent different user devices regardless of order or importance. For example, without departing from the scope of rights described in this document, a first element may be named a second element, and similarly, the second element may also be renamed to the first element.

A component (e.g., a first component) is "(operatively or communicatively) coupled with/to" another component (e.g., a second component); When referred to as "connected to", it should be understood that the certain component may be directly connected to the other component or connected through another component (eg, a third component). On the other hand, when an element (eg, a first element) is referred to as being “directly connected” or “directly connected” to another element (eg, a second element), the element and the above It may be understood that other components (eg, a third component) do not exist between the other components.

As used in this document, the expression "configured to" means "suitable for," "having the capacity to," depending on the circumstances. ," "designed to," "adapted to," "made to," or "capable of." The term "configured (or set) to" may not necessarily mean only "specifically designed to" hardware. Instead, in some contexts, the phrase "device configured to" may mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "a processor configured (or configured) to perform A, B, and C" may include a dedicated processor (e.g., embedded processor) to perform those operations, or by executing one or more software programs stored in a memory device. , may mean a general-purpose processor (eg, CPU or application processor) capable of performing corresponding operations.

Terms used in this document are only used to describe a specific embodiment, and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly dictates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by a person of ordinary skill in the art described in this document. Among the terms used in this document, terms defined in a general dictionary may be interpreted as having the same or similar meaning as the meaning in the context of the related art, and unless explicitly defined in this document, an ideal or excessively formal meaning. not be interpreted as In some cases, even terms defined in this document cannot be interpreted to exclude the embodiments of this document.

Each feature of the various embodiments of the present invention can be partially or entirely combined or combined with each other, and as those skilled in the art can fully understand, various interlocking and driving operations are possible, and each embodiment can be implemented independently of each other. It may be possible to implement together in an association relationship.

For clarity of interpretation of this specification, terms used in this specification will be defined below.

As used herein, the term "subject" may refer to any subject for which liver segmentation is desired. In this case, the subject disclosed in this specification may be any mammal except for humans, but is not limited thereto.

As used herein, the term “CT image” is a medical image captured by an image diagnosis device, and may include an abdominal region, but is not limited thereto.

Meanwhile, the CT image may be a 2D image, a 3D image, a still image of one cut, or a video composed of a plurality of cuts. For example, when a CT image is a video composed of a plurality of cuts, a mask for the liver region and liver blood vessel region is generated for each of the plurality of CT images according to the method for providing information on liver segmentation according to an embodiment of the present invention. can be obtained As a result, the present invention can perform liver segmentation simultaneously with reception of the CT image from the imaging diagnosis device, and thus can provide information on the liver, liver blood vessels, and divided liver in real time.

As used herein, the term “first segmentation model” may be a model configured to output a mask for the liver region by taking a CT image including the abdominal region as an input.

More specifically, the first segmentation model may be a model obtained by learning the CT image to obtain a mask of the liver region based on the CT image.

As used herein, the term “second segmentation model” may be a model configured to output a mask for the liver blood vessel region by taking a CT image including the abdominal region as an input.

More specifically, the second segmentation model may be a model obtained by learning CT stereoscopic volume images obtained from multiple patients using a CNN structure to obtain a mask of the liver blood vessel region based on the CT images.

Meanwhile, the division models may be U-net-based division learning models, but are not limited thereto. For example, split models include VGG net, DenseNet, Fully Convolutional Network (FCN) with an encoder-decoder structure, deep neural network (DNN) such as SegNet, DeconvNet, DeepLAB V3+, SqueezeNet, Alexnet, ResNet18, and MobileNet-v2. , GoogLeNet, Resnet-v2, Resnet50, Resnet101, and Inception-v3.

Hereinafter, a liver segmentation system based on an apparatus for providing information on liver segmentation according to an embodiment of the present invention will be described with reference to FIGS. 1 to 3 .

1 illustrates a liver segmentation system based on an apparatus for providing information on liver segmentation according to an embodiment of the present invention.

First, referring to FIG. 1 , a liver segmentation system 1000 may be a system configured to provide information on liver segmentation based on a CT image including an abdominal image of an object. At this time, the liver segmentation system 1000 includes an apparatus 100 for providing information on liver segmentation of an object based on a CT image, a medical staff device 200 receiving information on liver segmentation, and an image providing a CT image. The diagnosis device 300 may be configured.

First, the apparatus 100 for providing information on liver segmentation includes a general-purpose computer, a laptop computer, and/or a general-purpose computer that performs various calculations to segment the liver and liver blood vessels based on the user's CT image provided from the image diagnosis apparatus 300. It may include a data server and the like. At this time, the medical staff device 200 may be a device for accessing a web server providing a web page related to liver segmentation or a mobile web server providing a mobile web site, but is not limited thereto. don't

More specifically, the apparatus 100 for providing information on liver segmentation may receive a CT image from the image diagnosis apparatus 300 and provide information related to liver segmentation from the received CT image. At this time, the image diagnosis apparatus 300 may use a plurality of segmentation models.

The apparatus 100 for providing information on liver segmentation may provide data related to liver segmentation of an individual to the medical device 200 .

Data provided from the apparatus 100 for providing information on liver segmentation in this way may be provided as a web page through a web browser installed in the medical staff apparatus 200, or may be provided in the form of an application or program. In various embodiments, this data may be provided in a form incorporated into the platform in a client-server environment.

Next, the medical staff device 200 is an electronic device that requests provision of information on segmentation of an object and provides a user interface for displaying evaluation result data, including a smartphone, a tablet PC (Personal Computer), a laptop and/or or at least one of a PC and the like.

The medical staff device 200 may receive information about the liver and liver blood vessels of an object from the device 100 for providing information on liver segmentation, and display the received result through the display unit. Here, the information may further include not only the three-dimensional liver and three-dimensional liver blood vessels obtained by the segmentation model, but also the volume of the liver divided into a plurality of pieces by the liver blood vessels. In this embodiment, the device for providing information on liver division 100 and the medical staff device 200 have been described as being separated, but the device for providing information on liver division 100 and the medical device 200 are integrated into one device. can be implemented Alternatively, the apparatus 100 for providing information on liver segmentation and the apparatus 300 for diagnosing images may be implemented as one apparatus.

Referring to FIG. 2, components of the apparatus 100 for providing information on liver division according to the present invention will be described in detail.

2 is a schematic diagram illustrating an apparatus for providing information on liver segmentation according to an embodiment of the present invention.

Referring to FIG. 2 , an apparatus 100 for providing information on liver division includes a storage unit 110 , a communication unit 120 and a processor 130 .

First, the storage unit 110 may store various data for segmentation between objects. In various embodiments, the storage unit 110 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, magnetic memory , magnetic disks, and optical disks, and may include at least one type of storage medium.

The communication unit 120 connects the device 100 for providing information on liver division to enable communication with an external device. The communication unit 120 may transmit/receive various data by being connected to the medical staff device 200 and furthermore the image capturing device 300 using wired/wireless communication. Specifically, the communication unit 120 may receive a CT image including an abdominal image of an object from the image capture device 300 . Also, the communication unit 120 may transmit evaluation results to the medical device 200 .

The processor 130 is operatively connected to the storage unit 110 and the communication unit 120, and can perform various commands for segmenting an entity.

Specifically, the processor 130 may be configured to divide the liver and liver blood vessel regions based on the CT image received through the communication unit 120 and divide the liver into a plurality of regions based on the divided regions.

The processor 130 may execute a first segmentation model configured to output a mask for the liver region and a second segmentation model configured to output a mask for the liver vascular region, based on the CT image including the abdominal image. Furthermore, the liver may be finally divided into a plurality of regions by using an algorithm configured to divide the liver region into a plurality of regions based on the output liver blood vessel mask region.

On the other hand, the apparatus 100 for providing information on segmentation is not limited to being designed in terms of hardware. For example, the processor 130 of the apparatus 100 for providing information on liver division may be implemented as software. Accordingly, the results of the segmentation may be displayed through a display unit (not shown) of the apparatus 300 for image capturing to which the software is connected.

FIG. 3 illustratively illustrates the configuration of a medical device for receiving and outputting information on liver segmentation from a device for providing information on liver segmentation according to an embodiment of the present invention.

Referring together with FIG. 3 , the medical staff device 200 includes a communication unit 210 , a display unit 220 , a storage unit 230 and a processor 240 .

The communication unit 210 connects the medical staff device 200 to enable communication with an external device. The communication unit 210 may be connected to the apparatus 100 for providing information on liver division using wired/wireless communication to transmit various data related to liver division. Specifically, the communication unit 210 may receive information related to liver division of an individual from the apparatus 100 for providing information on liver division, for example, information such as the volume of each liver divided into a plurality of regions. The above information may be displayed and provided for a CT image, but is not limited thereto.

The display unit 220 can display various interface screens for displaying information related to segmentation of an object. For example, the display unit 220 can visualize and provide a liver divided into a plurality of regions of an object, and display and provide values obtained by measuring the volume of each divided liver.

In various embodiments, the display unit 220 may include a touch screen, and for example, a touch using an electronic pen or a part of the user's body, a gesture, a proximity, a drag, or a swipe A swipe or hovering input may be received.

The storage unit 230 may store various data used to provide a user interface for displaying result data. In various embodiments, the storage unit 230 may be a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (for example, SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) , a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium.

The processor 240 is operatively connected to the communication unit 210, the display unit 220, and the storage unit 230, and can perform various commands to provide a user interface for displaying result data.

Hereinafter, a liver segmentation information providing method according to an embodiment of the present invention will be described in detail with reference to FIGS. 4 and 5A to 5D. 4 exemplarily illustrates a procedure of a method for providing information on liver segmentation according to an embodiment of the present invention.

First, referring to FIG. 4 , a procedure for providing information on liver segmentation according to an embodiment of the present invention is as follows. First, a CT image including an abdominal image of an object is received (S410). Then, a mask of the liver region is acquired using the first segmentation model and a mask of the liver blood vessel region is obtained using the second segmentation model (S420). Next, a three-dimensional liver is created based on the divided liver region mask, and a three-dimensional liver blood vessel is created based on the divided liver blood vessel region mask (S430). Finally, the three-dimensional liver is divided into a plurality of regions using the three-dimensional blood vessels (S440).

More specifically, in the step of receiving a CT image (S410), a CT image including an abdominal image may be received. For example, it may be a CT image having a size of 512*512 input for liver and liver blood vessel segmentation.

According to an embodiment of the present invention, a plurality of CT images may be received in step S410 of receiving the CT images. For example, as a CT image captured in real time by driving an imaging device can be acquired, a plurality of CT images can be acquired in the step of receiving the CT image (S410).

After the CT image is received, preprocessing may be performed on the CT image. The size of the CT image is changed, and a window value may be applied to emphasize the liver region and liver blood vessels. Image processing techniques may then be applied to improve the contrast of the original image.

For example, equalization can be applied to the entire medical image by applying Image Sharpening (IS), Histogram Equalization (HE), and Contrast Limited Adaptive Histogram Equalization (CLAHE) techniques. there is.

5A to 5D illustrate a method for providing liver segmentation information according to an exemplary embodiment.

For example, referring to FIG. 5A together, a CT image 502 having a size of 512*512 received through receiving a CT image including an abdominal image (S410) is resized to 256 pixels horizontally and 256 pixels vertically. can In order to emphasize the HU (Hounsfield Unit) value between 40 and 60 of the liver area in the 12-bit CT DICOM image, the window value (Width:180, Center:50) was applied to convert it to an 8-bit CT image, and histogram smoothing was performed. can be applied Referring to (b) of FIG. 4B, a CT image 504 in which the liver region is emphasized by normalizing an 8-bit image having a pixel distribution between 0 and 255 to a pixel distribution between 0 and 1 (508) ) can be obtained. For example, CT image 504 with the liver region highlighted can be used to obtain a liver region mask.

The CT image 502 with a size of 512*512 received through the step of receiving the CT image including the abdominal image (S410) is resized to 128 pixels horizontally and 128 pixels vertically, and is sampled into 128 images of 128*128 pixels. (sampling) can be done. To emphasize blood vessels in the liver, window values (Width: 500, Center: 0) are applied, converted to 8-bit CT images, and histogram smoothing can be applied. Referring to (b) of FIG. 5A , a CT image 506 may be obtained by normalizing 510 an 8-bit image having a pixel distribution between 0 and 255 to a pixel distribution between 0 and 1. However, it is not limited thereto, and various methods capable of pre-processing the CT image may be employed. The CT image 506 can be used to obtain a mask of the liver vascular region.

Next, in obtaining a mask of the liver blood vessel region (S420), a first segmentation model configured to output a mask of the liver region by taking the CT image including the abdominal image as input and a second segment configured to output the mask of the liver blood vessel region A split model may be used.

For example, referring to FIG. 5B together, the preprocessed CT image 514 acquired in the step S410 of receiving the CT image 512, for example, the CT image 504 in FIG. A mask of the liver region 518 may be obtained by inputting the segmentation model.

The preprocessed CT image 516 obtained in the step of receiving the CT image (S410), for example, the CT image 506 in FIG. 5A, is input to the second segmentation model, and the hepatic vein area 520 and a mask of the portal vein region 522 may be acquired.

The first segmentation model may be a model obtained by learning a plurality of CT images in a U-net 2D structure to output a liver region mask, and the second segmentation model may include CTs obtained from a plurality of patients to output a liver vascular region mask. The image may be a model learned with a U-net stereoscopic based CNN structure, but is not limited thereto.

Next, a three-dimensional liver is generated based on the divided liver region mask, and a three-dimensional liver blood vessel is created based on the divided liver region mask (S430).

For example, referring to FIG. 5C , (a) may be a three-dimensional liver, (b) a three-dimensional blood vessel, and (c) may be a result display for positioning of a three-dimensional blood vessel in a three-dimensional liver.

More specifically, referring to FIG. 5B , a plurality of acquired liver area masks 608 may be changed to an original size of 512*512, and then merged into one to create a three-dimensional liver.

Furthermore, LCC (Largest Connected Component) algorithm may be applied between the generated three-dimensional bodies in order to remove parts other than the liver region. By applying the LCC (Largest Connected Component) algorithm, small volume regions can be removed while leaving only the largest solid liver.

In the present disclosure, the LCC (Largest Connected Component) algorithm acquires a liver region mask obtained in the step (S420) of a slice including a liver region mask and a pixel having the same value as a specific pixel in a slice adjacent to each other. direction can be detected. Then, a plurality of graphs can be created by connecting pixels having the same value as a specific pixel. Among a plurality of generated graphs, a graph with the largest number of connected nodes may be detected, and only the detected graph may be left. Through this, it is possible to remove a small volume region, that is, a part that is not a liver region, leaving only the largest three-dimensional liver.

(a) of FIG. 5C may be a three-dimensional cross corresponding to a graph in which the number of detected nodes is the largest. (a) may be used in the step of dividing the three-dimensional liver into a plurality of regions using the three-dimensional blood vessels (S440).

In the 26 directions, there may be 26 blocks (pixels) surrounding the block (pixel) in the center of the cube that is invisible. That is, the same type (value) can be found in 26 pixels adjacent to a specific pixel.

In the present disclosure, a node may mean a basic unit of data in a connection structure. That is, as an element constituting a graph, a point among points and lines constituting the graph may be referred to as a node.

(b) of FIG. 5C shows three-dimensional liver blood vessels, a hepatic vein 524 and a portal vein 526. More specifically, the hepatic vein area mask 520 and the portal vein area mask 522 having a size of 128*128*128 obtained in the step of acquiring the mask of the liver vessel area (S420) are reduced to the original size of 512*512*N. , and a three-dimensional intervascular vessel with the same number of images as the input image can be created.

The three-dimensional liver is divided into a plurality of regions using the generated inter-dimensional blood vessels (S440). (c) of FIG. 5C may display a result for confirming the position of the three-dimensional blood vessel (b) in the three-dimensional liver (a).

Hereinafter, a method of dividing the liver into a plurality of regions will be described in detail with reference to FIG. 5D.

Based on the three-dimensional liver vessels generated in the step of generating a three-dimensional liver based on the segmented liver region mask and generating the three-dimensional liver vessels based on the segmented liver vessel region mask (S430), Claude Couinaud proposed The liver can be divided in this way.

In the present disclosure, according to the method proposed by Claude Quinault, the liver is anatomically divided into eight compartments. According to the blood vessel flow, that is, it is divided into 4 segments based on the hepatic vein, and then divided up and down based on the portal vein, and there are a total of 8 segments.

By extracting and synthesizing axial images from the created three-dimensional blood vessels, images such as 528 and 534 in FIG. 5D can be created. If the three-dimensional blood vessels are extracted as dotted lines in order to find dividing lines to divide the image, images such as 529, 530, 535, and 536 in FIG. 5D can be generated. Reference numerals 531, 532, and 533 are hepatic vein regions, and 537 and 538 may be portal vein regions. The liver may be divided into a plurality of regions by using the location and direction of the extracted dotted line.

More specifically, it is possible to find each end point in the extracted dotted line, and find a center point connected to the end points and meeting them. Then, the region to be divided can be divided along the line with the center point and the end point. Hepatic veins can longitudinally divide the liver region, and hepatic portal veins can horizontally divide the liver region.

In various embodiments of the present invention, a step of measuring each volume between three-dimensional regions divided into a plurality of regions may be further included. Referring to 539 of FIG. 5D , volumes of regions 2, 3, 4, 5, 6, 7, and 8 may be respectively measured and provided to the medical staff device.

6 may be the final result of division. More specifically, after dividing the three-dimensional liver into a plurality of regions (S440), a single volume may be created by combining the divided plurality of liver regions. The created volume can be visualized on the hologram device.

Referring to FIG. 5D together, regions 2, 3, ,4, 5, 6, 7, and 8 are respectively (I), (II), (III), (IV), (V), and (VI) of FIG. , (VII).

In various embodiments of the present invention, information related to a surgical method may be provided to a medical staff device based on the divided region or the volume of each divided region.

For example, according to the location and size of the tumor, it can be divided into wedge resection, segmentectomy, and lobectomy. Depending on the location and size of the tumor, information on a surgical method or a region to be resected among the divided regions may be further provided.

The surgical method and providing apparatus described in the presented embodiment are not limited to the above-described contents and may be configured in various ways.

Although one embodiment of the present invention has been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and may be variously modified and implemented without departing from the technical spirit of the present invention. there is. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The protection scope of the present invention should be construed according to the claims below, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

100: device for providing information on liver division
110, 230: storage unit
120, 210: communication department
130, 240: processor
200: medical staff device
220: display unit
300: video recording device
502, 512: original size CT image
504, 514: CT images with liver regions highlighted
506, 516: CT images with liver vascular regions highlighted
508, 510: Normalization
518: Liver area mask
520: mask of hepatic vein area
522: Mask of the portal vein area
524: Hepatic Vein 526: Portal Vein

Claims (14)

As a method for providing segmentation information implemented by a processor,
Receiving a CT image including an abdominal image;
obtaining a liver mask based on the received CT image using a first segmentation model based on an artificial neural network configured to output a liver mask by taking the CT image as an input;
obtaining a mask of the liver blood vessel region based on the received CT image by using a second segmentation model based on an artificial neural network configured to output a mask of the liver blood vessel region;
Detecting a pixel having the same value as a specific pixel in a slice adjacent to the slice including the liver region mask in a predetermined direction;
Generating a plurality of graphs connecting pixels having the same value as the specific pixel;
Generating a three-dimensional liver based on the segmented liver region mask, including detecting a graph having the largest number of connected nodes among the plurality of graphs;
generating a three-dimensional liver blood vessel based on the segmented liver blood vessel region mask; and
and dividing the three-dimensional liver into a plurality of regions using the three-dimensional blood vessels. According to claim 1,
After receiving the CT image,
changing the size of the CT image and sampling it into several predetermined fields; or
Converting a CT image to which window values are applied to the liver region and liver blood vessels; or
A method for providing segmentation information further comprising applying histogram equalization and normalization. delete According to claim 1,
The step of dividing the three-dimensional space,
and dividing the three-dimensional liver into a plurality of regions by using the three-dimensional liver corresponding to a graph in which the number of the detected connected nodes is the largest, and using the three-dimensional blood vessels. For any one of claims 1, 2 and 4,
The step of dividing the three-dimensional space into a plurality of regions,
The method of providing liver segmentation information, comprising: extracting the three-dimensional blood vessel as a dotted line; and dividing the three-dimensional liver into a plurality of regions using the position and direction of the extracted dotted line. According to claim 1,
The method of providing liver segmentation information further comprising the step of measuring each volume of the three-dimensional space divided into the plurality of regions. According to claim 1,
After the step of dividing the solid into a plurality of regions,
The method of providing liver segmentation information further comprising generating a single volume by merging the plurality of divided liver regions. A communication unit configured to receive a CT image including an abdominal image;
And a processor connected to the communication unit,
the processor,
Obtaining a mask of the liver region based on the received CT image using a first segmentation model based on an artificial neural network configured to output a mask of the liver region by using the CT image as an input;
Obtaining a mask of the liver blood vessel region based on the received CT image using a second segmentation model based on an artificial neural network configured to output a mask of the liver blood vessel region;
Detecting a pixel having the same value as a specific pixel in a slice including the liver region mask and a slice adjacent to each other in an adjacent predetermined direction;
Creating a plurality of graphs connecting pixels having the same value as the specific pixel;
configured to detect a graph having the largest number of connected nodes among the plurality of graphs, and generate a three-dimensional liver based on the segmented liver region mask;
creating a three-dimensional liver blood vessel based on the segmented liver blood vessel region mask;
An apparatus for providing information on liver segmentation configured to divide the three-dimensional liver into a plurality of regions using the three-dimensional blood vessels. According to claim 8,
the processor,
After receiving the CT image,
Changing the size of the CT image and sampling it into several predetermined fields, or
Converting to a CT image with window values applied to the liver area and liver blood vessels, or
An informative device for interdivision further configured to apply histogram equalization and normalization. delete According to claim 8,
the processor,
When dividing the three-dimensional liver, information on liver segmentation configured to divide the three-dimensional liver into a plurality of regions by using the three-dimensional liver corresponding to the graph in which the number of the detected connected nodes is the largest is provided and the three-dimensional liver is divided into a plurality of regions using the three-dimensional blood vessels device for. For any one of clauses 8, 9 and 11,
the processor,
An apparatus for providing information on liver segmentation configured to extract the three-dimensional blood vessel as a dotted line and divide the three-dimensional liver into a plurality of regions using the position and direction of the extracted dotted line. According to claim 8,
the processor,
An apparatus for providing information on liver division further configured to measure volumes of the three-dimensional liver divided into the plurality of regions, respectively. According to claim 8,
the processor,
After dividing the three-dimensional liver into the plurality of regions, the apparatus for providing information on liver segmentation further configured to generate a single volume by merging the divided plurality of liver regions.

Images