WO2023247565A1 - Verfahren zum bestimmen von zahncharakteristika aus einem zahnbild - Google Patents
Verfahren zum bestimmen von zahncharakteristika aus einem zahnbild Download PDFInfo
- Publication number
- WO2023247565A1 WO2023247565A1 PCT/EP2023/066684 EP2023066684W WO2023247565A1 WO 2023247565 A1 WO2023247565 A1 WO 2023247565A1 EP 2023066684 W EP2023066684 W EP 2023066684W WO 2023247565 A1 WO2023247565 A1 WO 2023247565A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- tooth
- processing model
- image
- learning
- data set
- Prior art date
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C19/00—Dental auxiliary appliances
- A61C19/04—Measuring instruments specially adapted for dentistry
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
- A61B5/4542—Evaluating the mouth, e.g. the jaw
- A61B5/4547—Evaluating teeth
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C9/00—Impression cups, i.e. impression trays; Impression methods
- A61C9/004—Means or methods for taking digitized impressions
- A61C9/0046—Data acquisition means or methods
- A61C9/0053—Optical means or methods, e.g. scanning the teeth by a laser or light beam
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- the present invention relates to a method for determining tooth characteristics from a tooth image.
- Biofilm is a film that, if not removed, can cause dental diseases such as tooth decay. Regular removal, for example with a toothbrush, is therefore strongly recommended.
- the contrast agent fluorescein is known to fluoresce when illuminated by, for example, UV/blue light.
- US 2020/0201266 A1 shows a cleaning device for a household.
- This cleaning device can be designed for a wide variety of applications, such as cleaning a floor of a building, shaving a human body or cleaning teeth.
- This cleaning device can have a neural network with which different properties of an image of the object to be cleaned can be determined, such as the color of teeth, in order to be able to influence the cleaning process.
- US 2020/0146794 A1 describes an intelligent toothbrush that has a camera with which images of the teeth to be brushed can be captured. Using a neural network, the images can be evaluated to determine whether the teeth have plaque or tartar or whether there is inflammation in the oral cavity. The cleaning process with the toothbrush is adjusted accordingly.
- the invention is based on the object of creating a method for recognizing teeth simply, reliably and automatically.
- the task is solved by the subjects of the independent claims.
- Advantageous developments and preferred embodiments form the subject of the subclaims.
- a method for generating tooth characteristics includes providing a processing model, capturing at least one tooth image of a tooth, and calculating the tooth characteristics from the tooth images using the processing model.
- the processing model was trained using a data set.
- the data set includes at least one learning tooth image and one learning tooth characteristics, which are linked to one another.
- the tooth characteristics include at least boundaries of one or more teeth in the tooth image.
- Boundaries of teeth show a similar representation in the tooth image across multiple tooth images. This makes it particularly suitable for machine learning.
- the trained processing model learned where the boundaries of the teeth are typically located in the image.
- the processing model can be based on certain markers in the image, such as individual teeth that are visible with greater contrast in the original tooth image.
- the finest differences in brightness in the gray levels are evaluated as a limitation by the processing model, provided they fit into the entire boundary contour of the teeth.
- teeth especially of the same types of teeth, are similar across multiple tooth images.
- an incisor tooth is similar to another user's incisor tooth.
- the respective differences can then be recognized very easily using the machine learning processing model.
- tooth characteristics can also be recognized from tooth images, even if no specialist personnel evaluate the images.
- the method is very suitable for machine learning.
- the inventors have recognized, unlike the prior art discussed above in which machine learning systems are used to analyze images of an oral cavity for plaque, gingivitis, and the like, that due to the similar shape of teeth in different people, a machine learning system is very precise and reliable can recognize the boundary between tooth and gum, even if the optical conditions are not optimal due to the system. Clear identification of the boundary between the teeth and gums significantly increases the quality of oral cleaning.
- Tooth characteristics are data that describe certain features of a tooth.
- tooth characteristics are an image file with the same dimensions as the tooth image, where this image only contains binary data, for example 0 indicating that there is no tooth at this location and a 1 indicating that there is a tooth here. Depending on the presentation, such an image would appear as a black contour drawing of the tooth.
- the generated image of the tooth characteristics corresponds to the tooth image.
- Biofilm, plaque, dental plaque and dental dirt are synonymous within the scope of this application. They describe a substance that adheres to the teeth and usually contains saliva, bacteria and food particles.
- the tooth images are binary images.
- the tooth images are reconstructed before being input into the processing model.
- the reconstruction may include at least one of the following features:
- the tooth characteristics preferably represent boundaries of the tooth in the tooth image, in particular in relation to the gums and/or the tongue.
- the recognition of tooth characteristics may include a method for matching and/or classification or categorization of color aid programs. According to a preferred development, when the tooth characteristics are recognized by a machine learning algorithm, in particular a segmentation model is used for the area recognition of the tooth.
- a model can be used for object recognition. This includes a bounding box model and/or a model for tooth coordinate recognition.
- an algorithm for threshold value determination in particular an HSV, RGB, YCBCR, LAB threshold value determination, is used. Sections of the image can be highlighted using different colors.
- segmentation model could also be used to assign features or characteristics to areas.
- An area detection is carried out here. This is interesting, for example, when the characteristics have clearly defined boundaries, as is the case with tooth decay, for example.
- the tooth characteristics include features of the teeth, such as tooth discoloration, implants, de-mineralized areas, caries, etc.
- the tooth characteristics can be used in combination with the tooth image, which represents dental plaque, to create a map of the tooth in which not only the dental plaque but also the boundaries of the teeth are shown. This allows the plaque to be localized very precisely on the individual teeth and a cleaning process to be controlled accordingly.
- a tooth map with the boundary and the dental plaque can be used, for example, to appropriately control a tooth cleaning device, as described for example in the German patent application DE 102022 102 045.2, for cleaning the teeth.
- the tooth image is generated using a tooth dirt detection device.
- the contrast agent fluorescein has a fluorescence with the strongest intensity at 520 to 530 nm when excited with light with a wavelength of 465 to 500 nm.
- the very close wavelength spectrum of the exciting and emitted light leads to a signal-to-noise ratio that is too low in standard intraoral camera units of a dental dirt detection device to ensure reliable detection. Reflections that occur due to focused lighting solutions and blurry images from the camera unit are currently only compensated for with interoral cameras on the market by a greater distance from the tooth to the sensor unit.
- the dental dirt detection device preferably has a light filter to allow light with wavelengths between 480 nm to 530 nm to pass.
- an optical long-pass filter is preferably placed directly in front of the camera of the dental dirt detection device, which ideally has a cutoff wavelength of 480 nm to 530 nm and in particular about 510 nm and cuts off signals below this. Additionally, a bandpass or shortpass filter can be placed in front of the LEDs that illuminate the area to be detected in order to limit/focus the wavelength spectrum of the LEDs.
- a circular polarizer can also be used.
- an additional parameter can be taken into account to determine the tooth characteristics.
- the processing model can generate better tooth characteristics if, for example, the tooth type (such as an incisor) is known.
- An incisor tooth differs in shape from, for example, a molar.
- the machine learning is supervised machine learning.
- the processing model is trained on a data set by a machine learning algorithm.
- the data set includes at least one learning tooth image and at least one learning tooth characteristics, which are linked to one another.
- the processing model is improved by the processing model generating a learning tooth image of target tooth characteristics and then using a target algorithm to determine a measure of how much the target tooth characteristics and the learning tooth characteristics differ.
- the processing model is adjusted based on the specific measurement.
- a computer program product includes instructions that, when the program is executed by a computer, cause it to carry out the method described above.
- Figure 2 Block diagram of a system for determining
- FIG. 3b Block diagram of a system for the use of a
- the learning unit 2 includes a machine learning module 6, which is designed to use assignments 7 of tooth images 5 to learning tooth characteristics 8 in order to generate a processing model 9 therefrom.
- the learning unit 2 and the execution unit 3 are two different computers connected to each other via a computer network to exchange the processing model 9.
- the learning unit 2 and the execution unit 3 are mapped by the same computer.
- the tooth dirt detection device 4 preferably communicates wirelessly with the execution unit 3, for example via WLAN. However, wire-based communication is also conceivable.
- Tooth dirt detection device 4 is described in detail in the unpublished German patent application DE 10 2022 102 045.2 and this patent application is incorporated by reference in its entirety.
- the tooth dirt detection device 4 is designed such that a U-shaped section of the tooth dirt detection device 4 is introduced into the mouth of a user.
- the U-shaped section of the dental dirt detection device 4 has a sensor arrangement.
- a detection liquid is introduced into the oral cavity before the detection process.
- the detection fluid interacts with the biofilm and causes the biofilm to glow at another predetermined wavelength under the influence of light with a predetermined wavelength.
- the detection liquid is arranged in a detection capsule which can be inserted into the dental dirt detection device 4. The detection device then removes the detection liquid and pumps it onto the teeth.
- the tooth dirt detection device 4 consists of a handpiece, which can have a display on the side facing away from the user. On the side facing the user there is a mouthpiece that is inserted into the oral cavity and guides the sensor unit over the teeth.
- the mouthpiece has at least one camera unit with a camera.
- the camera unit alone has the dimensions 1x1x2, 7 mm and the entire sensor unit, including a protective glass, PCB (printed circuit board), filter and camera holder, has a diameter of 8 mm and a height of 3.8 mm. With these dimensions, the unit can be easily guided into an oral cavity.
- PCB printed circuit board
- an optical long-pass filter is preferably placed directly in front of the camera, which ideally has a cutoff wavelength of around 510 nm and cuts off signals below that.
- a bandpass or shortpass filter can be placed in front of the LEDs that illuminate the area to be detected in order to limit the wavelength spectrum of the LEDs.
- step S1 ( Figure 4).
- Tooth images 5 are manually assigned to tooth characteristics 11. Tooth images 5 are images of teeth that were recorded by a tooth dirt detection device 4. They typically show strong signal-to-noise ratios of dental plaque, but the demarcation of teeth, here tooth characteristics 11 , are very difficult to recognize. However, specialist personnel are able to determine these boundaries manually.
- an empty processing model 9 is initially used, which here consists of a neural network.
- empty means that the neural network has not yet been trained with any data, but contains the necessary basics and is ready to learn.
- step S4 in which the processing model 9 is transferred from the learning unit 2 to the execution unit 3.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Animal Behavior & Ethology (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Dentistry (AREA)
- Biophysics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Fuzzy Systems (AREA)
- Physical Education & Sports Medicine (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Radiology & Medical Imaging (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Rheumatology (AREA)
- Optics & Photonics (AREA)
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
- Image Analysis (AREA)
- Endoscopes (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2024575266A JP2025520657A (ja) | 2022-06-21 | 2023-06-20 | 歯の画像から歯の特徴を判定する方法 |
EP23734225.8A EP4543362A1 (de) | 2022-06-21 | 2023-06-20 | Verfahren zum bestimmen von zahncharakteristika aus einem zahnbild |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102022115398.3A DE102022115398A1 (de) | 2022-06-21 | 2022-06-21 | Verfahren zum Bestimmen von Zahncharakteristika aus einem Zahnbild |
DE102022115398.3 | 2022-06-21 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023247565A1 true WO2023247565A1 (de) | 2023-12-28 |
Family
ID=87003087
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2023/066684 WO2023247565A1 (de) | 2022-06-21 | 2023-06-20 | Verfahren zum bestimmen von zahncharakteristika aus einem zahnbild |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP4543362A1 (de) |
JP (1) | JP2025520657A (de) |
DE (1) | DE102022115398A1 (de) |
WO (1) | WO2023247565A1 (de) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200146794A1 (en) | 2018-11-08 | 2020-05-14 | SangGeun Lee | Oral information management system using smart toothbrush |
US20200179089A1 (en) | 2016-08-22 | 2020-06-11 | Kolibree SAS | Oral Hygiene System for Compliance Monitoring and Tele-Dentistry System |
US20200201266A1 (en) | 2018-12-21 | 2020-06-25 | The Procter & Gamble Company | Apparatus and method for operating a personal grooming appliance or household cleaning appliance |
US20210393026A1 (en) | 2020-06-22 | 2021-12-23 | Colgate-Palmolive Company | Oral Care System and Method for Promoting Oral Hygiene |
US20220189611A1 (en) * | 2020-12-11 | 2022-06-16 | Align Technology, Inc. | Noninvasive multimodal oral assessment and disease diagnoses apparatus and method |
DE102022102045A1 (de) | 2022-01-28 | 2023-08-03 | epitome GmbH | Vorrichtung und Verfahren zur Erfassung von Biofilm im Mundraum |
-
2022
- 2022-06-21 DE DE102022115398.3A patent/DE102022115398A1/de active Pending
-
2023
- 2023-06-20 EP EP23734225.8A patent/EP4543362A1/de active Pending
- 2023-06-20 JP JP2024575266A patent/JP2025520657A/ja active Pending
- 2023-06-20 WO PCT/EP2023/066684 patent/WO2023247565A1/de active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200179089A1 (en) | 2016-08-22 | 2020-06-11 | Kolibree SAS | Oral Hygiene System for Compliance Monitoring and Tele-Dentistry System |
US20200146794A1 (en) | 2018-11-08 | 2020-05-14 | SangGeun Lee | Oral information management system using smart toothbrush |
US20200201266A1 (en) | 2018-12-21 | 2020-06-25 | The Procter & Gamble Company | Apparatus and method for operating a personal grooming appliance or household cleaning appliance |
US20210393026A1 (en) | 2020-06-22 | 2021-12-23 | Colgate-Palmolive Company | Oral Care System and Method for Promoting Oral Hygiene |
US20220189611A1 (en) * | 2020-12-11 | 2022-06-16 | Align Technology, Inc. | Noninvasive multimodal oral assessment and disease diagnoses apparatus and method |
DE102022102045A1 (de) | 2022-01-28 | 2023-08-03 | epitome GmbH | Vorrichtung und Verfahren zur Erfassung von Biofilm im Mundraum |
Also Published As
Publication number | Publication date |
---|---|
EP4543362A1 (de) | 2025-04-30 |
DE102022115398A1 (de) | 2023-12-21 |
JP2025520657A (ja) | 2025-07-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE69918549T2 (de) | Gerät zur feststellung von zahnbelag mittels fluoreszenzmessung | |
US9870613B2 (en) | Detection of tooth condition using reflectance images with red and green fluorescence | |
DE112012004064B4 (de) | Diagnosesystem | |
EP2914201B1 (de) | Verfahren zur ermittlung mindestens eines relevanten einzelbildes eines dentalen objekts | |
DE102012021185A1 (de) | Verfahren zur optischen 3D-Vermessung von Zähnen mit verkleinerter Point-Spread-Funktion | |
CH680187A5 (de) | ||
EP2786696A1 (de) | Dentalkamerasystem | |
DE102022102045B4 (de) | Vorrichtung und Verfahren zur Erfassung von Biofilm im Mundraum | |
US20240138665A1 (en) | Dental imaging system and image analysis | |
DE602004009875T2 (de) | Verfahren zur Bildverarbeitung für Profilbestimmung mittels strukturiertem Lichts | |
DE102007014413B4 (de) | Verfahren zum Auswerten von Fluoreszenzbildsätzen und Vorrichtung zu seiner Durchführung | |
DE102009023952A1 (de) | Verfahren und Vorrichtung zur Bestimmung von Zahnfarben | |
DE60132701T2 (de) | System zur farbabstimmung | |
WO2023247565A1 (de) | Verfahren zum bestimmen von zahncharakteristika aus einem zahnbild | |
DE2450112B2 (de) | Verfahren und Anordnung zur zerstörungsfreien Analyse biologischer Zellen einer mindestens zwei unterschiedliche, Licht bekannter Wellenlange unterschiedlich stark absorbierende Zellen typen in zueinander festgelegter Lage enthaltenden Probe | |
DE112020004617T5 (de) | Endoskopsystem | |
DE20209441U1 (de) | Vorrichtung zum Erkennen von bakteriellem Befall an Zähnen | |
DE102019113283B4 (de) | Vorrichtung zur Abbildungserzeugung von Hautläsionen | |
EP4186469A1 (de) | Periodontalhandgerät | |
DE19724421C2 (de) | Verfahren und Vorrichtung zur quantitativen Bestimmung von dentaler Plaque | |
EP1269909A1 (de) | Verfahren und eine Vorrichtung zum Erkennen von krankhaften Veränderungen an einer Gewebeoberfläche, insbesondere Zähnen | |
EP4477136A1 (de) | Verfahren und system zur erkennung von zahnbelag | |
DE102017204500A1 (de) | "Verfahren und Anordnung zum Ermitteln einer nicht-therapeutischen Behandlung von Zähnen" | |
DE102022115396A1 (de) | Verfahren zum Reinigen von Zähnen und Reinigungssystem | |
DE10232682B4 (de) | Verfahren und Vorrichtung zum nichtmagnetischen Identifizieren von Lebewesen sowie Verwendung derselben |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23734225 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2024575266 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023734225 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2023734225 Country of ref document: EP Effective date: 20250121 |
|
WWP | Wipo information: published in national office |
Ref document number: 2023734225 Country of ref document: EP |