KR102183045B1 - System for automated implant identification and System for automated peripheral bone loss measurement - Google Patents

Abstract

An automated dental implant identification system according to an embodiment of the present invention includes: a learning unit for generating an implant learning model by learning a learning image input for each implant model in a deep learning method; And, based on the implant learning model, it is preferable to include an implant identification unit for identifying the implantation implant on the unread image to derive model information for the implantation implant.
On the other hand, the automated implant periphery bone loss calculation system according to an embodiment of the present invention detects the number of threads of the implant that the implant is exposed to outside the periphery bone from an unread image, and exposes the implant to the periphery bone. It includes a peripheral bone loss amount calculation unit that calculates the peripheral bone loss amount due to, and the peripheral bone loss amount is preferably calculated by multiplying the pitch interval of the implantation implant input to the peripheral bone loss amount calculation unit and the number of threads.

Description

System for automated implant identification and system for automated peripheral bone loss measurement}

The present invention relates to an automated dental implant identification system and an automated system for calculating the amount of bone loss around the implant, and in detail, by using deep learning technology, the implantable implant can be automatically recognized and identified from an unread image of unknown information. The present invention relates to an automated dental implant identification system and an automated implant peripheral bone loss calculation system capable of automatically measuring the amount of peripheral bone loss through image analysis of the implantable implant.

Since the introduction of a dental treatment technique for dental implants, various implant models have been developed.

As shown in Figure 1, the dental implant is a dental crown (6) that serves as a tooth, and an implant fixture (3) that is embedded in the alveolar bone (1) on the lower side of the gum (2) and serves as a root. It is made, an implant abutment 5 for supporting the dental crown 6 is further provided, and a fixing screw 4 for coupling the implant abutment 5 is added.

That is, since the implant fixture 3 is buried in the alveolar bone 1, the dentist cannot directly check the implant fixture 3 with the naked eye, and the implant fixture can be identified by an X-ray photograph. I had to perceive it visually.

As the related parts for implants are not standardized, implants with different specifications are being developed for each manufacturer. Accordingly, mutual compatibility between implant models is poor, and for long-term maintenance of an implanted dental implant, information on the manufacturer and product of the implant implant must be continuously maintained and recognized.

Of course, since customer-specific data are recorded in the hospital where the first implant was performed, the specifications of the implant fixture can be checked immediately, but it is difficult to accurately recognize the specifications of the implant fixture in the newly moved dental hospital. It is difficult for the patient to be aware of the implanted implant information for a long time, and there are many cases where the medical institution that performed the implantation is closed or related medical information is lost.

Accordingly, in the case of patients who have placed dental implants in the past, it is often difficult to identify the implant manufacturer and the implant model, and it is difficult to maintain the implant. In this case, the problem is solved through the experience or trial and error method of the medical practitioner, but this requires proficiency of the medical practitioner, and it is difficult for a medical practitioner with little clinical experience to properly grasp it.

In addition, after implantation, the proper function is possible only when the bone adhesion with the bone interface is made firmly. When a functional load is applied, most of the marginal bones around the implant are lost, resulting in bone loss. This bone loss occurs gradually from the neck of the implant toward the apical region.

Implants are intended for long-term use, and in order to use the implants for a long time without discomfort, periodic observations are required to prevent periodontitis.

In the periodic observation of the implant, since the implant is placed in the alveolar bone, a method of grasping the degree of bone loss of the surrounding bone where the implant is placed is used through a radiograph. Measuring the degree of loss of bone around the implant using dental radiographs is one of the academic and clinical indicators.

However, there is no automated tool to measure the degree of loss of surrounding bones from implant radiographs, so researchers and clinicians take radiographs on digital images and manually use a graphic program using a dedicated radiograph viewer. The situation is being measured.

In the case of such manual-dependent measurement, there is a problem in that the accuracy of the amount of loss of surrounding bones is low due to an error in the measured value due to the difference in the ratio with the actual object during radiographing. In addition, there is a problem that it is difficult to see that an objective actual amount of loss has been measured due to an error according to a measurer's vision and operation ability. That is, in measuring the corresponding index value, reproducibility and consistency are low depending on the skill of the operator, and it is difficult to accurately measure the amount of bone loss in the surrounding bone.

The Korean Journal of Prosthodontics Vol 32 No 3, 1994 discloses a study on alveolar bone loss and bone density changes during the first year of a root-type intraosseous implant.

An object of the present invention is to provide an automated dental implant identification system capable of automatically recognizing and identifying an implantable implant from an unread image of unknown information using a deep learning technology.

In addition, the present invention uses deep learning technology to identify a model of an implantable implant from an unread image of unknown information, and to automatically measure the amount of peripheral bone loss due to exposure of the implant to the outside of the surrounding bone. It aims to provide an implant identification system.

In addition, the present invention objectively measures the amount of peripheral bone loss by detecting the number of threads of the implant that is exposed outside the surrounding bone from an unread image of unknown information in order to solve the problem that comes from the conventional manual measurement of the amount of loss of surrounding bone It aims to provide an automated system for calculating the amount of bone loss around the implant.

An automated dental implant identification system according to an embodiment of the present invention includes: a learning unit for generating an implant learning model by learning a learning image input for each implant model in a deep learning method; And, based on the implant learning model, it is preferable to include an implant identification unit for identifying the implantation implant on the unread image to derive model information for the implantation implant.

In one embodiment of the present invention, the learning unit generates a plurality of augmented images through image processing that rotates the learning image at a preset rotation angle or adjusts the size of the learning image, using the learning image as an original, and It is preferable to learn the learning image and a plurality of augmented images by deep learning method.

In one embodiment of the present invention, it is preferable that the implant identification unit pre-processes the unread image to recognize the implantation implant from the unread image.

In one embodiment of the present invention, the implant identification unit, when a plurality of implantation implants are recognized in an unread image, detects the location information for each implantation implant, and each location information based on the implant learning model. It is preferable to identify a model of an implantable implant, derive model information for a plurality of implantable implants, and display and output the model information for each implantable implant according to the location information on an unread image.

In one embodiment of the present invention, the implant identification unit, based on the implant model identified as the implantation implant, it is preferable to calculate the similarity of the implantation implant to the implant model in a deep learning method.

In one embodiment of the present invention, it is preferable that the implant identification unit displays and outputs the model information and similarity of the implantable implant on an unread image at a position corresponding to the implantable implant.

In an embodiment of the present invention, it is preferable that the implant identification unit derives the model name of the implantable implant and the pitch interval between the threads of the implantable implant as model information.

In one embodiment of the present invention, the number of threads of the implant that is exposed outside the surrounding bone in an unread image is detected, and based on the number of threads and the pitch interval, the surrounding area due to exposure to the outside of the surrounding bone of the implant It is preferable to further include a peripheral bone loss amount calculation unit that calculates the bone loss amount.

In one embodiment of the present invention, the amount of periphery bone loss is preferably calculated by the product of the number of threads and the pitch interval.

In one embodiment of the present invention, the peripheral bone loss calculation unit is, when a portion of the implantation implant exposed outside the peripheral bone in the unread image is input as the measurement site, the thread of the implantation implant exposed outside the peripheral bone relative to the measurement site It is desirable to detect the number.

On the other hand, the automated system for calculating the amount of bone loss around the implant according to an embodiment of the present invention detects the number of threads of the implant that the implant is exposed to outside the surrounding bone from an unread image, and exposes the implant to the outside of the peripheral bone It includes a peripheral bone loss amount calculation unit that calculates the peripheral bone loss amount due to, and the peripheral bone loss amount is preferably calculated by multiplying the pitch interval of the implantation implant input to the peripheral bone loss amount calculation unit and the number of threads.

It is preferable that the peripheral bone loss calculation unit detects the number of threads of the implant that is exposed outside the peripheral bone at the measurement site when the portion of the unread image where the implant is exposed outside the surrounding bone is input as the measurement site.

The automated dental implant identification system of the present invention uses deep learning technology to automatically recognize and identify implants from unread images of unknown information to derive model information (model name, model specification, manufacturer, etc.) for implantation implants. can do.

In addition, the present invention can secure objectivity of model information for the implantable implant through the similarity of the implantable implant to the implant model.

Based on the model information for the implantable implant derived by the present invention, the medical practitioner can quickly proceed with the follow-up management and/or treatment of the implantable implant.

That is, the present invention provides useful information to the clinician even when the patient himself cannot know the manufacturer and specification of the implanted implant, thereby increasing the accuracy and efficiency of treatment to both the medical staff and the patient.

On the other hand, the automated implant periphery bone loss calculation system of the present invention can objectively calculate the periphery bone loss due to exposure of the implant to the outside of the periphery bone from an unread image.

The present invention can be utilized as one of the automated diagnostic data for dental implants by providing information on the extent of loss of bone around the implant to a patient or a clinician.

The information on the amount of loss of the surrounding bone calculated by the present invention can provide objectified and verified data on the current stability of the dental implant placed in the patient.

In addition, the present invention automatically measures the degree of loss of bone around the implant in the past, thereby eliminating unnecessary time and providing accurate and objective measurement data for numerous researchers and clinicians conducting retrospective studies on implants. Can provide.

1 schematically shows an installation state diagram in which a dental implant is placed on a gum.
Figure 2 schematically shows the configuration of an automated dental implant identification system according to an embodiment of the present invention.
3 is a flowchart of a learning unit according to an embodiment of the present invention.
Fig. 4(a) is an example of an image input to the learning unit, and Fig. 4(b) is an example of images in which an image input to the learning unit is augmented with a similar image.
5 is a view for explaining a flow chart of an implant identification unit according to an embodiment of the present invention.
6 is a view for explaining an example of image processing for a radiation image in an implant identification unit.
7 and 8 are diagrams for explaining a process of realizing a model of an implantable implant from an input unread image by an implant identification unit.
9 is a flowchart of a peripheral bone loss amount calculation unit according to an embodiment of the present invention.
10 is a view for explaining a process of calculating the amount of loss of peripheral bones due to exposure of the implant to the outside of the peripheral bone in the unread image.

Hereinafter, with reference to the accompanying drawings, an automated dental implant identification system and an automated dental implant periphery bone loss calculation system according to a preferred embodiment of the present invention will be described.

● Automated dental implant identification system

As shown in FIG. 2, the automated dental implant identification system includes a learning unit 110, an implant identification unit 120, and a peripheral bone loss calculation unit 130.

The learning unit 110 generates an implant learning model by learning a learning image for each implant model in a deep learning method. The learning image is a radiograph of an implant, and a radiograph used in a dental treatment area, such as a panoramic or apical radiograph, can be applied.

Referring to FIG. 3, a learning image is input to the learning unit 110 for each implant model (S11). In the learning unit 110, the training image may be stored in a folder (implant 1, implant 2, implant 3, etc.) divided for each implant model.

Referring to FIG. 4, the learning unit 110 generates a plurality of augmented images through image processing of rotating the learning image at a predetermined rotation angle or adjusting the image size using the learning image as an original. The learning unit 110 learns a plurality of augmented images in a deep learning method.

The learning unit 110 learns the learning images and the augmented images according to a preset deep learning algorithm to generate an implant learning model (S12). Deep learning algorithms are known algorithms for implementing deep learning techniques.

For each implant model, the learning unit 110 pre-stores the model name, model specification (eg, the length of the implant fixture, the pitch interval of the screw thread of the fixture, the diameter of the fixture, the material, etc.), and the manufacturer. Some of the specifications of the implant model can be added or omitted depending on the learning conditions.

Hereinafter, the implant identification unit 120 will be described with reference to FIGS. 5 to 8.

The implant identification unit 120 identifies the implantation implant on the unread image, based on the implant learning model, and derives model information for the implantation implant.

The unread image is input to the implant identification unit 120 (S21). Unread images are dental radiographic images of unknown information. In this embodiment, the implantation implant 10 refers to an implant placed on a tooth on a dental radiographic image, and refers to a part corresponding to the implant fixture illustrated in FIG. 1.

If the unread image is a radiograph of both the implant and the tooth taken at the same time, the implant identification unit 120 identifies the implant based on the implant learning model after passing through the recognition process of the implant.

On the other hand, if the unread image is a radiograph of the placement implant alone, the implant identification unit 120 immediately identifies the placement implant based on the implant learning model without the recognition process of the placement implant.

The implant identification unit 120 pre-processes an image of the unread image (S22) to recognize an implantable implant from the unread image. The image pre-processing (S22) is a process in which an unread image is converted into an image according to an image pre-processing algorithm preset in the implant identification unit 120.

The image preprocessing algorithm may be any one of noise removal, histogram leveling, binarization, inversion, Gaussian processing, masking processing, or boundary recognition.

Referring to FIG. 6, an example of image preprocessing for an unread image will be described as follows.

Figure 6(a) is an example of the original image of the unread image. 6(b) is an image in which the original image of FIG. 6(a) is histogram-leveled. Fig. 6(c) is an image in which the original image of Fig. 6(a) is binarized. 6(d) is an image in which the original image of FIG. 6(a) is reversed.

When a plurality of implantable implants are recognized in an unread image, the implant identification unit 120 may identify a model of each implantable implant based on the implant learning model, and may derive model information for a plurality of implantable implants ( S23).

The implant identification unit 120 may derive the model name and model specifications of the implantable implant as model information. As for the model specifications, the implant specifications provided by the manufacturer, such as the pitch gap between the threads of the implantable implant, the diameter of the implantable implant, and the length of the implantable implant, correspond.

Then, the implant identification unit 120 calculates the similarity of the implant model to the implant model in a deep learning method based on the implant model identified as the implant implant (S24). The present invention can secure objectivity of model information for an implantable implant through the similarity of the implantable implant to the implant model.

The implant identification unit 120 displays and outputs the model information and similarity of the implantable implant on an unread image at a position corresponding to the implantable implant (S25).

In this embodiment, an output image in which model information and similarity of the implantation implant are displayed on an unread image is referred to as a "read image". In the read image, model information, which is a result value derived from the implant identification unit 120, is displayed on the original of the unread image. The read image can be output to a monitor through a PC or printed out.

Referring to FIG. 7, a process in which the unread image input to the implant identification unit 120 is output as a read image will be described as follows. 7 is an example of an apical radiographic image as an unread image.

As shown in Fig. 7(a), an unread image of unknown information is input to the implant identification unit 120. Fig. 7(a) is an original image of an apical radiographic image.

Thereafter, as shown in FIG. 7(b), in the implant identification unit 120, an unread image of unknown information is subjected to an inverted image processing, and a portion corresponding to the implantable implant is processed to be black.

As described above, the implant identification unit 120 clearly distinguishes the implant and other parts from the image that has been reversed compared to the original through the image pre-processing (S22), so that the implant can be easily recognized. .

The implant identification unit 120 identifies the implantation implant from the apical radiographic image based on the implant learning model, and displays model information and similarity for the implantation implant as shown in FIG. 7(c). 7(c) is a read image, which is an image in which model information about an implantable implant is displayed on the original image.

As shown in Fig. 8, the implant identification unit can derive model information of the implantable implant on the panoramic radiation image through the same process as the case where the apical radiation image shown in Fig. 7 is input even when the panoramic radiation image is input. have.

FIG. 8(a) is an original panoramic radiation image, and FIG. 8(b) is an image in which model information on an implantable implant is displayed in the original of FIG. 8(a). The implant identification unit 120 outputs a read image (Fig. 8(b)) in which model information (model name and similarity) is displayed.

Hereinafter, the peripheral bone loss amount calculation unit 130 will be described.

As described in the background art, conventionally, there is no automated tool for measuring the degree of loss of the surrounding bone from an implant radiographic photograph, so the degree of loss of the surrounding bone is manually measured. In the case of manually measuring the degree of loss of surrounding bones, the accuracy of the amount of loss of surrounding bones is low due to the error of the measured value due to the difference in ratio with the actual object at the time of radiographing. In addition, there is a problem that it is difficult to see that an objective actual amount of loss has been measured due to an error according to a measurer's vision and operation ability.

The present invention automatically calculates the height at which the implant is exposed outside the surrounding bone from the unread image input to the peripheral bone loss calculation unit in order to solve the problem that comes from measuring the amount of loss of the surrounding bone manually in the prior art. This is to automatically calculate the amount of peripheral bone loss due to exposure outside the surrounding bone.

Peripheral bone loss calculation unit 130 detects the number of threads of the implant that is exposed outside the surrounding bone in the unread image, and based on the number of threads and the pitch interval, the surrounding bone due to exposure to the outside of the surrounding bone of the implant Calculate the amount of bone loss.

Referring to FIG. 9, a process of calculating the peripheral bone loss amount in the peripheral bone loss amount calculation unit 130 will be described as follows.

The image is input to the peripheral bone loss amount calculation unit 130 (S31). The image corresponds to a dental radiographic image with an implantable implant.

A portion for which the peripheral bone loss amount is desired to be measured is input to the peripheral bone loss amount calculation unit 130 (S31). As indicated by the red box in Fig. 10(a), the measurement site includes the implantation implant and the surrounding bone. As shown in FIG. 10(b), the peripheral bone loss amount calculation unit 130 separately extracts only the measurement area from the image (see FIG. 10(a)).

Then, the peripheral bone loss amount calculation unit 130 image-processes the measurement area (S32). As shown in FIG. 10(c), the measurement site is image-processed so that the implantation implant and the surrounding bone are expressed as an external boundary. In Fig. 10(c), the outline boundary for the implantable implant is indicated by L1. And, the outer boundary for the surrounding bone is indicated by L2.

Subsequently, the peripheral bone loss amount calculation unit 130 detects the number of threads in the external boundary L1 for the implantation implant when the external boundary L1 for the implantation implant exposed outside the peripheral bone at the measurement site is recognized (S33). Do (S35). In addition, if necessary, the user may additionally input the number of threads to the peripheral bone loss calculation unit 130 (S34).

Next, the peripheral bone loss amount calculation unit 130 calculates the peripheral bone loss amount based on the number of threads of the implantation implant exposed outside the peripheral bone and the pitch interval between the threads of the implantation implant (S36). The pitch gap between the threads of the implantable implant is based on the model information derived from the implant identification unit.

The peripheral bone loss amount calculation unit 130 is preset with a peripheral bone loss amount calculation algorithm. According to the peripheral bone loss calculation algorithm, the peripheral bone loss is calculated by the product of the number of threads and the pitch interval. Peripheral bone loss is the height at which the implant is exposed outside the surrounding bone.

Referring to FIG. 10(d), when the pitch interval is 0.45mmm and the number of threads exposed outside the peripheral bone is 5, the height at which the implantation implant is exposed outside the peripheral bone is calculated as 2.25mm.

The peripheral bone loss amount calculation unit 130 outputs a height value at which the implantable implant is exposed outside the peripheral bone as the peripheral bone loss amount (S38).

The present invention identifies several implantable implants present on a single unread image to derive model information for each implantable implant, and automatically calculates the amount of peripheral bone loss due to exposure of the implant to the outside of the surrounding bone. have.

Accordingly, according to the present invention, it is possible to obtain the amount of loss of surrounding bones using an unread image without any other dental examination, thereby increasing the efficiency of the dental examination.

In addition, the present invention easily obtains objective data on treatment information in case of gum disease due to long-term use of the implantable implant 10, and is useful information to the clinician even if the patient himself cannot know the manufacturer and specifications of the implanted implant. By providing, it is possible to increase the accuracy and efficiency of treatment for both medical staff and patients.

In addition, the present invention can provide objectified and verified data on the current stability of a dental implant placed in a patient.

The present invention can provide information to patients and clinicians about future management plans for the implanted implant.

● Automated implant periphery bone loss calculation system

Hereinafter, an automated system for calculating an amount of bone loss around an implant according to a preferred embodiment of the present invention will be described with reference to FIGS. 9 and 10.

The automated system for calculating the amount of bone loss around the implant according to the present invention is for calculating the amount of loss of the surrounding bones of the implant immediately without the identification process of the implant as described above, when the medical practitioner is aware of the model information for the implant. .

The peripheral bone loss calculation system is a system in which the peripheral bone loss calculation unit is independently operated.

The peripheral bone loss amount calculation unit detects the number of threads of the implantation implant exposed outside the surrounding bone by the implantation implant in the unread image, and calculates the amount of peripheral bone loss due to the exposure of the implantation implant outside the surrounding bone.

The peripheral bone loss calculation unit, when the portion of the unread image where the implanted implant is exposed to the outside of the peripheral bone is input as the measurement site (S31), and processes the measured area (S32).

The peripheral bone loss amount calculation unit detects the number of threads of the implantable implant exposed outside the peripheral bone at the measurement site (S33 to S35).

The peripheral bone loss amount calculation unit calculates the peripheral bone loss amount according to a preset peripheral bone loss amount calculation algorithm when a pitch interval between threads of the implantable implant is input. The amount of periphery bone loss is calculated by multiplying the pitch interval between the threads of the placement implant and the number of threads exposed outside the surrounding bone by the placement implant (S37).

The peripheral bone loss amount calculation unit 130 outputs a height value at which the implantable implant is exposed outside the peripheral bone as the peripheral bone loss amount (S38).

The above-described automated dental implant identification system automatically inputs the pitch gap between the threads of the implant into the peripheral bone loss calculation unit to calculate the peripheral bone loss amount, while the automated implant peripheral bone loss calculation system is the peripheral bone loss calculation unit. There is a difference in that the amount of peripheral bone loss is calculated by manually inputting the pitch interval between the threads of the implant. But,

Compared with the automated dental implant identification system, the peripheral bone loss system detects the number of threads exposed outside the surrounding bone by processing the unread image in the peripheral bone loss calculation unit. The calculation method is the same.

The automated implant periphery bone loss calculation system of the present invention can objectively calculate the periphery bone loss due to exposure of the implant to the outside of the periphery bone from an unread image through image analysis.

The present invention can be utilized as one of the automated diagnostic data for dental implants by providing information on the extent of loss of bone around the implant to a patient or a clinician.

The information on the amount of loss of the surrounding bone calculated by the present invention can provide objectified and verified data on the current stability of the dental implant placed in the patient.

In addition, the present invention automatically measures the degree of loss of bone around the implant in the past, thereby eliminating unnecessary time and providing accurate and objective measurement data for numerous researchers and clinicians conducting retrospective studies on implants. Can provide.

The present invention described above is not limited to the above-described embodiments and the accompanying drawings, and various substitutions, modifications and changes are possible within the scope of the technical spirit of the present invention. It will be obvious to those who have the knowledge of.

100: automated dental implant identification system
110: Learning Department
120: implant identification unit
130: peripheral bone loss calculation unit

Claims (12)

A learning unit for generating an implant learning model by learning the training image input for each implant model in a deep learning method; And
Based on the implant learning model, comprising an implant identification unit for identifying the implantation implant on the unread image to derive model information for the implant,
The implant identification unit derives a pitch interval between the model name of the implantation implant and the thread of the implantation implant from the model information,
In the unread image, the number of threads of the implantable implant exposed outside the peripheral bone is detected, and the amount of peripheral bone loss due to the exposure of the implantable implant to the outside of the peripheral bone is calculated based on the number of threads and the pitch interval. An automated dental implant identification system, characterized in that it further comprises a peripheral bone loss calculation unit. The method of claim 1,
The learning unit generates a plurality of augmented images through image processing for rotating the learning image at a predetermined rotation angle or adjusting the size of the learning image, using the learning image as an original,
The learning unit is an automated dental implant identification system, characterized in that for learning the learning image and the plurality of augmented images in a deep learning method. The method of claim 1,
The implant identification unit is an automated dental implant identification system, characterized in that by pre-processing the image of the unread image to recognize the implantation implant from the unread image. The method of claim 3,
The implant identification unit,
When a plurality of implantation implants are recognized in the unread image, position information for each implantation implant is detected,
By identifying a model of each implantation implant based on the implant learning model for each of the location information, model information for the plurality of implantation implants is derived,
An automated dental implant identification system, characterized in that for each of the implantable implants, the model information is displayed on the unread image and output according to the location information. The method of claim 1,
The implant identification unit,
An automated dental implant identification system, characterized in that, based on the implant model identified as the implantable implant, calculates the similarity of the implantable implant to the implant model in a deep learning method. The method of claim 5,
The implant identification unit automated dental implant identification system, characterized in that for displaying and outputting the model information and the similarity of the implantation implant on the unread image at a position corresponding to the implantation implant. delete delete The method of claim 1,
An automated dental implant identification system, characterized in that the peripheral bone loss amount is calculated by a product of the number of threads and the pitch interval. The method of claim 1,
The peripheral bone loss amount calculation unit,
In the unread image, when the part exposed outside of the surrounding bone is input as the measurement site,
An automated dental implant identification system, characterized in that detecting the number of threads of the implantable implant exposed outside the surrounding bone at the measurement site. It includes a peripheral bone loss amount calculation unit for calculating the amount of peripheral bone loss due to the exposure of the implant to the outside of the peripheral bone by detecting the number of threads of the implant that is exposed outside the surrounding bone in the unread image,
The peripheral bone loss amount is calculated by a product of a pitch interval of the implantable implant inputted to the peripheral bone loss amount calculation unit and the number of threads. The method of claim 11,
The peripheral bone loss amount calculation unit,
In the unread image, when the part exposed outside of the surrounding bone is input as the measurement site,
An automated implant peripheral bone loss calculation system, characterized in that for detecting the number of threads of the implantable implant exposed outside the peripheral bone at the measurement site.

Images