System and method for oral examination

Abstract

A dentine-enamel boundary detection system for an oral examination device is provided. The dentin-enamel boundary detection system includes: a light emitting module configured to emit light to illuminate an oral region of interest; two optical filters having different respective passbands, each of the two filters arranged to filter a portion of the fluorescent light emitted from the oral cavity structure in the oral cavity region of interest to pass through the filtered fluorescent light; and a sensor module configured to detect the filtered fluorescence and output corresponding sensor data. The system also includes a processor module configured to identify the presence of a dentine-enamel boundary in the region of interest of the oral cavity by processing the sensor data output by the sensor module.

Description

Technical Field

[0001] The present invention generally relates to devices and methods for oral examination, and in particular for examination of oral structures. In particular, but not exclusively, the present disclosure relates to a dentin-enamel boundary system for detecting the dentin-enamel boundary of teeth, which can be used to identify spaces between teeth and / or assess oral health, and also to devices incorporating such a system, and uses of such a system. Background Art

[0002] Various systems that include cameras for oral examination are known (sometimes referred to as "dental intraoral camera systems"). These devices are typically used to image a patient's teeth, gums, or other oral structures in a medical setting, such as to identify one or more oral structures, such as teeth, or to distinguish between abnormal and healthy dental surfaces by identifying plaque or caries on or in the teeth to determine whether one or more treatments should be performed on the oral structure.

[0003] However, there are many problems to overcome regarding the use of conventional imaging systems for oral examinations. One major problem is that in the user's oral environment, especially during tooth cleaning, there may be a variety of obscuring media: for example, water, saliva, toothpaste, and foam. Therefore, when such obstructions are present, it may be more difficult to accurately identify or distinguish different oral structures in the user's mouth.

[0004] In practice, it may be particularly desirable to be able to detect interdental spaces between a user's teeth, for example, to observe the health of teeth near the location of the interdental spaces, or to perform treatment on the interdental spaces. In view of the above-mentioned problems associated with visual identification of interdental spaces due to possible obstructions in the oral environment, interdental detection systems typically require physical probing or direct contact with the user's teeth in order to identify interdental spaces.

[0005] For example, EP3888589A1 discloses an interdental space detection component for an interdental care device, which includes an interdental probe that can be inserted into the user's mouth for interdental space detection. In this example, an optical detector can be used to determine the light intensity on either side of the probe, and thus derive the intensity distribution with respect to the distance from the teeth. That is, the probe needs to be in close contact with the teeth to provide an indication of whether the probe is in the interdental space, and time series data is required to determine the probe position.

[0006] It would be desirable to provide a solution for identifying interdental spaces that does not require physical interaction with the user's teeth, is capable of providing information at a given point in time, and is capable of satisfactorily identifying spaces even in the presence of one or more obscuring media.

[0007] The present invention has been designed in view of the above considerations. Summary of the invention

[0008] According to a first aspect of the present invention, there is provided a dentin-enamel boundary detection system for an oral inspection device, the dentin-enamel boundary detection system comprising: a light emitting module configured to emit light to illuminate an oral area of ​​interest; two optical filters having different corresponding passbands, each of the two optical filters being arranged to filter a portion of fluorescence emitted from an oral structure (e.g., a tooth) in the oral area of ​​interest to pass the filtered fluorescence; and a sensor module configured to detect the filtered fluorescence and output corresponding sensor data; wherein the system further comprises a processor module, the processor module being configured to identify the presence of a dentin-enamel boundary in the oral area of ​​interest by processing the sensor data output by the sensor module.

[0009] The term "oral structure" is used to refer to the physical structures present in the oral cavity, such as the teeth.

[0010] An optical filter is a device that preferentially transmits at least some wavelengths of light while reducing or preventing the transmission of at least some other wavelengths of light. The term "preferential filter" is used herein to define a filter configured to preferentially absorb light within a set or a series of predetermined wavelengths. Dentin and enamel each have different fluorescence emission spectra, so by providing two filters with different passbands, each filter is arranged to filter a portion of the fluorescence emitted from the oral structure, the data received at the sensor module can be used to identify the presence of the dentin-enamel boundary. Since the dentin-enamel boundary is identified by fluorescence, the boundary can be identified even in the presence of one or more shielding media. The characteristics of the dentin-enamel boundary can be used to assess oral health. For example, the size (e.g., width) of the boundary can be used to assess the extent of enamel damage, wherein a larger (e.g., wider) boundary area can indicate an increased degree of enamel erosion or damage compared to a smaller (e.g., narrower) boundary. In addition, since enamel erosion occurs primarily at the edges of the teeth to expose the underlying dentin in these areas, the system can also be used to identify gaps between teeth.

[0011] As described above, the light module is configured to emit light to illuminate the oral region of interest. The light emission module can be configured to emit light having a wavelength in the visible portion of the electromagnetic spectrum, and / or light in the invisible portion of the electromagnetic spectrum.

[0012] Optionally, the light emission module is configured to emit light with a wavelength in the range of 405 to 450nm. That is, the light emission module is configured to emit light in the near-ultraviolet range. In this way, the light emission module is configured to ensure strong fluorescence of the dentin and enamel in the oral area of ​​concern. Preferably, the light emission module does not emit light with a wavelength in the UV range (i.e., a wavelength of 400nm or less), and uses the near-UV range so that the health risks to the device user can be reduced. Therefore, the light emission module can be configured to emit light with a wavelength of 405nm or greater, 410nm or greater, 415nm or greater, or 420nm or greater. However, it may be desirable that the emission wavelength is not too high. This is because light with a higher wavelength may not have enough energy to excite the fluorescence of the teeth. Therefore, in some embodiments, the light emission module can be configured to emit light with a wavelength of 450nm or less, 440nm or less, or 430nm or less. In some preferred embodiments, the light emission module can be configured to emit light with a wavelength in the range of 405 to 420nm.

[0013] The specific form of the light emitting module is not particularly limited. In some embodiments, the light emitting module may include one or more light emitting diodes, such as LEDs. In other embodiments, the light emitting module may include a laser light source. In some embodiments, the light emitting module may be located near or adjacent to the sensor module.

[0014] The specific form of the optical filters used in the present invention is not particularly limited, as long as they must be suitable for being arranged in the optical path between the oral area of ​​interest and the sensor module. In some embodiments, the optical filter can be an integral dye filter. In other embodiments, the optical filter can include an interference coating. In some embodiments, the filters can each include an absorption filter, an interference filter, or a dichroic filter. Preferably, the filter includes an absorption filter because the absorption filter is generally relatively low cost and easy to obtain. The filter can be made of any suitable material: for example, they can be made of a glass material or a polymeric material (such as a resin). In some examples, the two optical filters can be or form part of a Bayer filter arrangement, which is part of the sensor module or is placed on the sensor module. For example, the sensor module may include a pixel array, and the two optical filters can form part of a Bayer arrangement on the pixel array of the sensor module. By arranging in this way, data of different channels associated with the fluorescence filtered by each optical filter can be read directly from the sensor module itself.

[0015] Optionally, the two optical filters include a blue filter and a red filter, the blue filter being configured to preferentially pass filtered fluorescence having a wavelength between 430 nm and 560 nm, and the red filter being configured to preferentially pass filtered fluorescence having a wavelength of 560 nm or greater. This can be achieved by selecting appropriate colors for the filters, particularly where the filters are integrally dyed filters. The inventors have recognized that by having two optical filters with passbands configured in this manner, the filtered fluorescence detected by the sensor module specifically indicates different levels of dentin and enamel in an area of ​​interest in the oral cavity highlighted due to differences in the fluorescence spectra of the dentin and enamel. In particular, it has been found that dentin and enamel each fluoresce strongly in the passband of the blue filter, while the fluorescence spectrum of enamel has a higher intensity than that of dentin in the region above 560 nm. Therefore, by comparing the filtered fluorescence in these passband regions, the dentin-enamel boundary can be easily identified by a process described in more detail below.

[0016] The precise form of the sensor module is not particularly limited, as long as it is configured to detect light reflected or emitted from the oral area of ​​interest and output corresponding sensor data. By detecting and analyzing the sensor module data, the detection system can identify the presence of the dentin-enamel boundary in the oral area of ​​interest at a specific time (e.g., when an image is taken). The sensor module may include a plurality of pixels (or picture elements), so in some examples, the sensor module may be referred to as a "pixelated" sensor module here. In some embodiments, the sensor module includes a camera (e.g., a large 2D array of pixels or sensors) or a photodetector. The sensor data output by the sensor module will generally include image data generated by the sensor module. Therefore, in the following disclosure, the phrases "output sensor data" and "generated image data" are used interchangeably. In some embodiments, the generated image data (output sensor data) includes red, green and blue (RGB) image data (e.g., corresponding to corresponding RGB pixels). The use of RGB image data can allow more accurate gap positioning compared to other types of image data. In alternative embodiments, other types of image data (e.g., black and white image data) can be used.

[0017] Optionally, the sensor module may be configured to detect the time at which the filtered fluorescence reaches the sensor module and output corresponding time data, and the processor module may be configured to process the time data output by the sensor module to identify the presence of the dentin-enamel boundary in the oral region of interest. The inventors have realized that the fluorescence lifetime of dentin is different from the fluorescence lifetime of enamel. In particular, it has been found that the fluorescence lifetime of dentin is longer than that of enamel. By detecting the arrival time of light filtered by each of the two optical filters, the dentin-enamel boundary can therefore be identified by a process described in more detail below. For example, the sensor module may include a single photon avalanche diode (SPAD), such as forming part of a 2D array of SPADs, wherein each SPAD provides a pixel in a SPAD image sensor, which can be used to time the arrival of photons passing through each of the two optical filters. Alternatively, the sensor module may include a gated imaging device, such as a complementary metal oxide semiconductor (CMOS) sensor. Of course, it should be understood that any suitable time-of-flight camera arrangement can be used in embodiments of the present invention. In some examples, the light emission module can be configured to generate repetitive short light pulses, and the sensor module can be configured to detect the time at which filtered fluorescent emissions arrive at the sensor module and output information related to the delay of the fluorescence relative to the timing of each pulse.

[0018] Optionally, the dentin-enamel boundary detection system may further include two polarization filters with orthogonal polarizations, each of which is arranged to filter a portion of the fluorescence emitted from the oral structures in the oral area of ​​interest to pass the polarized fluorescence. The inventors have recognized that the light emitted, reflected and / or scattered from each of the dentin, enamel and dentin-enamel boundary has different polarization characteristics. Therefore, the light that passes through the polarization filter to the sensor module carries information related to each of these characteristics, so that the presence of the dentin-enamel boundary can be detected based on the sensor output data related to the polarization state of the light according to the process described in more detail below. Optionally, the light emission module can be configured to emit polarized light, which can further assist in identifying the dentin-enamel boundary using the polarization filter.

[0019] Optionally, the processor module can be configured to identify the presence of interdental spaces in the oral region of interest. That is, the processor module can utilize the identification of the dentin-enamel boundary region in the oral region of interest to identify the presence of interdental spaces, which may be particularly advantageous for ensuring that any treatment is preferentially applied to the interdental spaces, which may be important for ensuring good oral health, as described in more detail below.

[0020] According to a second aspect of the present invention, there is provided an oral cavity inspection or treatment apparatus incorporating the dentin-enamel boundary detection system according to the first aspect.

[0021] Optionally, the oral inspection or treatment device may be a teeth cleaning appliance, such as a toothbrush, further comprising a main body and a cleaning tool head.

[0022] Optionally, one or both of the light emitting module and the sensor module of the dentin-enamel boundary detection system can be arranged on the cleaning tool head. This can help allow the dentin-enamel boundary detection system to operate when using a tooth cleaning appliance, and can provide a more accurate detection of the dentin-enamel boundary by positioning one or both of the light emitting module and the sensor module near the oral area of ​​interest. For example, positioning the light emitting module in this way can ensure that the light irradiating the oral area of ​​interest has a high intensity to provide a strong fluorescence response. Similarly, positioning the sensor module in this way can help ensure accurate identification of the dentin-enamel boundary. Alternatively or additionally, the light emitting module and / or the sensor module can be at least partially contained in the body of the device. By arranging the image sensor device at least partially in the body of the device, the space on the device can be more effectively managed. That is, the head of the device can be relatively small compared to the body. In addition, in an embodiment, the head of the device can be separated from the body. It can also be disposable, and the user may wish to replace the brush head regularly after use. Therefore, the light emitting module and / or the sensor module are at least partially arranged in the body, rather than completely arranged in the head, which can reduce the cost of replacement parts. Where the light emitting module and / or the sensor module may be at least partially contained within the body of the device, one or more guiding members may be provided to conduct light from / to the light emitting module and / or the sensor module. The guiding members may include one or more optical cables.

[0023] Optionally, the processor module can be provided as part of a controller module located in a remote device, wherein the remote device and the oral inspection or processing device can be configured to communicate with each other to allow the exchange of signals and / or data. The controller module can perform various data processing and / or control functions through one or more processors. In addition to processing the sensor data output by the sensor module, the controller and / or processor forming a part of the controller module can also be operated to perform various other data processing and / or control functions to identify the presence of interdental gaps in the oral area of ​​interest. The operations performed by the processor module can be performed by hardware and / or software. Providing a processor module in a remote device can help ensure that the oral inspection or processing device can meet any restrictions on its size (for example, it may be required to be a handheld device), and also increase the efficiency of the system. For example, by providing a remote processor module in this manner, the oral inspection or processing device may require less power and / or computing resources.

[0024] Optionally, when interdental spaces are identified in the oral area of ​​concern, the tooth cleaning appliance can be configured to treat the interdental spaces identified in the oral area of ​​concern. Plaque is particularly likely to accumulate in the interdental spaces, so identifying and treating this area helps ensure improved oral health.

[0025] According to a third aspect of the present invention, there is provided a method for detecting a dentin-enamel boundary in an oral region of interest, the method comprising the following steps: illuminating the oral region of interest with light; detecting light reflected or emitted from the oral region of interest, the light comprising filtered fluorescence, the filtered fluorescence having passed through two optical filters having different corresponding passbands, each of the two filters being arranged to filter a portion of the fluorescence emitted from the oral structure in the oral region of interest to pass the filtered fluorescence; outputting sensor data corresponding to the detected filtered fluorescence; and processing the sensor data to identify the presence of a dentin-enamel boundary in the oral region of interest based on the filtered fluorescence. As described above, dentin and enamel each have different fluorescence emission spectra, so by passing the fluorescence emitted from the oral structure through two filters having different passbands, data received from a sensor arranged to detect the filtered fluorescence can be used to identify the presence of a dentin-enamel boundary. Since the dentin-enamel boundary is identified by relying on fluorescence, the boundary can be identified even in the presence of one or more shielding media. The characteristics of the dentin-enamel boundary can be used to assess oral health. For example, the size (e.g., width) of the border can be used to assess the extent of enamel damage, where a larger (e.g., wider) border area can indicate an increased degree of enamel erosion or damage compared to a smaller (e.g., narrower) border. In addition, since enamel erosion occurs primarily at the edges of the teeth to expose the underlying dentin in these areas, this method can also be used to identify gaps between teeth.

[0026] Optionally, processing the sensor data to identify the presence of a dentin-enamel boundary in an oral region of interest may include creating a ratiometric image of the oral region of interest based on the ratio of the intensity of the filtered fluorescence passing through two optical filters. As described above, the inventors have recognized that by using two optical filters with different passbands, the filtered fluorescence detected by the sensor specifically indicates the different levels of dentin and enamel in the oral region of interest highlighted due to the difference in the fluorescence spectra of dentin and enamel. For each pixel position, a ratiometric image can be created by taking the ratio of the intensity of the filtered fluorescence through the first filter of the two optical filters to the intensity of the filtered fluorescence through the second filter of the two optical filters. For example, the two optical filters may form part of a Bayer filter covering the pixel array of the image sensor. Creating a ratiometric image may include obtaining the ratio between two channels read out from the image sensor (e.g., the ratio between the red and blue channels). Due to the different fluorescence spectra of dentin and enamel, the ratiometric image generated in this manner makes the dentin-enamel boundary clear and easier to identify.

[0027] Optionally, the light irradiating the oral area of ​​interest may have a wavelength in the range of 405 to 450nm. That is, the light irradiating the oral area of ​​interest may be in the near-ultraviolet range. In this way, the light is configured to ensure strong fluorescence of the dentin and enamel in the oral area of ​​interest. Preferably, the light irradiating the oral area of ​​interest may not have a wavelength in the UV range (i.e., a wavelength of 400nm or less), and the near-UV range is used, so that the health risks to the user can be reduced. Therefore, the light irradiating the oral area of ​​interest may have a wavelength of 405nm or greater, 410nm or greater, 415nm or greater, or 420nm or greater. However, it may be desirable that the wavelength is not too high. This is because light with a higher wavelength may not have enough energy to excite the fluorescence of the teeth. Therefore, in some embodiments, the light irradiating the oral area of ​​interest may have a wavelength of 450nm or less, 440nm or less, or 430nm or less. In some preferred embodiments, the light irradiating the oral area of ​​interest may have a wavelength in the range of 405 to 420nm.

[0028] Optionally, outputting sensor data corresponding to the detected light may include outputting time data identifying the time at which the light arrives at the sensor, and processing the sensor data to identify the presence of a dentin-enamel boundary in an oral region of interest may include processing the time data. The inventors have recognized that the fluorescence lifetime of dentin is different from the fluorescence lifetime of enamel. In particular, it has been found that the fluorescence lifetime of dentin is longer than the fluorescence lifetime of enamel. By detecting the arrival time of light filtered by each of the two filters, the dentin-enamel boundary can be identified.

[0029] In some embodiments, processing the sensor data to identify the presence of a dentin-enamel boundary in an oral region of interest may include creating a fluorescence lifetime image based on the time data. For example, the intensity and / or color of each pixel in the fluorescence lifetime image may be determined by the fluorescence lifetime based on the arrival time of light filtered by each of the two filters. Due to the different fluorescence lifetimes of dentin and enamel, the image produced in this manner makes the dentin-enamel boundary clear and easier to identify.

[0030] Optionally, detecting light reflected or emitted from the oral area of ​​interest may include detecting polarized fluorescence that has passed through two polarization filters having orthogonal polarizations, each of which is arranged to filter a portion of the fluorescence emitted from the oral structures in the oral area of ​​interest to pass the polarized fluorescence. The inventors have recognized that light emitted, reflected and / or scattered from each of the dentin, enamel and dentin-enamel boundary has different polarization characteristics. Therefore, the light passing through the polarization filter carries information related to each of these characteristics, so that the presence of the dentin-enamel boundary can be detected based on the polarization state of the light. Optionally, in some embodiments, illuminating the oral area of ​​interest with light may include illuminating the oral area of ​​interest with polarized light, which may further facilitate the identification of the dentin-enamel boundary using the polarization filter.

[0031] In some embodiments, processing the sensor data to identify the presence of a dentin-enamel boundary in an oral region of interest may include calculating Stokes parameters based on orthogonal polarization directions of polarized fluorescence. In addition, and / or alternatively, processing the sensor data to identify the presence of a dentin-enamel boundary in an oral region of interest may include creating a ratio image of the oral region of interest based on the intensity ratio of polarized fluorescence passing through two polarization filters. For example, for each pixel position, a ratio image may be created by taking the ratio of the intensity of filtered fluorescence passing through a first of two polarization filters to the intensity of filtered fluorescence passing through a second of the two polarization filters. Creating a ratio image may include acquiring the ratio between two channels read out from an image sensor, wherein the image may have a superimposed polarization filter grid. Due to the difference in the polarization spectra of fluorescence from dentin and enamel, the ratio image produced in this manner makes the dentin-enamel boundary clear and easier to identify.

[0032] For example, the method according to the third aspect of the present invention may be performed by the enamel-dentin boundary detection system according to the first aspect of the present invention, or by the oral cavity inspection or treatment device according to the second aspect of the present invention.

[0033] The invention includes combinations of the aspects and preferred features described, unless such combinations are expressly impermissible or explicitly avoided. For example, the method of the invention may be combined with any feature described with reference to the apparatus of the invention, and vice versa. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Embodiments and experiments illustrating the principles of the present invention will now be discussed with reference to the accompanying drawings, in which:

[0035] Figure 1 is a schematic diagram of a dentin-enamel boundary detection system according to an embodiment of the present invention;

[0036] Figure 2 is a schematic diagram of a filter arrangement and an image sensor that may be used in embodiments of the present invention;

[0037] Figure 3 is a schematic diagram of an oral treatment device according to an embodiment of the present invention;

[0038] Figure 4 is a flow chart illustrating a method of operating an oral treatment device according to an embodiment of the present invention; and

[0039] FIG5(a) shows the first channel of the oral structure image, FIG5(b) shows the second channel of the oral structure image, and FIG5(c) shows the Figure 5(a) and 5(b) The resulting ratio image. DETAILED DESCRIPTION

[0040] Aspects and embodiments of the present invention will now be discussed with reference to the accompanying drawings. Other aspects and embodiments will be apparent to those skilled in the art. All documents mentioned herein are incorporated herein by reference.

[0041] Figure 1 1 is a schematic diagram of a dentin-enamel boundary detection system 1 according to an embodiment of the present invention, the system being arranged to identify the presence of a dentin-enamel boundary and an interdental space G within an oral region of interest R in a user's oral cavity. In the schematic diagram shown, it can be seen that the components of the system are not contained in a single device, but are provided as a plurality of separate components. The system comprises a light emitting module 10, an optical filter arrangement 20, a sensor module 30 and a controller 40 comprising a processor module 40a.

[0042] Here, the light emitting module 10 is conveniently provided as a laser configured to emit light in the "near ultraviolet" range having a wavelength of 405nm. The laser is arranged to illuminate an oral area of ​​interest R within the oral cavity. Here, the oral area of ​​interest includes various oral structures, including one or more teeth. Irradiating the oral area of ​​interest with light having a wavelength of 405nm allows the teeth present in the oral area of ​​interest to fluoresce. However, because the light has a wavelength located in the "near ultraviolet" region of the electromagnetic spectrum, rather than a wavelength located in the ultraviolet range of the electromagnetic spectrum, the health risk to the user of the device can be reduced. In some preferred embodiments, the wavelength of the light emitted by the light emitting module is greater than 405nm, such as 410nm or greater, which can further reduce any health risks to the user.

[0043] The optical filter arrangement 20 in this embodiment includes two optical filters with different corresponding passbands. For example, the two optical filters can be placed adjacent to each other. In some embodiments, the optical filter arrangement 20 can also include two polarization filters with orthogonal polarizations. In some examples, the optical filter arrangement 20 can include a mosaiced array of different filter elements, as described below with reference to Figure 2 In more detail, it covers the pixel array of the image sensor. For example, the array of filter elements may include optical filters with different passbands and optionally include polarization filters. The optical filter arrangement 20 is arranged to be located in the optical path between the oral region of interest and the sensor module (as shown by the dotted line showing the field of view (FOV) of the sensor module).

[0044] The first of the two optical filters will preferentially transmit light with a wavelength between 430nm and 560nm, and will preferentially filter or block light with a wavelength outside this range. The second of the two optical filters will preferentially transmit light with a wavelength of 560nm or greater, and will preferentially filter or block light with a shorter wavelength than it. This means that the first optical filter will pass the fluorescence emitted by the dentin and enamel in the oral area of ​​interest, while the second optical filter will preferentially pass the fluorescence emitted by the enamel in the oral area of ​​interest (because the dentin has very low fluorescence above 560nm). By comparing the data from the sensor module 30 related to the light passing through each optical filter, the dentin-enamel boundary and the interdental space can be easily identified. In an embodiment where the optical filter arrangement 20 also includes a polarization filter, the dentin-enamel boundary can also be identified by comparing the data from the sensor module 30 related to the light passing through each polarization filter.

[0045] The sensor module 30 is represented by a "camera" icon in the schematic diagram. In practice, the form of the sensor module is not particularly limited, however, it preferably includes one or more image sensors. For example, the image sensor may include a 2D array of pixels or picture elements that are sensitive to light, so the image sensor can be referred to as a pixelated sensor module. Examples of such image sensors include, but are not limited to, charge coupled devices, CCDs, active pixel sensors such as complementary metal oxide semiconductors (CMOS), sensors, and single photon avalanche diodes (SPADs) - for example, formed as a 2D array of such elements. Although in this embodiment, the sensor module is a separate component arranged for use outside the oral cavity, in some embodiments, the sensor module is an intraoral sensor, that is, the sensor module is operable to be used at least partially inside the user's oral cavity to generate image data representing the user's oral cavity. For example, as will be discussed in further detail below, when the dentin-enamel boundary detection system is incorporated in an oral treatment device, the sensor module can be at least partially arranged on the head of the oral treatment device, and the head is arranged to be inserted into the user's oral cavity.

[0046] In this embodiment, since the sensor module 30 is provided as a separate component, the sensor module includes one or more processors (not shown). The sensor module is configured to detect light reflected or emitted from the oral region of interest R within the field of view FOV of the sensor module, which has passed through the optical filter arrangement 20. The sensor module is configured to output sensor data corresponding to the detected light, which in this case will be generated image data. In this embodiment, the generated image data (output sensor data) includes red, green and blue RGB image data.

[0047] In some examples, the sensor module 30 may also be configured to detect the time when the filtered fluorescence reaches the sensor module 30 and output corresponding time data. For example, the controller 40 may utilize information received from the light emitting module 10 (e.g., time data describing when the oral region of interest R is illuminated) and time data from the sensor module 30 to derive information related to the fluorescence lifetime, thereby identifying the dentin-enamel boundary.

[0048] The sensor module 30 is configured to transmit the output sensor data to the controller 40, as shown by the dotted line connecting the two components. This transmission can be performed by a wire that physically connects the sensor module 30 and the controller 40, or it can be performed by wireless transmission. The controller 40 is operable to perform various data processing and / or control functions, which will be described in more detail below. The controller 40 may include one or more components. One or more components may be implemented in hardware and / or software. One or more components may be located in the same location or may be remote from each other. The controller 40 may be embodied as one or more software functions and / or hardware modules. The controller 40 includes at least one processor 40a, which is configured to process instructions and / or data, and is particularly configured to process sensor data output from the sensor module 30. The operations performed by the one or more processors 40a may be performed by hardware and / or software. The controller 40 and / or the processor module 40a of the controller is operable to output a control signal for controlling one or more components of the dentin-enamel boundary detection system 1, or for controlling an oral treatment device containing a dentin-enamel boundary detection system.

[0049] Processor 40a may be part of a processing system including one or more processors and / or memory. One or more processors of the processing system may include a central processing unit (CPU). One or more processors may include a graphics processing unit (GPU). One or more processors may include one or more of a field programmable gate array (FPGA), a programmable logic device (PLD), or a complex programmable logic device (CPLD). One or more processors may include an application specific integrated circuit (ASIC). Those skilled in the art will appreciate that, in addition to the examples provided, many other types of devices may be used to provide one or more processors. One or more processors may include multiple co-located processors or multiple differently located processors. The operations performed by one or more processors may be performed by one or more of hardware, firmware, and software. It should be understood that the processing system may include more, fewer, and / or different components than described.

[0050] In an embodiment, the processor 40a processes the sensor data output by the sensor module through one or more data analysis algorithms. The data analysis algorithms can be configured to analyze the received data, such as image data, and generate outputs that can be used as conditions, by which the dentin-enamel boundary detection system 1 or an oral treatment device including the dentin-enamel boundary detection system 1 can be controlled. For example, they can be configured to output a signal indicating the presence of a dentin-enamel boundary in an oral area of ​​interest. In an embodiment, the data analysis algorithm includes a classification algorithm, such as a non-linear classification algorithm. In an embodiment, the data analysis algorithm includes a trained classification algorithm. However, in alternative embodiments, the data analysis algorithm includes other types of algorithms, for example, not necessarily trained and / or configured to perform classification.

[0051] In an embodiment, the processor 40a is configured to process the generated image data using a sliding window, which allows the position data of the dentin-enamel boundary to be determined by detecting the presence of the dentin-enamel boundary within the sliding window and determining a sub-region of the image containing the boundary. In the sliding window image analysis technique, a sliding window is passed through the image, sub-regions of the image are defined, and it is determined whether a boundary exists in each sub-region of the image. This will be described in more detail below.

[0052] In an embodiment, the generated image data is processed by extracting one or more image features from the image data and using the extracted one or more image features to determine the position data. For example, the image features may include texture-based image features. Since images are composed of pixels that are highly correlated to each other, image feature extraction is used to obtain the most representative and informative (i.e., non-redundant) information of the image in order to reduce dimensionality and / or facilitate learning of a classification algorithm.

[0053] In an embodiment, a discrete wavelet transform is used to extract one or more image features. The discrete wavelet transform can capture frequency and position information in an image. For example, in order to detect interproximal spaces based on an image for identifying a dentin-enamel boundary, the image frequency in the gap region is typically higher than the image frequency in the tooth or gum region. This allows the discrete wavelet transform to produce a frequency map of an image that can be used to detect interproximal spaces. In an embodiment, a Haar wavelet is used, which has a relatively low computational complexity and low memory usage compared to other wavelets. The coefficients of the wavelet transform (or their approximations) can be used as extracted image features. For example, the output of feature extraction based on the Haar wavelet applied to an image of size a×a may include a horizontal wave h (a / 4×a / 4), a vertical wave v (a / 4×a / 4), and a diagonal wave d (a / 4×a / 4). Other wavelets may be used in alternative embodiments.

[0054] The extracted features can be used in a sliding window applied to the image. For example, in the image sub-region defined by the sliding window, a 2×2 pooling can be performed on each of h, v, and d before they are vectorized and combined into a vector of size 1×108. This can be normalized together with the training data (e.g., training mean and variance values) from the training classification algorithm. A support vector machine SVM can be used as a non-probabilistic nonlinear binary classifier with a Gaussian radial basis function kernel, which receives the normalized data from the previous step. The trained SVM includes support vectors with trained coefficients and deviations, i.e., support vectors determined in a previous training phase. For example, given a set of images and basic truth labels, a classification algorithm can be trained to assign new samples to one category (e.g., dentin-enamel boundary region) or another category (e.g., non-boundary).

[0055] In an embodiment, one or more image features are extracted using at least one of an edge detector, a corner detector, and a blob extractor. Extracting image features using this method may provide more accurate detection and / or localization of the dentin-enamel boundary compared to other methods.

[0056] In an embodiment, the generated image data is processed using a trained classification algorithm configured to detect the dentin-enamel boundary. Using such a trained algorithm results in more accurate and / or more reliable boundary detection than without using the trained algorithm. In an embodiment, the classification algorithm comprises a machine learning algorithm. Such a machine learning algorithm can be improved (e.g., to improve the accuracy and / or reliability of the classification) through experience and / or training.

[0057] In an embodiment, the generated image data is processed to determine at least one feature of the identified dentin-enamel boundary. In an embodiment, the at least one feature is determined by processing the generated image data using a machine learning algorithm. The machine learning algorithm is trained to identify information used to distinguish boundaries. Such information includes features that represent boundaries, i.e., non-redundant features, and / or features that are predicted to vary between boundaries. The identified information may include at least one feature of a boundary. In an embodiment, such a machine learning algorithm (or one or more different machine learning algorithms) is also used to determine at least one feature of one or more previously identified boundaries, such as features that represent previously identified boundaries and / or can be used to distinguish boundaries, and features that are used to compare previously identified boundaries with currently identified boundaries. In an alternative embodiment, unique features of the boundaries are extracted from the original image data without using a machine learning algorithm.

[0058] In an embodiment, the output signal and / or the generated image data are used to modify the classification algorithm. That is, the generated signal and / or the generated image data can be used to train and / or further train the classification algorithm. Modifying the classification algorithm allows the accuracy and / or reliability of the algorithm to be improved through experience and / or the use of more training data. That is, the confidence in the determined dentin-enamel boundary position can be increased. In addition, modifying the classification algorithm allows the classification algorithm to be adapted to the user. By dynamically retraining the classification algorithm using the generated signal and / or the generated image data as training data, the classification algorithm can more reliably determine the intraoral position of the dentin-enamel boundary.

[0059] In an embodiment, training data is received from a remote device. The training data may be received from a network, such as the "cloud". Such training data may include classification data associated with other users. For example, such training data may include crowdsourced data. In an embodiment, such training data may be greater in quantity than classification data obtained directly using the dentin-enamel boundary detection system. Using training data from a remote device to modify a classification algorithm may improve the accuracy and / or reliability of the classification algorithm compared to not using such training data.

[0060] Figure 2 is a schematic diagram of an optical filter arrangement 21 and an image sensor 31 that may be used in embodiments of the present invention. For example, the filter arrangement may be used to refer to Figure 1 A dentin-enamel boundary detection system 1 is described.

[0061] The image sensor 31 comprises an array of pixels P(a), P(b). For example, the image sensor 31 may be a CCD such that the pixels P(a), P(b) are an array of link capacitors that are sensitive to incident light.

[0062] exist Figure 2 In the arrangement, the filter arrangement 21 includes a mosaic formed by two types of filters F(a), F(b). For example, the two types of filters can be optical filters, such as a blue filter type configured to preferentially pass filtered fluorescence having a wavelength between 430nm and 560nm, while a red filter type is configured to preferentially pass filtered fluorescence having a wavelength of 560nm or greater. Of course, it will be appreciated that any suitable number of types of filters may be used. For example, the filter arrangement 21 may include a mosaic formed by two types of optical filters and two polarization filters having orthogonal polarizations. Figure 2, for clarity, the two filter types F(a), F(b) are shown separately, but it will be appreciated that the filter arrangement may form a single-layer mosaic of filter types. In particular, the mosaic of filters may preferably be located directly in front of the image sensor 31, such that a first subset of pixels P(a) receives light that passes through the first filter type F(a), and a second subset of pixels P(b) receives light that passes through the second filter type F(b). Of course, if more filter types are used, the image sensor is divided into a greater number of pixel subsets, each receiving light that passes through a single filter type. In some embodiments, the filter arrangement takes the form of a Bayer filter, for example having red, green and blue optical filter types. By providing the filter arrangement 21 and image sensor 31 in this manner, data may be read out from the pixel subsets P(a), P(b) of the image sensor 31 (each pixel subset P(a), P(b) of the image sensor 31 may relate to a "channel" of data), and the data from each pixel subset P(a), P(b) may be compared in order to identify the dentin-enamel boundary in the region of interest of the oral cavity. For example, a ratio image can be formed by taking the ratio of adjacent pixels in different subsets.

[0063] The dentin-enamel detection system according to the present invention can be implemented in an oral treatment device. Figure 3 is a schematic diagram of an oral treatment device according to the present invention. In this example, the oral treatment device is a toothbrush, although in other embodiments, the oral treatment device can be a dental floss device, an oral irrigator, an interdental cleaning device, an oral care monitoring device, or any combination thereof.

[0064] In this embodiment, the oral treatment device 100 comprises a handle 101 and a tool head 102. The handle 101 forms the body of the device 100 and can be grasped by a user during use of the device 100. It is generally cylindrical. Figure 3 In the illustrated embodiment, the handle 101 includes a user interface 103. The user interface 103 includes a user operable button that is configured to be pressed by a user when the user holds the handle. This can be operable to control, for example, the power state of the oral treatment device 100, or provide user input to the oral treatment device in a known manner.

[0065] The tool head 102 includes a plurality of bristles 104 for performing a toothbrushing function, although as described above, the oral treatment device according to the present invention may take other forms that do not require bristles. For example, in some other embodiments, the oral treatment device 100 includes a dedicated fluid delivery device, for example, for performing treatments such as cleaning the gaps between adjacent teeth, and / or for delivering a cleaning or whitening medium to the user's teeth. The tool head 102 includes a head 105 and a rod 106. The rod connects the handle to the head of the tool head 102. The rod 106 is elongated in shape and is used to space the head of the tool head from the handle to facilitate the user to operate the oral treatment device 100. The head 102 and / or the rod 106 are detachable from the handle 101.

[0066] As described above, in this embodiment, the dentin-enamel boundary detection system is incorporated into the oral treatment device. Many components of the boundary detection system are not shown in this figure. However, a light emitting module 110 in the form of an LED is disposed on the stem 106 of the tool head 102. The sensor module 130 is also disposed on the stem 106 of the tool head and is covered by the optical filter arrangement 120 so that the optical filter arrangement 120 is disposed in the light path between the oral region of interest and the sensor module 130. An advantage of providing the light emitting module 110 and / or the sensor module 130 on the tool head 102 is that it allows for improved intraoral imaging.

[0067] Although in this embodiment, the light emitting module 110 and the sensor module 130 are disposed on the tool head 102, it is also contemplated that in some embodiments, these components may be located in the handle / body 101 of the device, and one or more guide components may be used to receive light from the light emitting module 110 and the sensor module 130 and transmit light from the light emitting module 110 and the sensor module 130. For example, the device may include one or more guide channels extending from a hole disposed on the tool head 102 along the rod 106 (e.g., within the rod 106) to the light emitting module 110 and the sensor module 130 located in the handle of the device. In this arrangement, the guide channel may include one or more optical cables.

[0068] It should be understood that the oral treatment device 100 may also include additional components not shown or described herein, such as a power source such as a battery, or other components conventionally found in oral treatment devices, such as an electric toothbrush, a dental floss device, an oral irrigator, an interproximal cleaning device, or an oral care monitoring device.

[0069] Figure 4 is a flow chart showing a method 20 of operating a boundary detection system or an oral treatment device incorporating a boundary detection system according to the present invention. The method 200 may be used to operate the Figure 1 and Figure 2The described dentin-enamel boundary detection system 1 or oral treatment device 100. The method 200 is at least partially performed by the processor module 40a of the boundary detection system.

[0070] In step 210, the light emitting modules 10, 110 are used to illuminate the oral region of interest with light. Figure 1 Consistent with the discussion above, in this embodiment the light is laser light having a wavelength of 405 nm, although other wavelengths may be used.

[0071] In step 220, the sensor module 30, 130 detects light slightly reflected from or emitted by the oral area of ​​interest, wherein the light includes filtered fluorescence that has passed through two optical filters having respective different passbands (e.g., in filter arrangements 20, 120), each of the two filters being arranged to filter a portion of the fluorescence emitted from the oral structures in the oral area of ​​interest to allow the filtered fluorescence to pass.

[0072] In step 230, the sensor module 30, 130 outputs sensor data (in this embodiment, generated image data representing at least a portion of the user's mouth).

[0073] In step 240, the generated image data is processed to identify the presence of a dentin-enamel boundary in the oral region of interest. In some embodiments, the data can be further processed to determine location data indicating the location of interproximal spaces between adjacent teeth in the user's oral cavity. For example, the generated image data is processed using a trained classification algorithm configured to identify interproximal spaces. The trained classification algorithm can be trained prior to use of the oral treatment device.

[0074] When the method is used to control an oral treatment device, the method may include a further optional step (not shown) of controlling the oral treatment device 100 to process the detected interdental spaces.

[0075] By using this method, the dentin-enamel boundary can be automatically detected in a more accurate manner than using existing systems by using a sensor module and a trained classification algorithm. In addition, in a system or device configured to deliver one or more treatments within the oral cavity (e.g., in a system configured to eject fluids at or near an identified oral structure), treatment delivery can be controlled accordingly without user input. This can have significant advantages. For example, a user does not need to determine when an oral treatment device that includes a boundary detection system is in a position suitable for treatment delivery. Instead, this determination can be made automatically based on intraoral image data generated by the sensor module and can be performed substantially in real time.

[0076] The method may be implemented at least in part by computer software stored in a (non-transitory) memory and executable by a processor, or by hardware, or by a combination of tangibly stored software and hardware (and tangibly stored firmware). The embodiments also extend to a computer program, in particular a computer program on or in a carrier, suitable for putting the above embodiments into practice. The program may be in the form of non-transitory source code, object code, or in any other non-transitory form suitable for use in the implementation of the process according to the embodiments. The carrier may be any entity or device capable of carrying the program, such as a RAM, ROM or optical storage device, etc.

[0077] FIG. 5 shows an example of data from two channels of an imaging device, such as the one described above with respect to Figure 2 The filter arrangement 21 and image sensor 31 described, and the ratio image derived from the two channels. In particular, Figure 5 is an example using optical filters, but it should be understood that similar results will be achieved if the filter arrangement and / or channels used involve different polarization states (e.g. orthogonal polarizations).

[0078] Figure 5(a) shows a first channel of an oral structure image. Specifically, Figure 5(a) shows an image obtained from a first subset of pixels of an image sensor, wherein the first subset of pixels is exposed to fluorescence received from an oral region of interest after the fluorescence passes through a red filter, the red filter being configured to preferentially pass filtered fluorescence having a wavelength of 560 nm or greater.

[0079] Figure 5(b) shows a second channel of an oral structure image. Specifically, Figure 5(b) shows an image obtained from a second subset of pixels of the image sensor, wherein the second subset of pixels is exposed to fluorescence received from an oral region of interest after the fluorescence passes through a blue filter configured to preferentially pass filtered fluorescence having a wavelength between 430 nm and 560 nm.

[0080] Figure 5(c) shows the Figure 5(a) and 5(b) In particular, Figure 5(c) is obtained by taking Figure 5(a) and 5(b) It should be understood that FIG5(c) shows a dark band around each tooth in the image, which highlights the dentin-enamel boundary of each tooth area where enamel erosion mainly occurs, exposing the underlying dentin.

[0081] The features disclosed in the preceding description, or in the following claims, or in the accompanying drawings, expressed in their specific form or as devices for performing the disclosed functions, or as methods or processes for obtaining the disclosed results, may, where appropriate, be used alone or in any combination of these features to implement the invention in its different forms.

[0082] Although the present invention has been described in conjunction with the above exemplary embodiments, many equivalent modifications and variations will be apparent to those skilled in the art when this disclosure is given. Therefore, the above exemplary embodiments of the present invention are considered to be illustrative rather than restrictive. Various changes may be made to the described embodiments without departing from the spirit and scope of the present invention.

[0083] For the avoidance of any doubt, any theoretical explanations provided herein are intended to enhance the reader's understanding. The inventors do not wish to be bound by any of these theoretical explanations.

[0084] Any section headings used herein are for organizational purposes only and are not to be construed as limiting the subject matter described.

[0085] Throughout the specification, including the following claims, unless the context requires otherwise, the words "comprise" and "comprising", and variations such as "comprises", "including" and "containing", will be understood to imply the inclusion of stated integers or steps or integers or groups of steps but not the exclusion of any other integers or steps or integers or groups of steps.

[0086] It must be noted that, as used in the specification and the appended claims, the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. Ranges may be expressed herein as from "about" one particular value, and / or to "about" another particular value. When such a range is expressed, another embodiment includes from the one particular value and / or to the other particular value. Similarly, when a value is expressed as an approximation by using the antecedent "about," it will be understood that the particular value forms another embodiment. The term "about" in relation to a numerical value is optional and means, for example, + / - 10%.

Claims

1. A dentin-enamel boundary detection system for an oral examination device, the dentin-enamel boundary detection system comprising: a light emitting module configured to emit light to illuminate an area of ​​interest in the oral cavity; two optical filters having respective different passbands, each of the two filters being arranged to filter a portion of the fluorescent light emitted from the oral structures in the oral region of interest to pass the filtered fluorescent light; and a sensor module configured to detect the filtered fluorescence and output corresponding sensor data; The system further includes a processor module configured to identify the presence of a dentin-enamel boundary in the oral region of interest by processing sensor data output by the sensor module. 2 . The dentin-enamel boundary detection system according to claim 1 , wherein the light emitting module is configured to emit light with a wavelength in the range of 405 to 450 nm.

3. The dentin-enamel boundary detection system according to claim 1 or 2, wherein the light emitting module comprises an LED light source or a laser light source.

4. A dentin-enamel boundary detection system according to any one of the preceding claims, wherein the two optical filters include a blue filter and a red filter, the blue filter being configured to preferentially pass filtered fluorescence having a wavelength between 430 nm and 560 nm, and the red filter being configured to preferentially pass filtered fluorescence having a wavelength of 560 nm or greater.

5. The dentin-enamel boundary detection system according to any one of the preceding claims, wherein: The sensor module is configured to detect the time when the filtered fluorescence reaches the sensor module and output corresponding time data, and The processor module is also configured to process the temporal data output by the sensor module to identify the presence of a dentin-enamel boundary in the oral region of interest.

6. The dentin-enamel boundary detection system of claim 5, wherein the sensor module comprises a single photon avalanche photodiode.

7. The dentin-enamel boundary detection system according to any one of the preceding claims, wherein: The system further includes two polarization filters having orthogonal polarizations, each of the two polarization filters being arranged to filter a portion of the fluorescent light emitted from the oral structures in the oral region of interest to pass the polarized fluorescent light.

8. The dentin-enamel boundary detection system according to claim 7, wherein the light emission module is configured to emit polarized light.

9. The dentin-enamel boundary detection system of any of the preceding claims, wherein the processor module is configured to identify the presence of interdental spaces in the oral region of interest.

10. An oral inspection or treatment device comprising the dentin-enamel boundary detection system according to any one of claims 1 to 9.

11. The oral cavity inspection or treatment device according to claim 10, wherein the oral cavity inspection or treatment device is a teeth cleaning tool, further comprising a main body and a cleaning tool head.

12. The oral inspection or treatment device according to claim 10, wherein one or both of the light emitting module and the sensor module of the dentin-enamel boundary detection system are disposed on the cleaning tool head.

13. An oral inspection or treatment device according to claim 11 or 12, wherein the processor module is arranged as part of a controller module located within the body of the teeth cleaning appliance.

14. An oral inspection or treatment device according to claim 11 or 12, wherein the processor module is configured as a part of a controller module located in a remote device, wherein the remote device and the oral inspection or treatment device are configured to communicate with each other to allow the exchange of signals and / or data.

15. The oral inspection or treatment device according to any one of claims 10 to 14, wherein when the existence of interdental spaces in the oral area of ​​interest is identified, the tooth cleaning appliance is configured to treat the identified interdental spaces in the oral area of ​​interest.

16. A method for detecting a dentin-enamel boundary, the dentin-enamel boundary being located in an area of ​​interest in an oral cavity, comprising the steps of: Shine light on the area of ​​concern in your mouth; detecting light reflected or emitted from the oral region of interest, the light comprising filtered fluorescence having passed through two optical filters having respective different passbands, each of the two filters being arranged to filter a portion of the fluorescence emitted from oral structures in the oral region of interest to pass the filtered fluorescence; outputting sensor data corresponding to the detected filtered fluorescence; and The sensor data is processed to identify the presence of a dentin-enamel boundary in the oral region of interest based on the filtered fluorescence.

17. A method for detecting a dentin-enamel boundary according to claim 16, wherein processing the sensor data to identify the presence of a dentin-enamel boundary in the oral region of interest includes creating a ratio image of the oral region of interest based on an intensity ratio of filtered fluorescence passing through the two optical filters.

18. A method for detecting the dentin-enamel boundary according to claim 16 or 17, wherein the light illuminating the oral region of interest has a wavelength in the range of 405 to 450 nm.

19. A method for detecting a dentin-enamel boundary according to any one of claims 16 to 18, wherein: Outputting sensor data corresponding to the detected light includes outputting time data identifying the time at which the light arrived at the sensor, and Processing the sensor data to identify the presence of a dentin-enamel boundary in the oral region of interest includes processing the temporal data.

20. The method for detecting a dentin-enamel boundary according to claim 19, wherein processing the sensor data to identify the presence of a dentin-enamel boundary in the oral region of interest comprises creating a fluorescence lifetime image based on the temporal data.

21. A method for detecting the dentin-enamel boundary according to any one of claims 16 to 20, wherein detecting light reflected or emitted from the oral area of ​​interest comprises detecting polarized fluorescence that has passed through two polarization filters having orthogonal polarizations, each of the two polarization filters being arranged to filter a portion of the fluorescence emitted from the oral structures in the oral area of ​​interest to allow the polarized fluorescence to pass.

22. The method for detecting a dentin-enamel boundary according to claim 21, wherein processing the sensor data to identify the presence of a dentin-enamel boundary in the oral region of interest comprises calculating Stokes parameters based on orthogonal polarization directions of the polarized fluorescence.

23. A method for detecting the dentin-enamel boundary according to claim 21 or 22, wherein processing the sensor data to identify the presence of the dentin-enamel boundary in the oral region of interest includes creating a ratio image of the oral region of interest based on the intensity ratio of the polarized fluorescence passing through the two polarization filters.

24. The method for detecting a dentin-enamel boundary according to any one of claims 16 to 23, wherein illuminating the oral region of interest with light comprises illuminating the oral region of interest with polarized light.

25. A method for detecting the dentin-enamel boundary according to any one of claims 16 to 24, wherein the method is performed by an enamel-dentin boundary detection system according to any one of claims 1 to 9 or an oral inspection or treatment device according to any one of claims 10 to 15.

Images