Digital periodontal disease monitoring and diagnosis system

Abstract

The invention relates to the related technical field of periodontal disease monitoring and diagnosis, and discloses a digital periodontal disease monitoring and diagnosis system, which comprises an intraoral scanning module, a multispectral imaging probe, a pressure sensing probe, a data processing terminal and a cloud analysis platform, the intraoral scanning module is used for acquiring three-dimensional structure data of teeth and gingiva and comprises a high-precision optical lens and an infrared positioning sensor. Through cooperative arrangement of the intraoral scanning module, the multispectral imaging probe and the pressure sensing probe, a complete soft tissue real-time detection, scanning and acquisition closed-loop structure can be formed; the objective quantitative diagnosis of periodontal pocket depth, attach loss and inflammatory activity can be realized through the visual interaction terminal and cloud platform data; the limitation of a single detection mode is eliminated through multi-source data fusion; through setting of a periodontal disease grading deep learning model in the cloud analysis platform, a traceable digital disease progress model can be constructed.

Description

Technical Field

[0001] This invention relates to the field of periodontal disease monitoring and diagnosis, and in particular to a digital periodontal disease monitoring and diagnosis system. Background Technology

[0002] Periodontal disease monitoring and diagnosis is an important part of the oral treatment process, which can comprehensively track and guide the overall degree of disease in the oral cavity and the treatment process.

[0003] Most existing periodontal disease probing procedures rely on the doctor's subjective judgment, which leads to errors. Furthermore, X-rays cannot monitor the condition of soft tissues in real time, resulting in a lack of real-time monitoring capabilities. Consequently, the recovery and treatment of periodontal disease cannot be tracked in real time, and there is also a lack of physiological parameter acquisition capabilities. To address these issues, a digital periodontal disease monitoring and diagnostic system is proposed. Summary of the Invention

[0004] This invention provides a digital periodontal disease monitoring and diagnostic system that solves the problems mentioned in the background art.

[0005] The technical problem solved by this invention is achieved through the following technical solution: A digital periodontal disease monitoring and diagnostic system includes an intraoral scanning module, a multispectral imaging probe, a pressure sensing probe, a data processing terminal, and a cloud analysis platform. The intraoral scanning module acquires three-dimensional structural data of teeth and gingiva and includes a high-precision optical lens and an infrared positioning sensor. The multispectral imaging probe, integrated at the end of the intraoral scanning module, emits visible and near-infrared light in the wavelength range of -nm and receives reflected spectral signals. The pressure sensing probe is connected to the probe body via a detachable interface and has a micro-force sensor and a displacement encoder at its tip. The data processing terminal has a built-in multi-core processor and GPU acceleration unit and receives real-time data streams from the above modules via wired / wireless interfaces. The cloud analysis platform is network-connected to the data processing terminal and deploys a periodontal disease grading deep learning model. The physical connections between the modules are as follows: The multispectral imaging probe is fixedly nested in the front slot of the intraoral scanning module; The pressure sensing probe is connected to a standard slot on the side of the probe body via a magnetic interface. The data processing terminal communicates with the front-end hardware module via a USB-C interface or Bluetooth 5.0 protocol.

[0006] Preferably, the multispectral imaging probe includes six sets of LED light source rings with different wavelengths, arranged concentrically around the lens, with wavelengths of 405nm, 530nm, 660nm, 810nm, 940nm, and 1200nm, respectively.

[0007] Preferably, the tip of the pressure sensing probe has a tapered blunt tip structure, the surface is covered with a biocompatible coating, and a piezoresistive sensor array is embedded inside.

[0008] Preferably, the deep learning model of the cloud-based analytics platform includes: A feature fusion layer is used to align 3D structural data, spectral feature maps, and probing bleeding index. A hierarchical decision network, employing an improved ResNet-50 architecture, outputs periodontal pocket depth classification and active inflammation probability values.

[0009] Preferably, the data processing terminal has a built-in data preprocessing unit that performs the following operations: ICP registration algorithm is applied to the 3D scan data; Perform Savitzky-Golay filtering on the spectral data; Dynamically calibrate probe pressure data to zero drift.

[0010] Preferably, it also includes a visual interactive terminal that synchronizes data with the cloud platform to render a heat map of periodontal pocket depth and an inflammation risk distribution map in real time.

[0011] Preferably, the visual interactive terminal generates a dynamic monitoring report, which includes a trend chart of gingival recession, a prediction of attachment loss rate, and a treatment suggestion matrix.

[0012] Preferably, the system workflow includes: The scanning module constructs a digital model of the dental arch at a resolution of 0.1 mm; The spectral probe simultaneously acquires gingival blood oxygen saturation and hemoglobin concentration during scanning. The pressure probe is automatically positioned to the probing site under system guidance, recording bag depth and bleeding signals; The cloud-based model integrates three types of data to generate the "Periodontal Health Index (PHI) Assessment Report".

[0013] The advantages and positive effects of this invention are as follows: by synergistically setting up the intraoral scanning module, multispectral imaging probe, and pressure sensing probe, a complete closed-loop structure for real-time detection, scanning, and acquisition of soft tissue can be formed; through the visualization interactive terminal and cloud platform data, the objective quantitative diagnosis of periodontal pocket depth, attachment loss, and inflammatory activity can be achieved; and by fusion of multi-source data, the limitations of a single detection method can be eliminated; and by setting up a deep learning model for periodontal disease grading within the cloud analysis platform, a traceable digital disease progression model can be constructed. Attached Figure Description

[0014] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0015] Figure 1 This is a schematic diagram of the process structure of the present invention.

[0016] The markings in the attached diagram are described below: 11. Intraoral scanning module; 12. High-precision optical lens; 13. Infrared positioning sensor; Multispectral imaging probe; 21. Magnetic interface; 31. Pressure sensing probe; 32. Micro-force sensor; 33. Displacement encoder; 34. Piezoresistive sensor array; Data processing terminal; 41. Multi-core processor; 42. GPU acceleration unit; 43. Data preprocessing unit; Cloud-based analytics platform; 51. Periodontal disease grading deep learning model; 511. Feature fusion layer; 512. Grading decision network; Visual interactive terminal. Detailed Implementation

[0017] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention. The embodiments of the invention are further described in detail below with reference to the accompanying drawings: Reference Figure 1 As shown, periodontal disease monitoring and diagnosis is an important part of the oral treatment process. It can comprehensively track and guide the overall disease severity and treatment process of the oral cavity. Most existing periodontal disease probe procedures rely on the doctor's subjective judgment, which leads to errors. Furthermore, X-rays cannot monitor the soft tissue condition in real time, lacking real-time monitoring capabilities, which makes it impossible to follow up on the recovery and treatment of periodontal disease in real time. It also lacks the ability to collect physiological parameters. In order to solve these problems, a digital periodontal disease monitoring and diagnosis system is proposed, including an intraoral scanning module 1, a multispectral imaging probe 2, a pressure sensing probe 3, a data processing terminal 4, and a cloud analysis platform 5. The intraoral scanning module 1 is used to acquire three-dimensional structural data of teeth and gums, and includes a high-precision optical lens 11 and an infrared positioning sensor 12. The multispectral imaging probe 2 is integrated at the end of the intraoral scanning module 1, emitting visible and near-infrared light with a wavelength range of 400-1300nm, and receiving reflected spectral signals. The pressure sensing probe 3 is connected to the probe body through a detachable interface, and its tip is equipped with a micro-force sensor 31 and a displacement encoder 32. The data processing terminal 4 has a built-in multi-core processor 41 and a GPU acceleration unit 42, and receives the real-time data stream from the above modules through a wired / wireless interface. The cloud analysis platform 5 is network connected to the data processing terminal 4 and is equipped with a periodontal disease grading deep learning model 51. The physical connection relationships between the modules are as follows: The multispectral imaging probe 2 is fixedly nested in the front slot of the intraoral scanning module 1; The pressure sensing probe 3 is connected to the standard slot on the side of the probe body via a magnetic interface 21. The data processing terminal 4 communicates with the front-end hardware module via a USB-C interface or Bluetooth 5.0 protocol. Through the coordinated setup of the intraoral scanning module 1, multispectral imaging probe 2, and pressure sensing probe 3, a complete closed-loop structure for real-time detection, scanning, and acquisition of soft tissue can be formed. Through the visualization interactive terminal 6 and cloud platform data, the objective quantitative diagnosis of periodontal pocket depth, attachment loss, and inflammatory activity can be achieved. The limitations of a single detection method are eliminated through multi-source data fusion. Through the setup of the periodontal disease grading deep learning model 51 in the cloud analysis platform 5, a traceable digital disease progression model can be constructed.

[0018] It should be noted that, due to the limitations of traditional single-spectrum imaging, the absorption / reflection characteristics of specific wavelengths of light differ under different pathological states of periodontal tissue, such as inflammation, edema, and plaque accumulation. Conventional white light or single-wavelength imaging cannot distinguish between these conditions. To address this issue, in this embodiment, the multispectral imaging probe 2 includes six sets of LED light source rings with different wavelengths, arranged concentrically around the lens, with wavelengths of 405nm, 530nm, 660nm, 810nm, 940nm, and 1200nm, respectively. Specifically, the above-mentioned dual innovations of spectral fingerprint capture and spatial consistency assurance overcome the technical bottleneck of non-invasive simultaneous acquisition of multiple parameters of the periodontal microenvironment, and realize cross-scale diagnosis from morphology to physiology (tissue structure → metabolic state) and provide high-dimensional reliable input for deep learning models.

[0019] Furthermore, the tip of the pressure sensing probe 3 is a tapered blunt-tip structure, with a biocompatible coating on the surface and a piezoresistive sensor array 33 embedded inside. The tapered blunt-tip structure allows for a wider detection range of the pressure sensing probe 3, and the biocompatible coating on the surface ensures better anti-interference performance of the probe. Moreover, the piezoresistive sensor array 33 enables "CT-like mechanical scanning of periodontal pockets," achieving dynamic modeling of the stress field within the pocket for the first time.

[0020] It should also be noted that the deep learning model of the cloud-based analytics platform 5 includes: Feature fusion layer 511 is used to align three-dimensional structural data, spectral feature maps, and probing bleeding index; The hierarchical decision network 512, employing an improved ResNet-50 architecture, outputs periodontal pocket depth classifications of 0-3mm, 4-5mm, and ≥6mm, along with active inflammation probability values. It overcomes the challenge of "morphological-functional data separation," achieving three-dimensional panoramic pathological imaging of periodontal pockets. It transforms physician experience into quantifiable deep learning decision factors, improving the diagnostic consistency Kappa value from 0.62 to 0.91. For the first time, it achieves objective monitoring of periodontitis activity through dynamic inflammation probability curves, filling a gap in clinical technology.

[0021] Furthermore, the data processing terminal 4 has a built-in data preprocessing unit 43, which performs the following operations: ICP registration algorithm is applied to the 3D scan data; Perform Savitzky-Golay filtering on the spectral data; Dynamically calibrate probe pressure data to zero drift.

[0022] Additionally, it includes a visual interactive terminal 6, which synchronizes data with the cloud platform to render real-time heat maps of periodontal pocket depth and inflammation risk distribution maps.

[0023] It is worth mentioning that the visual interactive terminal 6 generates a dynamic monitoring report, which includes a trend chart of gingival recession, a prediction of attachment loss rate, and a treatment suggestion matrix. The generation of the dynamic monitoring report with the trend chart of gingival recession, the prediction of attachment loss rate, and the treatment suggestion matrix can achieve the purpose of real-time monitoring of various tissues within the periodontium.

[0024] Furthermore, the system workflow includes: The scanning module constructs a digital model of the dental arch at a resolution of 0.1 mm; The spectral probe simultaneously acquires gingival blood oxygen saturation and hemoglobin concentration during scanning. The pressure probe is automatically positioned to the probing site under system guidance, recording bag depth and bleeding signals; The cloud-based model integrates three types of data to generate the "Periodontal Health Index (PHI) Assessment Report".

[0025] It should be emphasized that the embodiments described in this invention are illustrative rather than limiting. Therefore, this invention is not limited to the embodiments described in the specific implementation. Any other implementation methods derived by those skilled in the art based on the technical solutions of this invention also fall within the scope of protection of this invention.

Claims

1. A digital periodontal disease monitoring and diagnostic system, characterized in that: It includes an intraoral scanning module (1), a multispectral imaging probe (2), a pressure sensing probe (3), a data processing terminal (4), and a cloud analysis platform (5); The intraoral scanning module (1) is used to acquire three-dimensional structural data of teeth and gums, and includes a high-precision optical lens (11) and an infrared positioning sensor (12). The multispectral imaging probe (2) is integrated at the end of the intraoral scanning module (1), emits visible light and near-infrared light with a wavelength range of 400-1300nm, and receives reflected spectral signals; The pressure sensing probe (3) is connected to the probe body through a detachable interface, and its tip is equipped with a micro-force sensor (31) and a displacement encoder (32). The data processing terminal (4) has a built-in multi-core processor (41) and GPU acceleration unit (42), and receives real-time data streams from the above modules through a wired / wireless interface; The cloud analysis platform (5) is connected to the data processing terminal (4) via the network and is equipped with a periodontal disease grading deep learning model (51). The physical connection relationships between the modules are as follows: The multispectral imaging probe (2) is fixedly nested in the front slot of the intraoral scanning module (1); The pressure sensing probe (3) is connected to the standard slot on the side of the probe body via a magnetic interface (21); The data processing terminal (4) communicates with the front-end hardware module via a USB-C interface or Bluetooth 5.0 protocol.

2. The digital periodontal disease monitoring and diagnostic system according to claim 1, characterized in that: The multispectral imaging probe (2) contains six sets of LED light source rings with different wavelengths, arranged in concentric circles around the lens, with wavelengths of 405nm, 530nm, 660nm, 810nm, 940nm and 1200nm respectively.

3. The digital periodontal disease monitoring and diagnostic system according to claim 1, characterized in that: The pressure sensing probe (3) has a tapered blunt tip structure, a biocompatible coating on its surface, and a piezoresistive sensor array (33) embedded inside.

4. The digital periodontal disease monitoring and diagnostic system according to claim 1, characterized in that: The deep learning model of the cloud-based analytics platform (5) includes: The feature fusion layer (511) is used to align the three-dimensional structural data, spectral feature maps, and probing bleeding index; The hierarchical decision network (512) adopts an improved ResNet-50 architecture and outputs periodontal pocket depth classification and active inflammation probability values.

5. The digital periodontal disease monitoring and diagnostic system according to claim 1, characterized in that: The data processing terminal (4) has a built-in data preprocessing unit (43) that performs the following operations: ICP registration algorithm is applied to the 3D scan data; Perform Savitzky-Golay filtering on the spectral data; Dynamically calibrate probe pressure data to zero drift.

6. The digital periodontal disease monitoring and diagnostic system according to claim 1, characterized in that: It also includes a visual interactive terminal (6), which synchronizes data with the cloud platform and renders a heat map of periodontal pocket depth and an inflammation risk distribution map in real time.

7. The digital periodontal disease monitoring and diagnostic system according to claim 6, characterized in that: The visual interactive terminal (6) generates a dynamic monitoring report, which includes a trend chart of gingival recession, a prediction of attachment loss rate, and a treatment suggestion matrix.

8. The digital periodontal disease monitoring and diagnostic system according to claim 1, characterized in that: The system workflow includes: The scanning module constructs a digital model of the dental arch at a resolution of 0.1 mm; The spectral probe simultaneously acquires gingival blood oxygen saturation and hemoglobin concentration during scanning. The pressure probe is automatically positioned to the probing site under system guidance, recording bag depth and bleeding signals; The cloud-based model integrates three types of data to generate the Periodontal Health Index (PHI) assessment report.

Images