Programs, computers, and information processing methods

Abstract

This invention provides a program, a computer, and an information processing method that can efficiently and accurately support dentists in determining whether orthodontic treatment is feasible. [Solution] The system is provided with a reception means 32, an estimation means 38, and a determination means 40. The reception means 32 receives multiple dental images of the subject. The estimation means 38 uses a trained model 200 generated by machine learning using training data 210 which includes dental images and information on whether the images contain teeth that can be straightened, to estimate whether each of the multiple dental images contains teeth that can be straightened. The determination means 40 determines whether or not dental straightening is possible for the subject based on the estimation results from the estimation means 38.

Description

TECHNICAL FIELD

[0001] The present invention relates to a program, a computer, and an information processing method. BACKGROUND ART

[0002] In recent years, a technique is known in which a user wears a mouthpiece (aligner) on their dentition in daily life to perform orthodontic treatment. For example, Patent Document 1 discloses a technique for remotely performing orthodontic treatment using a mouthpiece to reduce the burden on the user. PRIOR ART DOCUMENTS PATENT DOCUMENTS

[0003] PATENT DOCUMENT 1 Japanese Patent No. 7594333 SUMMARY OF THE INVENTION PROBLEMS TO BE SOLVED BY THE INVENTION

[0004] Conventionally, the feasibility of orthodontic treatment and the selection of an orthodontic plan have been manually determined based on the experience of a dentist. For this reason, not only does the determination process require time and effort, but there is also variation in the determination accuracy of the feasibility of orthodontic treatment among dentists. In particular, there are limits to handling the number of teeth to be corrected and complex cases, and efficient and accurate diagnosis has been required.

[0005] In view of such points, the present disclosure aims to provide a program, a computer, and an information processing method that can efficiently and accurately assist a dentist in determining the feasibility of orthodontic treatment. MEANS FOR SOLVING THE PROBLEMS

[0006] The program of the present disclosure is A program that causes a computer to function as a receiving unit, an estimating unit, and a determining unit, wherein The receiving unit receives a plurality of dentition images of a subject, The estimation means uses a trained model generated by machine learning, which includes images of teeth and information on whether the images contain teeth that can be straightened, to estimate whether each of the multiple images of teeth contains teeth that can be straightened. The determination means is characterized by determining whether or not orthodontic treatment is feasible for the subject based on the estimation result by the estimation means.

[0007] In the program disclosed herein, The determination means can determine whether or not a predetermined mouthpiece orthodontic plan is applicable based on the estimation result from the estimation means.

[0008] In the program disclosed herein, The computer may further function as an image processing means. The reception means receives the dental arch scan data of the subject, The image processing means can process the dental scan data received by the receiving means to generate multiple dental images.

[0009] In the program disclosed herein, The image processing means may process the dental scan data received by the reception means to generate a dental image in which the upper and lower dental arches of the subject are captured at an angle from diagonally downward.

[0010] In the program disclosed herein, The estimation means can estimate whether or not a combined dental image, which is a combination of multiple dental images, contains teeth that can be treated with orthodontics.

[0011] In the program disclosed herein, The aforementioned computer may further function as an arch drawing means. The arch drawing means uses an object detection model generated by machine learning using training data including images of the upper and lower teeth to detect and classify teeth in each of the subject's upper and lower teeth images as part of a plurality of the teeth images, and draws an arch showing the teeth. The determination means can determine, based on the shape of the arch, whether orthodontic treatment is feasible for the subject or whether a predetermined mouthpiece orthodontic treatment plan is applicable.

[0012] The computer disclosed herein is A computer that functions as a reception means, an estimation means, and a determination means by executing a program, The aforementioned reception means receives multiple dental images of the subject, The estimation means uses a trained model generated by machine learning, which includes images of teeth and information on whether the images contain teeth that can be straightened, to estimate whether each of the multiple images of teeth contains teeth that can be straightened. The determination means is characterized by determining whether or not orthodontic treatment is feasible for the subject based on the estimation result by the estimation means.

[0013] The information processing method disclosed herein is: An information processing method performed by a computer having a control unit, The control unit performs the steps of receiving multiple dental images of the subject, The control unit performs the following steps: estimate whether each of the multiple dental images contains teeth that can be orthodontized, using a trained model generated by machine learning by using training data that includes images of teeth and information on whether the images contain teeth that can be orthodontized; The control unit performs the step of determining whether orthodontic treatment is feasible for the subject based on the estimation result, It is characterized by having the following features. [Effects of the Invention]

[0014] According to the program, computer, and information processing method of the present disclosure, it is possible to efficiently and accurately assist a dentist in determining whether orthodontic treatment is applicable. [Brief Description of the Drawings]

[0015] [Figure 1] 1 is a diagram schematically illustrating an information processing system according to an embodiment of the present disclosure. [Figure 2] 2 is a diagram illustrating an example of a dentition image to be estimated in the information processing system and the information processing method according to the embodiment of the present disclosure. [Figure 3] 3 is a diagram illustrating an example of an image showing an arch representing tooth alignment in the information processing system and the information processing method according to the embodiment of the present disclosure. [Figure 4] 4 is a diagram illustrating an exemplary flow of information processing of the information processing method according to the embodiment of the present disclosure. [Figure 5] 5 is a diagram illustrating another exemplary flow of information processing of the information processing method according to the embodiment of the present disclosure. [Modes for Carrying Out the Invention]

[0016] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings, but the invention according to the present disclosure is not limited thereto. Figures 1 to 5 are diagrams illustrating an information processing system 1 and an information processing method according to the present disclosure.

[0017] [Information Processing System (AI Orthodontic Treatment Applicability Determination Support System) 1] The information processing system 1 according to the present embodiment shown in Figure 1 includes a 3D scanner 2 and a server 3. The 3D scanner 2 and the server 3 can transmit and receive information wirelessly or by wire. For example, information may be transmitted and received via a communication network such as an internet line.

[0018] (3D Scanner 2) The 3D scanner 2 has an imaging unit 21 and a communication unit 22 (Figure 1). The imaging unit 21 acquires the subject's dental arch scan data by scanning the inside of the oral cavity, including the upper and lower teeth. From this dental arch scan data, an image is generated that will be used to estimate whether orthodontic treatment is feasible, as described later. The imaging unit 21 (3D scanner 2) is not particularly limited as long as it can acquire such dental arch scan data, and known dental 3D scanners, 3D optical cameras, etc., can be used. The "subject" is the person whose suitability for orthodontic treatment is to be determined.

[0019] The communication unit 22 includes a communication interface for sending and receiving information with external devices wirelessly or via wired connection. The dental arch scan data captured by the imaging unit 21 is transmitted to the server 3 by the communication unit 22.

[0020] <Server (Computer) 3> Server 3 can be composed of industrial computers, personal computers, tablet terminals, etc., and may also be a virtual server within a physical server accessible via the Internet. Furthermore, there may be multiple such hardware components or virtual servers, and any combination is permitted. The server 3 shown in Figure 1 includes a control unit 30, a storage unit 48, a communication unit 50, a display unit 52, and an operation unit 54.

[0021] (Control Unit 30) The control unit 30 consists of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an AI inference unit, etc., and controls the operation of the server 3. Specifically, the control unit 30 functions as a reception means 32, an image processing means 34, an arch drawing means 36, an estimation means 38, a determination means 40, an output means 42, an object detection model generation means 44, a trained model generation means 46, etc., by executing a program stored in the memory unit 48, which will be described later. These functions may be performed by executing one or more independent programs or applications. Furthermore, these programs and applications may be provided on a single terminal (server 3) or distributed across multiple terminals (including server 3), and in the latter case, they may be interconnected via wired cables or a communication network. Each means will be described later.

[0022] (Storage unit 48) The storage unit 48 is composed of, for example, an HDD (Hard Disk Drive), RAM (Random Access Memory), ROM (Read Only Memory), or SSD (Solid State Drive). Furthermore, the storage unit 48 is not limited to being built into the server 3, but may also be a storage medium that can be detachably attached to the server 3 (for example, a USB memory stick). Alternatively, instead of providing the storage unit 48, various types of information may be stored in other storage means (such as a cloud server).

[0023] The information stored in the memory unit 48 includes programs executed by the control unit 30, criteria for determining whether orthodontic treatment is feasible and whether orthodontic treatment plans are appropriate, as well as subject information such as the subject's dental scan data, dental images, and judgment results, the trained model 200 and its training data 210 (described later), and the object detection model 100 and its training data 110.

[0024] (Communications Section 50) The communication unit 50 includes a communication interface for sending and receiving information with external devices wirelessly or via a wired connection. The server 3 uses the communication unit 50 to send and receive information with the 3D scanner 2 (communication unit 22).

[0025] (Display section 52, operation section 54) The display unit 52 is, for example, a monitor, and displays various screens by receiving display command signals from the control unit 30. The operation unit 54 is, for example, a keyboard, and can give various commands (inputs) to the control unit 30. In this embodiment, a display operation unit such as a touch panel, which integrates the display unit 52 and the operation unit 54, may be used.

[0026] (Details of the control unit 30) (Reception method 32) The reception means 32 receives multiple images of the subject's teeth. Each image of teeth received by the reception means 32 is subject to estimation of the feasibility of orthodontic treatment by the estimation means 38, which will be described later. The reception means 32 may also receive scan data of the subject's teeth from the 3D scanner 2. The scan data of teeth received by the reception means 32 is processed by the image processing means 34, which will be described later, to become the image of teeth to be estimated by the estimation means 38. In other words, in the information processing system 1 according to this disclosure, it is assumed that the image of teeth received by the reception means 32 and subject to estimation of the feasibility of orthodontic treatment are the same as the image of teeth generated by the image processing means 34. For this reason, these images of teeth will be described together in relation to the image processing means 34 below.

[0027] Furthermore, the reception means 32 may also accept clinical data such as X-ray data of the subject's teeth. This data may also be used in the estimation process by the estimation means 38.

[0028] (Image processing means 34) The image processing means 34 processes (processes) the tooth scan data received by the reception means 32 to generate multiple tooth images. Figure 2 shows an example of tooth images to be estimated, but the number of tooth images generated by the image processing means 34 and to be estimated is not limited. Six tooth images shown as (a) to (f) in Figure 2 may be used. Furthermore, a larger number of tooth images is preferable because it allows for a more accurate determination of whether orthodontic treatment is possible. The number of tooth images can be appropriately set according to the orthodontic plan to be determined by the determination means 40.

[0029] The image processing means 34 may process the dental scan data received by the reception means 32 to generate a dental image (Figure 2(e)) of the subject's upper and lower teeth (specifically, the upper and lower teeth in a biting position as shown in Figure 2(b)) taken from an angle diagonally downward. Figure 2(e) "Diagonally downward" is a dental image that shows the teeth of a subject viewed from the front (front) surface taken from a 50° angle diagonally downward by processing the dental scan data (with the state in Figure 2(a) being 0°).

[0030] The "angle" from which the upper and lower dentition images are taken from a diagonal downward angle is not limited to 50°, but may be within the range of 40° to 60°, or for example, set to 55°. Within this range is preferable because it allows for more accurate estimation from a different perspective than the estimation results for other dentition images. It can be set appropriately according to the orthodontic plan to be determined by the determination means 40. Furthermore, in order to improve the determination accuracy, the image processing means 34 may be made to generate dentition images taken from multiple diagonal downward angles. In this way, malocclusions such as underbite, crossbite, deep bite, and protrusion can be estimated.

[0031] Figure 2 shows the following dental images: (a) an image of the upper and lower teeth viewed from the right side of the subject; (b) an image of the upper and lower teeth viewed from the front of the subject; (c) an image of the upper and lower teeth viewed from the left side of the subject; (d) an image of the upper teeth viewed from below; (e) an image of the upper and lower teeth viewed from diagonally below; (f) an image of the lower teeth viewed from above; and (g) an integrated dental image combining dental images (a) to (f).

[0032] Furthermore, the angles (orientations) of the dental arches shown in Figure 2 are illustrative examples, and the dental arches included in the training data and the target dental arch images may be identified at various angles. The number of teeth in each dental arch may also be appropriately set and changed according to the orthodontic plan. Moreover, it is not necessary to estimate all parts of each tooth; depending on the orthodontic plan, only the crown or root may be estimated. However, when determining the suitability of a plan that targets all teeth as a clear aligner orthodontic plan, it is preferable to prepare dental arch images at an angle in which all teeth can be seen, as shown in Figure 2.

[0033] (Arch drawing means 36) The arch drawing means 36 uses an object detection model 100 generated by machine learning using training data 110 which includes images of the upper and lower teeth to detect and classify teeth in each of the subject's upper and lower teeth images as part of multiple teeth images, and draws an arch that shows the alignment of the teeth (see Figure 3).

[0034] As explained using Figures 2 and 3, the object detection model 100 detects each tooth from images of the upper and lower dental arches, as shown in Figures 2(d) and 2(f). Then, based on the position and shape in each image, it classifies each tooth as a canine, molar, etc. Next, the object detection model 100 determines the center of each tooth in the dental arch image (the point in Figure 3), taking into account the characteristics of each tooth based on the classification results. The arch drawing means 36 (control unit 30) can draw an arch by connecting these centers. Furthermore, the degree of distortion of the subject's upper and lower dental arches can be determined from this arch.

[0035] Furthermore, the arch drawing means 36 may calculate information about the excess or deficiency of teeth within the dental arch image based on the detection and classification results by the object detection model 100. This information can also be used to determine whether orthodontic treatment is feasible.

[0036] The object detection model 100 can be generated by the object detection model generation means 44 described later, but as long as it can draw arches as described above, the generation method and training data 110 are not particularly limited. Various methods such as deep learning and supervised learning can be used as "machine learning".

[0037] (Estimation means 38) The estimation means 38 uses a trained model 200 generated by machine learning, which is created using training data 210 that includes images of teeth and information on whether the images contain teeth that can be straightened, to estimate whether each of the multiple images of teeth contains teeth that can be straightened. Images like the one shown in Figure 2 can be used as "images of teeth".

[0038] The information regarding whether the image contains teeth that can be treated with orthodontics should preferably be ground truth data labeled by a dentist indicating that orthodontic treatment is possible or that a clear aligner treatment plan is applicable.

[0039] "Machine learning" is not particularly limited as long as it can accept dental images as "input" and "output" whether or not the dental images contain teeth that can be treated with orthodontics. Various methods such as deep learning, supervised learning, and anomaly detection can be used.

[0040] The estimation means 38 can also estimate whether or not a combined dental arch image, which is a combination of multiple dental arch images, contains teeth that can be treated with orthodontics. Figure 2(g) is an example of a combined dental arch image, which is a combination of the dental arch images (a) to (f) shown in Figure 2. However, it is not always necessary to combine six dental arch images into a combined dental arch image; the number and type of dental arch images to be combined can be appropriately set and changed depending on the orthodontic plan to be determined.

[0041] Furthermore, when an image of teeth with an arch drawn by the arch drawing means 36 is input to the estimation means 38, it may estimate whether or not the image of the subject's teeth includes teeth that can be straightened (whether orthodontic treatment is possible, or whether a predetermined mouthpiece orthodontic treatment plan can be applied) by comparing the degree of distortion with a predetermined threshold.

[0042] (Judgment means 40) The determination means 40 determines whether or not orthodontic treatment is suitable for the subject based on the estimation result from the estimation means 38. "Orthodontic treatment" may be either wire braces or clear aligner treatment.

[0043] The determination means 40 can also determine whether a predetermined mouthpiece orthodontic plan is applicable based on the estimation results from the estimation means 38. The "mouthpiece orthodontic plan" is not particularly limited, and various orthodontic plans may be set. For example, there are plans that target all teeth, including molars, and partial orthodontic plans. Examples of partial orthodontic plans include plans that target only the upper teeth, plans that target only the 2 to 6 front teeth of the upper teeth, plans that target only the upper and lower teeth (for example, 4 to 32 teeth, 4 to 24 teeth, or 4 to 12 teeth), plans that target the 12 front teeth of the upper and lower teeth, and plans that target the 24 front teeth of the upper and lower teeth.

[0044] The determination means 40 may determine whether orthodontic treatment is feasible for the subject or whether a predetermined mouthpiece orthodontic treatment plan is applicable, based on the shape of the arch drawn by the arch drawing means 36. For example, the determination of whether or not a mouthpiece orthodontic treatment plan is applicable may be made using a rule-based method that compares the arch curvature threshold set for each mouthpiece orthodontic treatment plan.

[0045] (Output means 42) The output means 42 transmits a display instruction signal to the display unit 52 to display the determination result made by the determination means 40 on the display unit 52 (for example, Figure 4, step S50). By displaying such determination results, it is possible to support the dentist in determining whether or not orthodontic treatment is possible for the subject.

[0046] The output means 42 may further display the subject's dental image and details of the judgment result along with the judgment result. Details of the judgment result may include, for example, the confidence level of the judgment by the trained model 200 and the object detection model 100, as well as the reason or cause of the judgment.

[0047] Even if the judgment result indicates that orthodontic treatment is not possible, the output means 42 may further suggest conditions under which orthodontic treatment would be possible. For example, the output means 42 may display on the display unit 52 that it is suggesting treatment for the missing tooth, silver filling, cavities, periodontal disease, or gingivitis that caused the judgment result.

[0048] The output means 42 may also send an instruction signal to the display unit 52 to output sound, light, or color according to the judgment result. For example, if the teeth cannot be corrected, the output means 42 may send an instruction signal to the display unit 52 to highlight the tooth image or teeth that caused the judgment result with color or the like.

[0049] (Object detection model generation means 44, trained model generation means 46) The object detection model generation means 44 and the trained model generation means 46 generate the object detection model 100 and the trained model 200 using machine learning with the training data 110 and 210, respectively. As described above, the learning method is not limited as long as "input" and "output (classification)" are possible. Thus, the trained model 200 and the object detection model 100 are not limited to those generated by an external device, but may also be generated on the server 3.

[0050] The trained model 200 and / or object detection model 100 may function by the control unit 30 executing a program stored in the storage unit 48, or by a device other than the server 3 executing a predetermined program.

[0051] If a dental image estimated by the estimation means 38 to be suitable for orthodontic treatment is determined by a dentist to be unsuitable for orthodontic treatment, that dental image may also be used to retrain the trained model 200 (e.g., fine-tuning, RLHF).

[0052] While R-CNN, SSD, YOLO, and others can be used as the base training models for the pre-trained model 200 and the object detection model 100, the YOLO model is preferred in terms of accuracy and speed.

[0053] [Information Processing Method 1] Next, with reference to Figure 4, the information processing method 1 in the information processing system 1 described above will be explained. Here, an example is shown in which a program for determining whether orthodontic treatment is possible from a dental image is executed on the server 3. In the following explanation, components with the same reference numerals are the same as the components described above, and redundant explanations will be omitted as appropriate. Note that the processing shown below is performed by executing a program stored in the storage unit 48, but the information processing method relating to this disclosure is not limited to this.

[0054] First, the control unit 30 (reception means 32) receives multiple dental images of the subject (see Figure 2) (step S10).

[0055] Next, the control unit 30 (estimation means 38) uses a trained model 200 generated by machine learning, which is created using training data 210 that includes images of teeth and information on whether the images include teeth that can be straightened, to estimate whether each of the multiple images of teeth includes teeth that can be straightened (step S20).

[0056] Next, the control unit 30 (determination means 40) determines whether or not orthodontic treatment is possible for the subject based on the estimation result of step S20 (step S30).

[0057] In this embodiment, if it is estimated that all dental images include dental arches that can be treated with orthodontics (step S30, "YES"), the control unit 30 (determination means 40) determines that orthodontic treatment is possible for the subject (step S40). In this case, the control unit 30 (output means 42) outputs this determination result, all dental images, and the confidence level for each dental image to the display unit 52 (step S50). Thus, the process is completed. In other words, a final confirmation is made by the dentist.

[0058] On the other hand, if it is estimated that even one of the multiple dental images does not contain any teeth that can be straightened (step S30, "NO"), the control unit 30 (determination means 40) determines that orthodontic treatment is not possible for the subject (step S60). In this case, the control unit 30 (output means 42) outputs this determination result, all dental images, the confidence level for each dental image, and the reason for the determination result to the display unit 52 (step S70). Thus, the process ends.

[0059] [Information Processing Method 2] Next, with reference to Figure 5, we will explain information processing method 2 in information processing system 1. Information processing method 2 is an example in which, on server 3, a dental image is acquired from dental scan data and a program is executed to determine the suitability of the clear aligner orthodontic treatment plan. Repetitive explanations will be omitted as appropriate.

[0060] First, the control unit 30 (reception means 32) receives the subject's dental arch scan data from the 3D scanner 2 (step S100).

[0061] Next, the control unit 30 (image processing means 34) processes the received tooth scan data to generate a plurality of tooth images (Figures 2(a) to (f)) including a tooth image of the subject's upper teeth, a tooth image of the lower teeth, and a tooth image of the upper and lower teeth taken at an angle from diagonally below (step S110).

[0062] Next, the control unit 30 (image processing means 34) generates an integrated dental image (Figure 2(g)) by combining multiple dental images (step S120).

[0063] Next, the control unit 30 (arch drawing means 36) uses an object detection model 100 generated by machine learning using training data 110 which includes images of the upper and lower teeth to detect and classify teeth in the upper and lower teeth images of the subject, and draws an arch showing the alignment of the teeth (step S130).

[0064] Next, the control unit 30 (estimation means 38) uses the trained model 200 to estimate whether each of the multiple dental images obtained in step S110 and the integrated dental image obtained in step S120 contains dental arches that can be orthodontized (step S140).

[0065] Next, the control unit 30 (determination means 40) determines whether or not orthodontic treatment is possible for the subject based on the estimation result in step S140 and the arch shape acquired in step S130 (step S150).

[0066] In this embodiment, if it is estimated that all dental images include dental arches that can be treated with orthodontics (step S150, "YES"), the control unit 30 (determination means 40) determines that orthodontic treatment is possible for the subject (step S160).

[0067] Next, the control unit 30 (determination means 40) determines, based on the arch shape acquired in step S130, that a predetermined mouthpiece orthodontic plan can be applied (step S170).

[0068] Next, the control unit 30 (output means 42) outputs the determination result (including applicable orthodontic plans), all dental arch images (including arches), and the confidence level for each dental arch image to the display unit 52 (step S180). Thus, the process is completed.

[0069] On the other hand, if it is estimated that even one of the multiple dental images does not contain a dental arch that can be straightened (step S150, "NO"), the control unit 30 (determination means 40) determines that orthodontic treatment is not possible for the subject (step S190). In other embodiments, if the arch shape obtained in step S130 shows an abnormal value, the determination that orthodontic treatment is not possible may be made based solely on the information obtained in step S130.

[0070] Next, the control unit 30 (output means 42) outputs the determination result, all the dental images, the confidence level for each dental image, and the reason for the determination result to the display unit 52 (step S200). Thus, the process is completed.

[0071] The above-described information processing method is just one example, and the processing flow is not limited to what is described above. For example, the step of drawing the arch (step S130) may be performed before the step of generating the integrated dental arch image (step S120).

[0072] In another embodiment, instead of the step of determining whether orthodontic treatment is feasible for the subject (steps S150-S160), a determination step of determining whether a specific clear aligner treatment plan is applicable may be performed. In this case, images of teeth and / or arch shapes (curvature) that fit a predetermined clear aligner treatment plan may be used as training data 210 used to generate the trained model 200. In another embodiment, the feasibility of applying multiple clear aligner treatment plans may be estimated and determined simultaneously or sequentially. In this case, a trained model 200 will be created for each treatment plan. Furthermore, if it is determined that all treatment plans are not applicable, a step of determining that orthodontic treatment is not possible for the subject (step S190) may be performed.

[0073] The information processing system 1, computer (server 3), program, and information processing method according to this disclosure, having the configuration described above, is provided with a receiving means 32, an estimation means 38, and a determination means 40. The receiving means 32 receives multiple dental images of a subject. The estimation means 38 uses a trained model 200 generated by machine learning using training data 210 which includes dental images and information on whether the images contain teeth that can be orthodontally straightened, to estimate whether each of the multiple dental images contains teeth that can be orthodontally straightened. The determination means 40 determines whether orthodontic treatment is possible for the subject based on the estimation result by the estimation means 38. With such an information processing system 1, computer (server 3), program, and information processing method according to this disclosure, it is possible to efficiently and accurately support a dentist in determining whether orthodontic treatment is possible.

[0074] Furthermore, in the information processing system 1, computer (server 3), program, and information processing method relating to this disclosure, the determination means 40 may determine whether or not a predetermined mouthpiece orthodontic plan is applicable based on the estimation result by the estimation means 38. In this way, the number of training data 210 prepared to generate a trained model 200 in accordance with a specific mouthpiece orthodontic plan can be reduced.

[0075] Furthermore, the information processing system 1, computer (server 3), program, and information processing method relating to this disclosure may also include an image processing means 34. In this case, the receiving means 32 receives the subject's dental scan data, and the image processing means 34 processes the dental scan data received by the receiving means 32 to generate and acquire multiple dental images. In this way, a series of data processing can be completed on a single computer (server 3).

[0076] Furthermore, in the information processing system 1, computer (server 3), program, and information processing method relating to this disclosure, the image processing means 34 may process the dental scan data received by the reception means 32 to generate a dental image in which the subject's upper and lower dental arches are captured at an angle from diagonally below. Processing the dental scan data in this way increases the number of features for estimating orthodontic treatment using the trained model 200, which is preferable because it allows for more accurate estimation processing.

[0077] Furthermore, in the information processing system 1, computer (server 3), program, and information processing method related to this disclosure, the estimation means 38 can also estimate whether or not a combined dental arch image, which is a combination of multiple dental arch images, contains teeth that can be treated with orthodontics. By providing a combined dental arch image in this way, areas that might be overlooked in dental arch images viewed from a specific direction can be comprehensively included in the estimation target, and the estimation process can be performed with even greater accuracy.

[0078] Furthermore, in the information processing system 1, computer (server 3), program, and information processing method related to this disclosure, an arch drawing means 36 may be further provided that uses an object detection model 100 generated by machine learning using training data 110 including images of the upper and lower teeth to detect and classify teeth in each image of the subject's upper and lower teeth as part of multiple dental images, and draw an arch showing the alignment of the teeth. In this way, the determination means 40 can determine with even greater accuracy whether orthodontic treatment is possible for the subject or whether a predetermined mouthpiece orthodontic treatment plan is applicable, based on the shape of the arch.

[0079] Furthermore, the information processing system 1, computer (server 3), program, and information processing method related to this disclosure are not limited to the forms or combinations described above, and can be modified in various ways. [Explanation of Symbols]

[0080] 1. Information Processing System (AI Orthodontic Treatment Feasibility Determination Support System) 2 3D scanners 21 Imaging Department 22 Communications Department 3. Server (computer) 30 Control Unit 32 Reception methods 34 Image processing means 36 Arch drawing means 38 Estimation means 40 Judgment means 42 Output means 44 Object detection model generation means 46. ​​Means for generating trained models 48 Memory section 50 Communications Department 52 Display section 54 Operation section 100 Object Detection Models 110 Training Data 200 pre-trained models 210 Training Data

Claims

1. A program that causes a computer to function as a receiving means, an estimation means, and a determination means, The aforementioned reception means receives multiple dental images of the subject, The estimation means uses a trained model generated by machine learning, which includes images of teeth and information on whether the images contain teeth that can be straightened, to estimate whether each of the multiple images of teeth contains teeth that can be straightened. The determination means is a program that determines whether or not orthodontic treatment is possible for the subject based on the estimation result by the estimation means.

2. The program according to claim 1, wherein the determination means determines whether or not a predetermined mouthpiece orthodontic plan is applicable based on the estimation result by the estimation means.

3. The aforementioned computer is further made to function as an image processing means, The reception means receives the dental arch scan data of the subject, The program according to claim 1, wherein the image processing means processes the dental scan data received by the receiving means to generate a plurality of dental images.

4. The program according to claim 3, wherein the image processing means processes the dental scan data received by the receiving means to generate a dental image in which the upper and lower dental arches of the subject are captured at an angle from diagonally below.

5. The program according to claim 1 or 4, wherein the estimation means estimates whether or not a combined dental image obtained by combining a plurality of dental images includes dental arches that can be orthodontized.

6. The aforementioned computer is further made to function as an arch drawing means, The arch drawing means uses an object detection model generated by machine learning using training data including images of the upper and lower teeth to detect and classify teeth in each of the subject's upper and lower teeth images as part of a plurality of the teeth images, and draws an arch showing the teeth. The program according to claim 1, wherein the determination means determines, based on the shape of the arch, whether orthodontic treatment is possible for the subject or whether a predetermined mouthpiece orthodontic treatment plan is applicable.

7. A computer that functions as a reception means, an estimation means, and a determination means by executing a program, The aforementioned reception means receives multiple dental images of the subject, The estimation means uses a trained model generated by machine learning, which includes images of teeth and information on whether the images contain teeth that can be straightened, to estimate whether each of the multiple images of teeth contains teeth that can be straightened. The determination means is a computer that determines whether or not orthodontic treatment is possible for the subject based on the estimation result by the estimation means.

8. An information processing method performed by a computer having a control unit, The control unit performs the steps of receiving multiple dental images of the subject, The control unit performs the following steps: estimate whether each of the multiple dental images contains teeth that can be orthodontized, using a trained model generated by machine learning by using training data that includes images of teeth and information on whether the images contain teeth that can be orthodontized; The control unit performs the step of determining whether orthodontic treatment is feasible for the subject based on the estimation result, An information processing method equipped with [a specific feature].

Images