KR-20260062883-A - METHOD AND APPARATUS FOR DETECTING AREAS OF INTEREST IN AN AI-BASED ORAL SCAN MODEL

KR20260062883AKR 20260062883 AKR20260062883 AKR 20260062883AKR-20260062883-A

Abstract

An oral scanning device for detecting regions of interest can obtain three-dimensional oral scan data by scanning a user's oral cavity. Based on the three-dimensional oral scan data, the oral scanning device can extract multiple features including surface shape, texture, brightness, and scan reliability information. Based on the extracted multiple features, the oral scanning device can detect regions of interest within the three-dimensional oral scan data, including areas with a high probability of being missed during scanning and areas suspected of having cavities.

Inventors

전승현
김경국
최윤수

Assignees

아크리얼 주식회사

Dates

Publication Date: 20260507
Application Date: 20251029
Priority Date: 20241029

Claims (14)

In an oral scanning method performed by at least one device, A step of scanning the user's oral cavity to acquire 3D oral scan data; A step of extracting a plurality of features including surface shape, texture, brightness, and scan reliability information based on the above 3D oral scan data; and Based on the plurality of features extracted above, the method includes the step of detecting a region of interest within the 3D oral scan data, including a region with a high probability of being missed in the scan and a region suspected of having caries. Oral scanning region of interest detection method.
In claim 1, The above region of interest includes at least one of a biological reference region and a non-biological reference region, and The above biological reference region is, It includes at least one of an area with a high probability of being missed during scanning, an area suspected of tooth decay, and an area of surface non-uniformity, The above-mentioned non-biological reference region is, including at least one of a prosthetic prep site, an implant placement site, and a gingival margin, Oral scanning region of interest detection method.
In claim 1, Step of collecting voice data during the medical treatment process; A step of converting the above voice data into text data; A step of extracting dental terms from the above character data; and The method further comprises the step of adding a specific oral region corresponding to the extracted dental term as the region of interest. Oral scanning region of interest detection method.
In claim 1, A step of acquiring at least one of a first signal input, a second signal input, and a third signal input; and A step further comprising performing different operations in response to each of the above input signals, Oral scanning region of interest detection method.
In claim 4, Based on one of the first, second, and third signal inputs above, While moving the camera to the area of interest or a group including the area of interest, the distance, angle, and field of view of the camera are adjusted in consideration of the size and screen resolution of the area of interest, and By controlling the camera's line of sight or orientation based on the surface normal vector of the region of interest, the region of interest is recognized as facing forward in the camera image, and The method further includes the step of visually highlighting the aforementioned area of interest through color change, border highlighting, or transparency adjustment. Oral scanning region of interest detection method.
In claim 5, A step of dividing the screen into multiple regions to simultaneously display the region of interest from different viewing angles; The above plurality of regions includes at least one of the maxillary direction, lateral direction, anterior direction, or mandibular direction; and A step comprising controlling rotation, enlargement, or movement operations performed on one screen among the plurality of areas to be synchronized and reflected on other split screens, Oral scanning region of interest detection method.
In claim 6, A step of obtaining an input for selecting one of automatic viewing mode or manual operation mode; A step in which, when automatic viewing mode is selected, rotation, movement, and field of view adjustment of the camera for the area of interest or group are automatically performed; In the above automatic viewing mode, when input of the single button is detected, a step of temporarily stopping the automatic rotation or automatic viewing angle movement; and A step comprising resuming the automatic rotation or automatic view movement at the time when the above single button input ends, Oral scanning region of interest detection method.
In an oral scanning device for detecting a region of interest, the oral scanning device comprises at least one processor and a memory storing at least one instruction executed by the processor, and the at least one instruction is Scan the user's oral cavity to acquire 3D oral scan data; Based on the above 3D oral scan data, a plurality of features including surface shape, texture, brightness, and scan reliability information are extracted; and Based on the plurality of features extracted above, configured to detect a region of interest including an area with a high probability of being missed in the scan and an area suspected of having cavities within the 3D oral scan data, Oral scanning region of interest detection device.
In claim 8, The above region of interest includes at least one of a biological reference region and a non-biological reference region, and The above biological reference region is, It includes at least one of an area with a high probability of being missed during scanning, an area suspected of tooth decay, and an area of surface non-uniformity, The above-mentioned non-biological reference region is, including at least one of a prosthetic prep site, an implant placement site, and a gingival margin, Oral scanning region of interest detection device.
In claim 8, The above at least one command is, Collecting voice data during the medical treatment process; Convert the above voice data into text data; Extract dental terms from the above character data; and Set to add a specific oral region corresponding to the extracted dental term above as the region of interest, Oral scanning region of interest detection device.
In claim 8, The above at least one command is, Acquiring at least one of a first signal input, a second signal input, and a third signal input; and Set to perform different operations in response to each of the above input signals, Oral scanning region of interest detection device.
In claim 11, The above at least one command is, Based on one of the first, second, and third signal inputs above, While moving the camera to the area of interest or a group including the area of interest, the distance, angle, and field of view of the camera are adjusted in consideration of the size and screen resolution of the area of interest, and By controlling the camera's line of sight or orientation based on the surface normal vector of the region of interest, the region of interest is recognized as facing forward in the camera image, and The above area of interest is set to be visually highlighted through color change, border highlighting, or transparency adjustment, Oral scanning region of interest detection device.
In claim 12, The above at least one command is, Dividing the screen into multiple regions to simultaneously display the region of interest from different viewing angles; The above plurality of regions includes at least one of the maxillary direction, lateral direction, anterior direction, or mandibular direction; and A control configured to ensure that rotation, zoom, or movement operations performed on one of the aforementioned multiple areas are synchronized and reflected on other split screens. Oral scanning region of interest detection device.
In claim 13, The above at least one command is, Acquire an input for selecting either automatic viewing mode or manual operation mode; When automatic viewing mode is selected, rotation, movement, and field of view adjustment of the camera for the area of interest or group are performed automatically; In the above automatic viewing mode, when input from the single button is detected, the automatic rotation or automatic viewing angle movement is temporarily paused; and Set to resume the automatic rotation or automatic view movement at the time when the above single button input ends, Oral scanning region of interest detection device.

Description

Method and apparatus for detecting areas of interest in an AI-based oral scan model This specification relates to the field of oral scanner technology used in dental treatment processes. More specifically, it relates to a method and apparatus for detecting a region of interest in an artificial intelligence-based oral scan model, which uses an artificial intelligence algorithm to automatically detect a region of interest from a three-dimensional oral scan model obtained from an oral scanner, provides visual feedback on the detected region of interest, and enables the selection or exploration of the region of interest. Conventional oral scanner systems have mainly used a method of optically scanning the inside of a patient's oral cavity to create a 3D model, and allowing the user to view the 3D model on a monitor through operations such as rotation, enlargement, and reduction. Conventional oral scanner systems have an inefficient inspection process because users must manually locate regions of interest (e.g., areas that may be missed, areas with surface irregularities, etc.) within the scanned 3D model. In particular, it is difficult to accurately locate specific areas due to the complex structure and limited field of view inside the oral cavity. Furthermore, precise control is difficult when relying solely on scanner movement to rotate or move the model. Gyro sensor-based control is limited to rotation and struggles to naturally perform zoom or pan functions. As a result, users must perform repetitive operations to position the model at the desired angle. Due to such problems, there is a growing need for technology that can automatically identify regions of interest within a scanned 3D oral model and rapidly navigate those regions with only simple button input on the scanner itself. The present invention aims to overcome the limitations of such conventional technology. FIG. 1 is a system diagram including an oral scanning device for detecting a region of interest according to one embodiment of the present specification. FIG. 2 is a configuration diagram showing a single-button input pattern and function of a scanner in one embodiment of the present specification. FIG. 3 is a flowchart illustrating a camera adjustment algorithm during automatic viewing according to one embodiment of the present specification. FIG. 4 is a drawing illustrating a multi-viewing-angle display through screen splitting according to one embodiment of the present specification. FIG. 5 is a flowchart illustrating a method for stopping rotation and switching to manual operation via a scanner button during automatic viewing according to one embodiment of the present specification. FIG. 6 is a flowchart illustrating a method for detecting a region of interest in an artificial intelligence-based oral scan model according to one embodiment of the present specification. As the present specification is susceptible to various modifications and may have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present specification to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the present specification. Similar reference numerals have been used for similar components in the description of each drawing. Terms such as first, second, A, B, etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the rights of this specification, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and/or" includes a combination of a plurality of related described items or any of a plurality of related described items. When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. The terms used in this application are used merely to describe specific embodiments and are not intended to limit this specification. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to indicate the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other