KR20210020618A - Abnominal organ automatic segmentation based on deep learning in a medical image - Google Patents

Abstract

The present invention provides a deep learning-based automatic segmentation method of an abdominal organ in a medical image which can accurately perform automatic segmentation of an abdominal organ. The deep learning-based automatic segmentation method of an abdominal organ in a medical image comprises: a step of inputting a plurality of sagittal images, a plurality of coronal images, and a plurality of axial images of a two-dimensional medical video including an abdominal organ into a two-dimensional deep neural network to generate a plurality of prediction maps and a plurality of label data of a region of interest through the two-dimensional deep neural network; a step of performing weighted fusion on the generated plurality of prediction maps to generate a preliminary shape model of the region of interest; and a step of inputting the preliminary shape model and a three-dimensional medical video including the abdominal organ into a three-dimensional deep neural network to acquire a segmentation result of the region of interest through the three-dimensional deep neural network.

Description

Abdominal organ segmentation method based on deep learning in medical imaging {ABNOMINAL ORGAN AUTOMATIC SEGMENTATION BASED ON DEEP LEARNING IN A MEDICAL IMAGE}

The present invention relates to a method for automatically segmenting abdominal organs based on deep learning in medical images, and more particularly, to a method for automatic segmentation of abdominal organs using a 2D deep neural network and a 3D deep neural network.

In radiation therapy, it is important to accurately inject radiation into the tumor while minimizing the amount of radiation injected into the surrounding normal tissues. To this end, image-guided radiation therapy is widely used in which an image of a patient immediately before treatment is re-acquired and compared with the patient's posture and tumor position at the time of treatment plan to correct the patient's position or correct the treatment plan to increase the accuracy of treatment.

It is essential to measure the tumor size in order to evaluate the prognosis and treatment response of cancer. Tumor size is currently quantified using one-dimensional RECIST or two-dimensional WHO, but unproven evidence continues to emerge suggesting that line-length measurements may be misleading compared to 3D measurements of tumors. In addition, volumetric segmentation is required to analyze image features and determine tumor volume for treatment planning.

In order to treat these tumors, segmentation of abdominal organs in medical imaging (eg, computed tomography (CT)) is a priority process, and in order to minimize irradiation to the surrounding organs of cancer that occurs in the abdominal organs. The abdominal organ segmentation must precede the radiation treatment plan. In this case, if the clinical specialist manually divides the organ or uses a semi-automatic segmentation program to divide the abdominal organ, it takes a long time, and the results of the liver segmentation by the clinician There is a limitation in that differences occur, so studies of automatically segmenting abdominal organs are being conducted, but as shown in Fig. 1, abdominal organs (liver, heart, spleen, etc.) Since the locations are adjacent to each other and the brightness values are similar, leakage occurs to organs with similar brightness values in the vicinity during automatic division, and the shape and size of the liver vary from person to person, so accurate organ division is limited. There is.

Meanwhile, a technology called deep learning among machine learning algorithms has recently been in the spotlight in various fields. In particular, in the field of object recognition, a technology called CNN (convolutional neural network), a kind of deep learning, is in the spotlight. CNN is a model that simulates the brain function of a person based on the assumption that when a person recognizes an object, it extracts basic features of an object, then performs complex calculations in the brain and recognizes the object based on the result. CNNs are generally used with various filters for extracting features of an image through a convolution operation and a pooling or non-linear activation function for adding non-linear features (e.g. sigmod, ReLU (rectified)). linear unit), etc.) can be used.

With the increasing interest in deep learning, interest in deep learning is also increasing in various medical devices (eg, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), etc.).

iηek et al., "3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation", MICCAI 2016. Peng et al, "Large Kernel Matters: Improve Semantic Segmentation by Global Convolutional Network", arXiv, March 2017.

iηek et al., "3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation", MICCAI 2016.

The problem to be solved by the present invention is that the brightness value of any one of the abdominal organs is similar to the one of the abdominal organs by inputting the pre-shape model generated through the 2D deep neural network and the bounding volume of the abdomen into the 3D deep neural network. It is to provide a method of automatic division of abdominal organs that accurately divides at the boundary of the surrounding organs that appear to be displayed.

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

In the medical image according to an aspect of the present invention for solving the above-described problem, a method for automatically dividing abdominal organs based on deep learning includes a plurality of axial images and a plurality of coronal images of a two-dimensional medical image including abdominal organs. ) By inputting an image and a plurality of sagittal images into a two-dimensional deep neural network. Generating a plurality of label data and a plurality of prediction maps of a region of interest through the 2D deep neural network; Generating a pre-shape model of the region of interest by weighted fusion of each of the generated prediction maps; And inputting the 3D medical image including the abdominal organs and the pre-shape model into a 3D deep neural network. And obtaining a result of segmentation of the region of interest through the 3D deep neural network.

Other specific details of the present invention are included in the detailed description and drawings.

According to the present invention as described above, it has various effects as follows.

The present invention can accurately perform automatic division of abdominal organs.

In addition, the present invention can prevent over-segmentation in a 3D deep neural network by using a pre-shape model.

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

1 is a diagram showing the limiting points of liver segmentation in a contrast-enhanced abdominal CT image, (a) shows the liver and heart in an axial cross-sectional view, (b) shows a coronal cross-sectional view of the liver and surrounding organs, and (c) shows the liver and spleen. It is a view showing a sagittal cross-sectional view.
2 is a flowchart illustrating a method of automatically dividing abdominal organs according to an embodiment of the present invention.
3 is a block diagram illustrating a method of automatically dividing abdominal organs according to an embodiment of the present invention.
4 is an exemplary diagram for describing a 2D FCN according to an embodiment of the present invention.
5 is an exemplary diagram for explaining a 3D U-Net according to an embodiment of the present invention.
6 is a table for explaining the effect of the method of automatically dividing abdominal organs according to an embodiment of the present invention.
7 is an exemplary view for explaining the effect of the method of automatically dividing abdominal organs according to an embodiment of the present invention.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms, only the present embodiments are intended to complete the disclosure of the present invention, It is provided to fully inform the technician of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless specifically stated in the phrase. As used in the specification, “comprises” and/or “comprising” do not exclude the presence or addition of one or more other elements other than the mentioned elements. Throughout the specification, the same reference numerals refer to the same elements, and “and/or” includes each and all combinations of one or more of the mentioned elements. Although "first", "second", and the like are used to describe various elements, it goes without saying that these elements are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical idea of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not interpreted ideally or excessively unless explicitly defined specifically.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc., as shown in the figure It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is turned over, a component described as "below" or "beneath" of another component will be placed "above" the other component. I can. Accordingly, the exemplary term “below” may include both directions below and above. Components may be oriented in other directions, and thus spatially relative terms may be interpreted according to orientation.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Semantic segmentation, like general image segmentation, is not limited to simply dividing into similar areas in terms of certain features or calculated attributes, but a technology that divides semantically the same part and determines which category the part belongs to. Say.

That is, it may correspond to a technology for classifying which category of all pixels of an image belongs within a predefined category, and may correspond to pixelwise classification.

The semantic image segmentation method is largely divided into two categories. The first is a technique of extracting hand-craft features from the input image, dividing it into super-pixel units, and then dividing the image based on meaning. In more detail, a user may directly design and extract features that may serve as clues by analyzing given image data. Thereafter, segmentation may be performed in units of super pixels based on patterns of the extracted features. This process can lead to improved accuracy and speed. Thereafter, semantic image segmentation may be performed in units of each super pixel using a support vector machine, so that a corresponding pixel or super pixel may be determined in which classification it belongs. This method has a disadvantage in that the range of use of the system is limited because, when the type of image input to the system is changed, a corresponding handmade feature must be redesigned each time, and the manual feature extraction has a disadvantage in that the processing speed is slow.

The second is a technique of extracting features using deep learning and then classifying them in pixel units. As the performance of deep learning-based classification has been proven to be excellent, an approach using a convolutional neural network (CNN) structure has been proposed for semantic-based image segmentation. FCN (Fully Convolutional Networks), which has changed the CNN structure, shows excellent performance in image segmentation. After the superpixel division is performed, the CNN filter is trained using the training dataset, the image is segmented, and post-processing such as CRF (Conditional Random Field) can be performed.

Hereinafter, the segmentation described in the present invention may mean semantic image segmentation, and a semantic image segmentation method based on deep learning may be applied.

2 is a flowchart illustrating a method of automatically dividing abdominal organs according to an embodiment of the present invention. 3 is a block diagram illustrating a method of automatically dividing abdominal organs according to an embodiment of the present invention. 4 is an exemplary diagram for describing a 2D FCN according to an embodiment of the present invention. 5 is an exemplary diagram for explaining a 3D U-Net according to an embodiment of the present invention. 6 is a table for explaining the effect of the method of automatically dividing abdominal organs according to an embodiment of the present invention. 7 is an exemplary view for explaining the effect of the method of automatically dividing abdominal organs according to an embodiment of the present invention.

The present invention may be implemented as an automatic abdominal organ segmentation system, and may include an image input unit, a two-dimensional deep learning unit, a pre-shape model generation unit, a region cropping unit, and a 3D deep learning unit.

2 to 4, in an embodiment, in operation 21, a plurality of axial images 110 and a plurality of coronal images of a medical image 100 including an abdominal organ in the image input unit 120 and a plurality of sagittal images 130 may be input to the 2D deep neural network 200. For example, the 2D deep neural network 200 may include at least one of a 2D fully convolutional network (FCN) and a 2D U-net. For example, the medical image includes a 2D medical image (eg, x-ray image) and/or a 3D medical image (eg, CT image, MRI, PET image), and there is no particular limitation if it is a medical image. “Image” refers to a subject collected 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. The medical image 100 is voxel data and is composed of a plurality of slices, that is, a plurality of unit images.

In an embodiment, in operation 22, the 2D deep learning unit performs a plurality of label data 310, 320, 330 and a plurality of predictions of a region of interest through the 2D deep neural network 200. Maps 410, 420, 430, and Prediction maps may be generated. For example, the region of interest may be a region in which any one of the abdominal organs (eg, liver) is disposed.

In one embodiment, the 2D fully convolutional network (FCN) shown in FIG. 4 may correspond to the convolutional network structure proposed by “Large Kernel Matters - Improve Semantic Segmentation by Global Convolutional Network”, arXiv, Mar 2017. For example, as shown in FIG. 4, after the medical image 20 is input to the convolution layer to extract a component matching the convolutional filter, each component that has undergone resizing four times is a global convolutional network (GCN). , Boundary refinement (BR) can be input/output, and components matching the deconvolution filter from the lowest component are extracted and merged with the components of the nearest higher size, and label data ( 30) and prediction maps can be generated. The number of x, y, and channels disclosed in FIG. 4 is exemplary and can be variously modified.

In an embodiment, the plurality of prediction maps 410, 420, 430, and prediction maps have a lower resolution than the input medical image, but may have a plurality of channels. Through the generated prediction maps 410, 420, and 430, the prediction maps 410, 420, and 430 are shared with each other in the step of classifying an area and the step of detecting an object to classify a region and detect a region of interest (any one of the abdominal organs). That is, pixel labeling may be performed from a plurality of prediction maps 410, 420, 430, and prediction maps to distinguish an image region. In this case, pixel labeling may be performed by attaching the same number to all adjacent pixels having similar features of the input image. In addition, the pixel labeling result included in the plurality of label data 310, 320, and 330 may include probability distribution information for each pixel of a class to be classified of an image.

In one embodiment, the generation of a plurality of label data (310, 320, 330) and a plurality of prediction maps (410, 420, 430, Prediction map) may use a convolution neural network (CNN). However, the present invention is not limited thereto, and may vary depending on the purpose of use of the image processing apparatus, such as a deep neural network (DNN) or a recurrent neural network (RNN). Here, as an example, a plurality of label data 310, 320, 330 and a plurality of prediction maps 410, 420, 430, and prediction maps may be generated according to a 2D fully convolutional network (FCN).

In an embodiment, in operation 23, the pre-shape model generation unit is generated as a result of dividing each of a plurality of axial images 110, a plurality of coronal images 120, and a plurality of sagittal images. The three-dimensional label data 600 and the pre-shape model 700 of the region of interest may be generated by weighted fusion 500, respectively, of the plurality of prediction maps 410, 420, and 430. For example, the pre-shape model 700 may include 3D spatial shape information of the region of interest in the form of a probability map. For example, the pre-shape model 700 may include information that is meaningful for classifying an area in the medical image 100 and detecting an object, and may include, for example, luminous intensity, color, outline, etc. of the medical image 100. .

In one embodiment, the pre-shape model 700 is a plurality of prediction maps 410 corresponding to a plurality of axial images 310, a plurality of prediction maps corresponding to a plurality of coronal images 120 It may be calculated by a weighted average of 420 and a plurality of prediction maps 430 corresponding to the plurality of sagittal images 130. Specifically, the dictionary shape model 700 may be calculated by Equation 1 below.

[Equation 1]

y is the pre-shape model 700, n is the number of each of a plurality of axial images 310, a plurality of coronal images 320, and a plurality of sagittal images 330, yi Is the probability that the abdominal organs of the plurality of prediction maps 410, 420, and 430 are the region of interest, and wi may be a weight determined by Equation 2 below.

[Equation 2]

Accordingly, the pre-shape model 700 may be generated by integrating only a plurality of prediction maps 410, 420, and 430 having a probability of having an ROI of 0.5 or more.

In an embodiment, in operation 24, the region cropping unit may crop at least a part of the remaining regions of the pre-shape model 700 except for the ROI. For example, in order to reduce the computation process of the 3D deep neural network, a part of the boundary area may be cropped in the preshape model 700.

In an embodiment, in operation 25, the region cropping unit may crop at least a portion of the remaining regions of the 3D medical image 800 except for the ROI. For example, in order to reduce the operation process of the 3D deep neural network, a part of the boundary area in the 3D medical image 800 may be cropped. Specifically, for example, by using the brightness value information, a boundary portion completely different from the brightness value information of the liver and surrounding organs may be cropped.

In an embodiment, in operation 26, the image input unit may input a 3D medical image 800 including abdominal organs and a pre-shape model 700 to the 3D deep neural network 900. For example, the 3D deep neural network 900 may include a 3D U-net. Also, unlike this, the cropped pre-shape model and the cropped 3D medical image 810 may be input to the 3D deep neural network 900.

In one embodiment, the 3D U-net shown in FIG. 5 may correspond to the convolutional network structure proposed in “3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation”, MICCAI 2016. For example, The 3D U-Net may include a contracting path 40 shown on the left and an expansive path 50 shown on the right, and the contraction path follows a typical structure of a convolutional neural network. This involves iterative application of two 3x3 convolutions (unpadded convolutions), each of which has a rectified linear unit (ReLU) and a stride for downsampling. ) Is followed by a 2x2 maximum pooling operation of 2. In each downsampling step, the number of feature channels is doubled, and every step in the expansion path is upsampling the feature map ( upsampling) and a 2x2 convolution (“up-convolution”) that reduces the number of feature channels that follow it in half, concatenation with the feature map from the constriction path cropped correspondingly, and two 3x3 It consists of a convolution, followed by ReLU for each of the 2 3x3 convolutions. The above truncation is necessary because of the loss of border pixels in all convolutions. 1x1 synthesis in the final layer. The product is used to map each 64-component feature vector to a desired number of classes In this example neural network, all 22 convolutional layers are included, which is arbitrary. All 2x2, so that the segmentation map that comes out is neatly connected. It will be appreciated by those skilled in the art that it is important to select an input tile size such that a max-pooling operation is applied to a layer having an even number of x and y sizes.

In an embodiment, in operation 27, the 3D deep learning unit may obtain the segmentation result 10 of the ROI through the 3D deep neural network 900. Here, the segmentation result 10 may be an image in which a specific organ corresponding to the region of interest is segmented.

That is, the present invention considers the entire context information of the abdominal organ area in which the region of interest is arranged through a two-dimensional deep neural network and a pre-shape model, and the regional context in which the region of interest is located through a three-dimensional medical image using the pre-shape model. The speed and accuracy of abdominal organ segmentation can be increased by reducing the number of operations to grasp information.

On the other hand, the data set used to confirm the effect of the present invention includes 155 arterial phase CT images obtained for radiotherapy in liver cancer patients, of which 75 are for learning, 33 for validation, and 47 for testing. Divided into dragons. The pixel spacing and slice thickness of the image may be 0.65 to 0.79 mm or 3.0 to 7.0 mm.

To evaluate the accuracy of the segmentation result (10), Dice similarity coefficient (DSC), volumetric overlap error (VOE), sensitivity (Sensitivity, Sens), specificity (Specificity, Spec), and accuracy ( Accuracy) was calculated and compared through Equation 3.

[Equation 3]

Here, A is the manual segmentation result, B is the comparison method or the proposed method result, TP (True Positive) is the number of pixels in the automatically segmented region in the manual segmented organ region, and TN (True Negative) is not the manually segmented organ region. The number of pixels in the region that is not automatically divided in the region, FP (False Positive) is the number of pixels in the region that is automatically divided in a non-manually divided long-term region, and FN (False Negative) is the number of pixels in the region that is not automatically divided. It means the number of pixels in the region.

As shown in Figure 6. The DSC of the 2.5D+3D with shape-enhanced prior (pre-shape model) of the present invention was 94.3%, 5.4% higher than the previously proposed segmentation method (2.5D+3D without shape-enhanced prior), and the 2.5D segmentation method Was 3.4% higher than that. Meanwhile, here, 2.5D may mean forming label data and a prediction map through a 2D deep neural network. In the case of specificity, the partitioning method of the present invention exhibits 2.5% and 1.4% higher specificity than the 2.5D partitioning method. This is because the segmentation method of the present invention not only corrects fine details using a 3D deep neural network, but also uses a pre-shape model and a 3D medical image with improved shape (e.g., cropped) to be affected by the organs adjacent to the region of interest. This is because excessive segmentation is reduced by avoiding it as much as possible. In the case of sensitivity, 2.5D+3D without shape-enhanced prior shows 8.6% lower sensitivity than the 2.5D segmentation method. This is because 2.5D+3D without shape-enhanced prior shows a tendency of under-segmentation when the shape change of abdominal organs is large. However, the segmentation method proposed in the present invention shows 4.4% higher sensitivity than 2.5D+3D without shape-enhanced prior. This is because the dividing method of the present invention is more suitable for grasping large deformation of abdominal organs.

As shown in FIG. 7, each of case 1, case 2, case 3, case 4, and case 5 all uses the segmentation method (2.5D+3D with shape-enhanced prior) proposed by the present invention to reduce the liver to the abdominal organs. You can see that it divides correctly. Here, blue is true positive, green is false negative, and red is false positive. The 2.5D segmentation method shows excessive segmentation tendency due to leakage to adjacent organs, and the 2.5D+3D without shape-enhanced prior segmentation without prior shape model shows improvement of under segmentation by learning 3D deep neural networks. However, leakage to adjacent organs still occurs. However, the dividing method of the present invention using a pre-shape model can correct detailed parts of an organ to be divided and reduce leakage to adjacent organs.

The method for automatically segmenting abdominal organs based on deep learning in a medical image according to an embodiment of the present invention includes a plurality of axial images, a plurality of coronal images, and a plurality of two-dimensional medical images including abdominal organs. By inputting sagittal images into a two-dimensional deep neural network. Generating a plurality of label data and a plurality of prediction maps of a region of interest through the 2D deep neural network; Generating a pre-shape model of the region of interest by weighted fusion of each of the generated prediction maps; And inputting the 3D medical image including the abdominal organs and the pre-shape model into a 3D deep neural network. And obtaining a result of dividing the region of interest through the 3D deep neural network.

According to various embodiments, the region of interest may be a region in which any one of the abdominal organs is disposed.

According to various embodiments of the present disclosure, the step of cropping at least a part of a remaining area other than the ROI in the pre-shape model; And inputting the cropped pre-shape model to the 3D deep neural network.

According to various embodiments of the present disclosure, the step of cropping at least a portion of a region other than the region of interest in the 3D medical image; And inputting the cropped 3D medical image to the 3D deep neural network.

According to various embodiments of the present disclosure, by inputting the cropped pre-shape model and the cropped 3D medical image into the 3D deep neural network. And obtaining a result of dividing the region of interest through the 3D deep neural network.

According to various embodiments, the pre-shape model includes a plurality of prediction maps corresponding to the plurality of axial images, a plurality of prediction maps corresponding to the plurality of coronal images, and the plurality of sagittals. It may be calculated by a weighted average of a plurality of prediction maps corresponding to the image.

y는 사전형상모델이고, n은 복수의 축상(Axial) 이미지, 복수의 관상(Coronal) 이미지 및 복수의 시상(Sagittal) 이미지 각각의 개수이고, yi는 복수의 예측맵의 복부 장기가 관심 영역일 확률이고, wi는 하기 수학식 2

에 의해 결정되는 가중치일 수 있다.According to various embodiments, the dictionary shape model is calculated by Equation 1 below, and [Equation 1]

y is the pre-shape model, n is the number of each of a plurality of axial images, a plurality of coronal images, and a plurality of sagittal images, and yi is a region of interest in the abdominal organs of the plurality of prediction maps. Probability, wi is the following equation (2)

It may be a weight determined by.

According to various embodiments, the pre-shape model may include 3D spatial shape information of the ROI in the form of a probability map.

According to various embodiments, the 2D deep neural network may include at least one of a 2D fully convolutional network (FCN) and a 2D U-net.

According to various embodiments, the 3D deep neural network may include a 3D U-net.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. Software modules include Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those of ordinary skill in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features. You can understand. Therefore, the embodiments described above are illustrative in all respects, and should be understood as non-limiting.

100: medical image
200: 2D deep neural network
310,320,330: label data
410,420,430: prediction map
700: pre-shape model
800: 3D medical image
900: 3D deep neural network

Claims (11)

In the method of automatic segmentation of abdominal organs based on deep learning in medical images,
By inputting a plurality of axial images, a plurality of coronal images, and a plurality of sagittal images of a 2D medical image including abdominal organs into a 2D deep neural network, the 2D deep neural network is Generating a plurality of label data and a plurality of prediction maps of a region of interest through the method;
Generating a pre-shape model of the region of interest by weighted fusion of each of the generated prediction maps; And
And inputting the 3D medical image including the abdominal organs and the pre-shape model into a 3D deep neural network, and obtaining a result of segmentation of the ROI through the 3D deep neural network. A method for automatic segmentation of abdominal organs in medical images based on deep learning. The method of claim 1,
The region of interest is an area in which any one of the abdominal organs is disposed. The method of automatically segmenting abdominal organs in a medical image based on deep learning. The method of claim 1,
Cropping at least a portion of the remaining areas other than the ROI in the pre-shape model; And
The method of automatically segmenting abdominal organs in a medical image based on deep learning, further comprising: inputting the cropped pre-shape model to the 3D deep neural network. The method of claim 3,
Cropping at least a portion of the remaining area other than the ROI in the 3D medical image; And
Inputting the cropped 3D medical image to the 3D deep neural network; the method of automatically segmenting abdominal organs in a medical image based on deep learning, further comprising. The method of claim 4,
And inputting the cropped pre-shape model and the cropped 3D medical image to the 3D deep neural network, and obtaining a segmentation result of the ROI through the 3D deep neural network. A method for automatic segmentation of abdominal organs in medical images based on deep learning. The method of claim 1,
The pre-shape model includes a plurality of prediction maps corresponding to the plurality of axial images, a plurality of prediction maps corresponding to the plurality of coronal images, and a plurality of prediction maps corresponding to the plurality of sagittal images. A method for automatically segmenting abdominal organs in a medical image based on deep learning, characterized in that it is calculated by a weighted average of a prediction map. The method of claim 6,
The prior shape model is calculated by Equation 1 below,
[Equation 1]

y is the pre-shape model, n is the number of each of a plurality of axial images, a plurality of coronal images, and a plurality of sagittal images, and yi is a region of interest in the abdominal organs of the plurality of prediction maps. Probability, and wi is a weight determined by Equation 2 below. A method of automatically segmenting abdominal organs in a medical image based on deep learning.
[Equation 2]

The method of claim 1,
The pre-shape model includes 3D spatial shape information of the region of interest in the form of a probability map. A method for automatically segmenting abdominal organs in a medical image based on deep learning, characterized in that. The method of claim 1,
The 2D deep neural network includes at least one of a 2D fully convolutional network (FCN) and a 2D U-net. A method of automatically segmenting abdominal organs in a medical image based on deep learning. The method of claim 1,
The 3D deep neural network is a method of automatically segmenting abdominal organs in a medical image based on deep learning, characterized in that the 3D deep neural network includes a 3D U-net. A program for automatic division of abdominal organs in a medical image based on deep learning, which is combined with a computer that is hardware and stored in a medium to execute the method of any one of claims 1 to 10.

Images