KR20180061888A - Method for generating surgery plan for orbital wall reconstruction, surgery plan server performing the same, and storage medium storing the same - Google Patents

Abstract

The present invention relates to a method for generating a surgery plan which includes the following steps: (a) receiving medical image data for a face of a patient; (b) generating a three-dimensional model of the orbital wall based on the medical image data; (c) determining a fractured area from the three-dimensional model of the orbital wall; and (d) designing an implant to be used in a surgery of the fractured area by comparing the fractured area of the orbital wall with a normal orbital wall. According to the present invention, the time for the surgery can be reduced and the success rate of the surgery can be improved.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an operation plan creation method for orbital wall reconstruction, an operation plan creation server for performing the operation plan creation method, and a recording medium for storing the same.

More particularly, the present invention relates to a technique for creating a surgical plan, and more specifically, for a surgical plan optimized for orbital wall reconstruction, a three-dimensional model of the orbital wall is created from a medical image, A surgical planning creating method for designing an implant to be used for surgery, a surgical planning creating server for performing the same, and a recording medium storing the same.

Orbital wall reconstruction is a reconstruction of the orbit by inserting a titanium plate into the orbital wall fracture site. It is not only important for functional and aesthetic harmony, but also because of the complicated anatomical structure of the orbit. However, the conventional operation method has a problem that the operation time is delayed depending on the physician's experience, and a large error is generated because the titanium plate inserted in the fracture site is cut and bent in accordance with the affected part during surgery , Problems such as diplopia and eye position asymmetry may persist after surgery.

Therefore, in order to shorten the operation time and improve the success rate of the orbital wall reconstruction, it is required to find out the fracture area through the orbital wall modeling and to help the operation plan through the patient-customized implant design. Based on this need, Proplan CMF, Mimics, 3 Software such as -matic provides the function to plan the surgery through orbital wall modeling and diagnosis of the fracture area. However, such software is also not optimized for orbital wall reconstruction, such as manual detection of the orbital wall.

In order to reconstruct the orbital wall, three-dimensional model of the orbit is used to confirm the location of the fracture and the degree of fracture. Because the orbital wall is very thin, the value of the Hounsfiled Unit (HU) between +700 and +3000 In the 3-D model, there is a hole in both the normal orbital fracture and the fractured area. For this, when modeling by manual segmentation, it takes a lot of time and effort because a large number of medical image slices must be examined. Therefore, the conventional technique is difficult to use and takes a long time, so that it is still difficult to design a patient-customized implant.

Korean Patent Publication No. 10-2006-0028044

The object of the present invention is to create a three-dimensional model of the orbital wall from the medical image data, to determine and diagnose the fracture area from the three-dimensional model of the orbital wall, And to provide a method of generating a surgical plan for analyzing an operation result after surgery.

According to a first aspect of the present invention, there is provided a surgical plan generation method comprising: (a) receiving medical image data on a face of a patient; (b) generating a three-dimensional model of the orbital wall based on the medical image data; (c) determining and diagnosing a fracture area from a three-dimensional model of the orbital wall; And (d) designing an implant to be used in surgery of the fracture area by comparing the fracture area of the orbital wall with the normal orbital wall.

Preferably, the step (b) includes the steps of: (b-1) dividing the medical image data into multiple areas; (b-2) extracting a face region from the multi-region image; (b-3) extracting the ethmoid region from the image divided into the multiple regions; (b-4) extracting a bone region including an orbital wall from the image divided into the multiple regions; And (b-5) generating a three-dimensional model of the orbital wall based on the orbital wall of the extracted bony region.

Preferably, in the step (b-1), a contrast histogram is obtained based on the distribution of light and dark in the medical image data, and an Adaptive Global Maximum Clustering (AGMC) algorithm is applied to the contrast histogram to be divided into at least two partial regions The divided multi-regions may have a label value.

Preferably, the step (b-2) includes the step of setting a face label value among the label values of the multi-area and extracting the face area by distinguishing the face area and the non-face area according to the face label value can do.

Preferably, in the step (b-3), the label value of the non-ethmoidal region is changed based on the label value of the ethmoidal region in the face region of the image divided into the multi-regions to remove the non- step; And extracting the ethmoid region by applying an active contour technique using the minimum label value in the image from which the non-ethmoidal region is removed.

Preferably, the step (b-4) includes the steps of extracting an initial bone region based on a label value of a bone region in the image divided into the multiple regions; And extracting a bone region including an orbital wall by applying an active contour technique based on the initial bone region and the extracted ethmoid region.

Preferably, the step (c) includes the steps of: (c-1) detecting a fracture candidate region by symmetrically aligning the normal orbit in the three-dimensional model of the orbital wall with the fractured orbit; And (c-2) measuring the fracture candidate region.

Preferably, the step (c-1) includes the steps of: receiving information of the reference plane for symmetry; Symmetrically aligning the normal orbit with the fractured orbit around the reference plane to match the position of the normal orbit with the fractured orbit; And determining and displaying a fracture candidate region according to a distance difference between the matched normal orbit and the fracture orbit, wherein the step (c-2) comprises: extracting a fracture region from the fracture candidate region; And measuring the distance, area, and angle of the area.

Preferably, (e) analyzing the surgical result based on the preoperative orbital wall including the fracture area, the orbital wall after surgery using the implant, and the orbital volume and eye position for the normal orbital wall As shown in FIG.

According to a second aspect of the present invention, there is provided a surgical plan creation server, comprising: a video data receiving unit for receiving medical image data on a face of a patient; A modeling unit for generating a three-dimensional model of the orbital wall based on the medical image data; A fracture diagnosis unit for determining and diagnosing a fracture area from the three-dimensional model of the orbital wall; And an implant designing unit for designing an implant to be used for surgery of the fracture area by comparing the fracture area of the orbital wall with the normal orbital wall.

Preferably, the modeling unit includes: a multi-region division module for dividing the medical image data into multiple regions; A face region extraction module for extracting a face region from the image divided into the multiple regions; An ethmoid region extracting module for extracting the ethmoid region from the image divided into the multiple regions; A bone region extraction module for extracting a bone region including an orbital wall from the image divided into the multiple regions; And a model generation module for generating a three-dimensional model of the orbital wall based on the orbital wall of the extracted bony area.

Preferably, the multi-region segmentation module obtains a light and dark histogram based on the distribution of light and dark in the medical image data, and applies an Adaptive Global Maximum Clustering (AGMC) algorithm to the light and dark histogram, Region, and the divided multi-region may have a label value.

Preferably, the face area extraction module may set a face label value among the label values of the multi-areas, and extract the face area by separating the face area and the non-face area according to the face label value.

Preferably, the ethmoidal region extracting module removes the non-ethmoidal region by changing the label value of the non-ethmoidal region based on the label value of the ethmoid region in the face region of the image divided into the multi-regions, We can extract the ethmoid region by applying the active contour method using the minimum label value in the image where the non - ethorhoidal region is removed.

Preferably, the bony region extraction module extracts an initial bony region based on the label value of the bony region in the image divided into the multiple regions, and applies an active contour technique based on the initial bony region and the extracted ethmoid region So that a bone region including the orbital wall can be extracted.

Preferably, the fracture diagnosis unit includes a detection module for detecting a fracture candidate region by symmetrically aligning the normal orbit with the fractured orbit in the three-dimensional model of the orbital wall; And a measurement module for measuring the fracture candidate region.

Preferably, the detecting module receives the information of the reference plane for symmetry, aligns the normal orbital with the fractured orbit by symmetrically aligning the normal orbit with the fractured orbit around the reference plane, The measurement module determines and displays a fracture candidate region according to a distance difference between the normal orbit and the fracture orbital, and the measurement module extracts a fracture region from the fracture candidate region and measures the distance, area, and angle of the fracture region have.

Preferably, a surgical result analysis unit for analyzing the surgical results based on the preoperative orbital wall including the fracture region, the orbital wall after surgery using the implant, and the orbital volume and eye position for the normal orbital wall .

As described above, according to the present invention, it is possible to shorten the operation time and improve the success rate of the orbital wall reconstruction, and thus to provide an optimal surgical planning technique for orbital wall reconstruction

1 is a block diagram of a surgical plan generation server according to a preferred embodiment of the present invention.
FIG. 2 is a flowchart illustrating a method of generating a surgical plan performed by the surgical plan creation server of FIG. 1;
Figure 3 is an illustration of an image segmented into multiple regions.
4 is an illustration of an image showing a process of extracting a face region.
5 is an illustration of an image showing a process of extracting the ethmoid region.
6 is an example of an image showing a process of extracting a bone region.
Figure 7 is an illustration of a three-dimensional model of the orbital wall.
Fig. 8 is an example of an image showing a process of matching the orbital position.
Fig. 9 is an example of a video image showing a fracture region.
10 is an example of an image measuring a fracture area.
11 is an illustration of an implant design.
12 is an illustration of an image representing the orbital volume.
13 is an example of an image for measuring the eyeball position.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will be more apparent from the following detailed description taken in conjunction with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification. "And / or" include each and every combination of one or more of the mentioned items.

Although the first, second, etc. are used to describe various elements, components and / or sections, it is needless to say that these elements, components and / or sections are not limited by these terms. These terms are only used to distinguish one element, element or section from another element, element or section. Therefore, it goes without saying that the first element, the first element or the first section mentioned below may be the second element, the second element or the second section within the technical spirit of the present invention.

Also, in each step, the identification code (e.g., a, b, c, etc.) is used for convenience of explanation, and the identification code does not describe the order of each step, Unless the order is described, it may happen differently from the stated order. That is, each step may occur in the same order as described, may be performed substantially concurrently, or may be performed in reverse order.

The terminology used herein is for the purpose of illustrating embodiments and is not intended to be limiting of the present invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. It is noted that the terms "comprises" and / or "comprising" used in the specification are intended to be inclusive in a manner similar to the components, steps, operations, and / Or additions.

Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense commonly understood by one of ordinary skill in the art to which this invention belongs. Also, commonly used predefined terms are not ideally or excessively interpreted unless explicitly defined otherwise.

In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The following terms are defined in consideration of the functions in the embodiments of the present invention, which may vary depending on the intention of the user, the intention or the custom of the operator. Therefore, the definition should be based on the contents throughout this specification.

1 is a block diagram of a surgical plan generation server according to a preferred embodiment of the present invention.

Referring to FIG. 1, the surgical plan creation server 100 includes an image data receiving unit 110, a modeling unit 120, a fracture diagnosis unit 130, an implant design unit 140, and a control unit 150.

The modeling unit 120 may include a multi-region segmentation module 121, a face region extraction module 122, an ethmoid region extraction module 123, a bone region extraction module 124, and a model generation module 125 And the fracture diagnosis unit 130 includes a detection module 131 and a measurement module 132. [ The control unit 150 controls the operations of the image data receiving unit 110, the modeling unit 120, the fracture diagnosis unit 130, and the implant design unit 140 and the flow of data.

Hereinafter, the operation plan creation method performed by the operation plan creation server 100 shown in FIG. 2 will be described with reference to the operation plan creation method.

The image data receiving unit 110 receives the medical image data on the face of the patient (step S210). Preferably, the image data receiving unit 110 can receive the CT image data of the patient corresponding to the two-dimensional image, and the orbital wall reconstruction proceeds with respect to the fracture due to blunt trauma around the orbital. Therefore, And the CT image data of the face part can be received.

The modeling unit 120 generates a three-dimensional model of the orbital wall based on the medical image data (step S220). Because the medial bones of the orbit are very thin, it is difficult to distinguish them from the CT image by the naked eye. In general, when using the threshold-based segmentation method used for dividing the bone tissue, the orbital wall is discontinuously broken in the 3-dimensional model and unnecessary noise Additional manual detection of the user is required. Accordingly, in the present invention, a method of automatically detecting the orbital bone by dividing the adjacent ethmoidal region in a two-dimensional horizontal plane image is used in order to minimize the input of the user and to facilitate the creation of the surgical plan, Is performed through the operation of each module of the modeling unit 120 to be described.

First, the multi-region division module 121 of the modeling unit 120 divides medical image data into multiple regions. 3, the multi-region segmentation module 121 obtains a contrast histogram based on the distribution of light and darkness in the medical image data as shown in FIG. 3A, adds Adaptive Global Maximum Clustering (AGMC) ) Algorithm, as shown in FIG. 3 (b), into multiple regions divided into two or more partial regions. Here, the divided multi-area may have a label value, and the label value may have a larger value as the contrast becomes darker as the contrast becomes darker and a smaller value becomes as the contrast becomes brighter.

The face region extraction module 122 extracts the face region from the multi-region image. Preferably, the face area extraction module 122 sets a face label value among the label values of the multiple areas to limit the area corresponding to the actual face part to the area of interest, The face region can be extracted by dividing the face region.

More specifically, referring to FIG. 4, the face area extraction module 122 extracts a label value one greater than the minimum label value from the label value of the multi-region in the multi-region image as shown in FIG. 4 (a) Value, and the region above the face label value is displayed in white and the remaining region is displayed in black, thereby binarizing the image as shown in FIG. 4 (b). Here, in an image divided into multiple regions, an area having a minimum label value corresponding to a black color corresponds to a blank space, so that a label value one larger than the minimum label value is set as a face label value. Then, the face area extraction module 122 fills all of the face area in white as shown in FIG. 4 (c) so as to include all of the face area in the binarized image, The face region is extracted as shown in red in FIG. 4 (d) according to the facial region shown in FIG.

The ethmoid sinus region extraction module 123 extracts the ethmoid sinus region from the multi-domain image. 5, the ethmoidal region extracting module 123 extracts the non-ethnocardiographic region based on the label value of the ethmoid region in the face region of the image divided into the multi-regions as shown in FIG. 5 (a) You can remove the non-ethmoid region by changing the label value. The image shown in FIG. 5 (b) is the image in which the non-ethorhoidal region is removed. Here, the removed non-ethalotic region has the label value of the ethmoidal region, but the portion overlapping the ethmoidal region extracted from the previous image . That is, based on the intersection of the region extracted from the previous image of the current image to extract the ethmoid region and the region having the label value of the ethmoid region from the current image, the region having the label value of the ethmoid region in the current image The region of the previous image that does not overlap with the region extracted from the ethmoid sinus region is removed corresponding to the non-ethmoidal region.

Preferably, the ethmoid sinus area extraction module 123 applies the active contour technique using the minimum label value in the image from which the non-ethmoidal region shown in FIG. 5 (B) is removed, The ethmoid region can be extracted as shown. Specifically, the bone is extracted using an active contour technique based on a level set function that sets the area having the minimum label value as the contour of the initial ethmoid sinus area.

The bony region extraction module 124 extracts a bony region including the orbital wall from an image divided into multiple regions. 6, the bony region extraction module 124 extracts a region having a label value of a bony region as an initial bony region in an image divided into the multi-regions shown in (a) of Fig. 6, (B), the active contour method based on the level set function based on the initial bone region and the extracted ethmoid region is used as the initial contour based on the initial bone region and the extracted ethmoid region, The region can be extracted as shown in Fig. 6 (c).

The model generation module 125 generates a three-dimensional model of the orbital wall based on the orbital wall of the extracted bony region. Preferably, the model generation module 125 may apply a Marching Cude algorithm to the extracted orbital wall to construct a three-dimensional model of the orbital wall as shown in FIG.

The fracture diagnosis unit 130 determines a fracture area from the three-dimensional model of the orbital wall (step S230). First, the detection module 131 of the fracture diagnosis unit 130 detects the fracture candidate region by symmetrically aligning the normal orbit with the fractured orbit in the three-dimensional model of the orbital wall. Since the left and right orbitals are symmetrical, a fracture candidate region can be detected by mirroring the normal orbit with the fractured orbit.

8, the detection module 131 may receive information of a reference plane for symmetry, and more specifically, a user may receive a three-dimensional model of the orbital wall, as shown in FIG. 8 (a) The detection module 131 selects the inner wall of the normal orbit (portion indicated by blue) and the inner wall of the fracture orbit (portion indicated with red) and draws a straight line at a desired position of the user, as shown in FIG. 8 (b) , A plane having a normal vector as a vector in the direction of the user's viewpoint can be automatically generated and set as a reference plane.

 8 (c), the normal orbital can be replicated to the fractured orbit by symmetrically aligning the normal orbital fracture with the fractured orbit around the reference plane, and as shown in FIG. 8 (d) The position of the normal orbit and the fracture orbital can be matched. An ICP (Iterative Closest Point) algorithm can be used for the matching method. The ICP algorithm calculates a direction vector closest to the fracture orbital in the mirrored normal orbit, derives a transformation matrix that minimizes the square mean error from the direction vector , Moving the mirrored normal orbits to the fracture orbital according to the transformation matrix, calculating the distance error, and repeating calculation until the distance error becomes less than a certain level.

9, the detection module 131 uses the color map corresponding to the distance difference to determine whether orbital wall 3 (orbital wall) The fracture candidate area is displayed in the dimensional model.

The metrology module 132 then measures the fracture candidate area in a three-dimensional model of the orbital wall in which the fracture candidate area is displayed to analyze the degree of fracture. This helps diagnosis for surgery. Preferably, when the user selects a fracture region in the fracture candidate region, the metrology module 132 may measure the area of the fracture region selected by the user, and if the user selects a start point and an end point of the particular location, 132 may measure the length, i.e., the distance, between the corresponding start and end points as shown in FIG. 10. When the user selects three vectors forming the vector, the measurement module 132 calculates the distance The angle between the vectors can be measured.

The implant designing unit 140 designates the implant to be used for the operation of the fracture area by comparing the fracture area of the orbital wall with the normal orbital wall (step S240). Preferably, the implant designing unit 140 designs the implant with respect to the normal orbital so that the left and right orbitals are symmetrical.

More specifically, the implant designing unit 140 obtains a difference region by performing a difference operation on a normal orbital mirror and a fractured eye that are mirrored around a reference plane. Here, the difference operation of the fire operation corresponds to removing regions overlapping each other in the two three-dimensional shapes, and the difference region corresponds to the non-overlapping regions obtained by the difference operation of the non-operation. That is, when the implant designing unit 140 performs the difference calculation of the non-operation in the three-dimensional model of the normal orbital and fracture orbits, since the normal orbital and fractured orbits do not overlap with each other in the fracture region, A difference region corresponding to a candidate region that can be the main body of the image can be obtained. Next, the implant designing unit 140 removes regions other than the portions to be the main bodies of the implants in the difference region through user interaction, and removes the regions from the points of the three-dimensional model surface obtained by the implant body using an offsetting method Implants can be designed by merging with the existing three-dimensional model after moving by offset distance in the normal vector direction. Implants designed through the implant design section 140 are shown in red in FIG.

In one embodiment, the surgical plan creation server 100 may further include a surgical result analysis unit (not shown), and the surgical result analysis unit may be configured to include a fracture area The surgical results can be analyzed on the basis of orbital volume and eye position for the orbital wall, the orbital wall, and the normal orbital wall after surgery using the orbital wall, implant, and the orbital wall. Preferably, the surgical results can be analyzed based on whether the volume of the orbital and normal orbits after surgery and the eye position are symmetrical.

More specifically, when medical image data of a patient, for example, a CT image, is received through the image data receiving unit 210 after the operation, a three-dimensional model of the orbital wall is generated through the modeling unit 120, The result analyzing unit can compare the orbital volume of the three-dimensional model of the orbital wall generated by the modeling unit 120 and the eye position difference in the two-dimensional horizontal plane image. Preferably, the orbital volume is measured by comparing the volume of the orbit before surgery, the orbit after surgery, and the normal orbit. When the user selects the left orbital inner wall from the three-dimensional model of the orbital wall, the selected three- , The orbital volume can be obtained by inverting the direction of the normal vector of each cell of the three-dimensional shape outward and filling the holes in the orbital and orbital anterior via the mesh healing algorithm. Here, the mesh healing algorithm is a method of correcting a defect by reconnecting an incorrectly connected part or a broken part when a defect such as an erroneous connection or a broken connection exists between a cell and a cell forming a three-dimensional shape . The orbital volume obtained through such a method is as shown in Fig.

13, when the user selects the outer end point and the orbital end point of the eye on the two-dimensional horizontal plane image of the medical image data received through the image data receiving unit 110, And the operation result analyzing unit displays the three-dimensional model together so that the three-dimensional position of the two-dimensional horizontal image in which the eye position is measured can be grasped.

The method of generating a surgical plan according to an embodiment of the present invention may also be embodied as computer-readable codes on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.

For example, the computer-readable recording medium includes a ROM, a RAM, a CD-ROM, a magnetic tape, a hard disk, a floppy disk, a removable storage device, a nonvolatile memory, , And optical data storage devices.

In addition, the computer readable recording medium may be distributed and executed in a computer system connected to a computer communication network, and may be stored and executed as a code readable in a distributed manner.

Although the preferred embodiments of the surgical planning creation method for the orbital wall reconstruction according to the present invention, the surgery plan creation server for performing the surgical planning, and the recording medium storing the operation plan creation server have been described, the present invention is not limited thereto, It is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

100: Operation plan generation server
110:
120: Modeling unit
121: Multi-zone division module
122: face area extraction module
123: Ethmoid region extraction module
124: Bone area extraction module
125: Model generation module
130: fracture diagnosis unit
131: Detection module
132: Measurement module
140: Implant design department
150:

Claims (19)

(a) receiving medical image data for a face of a patient;
(b) generating a three-dimensional model of the orbital wall based on the medical image data;
(c) determining and diagnosing a fracture area from a three-dimensional model of the orbital wall; And
(d) designing an implant to be used in surgery of the fracture area by comparing the fracture area of the orbital wall with the normal orbital wall.
2. The method of claim 1, wherein step (b)
(b-1) dividing the medical image data into multiple areas;
(b-2) extracting a face region from the multi-region image;
(b-3) extracting the ethmoid region from the image divided into the multiple regions;
(b-4) extracting a bone region including an orbital wall from the image divided into the multiple regions; And
(b-5) generating a three-dimensional model of the orbital wall based on the orbital wall of the extracted bone region.
3. The method of claim 2, wherein the step (b-1)
Obtaining a contrast histogram based on a distribution of light and dark in the medical image data and dividing the contrast histogram into multiple regions divided into at least two partial regions by applying an Adaptive Global Maximum Clustering (AGMC) algorithm to the contrast histogram,
Wherein the divided multi-regions have a label value.
3. The method of claim 2, wherein the step (b-2)
And setting the face label value among the label values of the multi-areas, and extracting the face area by distinguishing the face area and the non-face area according to the face label value.
3. The method of claim 2, wherein the step (b-3)
Removing the non-ethmoidal region by changing the label value of the non-ethmoidal region based on the label value of the ethmoidal region in the face region of the image divided into the multiple regions; And
And extracting the ethmoid region from the non-ethmoidal region by applying an active contour technique using the minimum label value.
The method of claim 2, wherein the step (b-4)
Extracting an initial bone region based on a label value of a bone region in the image divided into the multiple regions; And
And extracting a bone region including an orbital wall by applying an active contour technique based on the initial bone region and the extracted ethmoid region.
2. The method of claim 1, wherein step (c)
(c-1) detecting a fracture candidate region by symmetry of a normal orbit in a three-dimensional model of the orbital wall with a fractured orbit; And
and (c-2) measuring the fracture candidate region.
8. The method of claim 7,
The step (c-1)
Receiving information of the reference plane for symmetry;
Symmetrically aligning the normal orbit with the fractured orbit around the reference plane to match the position of the normal orbit with the fractured orbit; And
And determining and displaying a fracture candidate region according to a distance difference between the matched normal orbit and the fracture orbital,
The step (c-2)
Extracting a fracture region from the fracture candidate region, and measuring a distance, an area, and an angle of the fracture region.
The method according to claim 1,
(e) analyzing the surgical result based on the pre-operative orbital wall including the fracture region, the orbital wall after surgery using the implant, and the orbital volume and eye position for the normal orbital wall Wherein the method comprises the steps of:
An image data receiving unit for receiving medical image data on a face of a patient;
A modeling unit for generating a three-dimensional model of the orbital wall based on the medical image data;
A fracture diagnosis unit for determining and diagnosing a fracture area from the three-dimensional model of the orbital wall; And
And an implant designing unit for designing an implant to be used for surgery of the fracture area by comparing the fracture area of the orbital wall with the normal orbital wall.
11. The apparatus of claim 10, wherein the modeling unit
A multi-region segmentation module for segmenting the medical image data into multiple regions;
A face region extraction module for extracting a face region from the image divided into the multiple regions;
An ethmoid region extracting module for extracting the ethmoid region from the image divided into the multiple regions;
A bone region extraction module for extracting a bone region including an orbital wall from the image divided into the multiple regions; And
And a model generation module for generating a three-dimensional model of the orbital wall based on the orbital wall of the extracted bony region.
12. The apparatus of claim 11, wherein the multi-
A brightness histogram based on a distribution of light and dark in the medical image data is obtained, and an adaptive global maximum clustering (AGMC) algorithm is applied to the light and dark histogram to divide the area into at least two sub-
Wherein the divided multi-regions have a label value.
12. The method of claim 11, wherein the face region extraction module
Sets face label values among the label values of the multi-areas, and extracts the face regions by distinguishing face regions from non-face regions according to the face label values.
12. The method of claim 11, wherein the ethmoid region extraction module
Removing the non-ethnocultural region by changing a label value of the non-ethmoidal region based on the label value of the ethmoidal region in the face region of the image divided into the multi-regions, Wherein an active contour technique using a minimum label value is applied to extract an ethmoid region.
12. The apparatus of claim 11, wherein the bony region extraction module
Extracting an initial bone region based on a label value of a bone region in the image divided into the multiple regions, applying an active contour technique based on the initial bone region and the extracted ethmoid region, And extracting the surgical plan from the patient.
11. The method according to claim 10, wherein the fracture diagnosis unit
A detection module for detecting a fracture candidate region by symmetrically aligning the normal orbit with the fractured orbit in the three-dimensional model of the orbital wall; And
And a measurement module for measuring the fracture candidate region.
17. The method of claim 16,
Wherein the detection module comprises:
Wherein the information about the reference plane for symmetry is received and the normal orbital is symmetrically made to the fractured orbit around the reference plane to match the positions of the normal orbital and the fractured orbital and the distance between the matched normal orbit and the fracture orbital The fracture candidate region is determined and displayed according to the difference,
Wherein the measurement module comprises:
Extracting a fracture region from the fracture candidate region, and measuring a distance, an area, and an angle of the fracture region.
11. The method of claim 10,
And a surgical result analysis unit for analyzing the surgical result based on the pre-operative orbital wall including the fracture region, the orbital wall after the surgery using the implant, and the orbital volume and the ocular position for the normal orbital wall Wherein the operation plan generation server comprises:
A computer-readable recording medium having recorded thereon a computer program for executing the method of any one of claims 1 to 9.

Images