DETECTION OF DENTAL DISEASE USING CONVOLUTIONAL NEURAL NETWORK (CNN)

Abstract

DETECTION OF DENTAL DISEASE USING CONVOLUTIONAL NEURAL NETWORK (CNN) The main design of the present invention discloses the detection of dental diseases using Convolutional Neural Network (CNN), which comprises dataset preprocessing, feature extraction, IoT cloud server, and more. The main purpose of the present invention is to provide the early detection of dental conditions by capturing detailed X-ray images of the teeth, analyzing these images using deep learning techniques, and notifying users or healthcare providers about potential dental issues. The system employs an image preprocessing module to enhance image quality, followed by an image segmentation module that isolates relevant anatomical structures. The CNN architecture identifies and classifies various dental diseases, including cavities and periodontal conditions, by analyzing significant features from the X-ray images. By generating segmentation masks, the system aids in diagnosing dental diseases and planning appropriate treatment strategies which enables timely intervention, ultimately improving patient outcomes.

Specification

Description:TITLE OF THE INVENTION: DETECTION OF DENTAL DISEASE USING CONVOLUTIONAL NEURAL NETWORK (CNN)
FIELD OF THE INVENTION
[0001] The present invention relates to the field of Dentistry and medical imaging. More particularly, the present invention relates to a system for the detection of dental disease using a Convolutional Neural Network (CNN).
BACKGROUND OF THE INVENTION
[0002] Dental diseases, including caries, periodontal disease and oral cancers, pose significant health challenges globally. Traditional diagnostic methods primarily involve clinical examinations and the use of dental X-rays. Clinicians visually assess patients' oral health, relying on their expertise and experience to identify potential issues. X-rays provide essential insights into the internal structure of teeth and surrounding tissues, allowing for the detection of conditions that are not immediately visible during physical examinations.
[0003] However, these conventional methods have inherent limitations. Visual examinations can be subjective, leading to variability in diagnoses based on individual clinicians' interpretations. Early-stage dental diseases may go unnoticed, resulting in delayed treatment and progression to more severe conditions. X-ray imaging, while valuable, is also constrained by factors such as image quality, interpretation challenges, and the potential for human error. The interpretation of X-ray images can be complex, requiring considerable expertise, and even experienced practitioners may overlook subtle signs of disease.
[0004] Moreover, the reliance on human judgment in these traditional methods may result in inconsistent diagnostic outcomes. Additionally, traditional diagnostic procedures often involve time-consuming processes and may not be readily accessible to all patients, particularly in underserved areas. The growing need for more efficient, accurate and reliable diagnostic tools in dentistry has highlighted the necessity for innovative approaches that can complement or enhance traditional methods. So, the present invention provides detection of dental diseases using CNN to improve diagnostic capabilities. This method allows for early identification of conditions, facilitating timely intervention for better patient care.
[0005] However, many efforts were made to prevent dental diseases. Some of the references are given below:
Prior Arts:
[0006] US10722191B2 describes the system and method of digital X-ray diagnosis and evaluation of dental disease, focusing on the analysis of teeth in a mouth. The method utilizes a user-movable cursor to identify specific areas on a tooth in an X-ray image, measuring bone density and depth at that location. This allows for the calculation of local density values that vary with the cursor's position, as well as maximum density values from the surrounding bone. These values are crucial for assessing dental conditions such as dental caries, dental abscesses, and periodontal disease. The system enhances diagnostic capabilities by dynamically displaying the local and maximum density values in real time, enabling practitioners to visualize changes as the cursor moves which supports informed decision-making in treatment planning, providing a detailed assessment of bone density around specific teeth.
[0007] US8417010B1 describes the system and method of digital X-ray diagnosis and evaluation of dental disease, focusing on the diagnosis and assessment of periodontal disease in teeth. The method involves measuring bone depth relative to the cemento-enamel junctions of adjacent teeth and assessing bone density along the contour between these teeth. A numerical crestal density (CD) value is then calculated from the measured bone density, providing critical data for evaluating periodontal conditions. Additionally, the system incorporates a calibration method to correct variations in optical densities in acquired images. This calibration involves the use of composite calibration blocks that simulate dental tissues and defects, enabling adjustments to ensure exact imaging results. By comparing known and calculated numerical decay values, the calibration enhances the reliability of the dental digital X-ray imaging system.
[0008] CN108389207B describes the system and method of dental disease diagnosis, incorporating a method for tooth image recognition that involves acquiring an image of a tooth area to be detected and inputting this image into a dental disease recognition model, which outputs results identifying the position and type of dental disease. The image acquisition process utilizes an intelligent device that includes a handheld part and an upper acquisition part, connected by a rod and equipped with a waterproof cover. The image acquisition module contains various components such as an ARM processor for image processing and video coding, LED light units for illumination, and a gyroscope for stability during image capture. Prior to inputting the image into the recognition model, brightness and contrast evaluations are performed to enhance the image if necessary. The dental disease recognition model is trained using a MASK-RCNN convolutional neural network, which processes multiple sample images to achieve accurate localization and classification of dental diseases by filtering and matching color and texture features from the acquired images.
[0009] Indian patent application 202411041172 describes an oral health maintenance assistive device consists of an elongated cylindrical body with proximal and distal portions. A user-friendly handle allows positioning toward the mouth, while an AI-based imaging unit determines the distance to the user's mouth. An L-shaped telescopic rod with an electronic nozzle dispenses toothpaste over primary bristles on a platform. Motorized sliders translate secondary bristles, and a gyroscopic sensor monitors platform angular velocity. A color sensor evaluates the user's teeth, and a speaker delivers voice commands for guidance. A dirt sensor detects debris on the bristles, and an L-shaped telescopic bar with spikes vibrates for enhanced cleaning. Finally, a U-shaped plate effectively cleans the user's tongue.
[0010] State-of-the-art suffers from the following limitations:
[0011] The state of the arts does not consider the detection of dental disease using convolutional neural networks (CNN). The existing system lacks the capability to perform automated analysis of dental X-ray images and does not utilize cloud-based technologies for data management and diagnosis. So, the present invention provides a detection of dental disease using convolutional neural networks (CNN). Dental X-ray images from various dental clinics are securely collected and processed, ensuring standardized quality through noise reduction, resizing to uniform dimensions and normalization to enhance contrast and brightness. The image processing phase prepares the X-ray images for reliable analysis. Utilizing a Convolutional Neural Network (CNN) architecture, the system performs feature extraction to identify significant patterns related to dental conditions. The classification phase subsequently categorizes dental diseases, such as cavities, periodontal disease and tooth fractures. The diagnostic results are transmitted to an IoT Cloud Server, which manages data storage, analysis and real-time notifications, which ensures timely communication of findings to healthcare providers and patients, facilitating prompt diagnosis and informed dental health management.
OBJECTIVES OF THE INVENTION
[0012] The main objective of the present invention is to provide automated detection and classification of dental diseases from X-ray images using advanced image processing techniques and Convolutional Neural Networks (CNNs).
[0013] Another objective of the present invention is to ensure standardized pre-processing of dental X-ray images, including resizing, normalization and noise reduction, to enhance image quality and consistency across various dental clinics and hospitals.
[0014] Another objective of the present invention is to employ Convolutional Neural Networks (CNNs) for robust feature extraction from dental X-ray images, enabling reliable identification of significant patterns and elements related to various dental conditions.
[0015] Further objective of the present invention is to classify detected dental diseases into categories such as cavities, periodontal disease and tooth fractures, providing a detailed evaluation of dental health based on the analyzed X-ray images.
[0016] Yet another objective of the present invention is to connect the diagnostic results to an IoT cloud server, facilitating efficient data storage, analysis and real-time notifications for healthcare providers and patients, ensuring timely communication and management of dental health issues.
SUMMARY OF THE INVENTION
[0017] The present invention summary is easy to understand before the hardware and system enablement were illustrated in this present invention. There have been multiple possible embodiments that do not expressly point up in this method's present acknowledgment. Here, the conditions are used to explain the purpose of exacting versions or embodiments for understanding the present invention
[0018] Another aspect of the present invention is the detection of dental diseases using convolutional neural networks (CNN), which involves a system that analyzes Dental X-ray images for identifying and classifying various dental conditions. Dental X-ray images collected from multiple dental clinics are processed to enhance their quality and ensure uniformity through techniques such as resizing, normalization and noise reduction. The Convolutional Neural Network (CNN) performs feature extraction to identify significant patterns associated with dental diseases. Following this, the system classifies the detected conditions into categories such as cavities, periodontal disease and tooth fractures. The diagnostic results are transmitted to an IoT cloud server, which manages data storage and analysis, providing real-time notifications to healthcare providers and patients, thereby facilitating timely diagnosis and treatment of dental health issues.
[0019] Accordingly, one aspect of the present invention is the preprocessing of Dental X-ray images. This crucial step involves standardizing image dimensions and enhancing the quality of the images through normalization, which adjusts brightness and contrast levels to ensure consistency across the dataset. Additionally, noise reduction techniques are applied to remove any artifacts or distortions present in the X-ray images which are essential for preparing the images for reliable analysis and ensuring reliable results from the subsequent CNN classification process.
[0020] Another aspect of the present invention is the feature extraction and classification process performed by the Convolutional Neural Network (CNN). Once the images are preprocessed, the CNN is employed to analyze the refined X-ray images to identify significant patterns and features indicative of dental conditions. The CNN architecture, comprising convolutional layers and pooling layers, captures intricate details within the images, enabling the system to detect anomalies such as cavities, periodontal disease and other dental pathologies. During this process, the extracted features are utilized for classification, wherein the CNN categorizes the detected conditions based on learned patterns from the training data.
[0021] Still, another aspect of the present invention is the transmission of diagnostic results to an IoT cloud server. After classification, the system securely transmits the diagnostic results to the cloud server, which is responsible for managing data storage and analysis. The server processes the results to generate detailed reports, providing real-time notifications to both healthcare providers and patients.
BRIEF DESCRIPTION OF THE DRAWINGS
[0022] The accompanying drawings, which are incorporated, constitute a part of the specification, illustrate the invention's embodiment, and the description serves to explain the principles of the invention.
[0023] Various embodiments will be described under the appended drawings, which are provided to illustrate the present invention.
[0024] Figure.1 illustrates the block diagram of the present invention as provided in the present invention.
[0025] Figure 2 illustrates the CNN model for dental disease diagnosis as provided in the present invention.
[0026] Figure 3 illustrates the flow chart of the present invention as provided in the present invention.
[0027] Figure 4 illustrates the communication protocol diagram of the present invention as provided in the present invention.
DETAILED DESCRIPTION OF THE INVENTION
[0028] The present invention is easily understood with references, detailed descriptions, block diagrams, and figures. Here, various embodiments have been discussed regarding the block diagram, architecture, and other references. Some embodiments of this invention, illustrating its features, will now be discussed, and the disclosed embodiments are merely exemplary of the invention that may be embodied in various forms.
[0029] In contemporary dental imaging, the detection of dental diseases from X-ray images typically involves manual interpretation, which can be time-consuming and subject to human error. The accurate identification of conditions such as cavities, periodontal disease and fractures is crucial for timely intervention and effective treatment planning. Once identified, these conditions require regular monitoring to assess progression and guide appropriate therapeutic measures. However, traditional manual methods lack standardized approaches, leading to variability in diagnostic accuracy across dental clinics. This inconsistency may result in delays in diagnosis and treatment, adversely affecting patient outcomes.
[0030] So, the present invention provides an innovative solution for the detection of dental diseases using Convolutional Neural Networks (CNN), aimed at enhancing diagnostic accuracy and efficiency in dental care. The system comprises several components, including Dental X-ray images, image processing modules, a Convolutional Neural Network (CNN), an IoT Cloud server and more. The process commences with the Dental X-ray Dataset, which is a collection of X-ray images gathered from various dental clinics and hospitals. This diverse dataset is essential for ensuring that the system can generalize well across different populations and types of dental conditions.
[0031] Once the X-ray images are collected, they undergo a series of image processing steps designed to enhance their quality and ensure uniformity. These preprocessing techniques include resizing the images to standardize dimensions, normalization to adjust brightness and contrast levels and noise reduction to eliminate any artifacts or distortions. Such preprocessing is pivotal for preparing the images for reliable analysis, as it ensures that the subsequent steps in the diagnostic process are based on high-quality data. Without these enhancements, the performance of the CNN could be significantly compromised, leading to potential misdiagnoses.
[0032] After the images have been preprocessed, they are analyzed using a Convolutional Neural Network (CNN). The CNN plays a pivotal role in the detection system, as it performs feature extraction to identify significant patterns and characteristics that are indicative of various dental conditions. This phase is essential for the system to recognize subtle differences in the X-ray images that might indicate issues such as cavities, periodontal disease or tooth fractures.
[0033] Following the feature extraction phase, the CNN transitions into the classification phase, where it assesses the extracted features to detect and categorize the identified dental diseases. The automated analysis provided by this system not only enhances the reliability of diagnoses but also accelerates the evaluation process, allowing dental professionals to make informed decisions quickly, which is particularly beneficial in busy dental practices, where timely interventions can significantly impact patient outcomes.
[0034] Once the diagnostic results have been generated, they are transmitted to an IoT Cloud Server that manages several critical functions, including data storage, data analysis and real-time notifications. The cloud server securely stores the diagnostic results and processes them to generate detailed reports that are essential for both patients and healthcare providers. Moreover, the cloud system is designed to send alerts and detailed findings promptly, ensuring that healthcare providers are notified of critical results that require immediate attention.
[0035] Patients also benefit from the cloud-based infrastructure, as they can access their results and follow-up reminders through a dedicated Patient Portal which keeps patients informed about their dental health and any necessary actions they need to take, fostering greater engagement in their care. By providing easy access to diagnostic information, the system encourages proactive management of dental health, empowering patients to seek timely treatment and follow appropriate care protocols.
[0036] The present invention shows the block diagram of the present invention (100) further detailed descriptions of the present invention are stated here in the attached drawings. Thus, the detailed embodiments of the present invention are disclosed here to describe the present invention.
[0037] In this embodiment of the present invention, as shown in the figure.1 refers to the block diagram of the present invention (100), which comprises Dental X-ray dataset from different regions (101), Image Processing (102), CNN(103), IoT Cloud server (104) and more.
[0038] The system begins with a Dental X-ray Dataset (101), comprising a collection of X-ray images sourced from various dental clinics and hospitals. This dataset forms the foundation for the system's analytical processes. The collected images undergo a series of Image Processing (102) steps designed to enhance their quality, which includes cropping (1021) to focus on relevant areas, resizing (1022) to standardize image dimensions, noise reduction (1023) to eliminate artifacts and distortions, and normalization (1024) to adjust brightness and contrast levels. These preprocessing techniques are essential for ensuring that the images are consistent and suitable for reliable analysis.
[0039] Once the images have been preprocessed, they are fed into a Convolutional Neural Network (CNN) (103), which is responsible for both feature extraction and classification. During the feature extraction phase, the CNN identifies key patterns and features in the X-ray images that are indicative of dental diseases such as cavities, periodontal disease and tooth fractures. These features are essential for making reliable diagnoses. In the classification phase, the CNN categorizes the identified dental conditions based on the extracted features, providing a detailed evaluation of the patient's dental health which reduces the potential for human error and accelerates the diagnostic timeline, enabling more timely interventions by dental professionals.
[0040] Following the analysis by CNN, the diagnostic results are securely transmitted to an IoT Cloud Server (104). The cloud server plays a pivotal role in managing several key functions, including data storage, data analysis and real-time notifications. Once the results are stored in the cloud, they are processed to generate detailed diagnostic reports, which are essential for both healthcare providers and patients. Additionally, the IoT cloud server (104) sends alerts and findings to relevant parties, ensuring that healthcare providers receive timely notifications for diagnosis and treatment, while patients are kept informed of their results.
[0041] For healthcare providers (105), the system ensures that they receive real-time notifications that facilitate timely diagnosis and prompt initiation of treatment which is essential for improving patient outcomes, as it allows for the early detection and management of dental diseases. The system also incorporates a Patient Portal (106), which provides patients with easy access to their diagnostic results and follow-up reminders.
[0042] In another embodiment of the present invention is shown in the figure.2 refers to the CNN model for dental disease diagnosis (200), which comprises the Dental diseases image dataset (201), pooling layer (2x2) (203), Convolution layer, 60 filters (5x5) (RELU) (204), Pooling layer (2x2) (205), Fully connected layer (Dropout) (208) and more.
[0043] The process begins with the Dental Diseases Image Dataset (201), which acts as the input to the CNN. This dataset includes X-ray images that are important for the network to learn from and eventually classify into different categories of dental conditions. These images capture a wide range of dental diseases, ensuring the network is trained on a diverse set of cases for robust diagnostic capabilities.
[0044] The network's first step in processing these images is the Convolution Layer (202). In this layer, the system applies 30 filters, each of size 5x5 pixels, to the input images. These filters scan the image to detect important features, such as edges, shapes, and textures, that are relevant to dental health. The use of the ReLU activation function introduces non-linearity, allowing the model to capture more complex patterns that linear functions would miss. The ReLU function ensures that the CNN can model intricate relationships in dental images, such as subtle differences between healthy tissue and early signs of disease. This layer is critical for transforming the raw image data into a more structured form that highlights key features.
[0045] Following the convolution operation, the output passes through a Pooling Layer (203). This layer performs a 2x2 max pooling operation, which reduces the dimensionality of the feature maps produced by the previous layer. By retaining the most significant information from each 2x2 region of the feature map, this step reduces the computational complexity of the network while preserving the essential features needed for diagnosis. Pooling layers help make the network more efficient by focusing only on the most important parts of the image, such as regions showing dental abnormalities. After this, a second Convolution Layer (204) with 60 filters, also of size 5x5, is applied, further refining the feature maps. Again, the ReLU activation is used to ensure the model captures complex patterns related to dental diseases.
[0046] As the network progresses, another Pooling Layer (207) is applied to further reduce the dimensionality of the feature maps. The role of these repeated convolution and pooling operations is to enable the CNN to recognize increasingly complex patterns in the X-ray images. This is followed by a third Convolution Layer (205), also with 60 filters, to detect even more specific features, and another Pooling Layer (206) to reduce dimensionality. At this point, the feature maps contain highly refined representations of the dental images, ready to be classified. The Fully Connected Layer (208) takes these refined feature maps, flattens them into a one-dimensional vector, and connects them to neurons in the next layer. This dense connection enables the network to combine all the learned features to make a final decision on the diagnosis. Dropout is applied at this stage to prevent overfitting by randomly deactivating some neurons during training, ensuring the network generalizes well to new, unseen images.
[0047] Finally, the output from the fully connected layer is passed through a Softmax Layer, which computes the probability distribution over the possible output classes. This allows the network to assign a probability to each dental condition based on the features it has learned from the input images. The Output Layer (209) then produces the final diagnostic result, indicating the specific dental disease or a healthy outcome.
[0048] The other embodiment of the present invention is shown in the figure.3 refers to the flow chart of the present invention (300), which comprises dataset collection (301), Image preprocessing (302), Image augmentation and feature extraction (303), data splitting (304) and Evaluation and visualization (307).
[0049] The flowchart outlines the detailed process of diagnosing dental diseases using a Convolutional Neural Network (CNN). It begins with Dataset Collection (301), where dental X-ray images are gathered from various sources, including dental clinics and hospitals. Following dataset collection, the images undergo Image Preprocessing (302) to improve their quality and ensure uniformity across the dataset. Preprocessing involves multiple tasks, such as cropping to focus on the relevant parts of the X-rays, resizing to standardize dimensions and applying noise reduction techniques to remove artifacts and distortions. Normalization is also applied to adjust the brightness and contrast, ensuring that the images are consistent and free from variability that could affect model training. These preprocessing steps are essential to prepare the images for the subsequent stages, as they enhance the clarity of the important features that the CNN will later analyze.
[0050] The next stage is Image Augmentation and Feature Extraction (303), where the dataset is expanded using image augmentation techniques. This involves generating new variations of the images by rotating, flipping, zooming, or shearing them. Augmentation helps the model generalize better by exposing it to a wider range of image orientations and conditions, which reduces the risk of overfitting. Simultaneously, feature extraction methods are applied to detect important elements in the images, such as edges, shapes and textures that are crucial for dental disease diagnosis. These features provide CNN with the necessary information to differentiate between healthy teeth and various dental conditions.
[0051] After preprocessing and augmentation, the data is divided into subsets in the Data Splitting (304) stage. The dataset is split into a Training Dataset (3041) and a Testing Dataset (3042). The training dataset is used to teach the CNN model, allowing it to adjust its internal parameters and learn the patterns associated with dental diseases. The testing dataset is reserved for evaluating the model's performance on unseen data, ensuring that the model can generalize its learned knowledge to new, real-world cases. This separation of data is essential for assessing how well the model will perform when applied in clinical settings.
[0052] The CNN Model Training (305) step is where the actual learning takes place. The preprocessed and augmented images from the training dataset are fed into the CNN, which gradually learns to identify features that correspond to different dental diseases. During training, the model's parameters are continuously updated to minimize the error between its predictions and the actual labels of the images. This iterative process allows the CNN to refine its ability to classify dental conditions accurately. After the model is fully trained, it proceeds to Model Testing (306), where its performance is evaluated on the testing dataset.
[0053] Finally, the process concludes with Evaluation and Visualization (307). The model's performance is analyzed using various evaluation metrics, providing a clear assessment of how well it can diagnose dental diseases. Additionally, visualization techniques may be employed to interpret the model's decision-making process, such as examining the feature maps or attention weights to understand which parts of the images the CNN focuses on during classification. This stage helps in identifying any areas where the model may need further improvement and provides a clearer picture of its overall diagnostic capabilities.
[0054] The other embodiment of the present invention is shown in the figure.4 refers to the communication protocol diagram of the present invention (400). The interaction occurs among the Dental X-ray dataset from different regions (401), IoT cloud server (Data storage and processing) (402), Processing node (Segmentation and preprocessing) (403) and Classification Node (Analysis and classification using CNN) (404).
[0055] The communication protocol diagram for the dental disease diagnosis system begins with the Dental X-ray Dataset (401), which is the foundational input for the entire process. This dataset comprises a diverse collection of dental X-ray images sourced from various regions, capturing a wide range of dental conditions. The quality and variety of these images are crucial, as they provide the necessary data for training and testing the Convolutional Neural Network (CNN) that will ultimately classify the dental diseases.
[0056] Following the acquisition of the dental X-ray images, they are sent to the IoT Cloud Server (402), which is responsible for the storage and initial processing of the images. By utilizing an IoT cloud architecture, the system benefits from scalable storage solutions and enhanced accessibility. The cloud server facilitates the management of large datasets, allowing for efficient data processing and real-time updates which ensures that healthcare providers can access patient information and images from anywhere, streamlining the workflow and making collaboration among professionals more efficient.
[0057] Once the images are securely stored in the cloud, they are forwarded to the Processing Node (Segmentation & Preprocessing) (403). In this stage, the images undergo essential preprocessing steps, including Image Segmentation, which involves dividing each X-ray into distinct regions based on characteristics such as teeth and gums. This segmentation is vital for isolating areas of interest that the CNN will analyze. Additionally, preprocessing tasks like noise reduction and normalization enhance the quality of the images, ensuring that they are in optimal condition for analysis.
[0058] The processed images are then sent to the Classification Node (Analysis & Classification using CNN) (404), where the core analysis occurs. Here, the CNN architecture comes into play, designed specifically for analyzing image data. The CNN employs multiple layers that extract features from the segmented images, identifying patterns associated with various dental diseases. This classification process allows the CNN to analyze the images, using its training to diagnose conditions based on the learned characteristics of the diseases.
[0059] After the analysis, the system proceeds to Generate Results Reports, which provide detailed insights into the detected dental diseases. These reports summarize the findings and provide critical information that healthcare providers can use for treatment planning. Once generated, these results are shared through a Healthcare Provider/Patient's Portal. This portal facilitates easy access to diagnostic information for both healthcare providers and patients, fostering transparent communication. , Claims:We claim,
1. A dental disease detection system (100) utilizing a Convolutional Neural Network (CNN) to analyze Dental X-ray images, comprising:
a) a Dental X-ray dataset (101) sourced from various dental clinics and hospitals for comprehensive analysis;
b) an Image Processing unit (102) to enhance image quality through cropping (1021), resizing (1022), noise reduction (1023) and normalization (1024);
c) a CNN (103) for feature extraction and classification of dental diseases;
d) an IoT Cloud server (104) for secure data transmission and storage; and
e) a Patient Portal (106) for user access to diagnostic results.
2.The dental disease detection system (100) as claimed in Claim 1, wherein the said Image Processing unit (102) applies a series of preprocessing techniques including cropping (1021), resizing (1022), noise reduction (1023) and normalization (1024) to ensure the consistency and suitability of X-ray images for analysis by the CNN (103).
3.The dental disease detection system (100) as claimed in Claim 1, wherein the said CNN (103) performs feature extraction to identify patterns indicative of dental diseases, including cavities, periodontal disease and tooth fractures, followed by classification to provide detailed evaluations of patients' dental health.
4. The dental disease detection system (100) as claimed in Claim 1, wherein the IoT Cloud server (104) securely transmits diagnostic results from the CNN (103) and facilitates data storage, analysis and real-time notifications to healthcare providers (105) and patients.

Documents