Description:FIELD OF THE INVENTION

[0001] The present invention relates to a breast cancer detection system from ultrasound images using spatial and temporal feature extraction, enabling earlier diagnoses. The system also enhances detection reliability through efficient distributed data processing, ensuring consistent and timely patient outcomes.

BACKGROUND OF THE INVENTION

[0002] Mammography, the primary screening method, uses low-dose X-rays to detect tumors or microcalcifications. Ultrasound and MRI provide detailed imaging for further evaluation. AI algorithms analyze imaging data, improving accuracy by identifying patterns indicative of cancer. Biopsies confirm diagnoses by examining tissue samples. These systems enable early detection, critical for effective treatment and improved survival rates. Regular screenings, combined with clinical breast exams and self-exams, enhance the system’s effectiveness in detecting breast cancer at treatable stages.

[0003] Traditional breast cancer detection methods include mammography, clinical breast exams (CBE), and breast self-exams (BSE). Mammography uses low-dose X-rays to identify tumors or microcalcifications but has limitations: it may miss 10-20% of cancers (false negatives), especially in dense breasts, and can produce false positives, leading to unnecessary biopsies. CBE, performed by healthcare professionals, relies on physical palpation but misses small or deep tumors and depends on examiner skill. BSE encourages self-awareness but lacks sensitivity, often missing early-stage cancers. These methods are less effective in younger women with denser breasts and may require supplementary imaging for accuracy.

[0004] WO2024141932A1 discloses an apparatus and method for early detection of breast cancer uses ultra- wideband and multi-angle microwave imaging. The apparatus includes a matching dielectric layer and a conformal antenna array with antenna elements arranged in a hemispherical pattern. The method achieves high resolution and high signal-to-clutter ratio using synthesized focusing (SF) and specialized clutter rejection (SCR) algorithms. The improved performance of the method is demonstrated experimentally using a realistic, heterogeneous breast phantom composed of materials whose dielectric properties closely match those of skin, adipose, glandular, and tumorous breast tissue.

[0005] US11479822B2 discloses an intended to provide a kit or a device for the detection of breast cancer and a method for detecting breast cancer. The present invention provides a kit or a device for the detection of breast cancer, comprising nucleic acid(s) capable of specifically binding to a miRNA in a sample of a subject, and a method for detecting breast cancer, comprising measuring the miRNA in vitro.

[0006] Conventionally, many systems are available in the market for breast cancer detection but existing detection systems often lack efficient distributed processing, struggling under high demand. They may also suffer from overfitting, leading to inconsistent or inaccurate diagnoses, and often don't fully leverage spatial and temporal features from ultrasound images.

[0007] In order to overcome the aforementioned drawbacks, there exists a need in the art to develop a system accurately detects breast cancer via advanced image analysis, ensuring reliable and consistent diagnoses even under heavy load, ultimately leading to earlier detection and better patient outcomes.

OBJECTS OF THE INVENTION

[0008] The principal object of the present invention is to overcome the disadvantages of the prior art.

[0009] An object of the present invention is to develop a system that is capable of accurately detect breast cancer by analyzing ultrasound images using a combination of spatial and temporal feature extraction techniques for improved classification, thus leading to earlier diagnosis and better patient outcomes.

[0010] Another object of the present invention is to develop a system that is capable of enhance the reliability of breast cancer detection by processing patient data efficiently, even during high system demand, through distributed data handling, therefore ensuring consistent and timely diagnoses for all patients.

[0011] Yet another object of the present invention is to develop a system that is capable of ensure consistent and accurate breast cancer detection by monitoring system performance and preventing model overfitting during data processing, thus maintaining high diagnostic reliability over time.

[0012] The foregoing and other objects, features, and advantages of the present invention will become readily apparent upon further review of the following detailed description of the preferred embodiment as illustrated in the accompanying drawings.

SUMMARY OF THE INVENTION

[0013] The present invention relates to a breast cancer detection system enhances breast cancer detection reliability through efficient distributed data processing, ensuring timely diagnoses even during high system demand. It also maintains consistent accuracy by monitoring system performance and preventing model overfitting, ensuring sustained diagnostic reliability.

[0014] According to an embodiment of the present invention, a breast cancer detection system comprising an IOT end module that scans patient data using ultrasound imaging, a gateway networking module that receives patient data from the IOT End Device Module and processes it using a trained CNN (convolutional neural network) and RNN (recurrent neural networks) module to detect breast cancer, a fog innovation node module that receives patient data from the gateway networking module, an information director module that selects which fog innovation node module to send patient data to for processing, a cloud data center module that stores patient data when the Fog innovation node module is overloaded and a service observer module that monitors the performance of the gateway networking module and fog innovation ode module to ensure accurate breast cancer detection.

[0015] While the invention has been described and shown with particular reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

[0016] These and other features, aspects, and advantages of the present invention will become better understood with regard to the following description, appended claims, and accompanying drawings where:
Figure 1 illustrates a block diagram depicting workflow of a breast cancer detection system.

DETAILED DESCRIPTION OF THE INVENTION

[0017] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.

[0018] In any embodiment described herein, the open-ended terms "comprising," "comprises,” and the like (which are synonymous with "including," "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of," consists essentially of," and the like or the respective closed phrases "consisting of," "consists of, the like.

[0019] As used herein, the singular forms “a,” “an,” and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.

[0020] The present invention relates to a breast cancer detection system that accurately detect breast cancer from ultrasound images using spatial and temporal feature extraction, leading to earlier diagnoses. It also ensures consistent and accurate detection by monitoring system performance and preventing model overfitting, maintaining high diagnostic reliability.

[0021] Referring to Figure 1, a block diagram depicting workflow of a breast cancer detection system is illustrated, comprising a IOT end module, gateway networking module, fog innovation node module, information direction module, cloud data center module, service observation module.

[0022] The invention is a breast cancer detection system that uses advanced technology to improve the accuracy and efficiency of diagnosing breast cancer from ultrasound images. The system integrates Internet of Things (IoT) devices, machine learning, and distributed computing to process patient data reliably and quickly. It consists of six main components that work together to scan, process, store, and monitor data for effective breast cancer detection.

[0023] The first component is the IoT end module, which uses ultrasound imaging to collect patient data. This module scans breast tissue and captures detailed images, serving as the primary data source for the system. It ensures high-quality data collection, which is critical for accurate diagnosis.

[0024] The Ultrasound imaging works by sending high-frequency sound waves into the body using a probe called a transducer. These sound waves travel through tissues and bounce back when they hit different structures, such as organs or blood vessels. The transducer then receives the reflected echoes and sends this information to a computer. The computer processes the signals to create real-time images of the internal body parts. Ultrasound imaging is commonly used in medical diagnosis because it is safe, non-invasive, and provides detailed images of soft tissues, helping doctors examine organs, monitor fetal development, and diagnose various conditions.

[0025] The second component, the gateway networking module, receives the ultrasound data from the IoT end module. It processes this data using a trained convolutional neural network (CNN) and recurrent neural network (RNN) module to detect signs of breast cancer. The CNN extracts spatial features, such as patterns in the ultrasound images, while the RNN, specifically using Long Short-Term Memory (LSTM) units, analyzes temporal features to track changes over time. The gateway splits the data into 80% for training the CNN and RNN and 20% for testing, ensuring the model is well-trained and validated. The CNN and RNN module uses a ReLU activation function to enhance feature detection and a SoftMax layer for accurate classification of images as cancerous or non-cancerous.

[0026] Further, the third component is the fog innovation node module, which steps in when the gateway networking module is overloaded. It processes patient data using the same CNN and RNN module, ensuring no delays in diagnosis. To prevent overfitting, this module employs dropout regularization, which randomly disables some neurons during training to improve the model’s generalization to new data.

[0027] The CNN-RNN module combines convolutional neural networks (CNN) and recurrent neural networks (RNN, such as LSTM) to process spatiotemporal data. The CNN extracts spatial features from each frame or segment, capturing textures and patterns. These features are then passed to an LSTM, which models temporal dependencies across sequences. The spatial features from CNN and temporal features from LSTM are concatenated into a single feature vector, providing a comprehensive representation of both spatial and temporal information. This combined feature is then used for classification or other downstream tasks, making the model effective for video analysis, action recognition, and sequential data understanding.

[0028] The fourth component, mention herein the information director module, manages data flow by selecting the appropriate fog innovation node for processing when the gateway is busy. This ensures efficient workload distribution and maintains system performance under high demand. The information director module is a component responsible for managing and controlling data flow within a system. It gathers, processes, and distributes information to different parts of the system or external devices. This module ensures that relevant data is available to users or other modules when needed, maintaining data accuracy and security. It also handles tasks such as data storage, retrieval, and communication protocols. The information director module helps improve system efficiency by coordinating data exchange, reducing errors, and ensuring smooth operation.

[0029] The fifth component is the cloud data center module, which stores all patient data securely for long-term access. It also processes data when the fog innovation nodes are overloaded, acting as a backup to maintain uninterrupted operation. The cloud module ensures scalability and reliability, especially during peak usage. The cloud data centre module is a core component of cloud computing infrastructure that provides scalable, flexible, and secure storage and processing resources. It consists of interconnected servers, storage systems, networking hardware, and virtualization protocols. This module manages data hosting, resource allocation, and workload distribution across multiple virtual environments. It enables users to access and store data remotely via the internet, supporting services like cloud storage, computing, and applications. The cloud data center module ensures high availability, redundancy, and security, facilitating efficient management of large-scale data operations and supporting diverse cloud services for businesses and individuals.

[0030] The sixth component, the service observer module, monitors the performance of the gateway networking module and fog innovation nodes. It checks for processing delays, errors, or inaccuracies in breast cancer detection, ensuring the system operates reliably and delivers consistent results. The service observer module is a component designed to monitor and track the performance, status, and health of various services within a system. It collects real-time data on service availability, response times, errors, and resource usage. The module helps in detecting issues, ensuring service reliability, and providing insights for troubleshooting and optimization. It often integrates with dashboards or alerting systems to notify administrators of potential problems. By continuously observing service behavior, the service observer module enhances system stability, supports proactive maintenance, and improves overall user experience through timely insights and interventions.

[0031] The system’s strength lies in its ability to combine IoT, machine learning, and distributed computing for fast and accurate breast cancer detection. By using CNN and RNN with ReLU and SoftMax, it achieves high classification accuracy. Dropout regularization prevents overfitting, while the fog and cloud modules ensure scalability and reliability. This invention offers a practical solution for early breast cancer detection, improving patient outcomes through timely and precise diagnosis.

[0032] The present invention work best in the manner, where the invention operates through six interconnected components to facilitate accurate and efficient breast cancer detection using ultrasound images. The process begins with the IoT end module, which employs ultrasound imaging via transducer probes to capture high-quality breast tissue images, serving as the primary data source. Data from this module is transmitted to the gateway networking module, which processes it using a CNN-RNN module combining convolutional neural networks for spatial feature extraction and LSTM-based RNNs for analyzing temporal changes enhanced with ReLU activation and SoftMax classification to distinguish between cancerous and non-cancerous tissues. When the gateway is overloaded, the fog innovation node module steps in, performing similar processing with dropout regularization to prevent overfitting, ensuring no delays in diagnosis. The information director module manages data flow by directing processing requests to appropriate fog nodes, maintaining system efficiency during high demand. All data is securely stored and processed in the cloud data center module, which provides scalability, redundancy, and backup capabilities. Meanwhile, the service observer module continuously monitors performance, detecting delays, errors, or inaccuracies in detection processes, thus maintaining system reliability. This integrated system leverages IoT, machine learning, distributed computing, and advanced neural network techniques to enable rapid, accurate breast cancer diagnosis, improving early detection and patient outcomes through reliable, scalable, and real-time analysis.

[0033] Although the field of the invention has been described herein with limited reference to specific embodiments, this description is not meant to be construed in a limiting sense. Various modifications of the disclosed embodiments, as well as alternate embodiments of the invention, will become apparent to persons skilled in the art upon reference to the description of the invention. , Claims:1) A breast cancer detection system, comprising:

i) an IOT end module that scans patient data using ultrasound imaging;
ii) a gateway networking module that receives patient data from the IOT End Device Module and processes it using a trained CNN (convolutional neural network) and RNN (recurrent neural networks) module to detect breast cancer;
iii) a fog innovation node module that receives patient data from the gateway networking module and processes it using the CNN and RNN module when the gateway networking module is overloaded;
iv) an information director module that selects which fog innovation node module to send patient data to for processing;
v) a cloud data center module that stores patient data and processes it when the Fog innovation node module is overloaded; and
vi) a service observer module that monitors the performance of the gateway networking module and fog innovation ode module to ensure accurate breast cancer detection.

2) The system as claimed in claim 1, wherein the CNN and RNN module uses a ReLU activation function and a SoftMax layer to improve classification accuracy of breast cancer ultrasound images.

3) The system as claimed in claim 1, wherein the gateway networking module splits patient data into 80% training and 20% testing sets for training the CNN and RNN module.

4) The system as claimed in claim 1, wherein the fog innovation node module uses dropout regularization to prevent overfitting during breast cancer detection.

5) The system as claimed in claim 1, wherein the CNN and RNN module concatenates CNN-extracted spatial features with LSTM-extracted temporal features before classification.