Description:FIELD OF THE INVENTION

[0001] The present invention relates to a system for detecting lung and colon cancer that is capable of detecting the lung and colon cancer quickly by classifying the stages of the cancer in a precise manner automatically.

BACKGROUND OF THE INVENTION

[0002] Lung and colon cancers are types of malignant tumors that originate in the lungs and colon (large intestine), respectively. Lung cancer is often linked to smoking, environmental exposures, and genetic factors, and may present with symptoms like persistent cough, chest pain, or shortness of breath. Colon cancer typically develops from polyps in the colon or rectum and may cause changes in bowel habits, blood in stool, or abdominal discomfort. Detection of these cancers involves various methods: imaging techniques such as chest X-rays, CT scans, and colonoscopies allow visualization of tumors; laboratory tests like blood markers (e.g., carcinoembryonic antigen for colon cancer) can aid diagnosis; and biopsy procedures confirm malignancy. Early detection is crucial for effective treatment and improved prognosis.

[0003] Traditionally, lung and colon cancer detection relied on methods such as chest X-rays, sputum cytology, and colonoscopy, which have notable drawbacks. Chest X-rays and sputum tests for lung cancer often lack sensitivity, potentially missing early-stage tumors, and may produce false positives or negatives, leading to delayed diagnosis. Colonoscopy, the gold standard for colon cancer detection, is invasive, uncomfortable for patients, and requires bowel preparation, which can deter patients from screening regularly. Additionally, these traditional methods involve exposure to radiation and carry risks like perforation or bleeding during invasive procedures. Consequently, these limitations highlight the need for more accurate, less invasive, and patient-friendly diagnostic techniques in early cancer detection.

[0004] EP2253714A1 The present invention relates to a method for detecting lung cancer using a lung cancer-specific biomarker, and more particularly to a biomarker for lung cancer diagnosis, which can detect methylation of PCDHGA12 gene whose 5'UTR or exon 1 region is specifically methylated in lung cancer cells, and to a method of detecting lung cancer and the stage of its progression using the biomarker. The diagnostic kit according to the present invention makes it possible to diagnose lung cancer at an early stage in an accurate and rapid manner compared to conventional methods and can be used for prognosis and monitoring of lung cancer and the stage of its progression.

[0005] US20130345322A1 The present invention provides a method for diagnosing or detecting colorectal cancer in a subject, the method comprising determining the presence and/or level of biomarkers selected from IL-8, IGFBP2, MAC2BP, M2PK, IL-13, DKK-3, EpCam, MIP1β, TGFβ1, and TIMP-1. The invention also relates to diagnostic kits comprising reagents for determining the presence and/or level of the biomarkers and methods of detecting or diagnosing colorectal cancer.

[0006] Conventionally, many devices have been developed to detect the lung and colon cancer but these devices lack automated detection which might causes mistakes and delays limiting portability and necessitates high performance computers unable to provide the real time data.

[0007] In order to overcome the aforementioned drawbacks, there exists a need in the art to develop a system that is capable of detecting the lung and colon cancer quickly by classifying different stages of the cancer precisely. Additionally, the system is capable of securing the data during collection, processing and storage for maintaining privacy of the user providing it in the real time.

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 detecting the lung and colon cancer, classifying stages of the cancer precisely by reducing delays and improving the speed.

[0010] Another object of the present invention is to develop a system that is capable of securing the data during collection, processing and storage for maintaining privacy of the user.

[0011] Yet another object of the present invention is to develop a system that is capable of enabling remote dataset access and real time communication by reducing power usage and providing more effective interference.

[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 system for detecting lung and colon cancer that is capable of detecting different stages of the lung and colon cancer in real time quickly and precisely. Additionally the system is capable of securing the data of the user to maintain privacy.

[0014] According to an embodiment of the present invention, a system for detecting lung and colon cancer comprising of a gateway module, such as a smartphone or tablet, that collects patient data and sends it to a master computer module, the module preprocesses medical images to improve quality before analysis by using hyper parameter tuning to improve classification accuracy and reduce errors, a master computer module that receives and processes the patient data from the gateway module, a cloud controller module that manages data storage and access on a cloud platform, manages the storage of processed patient data on a cloud platform and allows remote access to the stored data for further analysis.

[0015] According to another embodiment of the present invention, the system further comprise of a CNN-based module that analyzes medical images to classify lung and colon cancer stages classifies the images into cancer stages, from Stage 0 to Stage 4, using deep learning, a fog computing module that processes data locally to reduce delays and improve speed, a service director module that coordinates data flow between the gateway module, master computer module, and clouds controller module, a protection supervisor module that secures patient data during collection, processing, and storage and a service observer module that monitors the performance of the CNN-based module to ensure accurate cancer stage classification.

[0016] 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

[0017] 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 of a system for detecting lung and colon cancer.

DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] 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.

[0020] 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.

[0021] The present invention relates to a system for detecting lung and colon cancer that is capable of detecting the lung and colon cancer with classifying different stages of the cancer precisely in real time by utilizing low power processors and maintaining the user’s data privacy while data collection, processing, and storage.

[0022] Referring to Figure 1, a block diagram of a system for detecting lung and colon cancer comprising a gateway module, connected to a master computer module, connected to a cloud controller module, that is connected to a service director module, connected to a protection supervisor module connected to a service observer module, connected to a CNN-based module, connected to a fog computing module.

[0023] The system disclosed herein includes a gateway module such as a smartphone or tablet. The gateway module collects a patient’s data and send it to a master computer module. It functions as an intermediary system that collects a patient’s data from medical devices through interfaces such as Bluetooth, Wi-Fi. It processes the raw signals, converts them into standardized digital formats, and performs initial data filtering. Using embedded microcontrollers, the gateway securely transmits the processed data via wireless communication protocols like MQTT, HTTP, to the master computer module.

[0024] The master computer module receives the data and processes the data from the gateway module. It functions by continuously listening for incoming data transmissions from the gateway module via network protocols such as TCP/IP, MQTT, or HTTP over a wireless connection. Upon receiving the data, it authenticates and decrypts the information to ensure security and integrity. The data is then parsed and organized within the system, where it undergo further processing such as filtering. The master computer stores the processed data in databases for historical tracking and utilizes analytical tools, machine learning models for real-time assessment or decision-making.

[0025] After processing the data, a cloud controller module is present in the system accessed on cloud platform. The cloud controller manages the storage of processed patient data on cloud platform and allows the user to remotely access the stored data for further analysis. The cloud controller module operates as an intermediary that manages communication between the master computer module and the cloud platform. It securely transmits processed patient data from the local system to the cloud using encrypted protocols such as HTTPS over TLS, ensuring data confidentiality and integrity. The cloud controller handles data storage by organizing and uploading the information into cloud databases like AWS S3. It also manages user authentication and access control, enabling authorized users to remotely log in through web to retrieve, visualize, and analyze the stored data in real-time. Furthermore, the cloud controller facilitate automated data synchronization, backup, and integration with analytical tools enabling healthcare providers to perform remote monitoring, diagnostics, and decision-making efficiently from any location.

[0026] The system includes a service director module that coordinates data flow between the gateway module, master computer module, and clouds controller module. The service director module functions as a centralized orchestrator that manages and coordinates data flow among the gateway module, master computer module, and cloud controller module. It operates by establishing secure communication channels using protocols like MQTT to facilitate real-time data exchange. The service director receives raw data from the gateway module, directs it to the master computer module for processing and analysis, and then oversees the transfer of processed data to the cloud controller module for storage and remote access. It also monitors system statuses, manages data routing based on predefined rules or priorities, and ensures synchronization and integrity across all components. Additionally, the service director handles error detection, retries, and logging to maintain seamless, reliable operation of the entire system, enabling efficient coordination and data management in a distributed healthcare monitoring environment.

[0027] Once the data of the patient is stored, a CNN-based module present in the system preprocesses medical images to improve quality before analysis and then analyze the medical images. The CNN-based module uses techniques such as normalization, noise reduction, contrast enhancement, and resizing to improve image quality and ensure consistency for accurate analysis. It then feeds these enhanced images into a convolutional neural network, which automatically extracts hierarchical features through layers of convolution, pooling, and activation functions. The CNN analyzes the features to identify patterns, structures, or abnormalities relevant to medical diagnosis, such as tumors or lesions. During training, the network learns to classify or segment images based on labeled datasets, and during inference, it applies this learned knowledge to new images for automated diagnosis or detection. This combination of preprocessing and deep learning-based analysis enables accurate, efficient, and automated interpretation of medical images, aiding clinicians in decision-making.

[0028] The CNN-based module classify lung and colon cancer stages classifies the images into cancer stages, from Stage 0 to Stage 4, using deep learning. During training, the CNN learns to recognize subtle patterns and morphological differences associated with each cancer stage by minimizing a loss function that compares its predictions to labeled ground truth data. Once trained, the model applies its learned feature representations to new images, producing probability scores for each stage (Stage 0 to Stage 4) through a fully connected classifier layer, and assigns the stage with the highest confidence. This deep learning approach enables accurate, automated staging of cancer by capturing complex visual cues that may be challenging for manual analysis.

[0029] A service observer module that monitors the performance of the CNN-based module to ensure accurate cancer stage classification by using hyper parameter tuning to improve classification accuracy and reduce errors. The service observer module continuously evaluates key metrics such as accuracy, precision, recall, and loss during training and inference. It tracks these metrics over time to detect potential issues like overfitting, under fitting in data distribution. To enhance classification accuracy and reduce errors, the observer employs hyper parameter tuning techniques such as grid search, random search, Bayesian optimization to adjust parameters like learning rate, number of layers, filter sizes, dropout rates, and batch size. These adjustments validates on a separate validation set to identify optimal configurations that improve model generalization. Once optimal hyper parameters are determined, the updated model is retrained or fine-tuned to achieve better performance, ensuring reliable and accurate cancer stage classification while maintaining robustness against variability in input data.

[0030] After classifying the stages of the cancer, a fog computing module processes data locally to reduce delays and improve speed. The fog computing module processes data locally at or near the data source such as medical imaging devices by deploying lightweight computing resources within the local network infrastructure. It pre-processes, analyzes, and filters raw data in real-time, performing tasks like feature extraction, anomaly detection, preliminary classification without relying on distant cloud servers. This localized processing reduces latency by minimizing data transmission delays and decreases bandwidth usage, enabling faster decision-making crucial for time-sensitive applications like cancer diagnosis. The fog node also synchronize with centralized cloud systems for comprehensive analysis or storage, but its primary function is to ensure rapid, efficient, and secure data handling at the edge, thereby improving overall system responsiveness and supporting immediate clinical interventions.

[0031] Herein, a protection supervisor module that secures patient data during collection, processing, and storage. The protection supervisor module ensures the security and privacy of patient data throughout collection, processing, and storage by implementing multi-layered security measures such as encryption, access control, and authentication protocols. During data collection, it encrypts sensitive information using strong cryptographic process to prevent unauthorized interception. It enforces strict access controls and role-based permissions to restrict data access to authorized personnel only, ensuring compliance with privacy regulations like HIPAA. During data processing, the module monitors and logs all access and operations, detecting potential anomalies or unauthorized activities through intrusion detection systems. When data is stored, it employs secure storage, including encrypted databases and secure key management, to safeguard against breaches. Additionally, it incorporate audit trails and real-time alerts to promptly identify and respond to security threats, thereby maintaining the integrity, confidentiality, and privacy of patient information throughout its lifecycle.

[0032] The present invention works best in the following manner, the gateway module collects the patient’s data and send it to the master computer module. The master computer module receives the data and processes the data from the gateway module. The cloud controller manages the storage of processed patient data on cloud platform and allows the user to remotely access the stored data for further analysis. The service director module that coordinates data flow between the gateway module, master computer module, and clouds controller module. The CNN-based module present in the system preprocesses medical images to improve quality before analysis and then analyze the medical images module classifying lung and colon cancer stages classifies the images into cancer stages, from Stage 0 to Stage 4, using deep learning. The service observer module that monitors the performance of the CNN-based module to ensure accurate cancer stage classification by using hyper parameter tuning to improve classification accuracy and reduce errors. The fog computing module processes data locally to reduce delays and improve speed. The protection supervisor module that secures patient data during collection, processing, and storage.

[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 system for detecting lung and colon cancer, comprising:

i) a gateway module, such as a smartphone or tablet, that collects patient data and sends it to a master computer module;
ii) a master computer module that receives and processes the patient data from the gateway module;
iii) a cloud controller module that manages data storage and access on a cloud platform, manages the storage of processed patient data on a cloud platform and allows remote access to the stored data for further analysis;
iv) a CNN-based module that analyzes medical images to classify lung and colon cancer stages classifies the images into cancer stages, from Stage 0 to Stage 4, using deep learning; and
v) a fog computing module that processes data locally to reduce delays and improve speed.

2) The system as claimed in claim 1, wherein the system further comprising a service director module that coordinates data flow between the gateway module, master computer module, and clouds controller module.

3) The system as claimed in claim 1, wherein the system further comprising a protection supervisor module that secures patient data during collection, processing, and storage.

4) The system as claimed in claim 1, wherein the system further comprising a service observer module that monitors the performance of the CNN-based module to ensure accurate cancer stage classification.

5) The system as claimed in claim 1, wherein the module preprocesses medical images to improve quality before analysis.

6) The system as claimed in claim 1, wherein the module uses hyper parameter tuning to improve classification accuracy and reduce errors.