1. A hybrid metaheuristic-based medical image analysis system (100), the system (100) comprising: a user device (102) configured to collect medical image data of a user through a user interface (104); a communication network (106) configured to establish a communication link for data transmission within the system (100); a processing unit (108) connected to the user device (102) via the communication network (106) and configured to process real-time data for hybrid metaheuristic-based medical image analysis, wherein the processing unit (108) further comprises: a data input module (110) configured to receive real-time data from the user device (102); a preprocessing module (112) configured to clean, normalize and reduce noise in the received data to enhance data quality; a feature extraction module (114) configured to extract relevant features from the pre-processed data; an adaptive hybrid optimization module (116) configured to perform joint optimization of selected features and model parameters using adaptive search strategies; a segmentation module (118) configured to segment regions of interest from the medical image data based on the optimized adaptive hybrid; a disease detection module (120) configured to analyse the segmented regions and detect the presence of disease; a disease classification module (122) configured to classify the detected disease into multiple categories; a performance evaluation module (124) configured to evaluate the performance of medical image analysis results; and an output module (126) configured to transmit segmented images, detected diseases, classified disease categories, and evaluated performances to the user device (102).

2. The system (100) as claimed in claim 1, wherein the system (100) further comprises a cloud database (128) configured to store and manage processed medical image data, optimized model parameters, and analysis results.

3. The system (100) as claimed in claim 1, wherein the user device (102) configured to collect medical image data including radiological images, dermoscopic images, and microscopic images.

4. The system (100) as claimed in claim 1, wherein the feature extraction module (114) configured to extract relevant features including intensity features, structural features, and texture-based features from the pre-processed data.

5. The system (100) as claimed in claim 1, wherein the adaptive hybrid optimization module (116) configured to perform joint optimization of selected features and model parameters using adaptive search strategies including a combination of sparrow search algorithm, particle swarm optimization, and differential evolution.

6. The system (100) as claimed in claim 1, wherein the segmentation module (118) utilizes U-Net model to segment regions of interest from the medical image data.

7. The system (100) as claimed in claim 1, wherein the disease classification module (122) configured to classify the detected disease into multiple categories including but not limited to benign, malignant, pre-cancerous conditions, tumors, lesions, infections, and organ-specific abnormalities using convolutional neural networks.

8. The system (100) as claimed in claim 1, wherein the performance evaluation module (124) configured to evaluate the performance of medical image analysis results including but not limited to accuracy, intersection over union, dice coefficient, and f1 score.

9. The system (100) as claimed in claim 1, wherein the performance evaluation module (124) utilizes pre-trained architectures including vgg16, vgg19, and mobilenet to evaluate the performance of medical image analysis results.

10. A method (200) for hybrid metaheuristic-based medical image analysis system (100), the method (200) comprising: collecting medical image data of a user through a user interface (104) via a user device (102); establishing a communication link for data transmission within the system (100) via a communication network (106); processing real-time data for hybrid metaheuristic-based medical image analysis via a processing unit (108), comprising several modules; receiving real-time data from the user device (102) via a data input module (110); cleaning, normalizing and reducing noise in the received data to enhance data quality via a preprocessing module (112); extracting relevant features from the pre-processed data via a feature extraction module (114); performing joint optimization of selected features and model parameters using adaptive search strategies via an adaptive hybrid optimization module (116); segmenting regions of interest from the medical image data based on the optimized adaptive hybrid via a segmentation module (118); analysing the segmented regions and detect the presence of disease via a disease detection module (120); classifying the detected disease into multiple categories via a disease classification module (122); evaluating the performance of medical image analysis results via a performance evaluation module (124); transmitting segmented images, detected diseases, classified disease categories, and evaluated performances to the user device (102) via an output module (126); and displaying segmented images, detected diseases, classified disease categories, and evaluated performances on the user interface (104) of the user device (102).

Description:FIELD OF DISCLOSURE
[0001] The present disclosure generally relates to computational intelligence and medical imaging, more specifically, relates to a hybrid metaheuristic-based medical image analysis system using deep learning.
BACKGROUND OF THE DISCLOSURE
[0002] Medical image analysis plays a critical role in modern healthcare, enabling early diagnosis, disease monitoring, and treatment planning. With the rapid growth of digital imaging technologies, large volumes of medical data are generated daily including images from modalities such as X-ray, MRI, CT, and dermoscopy. Analyzing these images manually is time-consuming, prone to human error, and often requires specialized expertise. Therefore, automated systems for accurate and efficient medical image interpretation have become an essential focus of research and development.
[0003] Traditional approaches to medical image analysis include machine learning and early deep learning techniques. These methods typically rely on manual or static optimization of model parameters, handcrafted feature extraction, or separate processing steps for feature selection and model training. Although such methods have demonstrated some success in specific tasks, they frequently encounter several significant limitations. One common issue is slow convergence during model training, particularly when handling large and complex medical imaging datasets, which increases computational cost and processing time. Additionally, these approaches often exhibit reduced accuracy when applied across diverse patient populations, imaging devices, or clinical conditions, limiting their generalizability and reliability. Many traditional systems also struggle to adapt to variations in image quality, noise, lighting conditions, or anatomical differences, making them sensitive to inconsistencies in real-world data. Furthermore, feature selection and model optimization are often performed separately, which leads to suboptimal results, inefficiency, and higher memory usage. These constraints hinder the scalability and practical deployment of such systems in clinical environments where rapid, accurate, and robust decision-making is required. As a result, despite their contributions to early automated medical imaging, traditional methods are often inadequate for achieving consistent, high-performance outcomes across multiple datasets, disease types, and real-world clinical scenarios.
[0004] The present invention overcomes the aforesaid limitations by providing an adaptive and integrated approach that automatically improve model performance while efficiently handling large and complex medical imaging datasets. The system dynamically optimizes model configurations and selectively identifies the most relevant image features, thereby reducing computational overhead and improving accuracy and robustness. By enabling improved generalization across diverse datasets and ensuring reliable medical image interpretation, the invention facilitates scalable and practical deployment in real-world clinical environments, thereby overcoming the constraints associated with conventional static optimization approaches.
SUMMARY OF THE DISCLOSURE
[0005] The following is a summary description of illustrative embodiments of the invention. It is provided as a preface to assist those skilled in the art to more rapidly assimilate the detailed design discussion which ensues and is not intended in any way to limit the scope of the claims which are appended hereto in order to particularly point out the invention.
[0006] According to illustrative embodiments, the present disclosure focuses on a hybrid metaheuristic-based medical image analysis system which overcomes the above-mentioned disadvantages or provide the users with a useful or commercial choice.
[0007] An objective of the present disclosure is to create a system that enables adaptive and automated optimization of deep learning models in medical image analysis.
[0008] Another objective of the present disclosure is to design a system that that simultaneously performs hyperparameter tuning and feature selection, improving efficiency.
[0009] Another objective of the present disclosure is to introduce a system that dynamically balances exploration and exploitation during optimization for faster convergence and better performance.
[0010] Another objective of the present disclosure is to create a system that enhances accuracy, robustness, and generalization across diverse datasets, imaging devices, and patient populations.
[0011] Another objective of the present disclosure is to design a system that enable scalable analysis of large and complex medical imaging datasets for real-world deployment.
[0012] Another objective of the present disclosure is to introduce a system that ensure reliable performance under challenging conditions.
[0013] Yet another objective of the present disclosure is to create a system that provides a clinically deployable framework for accurate, interpretable, and efficient medical image analysis.
[0014] In light of the above, in one aspect of the present disclosure, a hybrid metaheuristic-based medical image analysis system is disclosed herein. The system comprises a user device configured to collect medical image data of a user through a user interface. The system includes a communication network configured to establish a communication link for data transmission within the system. The system further includes a processing unit connected to the user device via the communication network and configured to process real-time data for hybrid metaheuristic-based medical image analysis, wherein the processing unit further comprises a data input module configured to receive real-time data from the user device, a preprocessing module configured to clean, normalize and reduce noise in the received data to enhance data quality, a feature extraction module configured to extract relevant features from the pre-processed data, an adaptive hybrid optimization module configured to perform joint optimization of selected features and model parameters using adaptive search strategies, a segmentation module configured to segment regions of interest from the medical image data based on the optimized adaptive hybrid, a disease detection module configured to analyse the segmented regions and detect the presence of disease, a disease classification module configured to classify the detected disease into multiple categories, a performance evaluation module configured to evaluate the performance of medical image analysis results, an output module configured to transmit segmented images, detected diseases, classified disease categories, and evaluated performances to the user device.
[0015] In one embodiment, the system further comprises a cloud database configured to store and manage processed medical image data, optimized model parameters, and analysis results.
[0016] In one embodiment, the user device configured to collect medical image data including radiological images, dermoscopic images, and microscopic images.
[0017] In one embodiment, the feature extraction module configured to extract relevant features including intensity features, structural features, and texture-based features from the pre-processed data.
[0018] In one embodiment, the adaptive hybrid optimization module configured to perform joint optimization of selected features and model parameters using adaptive search strategies including a combination of sparrow search algorithm, particle swarm optimization, and differential evolution.
[0019] In one embodiment, the segmentation module utilizes U-Net model to segment regions of interest from the medical image data.
[0020] In one embodiment, the disease classification module configured to classify the detected disease into multiple categories including but not limited to benign, malignant, pre-cancerous conditions, tumors, lesions, infections, and organ-specific abnormalities using convolutional neural networks.
[0021] In one embodiment, the performance evaluation module configured to evaluate the performance of medical image analysis results including but not limited to accuracy, intersection over union, dice coefficient, and f1 score.
[0022] In one embodiment, the performance evaluation module utilizes pre-trained architectures including vgg16, vgg19, and mobilenet to evaluate the performance of medical image analysis results.
[0023] In light of the above, in one aspect of the present disclosure, a method for hybrid metaheuristic-based medical image analysis system is disclosed herein. The method comprises collecting medical image data of a user through a user interface via a user device. The method includes establishing a communication link for data transmission within the system via a communication network. The method further includes processing real-time data for hybrid metaheuristic-based medical image analysis via a processing unit, comprising several modules. The method also includes receiving real-time data from the user device via a data input module. Furthermore, the method includes cleaning, normalizing and reducing noise in the received data to enhance data quality via a preprocessing module. Moreover, the method includes extracting relevant features from the pre-processed data via a feature extraction module performing joint optimization of selected features and model parameters using adaptive search strategies via an adaptive hybrid optimization module. The method further includes segmenting regions of interest from the medical image data based on the optimized adaptive hybrid via a segmentation module. The method also includes analysing the segmented regions and detect the presence of disease via a disease detection module. Furthermore, the method includes classifying the detected disease into multiple categories via a disease classification module. Moreover, the method includes evaluating the performance of medical image analysis results via a performance evaluation module. The method further includes transmitting segmented images, detected diseases, classified disease categories, and evaluated performances to the user device via an output module. At last, the method includes displaying segmented images, detected diseases, classified disease categories, and evaluated performances on the user interface of the user device.
[0024] These and other advantages will be apparent from the present application of the embodiments described herein.
[0025] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
[0026] These elements, together with the other aspects of the present disclosure and various features are pointed out with particularity in the claims annexed hereto and form a part of the present disclosure. For a better understanding of the present disclosure, its operating advantages, and the specified object attained by its uses, reference should be made to the accompanying drawings and descriptive matter in which there are illustrated exemplary embodiments of the present disclosure.
BRIEF DESCRIPTION OF THE DRAWINGS
[0027] To describe the technical solutions in the embodiments of the present disclosure or in the prior art more clearly, the following briefly describes the accompanying drawings required for describing the embodiments or the prior art. Apparently, the accompanying drawings in the following description merely show some embodiments of the present disclosure, and a person of ordinary skill in the art can derive other implementations from these accompanying drawings without creative efforts. All of the embodiments or the implementations shall fall within the protection scope of the present disclosure.
[0028] The advantages and features of the present disclosure will become better understood with reference to the following detailed description taken in conjunction with the accompanying drawing, in which:
[0029] FIG. 1 illustrates a block diagram of a hybrid metaheuristic-based medical image analysis system, in accordance with an embodiment of the present disclosure; and
[0030] FIG. 2 illustrates a flow chart of a method, outlining the sequential steps for the hybrid metaheuristic-based medical image analysis system, in accordance with an embodiment of the present disclosure.
[0031] Like reference, numerals refer to like parts throughout the description of several views of the drawing.
[0032] The hybrid metaheuristic-based medical image analysis system is illustrated in the accompanying drawings, which like reference letters indicate corresponding parts in the various figures. It should be noted that the accompanying figure is intended to present illustrations of exemplary embodiments of the present disclosure. This figure is not intended to limit the scope of the present disclosure. It should also be noted that the accompanying figure is not necessarily drawn to scale.
DETAILED DESCRIPTION OF THE DISCLOSURE
[0033] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure.
[0034] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be apparent to one skilled in the art that embodiments of the present disclosure may be practiced without some of these specific details.
[0035] Various terms as used herein are shown below. To the extent a term is used, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.
[0036] The terms “a” and “an” herein do not denote a limitation of quantity but rather denote the presence of at least one of the referenced items.
[0037] The terms “having”, “comprising”, “including”, and variations thereof signify the presence of a component.
[0038] Referring now to FIG. 1 and FIG. 2 to describe various exemplary embodiments of the present disclosure. FIG. 1 illustrates a block diagram of a hybrid metaheuristic-based medical image analysis system 100, in accordance with an embodiment of the present disclosure.
[0039] The system 100 may include a user device 102. The system 100 may include a communication network 106. The system 100 may include a processing unit 108, which further comprises a data input module 110, a preprocessing module 112, a feature extraction module 114, an adaptive hybrid optimization module 116, a segmentation module 118, a disease detection module 120, a disease classification module 122, a performance evaluation module 124, an output module 126. The system 100 may include a cloud database 128.
[0040] The user device 102 configured to collect medical image data of a user through a user interface 104. The user device 102 includes but not limited to a smartphone, tablet, computer and any other wearable device capable of data processing and user interaction.
[0041] In one embodiment of the present invention, the user device 102 configured to collect medical image data including radiological images, dermoscopic images, and microscopic images.
[0042] In one embodiment of the present invention, the user device 102 collects medical image data including radiological images such as X-ray, computed tomography, magnetic resonance imaging, dermoscopic images for skin lesion analysis, and microscopic images obtained from histopathology.
[0043] In one embodiment of the present invention, the user interface 104 provides real-time feedback to ensure the quality and completeness of the data being collected.
[0044] In one embodiment of the present invention, the user interface 104 may also provide zooming, annotation, highlighting, and comparison tools to assist medical professionals in reviewing the results.
[0045] The communication network 106 configured to establish a communication link for data transmission within the system 100. The communication network 106 may include but not be limited to wired and wireless networks.
[0046] In one embodiment of the present invention, the communication network 106 includes wireless networks including but not limited to Bluetooth and wireless fidelity.
[0047] In one embodiment of the present invention, the system 100 further comprises the cloud database 128 configured to store and manage processed medical image data, optimized model parameters, and analysis results. The cloud database 128 provides secure, scalable, and centralized storage for maintaining historical patient image records, segmented outputs, detected abnormalities, classified disease categories, and performance evaluation metrics.
[0048] In one embodiment of the present invention, the cloud database 128 supports longitudinal monitoring by maintaining time-stamped records of medical images and analysis results, thereby allowing tracking of disease progression.
[0049] The processing unit 108 connected to the user device 102 via the communication network 106 and configured to process real-time data for hybrid metaheuristic-based medical image analysis.
[0050] In one embodiment of the present invention, the processing unit 108 may include but not be limited to a microcontroller, a microprocessor, a central processing unit, and many more.
[0051] In one embodiment of the present invention, the processing unit 108 acts as the core computational component of the system 100, responsible for executing preprocessing, feature extraction, optimization, segmentation, detection, classification, performance evaluation, and result generation operations.
[0052] In one embodiment of the present invention, the processing unit 108 operates in a highly automated, scalable, and secure manner to facilitate medical imaging workflows.
[0053] The data input module 110 configured to receive real-time data from the user device 102. The data input module 110 serves as the initial entry point of image data into the processing unit 108 and is responsible for securely ingesting, validating, and organizing the received data for further processing.
[0054] In one embodiment of the present invention, the data input module 110 may also buffer incoming data streams, handle batch uploads, and manage real-time data synchronization to prevent data loss.
[0055] In one embodiment of the present invention, the data input module 110 forwards the received medical image data to the preprocessing module 112 for further enhancement and analysis within the system 100.
[0056] The preprocessing module 112 configured to clean, normalize and reduce noise in the received data to enhance data quality. The preprocessing module 112 receives validated image data from the data input module 110 and performs a series of image enhancement operations to standardize and improve the quality of the images prior to feature extraction and optimization.
[0057] In one embodiment of the present invention, the preprocessing module 112 may perform operations including but not limited to image resizing, intensity normalization, contrast enhancement, histogram equalization, filtering, background removal, and artifact suppression.
[0058] In one embodiment of the present invention, the preprocessing module 112 performs advanced image conditioning and standardization operations to ensure analytical consistency and improve downstream model performance.
[0059] The feature extraction module 114 configured to extract relevant features from the pre-processed data. The feature extraction module 114 transforms raw pixel-level information into structured quantitative descriptors that represent the underlying anatomical and pathological characteristics present in the medical images.
[0060] In one embodiment of the present invention, the feature extraction module 114 configured to extract relevant features including intensity features, structural features, and texture-based features from the pre-processed data.
[0061] In one embodiment of the present invention, the intensity-based features may include statistical measures derived from pixel intensity distributions such as mean intensity, median, variance, standard deviation, skewness, kurtosis, entropy, and energy. These features capture brightness variations and abnormal intensity patterns associated with lesions, tumors, and inflamed tissues. The structural features may include shape descriptors and morphological characteristics such as area, perimeter, compactness, eccentricity, circularity, elongation, convexity, boundary irregularity, and contour-based parameters. These features are particularly useful in identifying irregular lesion shapes and tumor growth patterns. And the texture-based features may be extracted using statistical and mathematical models such as gray level co-occurrence matrix, gray level run length matrix, local binary patterns, gabor filters, wavelet transforms, haralick features, and fractal analysis. These features capture micro-pattern variations, heterogeneity, and tissue granularity that are often indicative of pathological conditions.
[0062] In one embodiment of the present invention, the feature extraction module 114 enhances computational efficiency and improving generalization capability across diverse medical datasets.
[0063] The adaptive hybrid optimization module 116 configured to perform joint optimization of selected features and model parameters using adaptive search strategies. The adaptive hybrid optimization module 116 receives extracted feature vectors from the feature extraction module 114 and generates optimized feature subsets along with tuned hyperparameters for the downstream segmentation and classification.
[0064] In one embodiment of the present invention, the adaptive hybrid optimization module 116 configured to perform joint optimization of selected features and model parameters using adaptive search strategies including a combination of sparrow search algorithm, particle swarm optimization, and differential evolution.
[0065] In one embodiment of the present invention, the adaptive hybrid optimization module 116 may further support multi-objective optimization, balancing segmentation accuracy, computational efficiency, complexity, and generalization performance to ensure scalability for large-scale medical imaging datasets.
[0066] The segmentation module 118 configured to segment regions of interest from the medical image data based on the optimized adaptive hybrid. The segmentation module 118 analyses the image at the pixel level and divides it into meaningful regions.
[0067] In one embodiment of the present invention, the segmentation module 118 utilizes U-Net model to segment regions of interest from the medical image data.
[0068] In one embodiment of the present invention, the segmentation module 118 isolates regions such as tumors, lesions, abnormal tissues, infected areas, and specific organs from the surrounding healthy tissue. This process helps in clearly distinguishing the region of interest from the background, thereby simplifying further disease detection and classification.
[0069] The disease detection module 120 configured to analyse the segmented regions and detect the presence of disease. The disease detection module 120 examines the extracted regions of interest, such as suspected tumors, lesions, abnormal tissues, and infected areas.
[0070] In one embodiment of the present invention, the disease detection module 120 compares the optimized and extracted features with reference datasets and trained model parameters stored in the cloud database 128 to detect the presence of disease conditions.
[0071] The disease classification module 122 configured to classify the detected disease into multiple categories. The classification output is subsequently forwarded to the performance evaluation module 124 for validation and accuracy assessment before being transmitted to the user device 102 for review.
[0072] In one embodiment of the present invention, the disease classification module 122 configured to classify the detected disease into multiple categories including but not limited to benign, malignant, pre-cancerous conditions, tumors, lesions, infections, and organ-specific abnormalities using convolutional neural networks.
[0073] In one embodiment of the present invention, the classification module 122 may support multi-class and multi-label classification to handle complex medical cases where multiple pathological conditions coexist. The classification module 122 may further incorporate probability-based decision thresholds to reduce false classifications and improve clinical reliability.
[0074] The performance evaluation module 124 configured to evaluate the performance of medical image analysis results. The performance evaluation module 124 checks whether the system 100 provides stable and consistent results under different conditions such as image noise, variations in lighting, and class imbalance.
[0075] In one embodiment of the present invention, the performance evaluation module 124 configured to evaluate the performance of medical image analysis results including but not limited to accuracy, intersection over union, dice coefficient, and f1 score.
[0076] In one embodiment of the present invention, the performance evaluation module 124 utilizes pre-trained architectures including vgg16, vgg19, and mobilenet to evaluate the performance of medical image analysis results.
[0077] In one embodiment of the present invention, the performance evaluation module 124 is further configured to assess robustness, generalization capability, and computational efficiency across multiple datasets by performing cross-dataset validation, noise resilience testing, class imbalance analysis, and adversarial robustness evaluation.
[0078] The output module 126 configured to transmit segmented images, detected diseases, classified disease categories, and evaluated performances to the user device 102.
[0079] In one embodiment of the present invention, the output module 126 serves as the final stage in the system 100, ensuring that all relevant analytical outcomes are delivered to the end user in a structured, interpretable, and clinically useful format.
[0080] FIG. 2 illustrates a flow chart of a method 200, outlining the sequential steps for the hybrid metaheuristic-based medical image analysis system 100, in accordance with an embodiment of the present disclosure.
[0081] At step 202, the medical image data of a user is collected through a user interface 104 via a user device 102.
[0082] At step 204, the communication link for data transmission is established within the system 100 via a communication network 106.
[0083] At step 206, the real-time data for hybrid metaheuristic-based medical image analysis is processed via a processing unit 108, comprising several modules.
[0084] At step 208, the real-time data is received from the user device 102 via a data input module 110.
[0085] At step 210, the received data is cleaned, normalized and reduced noise to enhance data quality via a preprocessing module 112.
[0086] At step 212, the relevant features are extracted from the pre-processed data via a feature extraction module 114.
[0087] At step 214, the joint optimization of selected features and model parameters are performed using adaptive search strategies via an adaptive hybrid optimization module 116.
[0088] At step 216, the regions of interest is segmented from the medical image data based on the optimized adaptive hybrid via a segmentation module 118.
[0089] At step 218, the segmented regions is analysed and detect the presence of disease via a disease detection module 120.
[0090] At step 220, the detected disease is classified into multiple categories via a disease classification module 122.
[0091] At step 222, the performance of medical image analysis results are evaluated via a performance evaluation module 124.
[0092] At step 224, the segmented images, detected diseases, classified disease categories, and evaluated performances are transmitted to the user device 102 via an output module 126.
[0093] At step 226, the segmented images, detected diseases, classified disease categories, and evaluated performances are displayed on the user interface 104 of the user device 102.
[0094] In the best mode of operation of the present invention, the system 100 designed for accurate, robust, and automated analysis of medical images. The system 100 utilizes the user device 102, which collects medical image data including radiological images, dermoscopic images, and microscopic images of a user through the user interface 104. A secure communication link is established via the communication network 106 to facilitate seamless data transmission throughout the system 100. Once the image is collected, it is transmitted to the processing unit 108, which comprises several specialized modules. Initially, the data is received through the data input module 110, where it is securely ingested into the system 100. The received data is then forwarded to the preprocessing module 112 which cleans, normalizes, and reduces noise to enhance data quality and ensure that the images are suitable for subsequent analysis. Following preprocessing, the feature extraction module 114 extracts relevant features such as intensity patterns, structural details, and texture-based features. These features are then provided to the adaptive hybrid optimization module 116, which applies a combination of metaheuristic algorithms such as sparrow search algorithm, particle swarm optimization, and differential evolution to jointly optimize model parameters and select the most relevant features. The adaptive hybrid optimization module 116 dynamically adjusts exploration and exploitation based on convergence patterns, population diversity, and fitness feedback, thereby optimizing selected features and model parameters for subsequent analysis. The segmentation module 118 receives the optimized parameters and segment regions of interest from the medical images such as tumors, lesions, and organs. The segmented regions are then forwarded to the disease detection module 120, which determines the presence of abnormalities. Upon detection, the disease classification module 122 classifies the disease into specific categories including but not limited to benign, malignant, pre-cancerous conditions, tumors, lesions, infections, and organ-specific abnormalities using convolutional neural networks for accurate categorization. The classification results are evaluated by the performance evaluation module 124 to assess the accuracy, robustness, and generalization of the analysis. Finally, the output module 126 transmits the results including segmented images, detected abnormalities, classified disease categories, and evaluation metrics back to the user device 102. These results are visually presented on the user interface 104 for interpretation by the end-user, providing a comprehensive and interpretable diagnostic overview. In addition, the system 100 employs the cloud database 130 securely stores processed image data, optimized model parameters, and analysis results for advanced analysis and cross-patient knowledge management.
[0095] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it will be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0096] A person of ordinary skill in the art may be aware that, in combination with the examples described in the embodiments disclosed in this specification, units and algorithm steps may be implemented by electronic hardware, computer software, or a combination thereof.
[0097] The foregoing descriptions of specific embodiments of the present disclosure have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present disclosure to the precise forms disclosed, and many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described to best explain the principles of the present disclosure and its practical application, and to thereby enable others skilled in the art to best utilize the present disclosure and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient, but such omissions and substitutions are intended to cover the application or implementation without departing from the scope of the present disclosure.
[0098] Disjunctive language such as the phrase “at least one of X, Y, Z,” unless specifically stated otherwise, is otherwise understood with the context as used in general to present that an item, term, etc., may be either X, Y, or Z, or any combination thereof (e.g., X, Y, and/or Z). Thus, such disjunctive language is not generally intended to, and should not, imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z to each be present.
[0099] In a case that no conflict occurs, the embodiments in the present disclosure and the features in the embodiments may be mutually combined. The foregoing descriptions are merely specific implementations of the present disclosure but are not intended to limit the protection scope of the present disclosure. Any variation or replacement readily figured out by a person skilled in the art within the technical scope disclosed in the present disclosure shall fall within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
, Claims:I/We Claim:
1. A hybrid metaheuristic-based medical image analysis system (100), the system (100) comprising:
a user device (102) configured to collect medical image data of a user through a user interface (104);
a communication network (106) configured to establish a communication link for data transmission within the system (100);
a processing unit (108) connected to the user device (102) via the communication network (106) and configured to process real-time data for hybrid metaheuristic-based medical image analysis, wherein the processing unit (108) further comprises:
a data input module (110) configured to receive real-time data from the user device (102);
a preprocessing module (112) configured to clean, normalize and reduce noise in the received data to enhance data quality;
a feature extraction module (114) configured to extract relevant features from the pre-processed data;
an adaptive hybrid optimization module (116) configured to perform joint optimization of selected features and model parameters using adaptive search strategies;
a segmentation module (118) configured to segment regions of interest from the medical image data based on the optimized adaptive hybrid;
a disease detection module (120) configured to analyse the segmented regions and detect the presence of disease;
a disease classification module (122) configured to classify the detected disease into multiple categories;
a performance evaluation module (124) configured to evaluate the performance of medical image analysis results; and
an output module (126) configured to transmit segmented images, detected diseases, classified disease categories, and evaluated performances to the user device (102).
2. The system (100) as claimed in claim 1, wherein the system (100) further comprises a cloud database (128) configured to store and manage processed medical image data, optimized model parameters, and analysis results.
3. The system (100) as claimed in claim 1, wherein the user device (102) configured to collect medical image data including radiological images, dermoscopic images, and microscopic images.
4. The system (100) as claimed in claim 1, wherein the feature extraction module (114) configured to extract relevant features including intensity features, structural features, and texture-based features from the pre-processed data.
5. The system (100) as claimed in claim 1, wherein the adaptive hybrid optimization module (116) configured to perform joint optimization of selected features and model parameters using adaptive search strategies including a combination of sparrow search algorithm, particle swarm optimization, and differential evolution.
6. The system (100) as claimed in claim 1, wherein the segmentation module (118) utilizes U-Net model to segment regions of interest from the medical image data.
7. The system (100) as claimed in claim 1, wherein the disease classification module (122) configured to classify the detected disease into multiple categories including but not limited to benign, malignant, pre-cancerous conditions, tumors, lesions, infections, and organ-specific abnormalities using convolutional neural networks.
8. The system (100) as claimed in claim 1, wherein the performance evaluation module (124) configured to evaluate the performance of medical image analysis results including but not limited to accuracy, intersection over union, dice coefficient, and f1 score.
9. The system (100) as claimed in claim 1, wherein the performance evaluation module (124) utilizes pre-trained architectures including vgg16, vgg19, and mobilenet to evaluate the performance of medical image analysis results.
10. A method (200) for hybrid metaheuristic-based medical image analysis system (100), the method (200) comprising:
collecting medical image data of a user through a user interface (104) via a user device (102);
establishing a communication link for data transmission within the system (100) via a communication network (106);
processing real-time data for hybrid metaheuristic-based medical image analysis via a processing unit (108), comprising several modules;
receiving real-time data from the user device (102) via a data input module (110);
cleaning, normalizing and reducing noise in the received data to enhance data quality via a preprocessing module (112);
extracting relevant features from the pre-processed data via a feature extraction module (114);
performing joint optimization of selected features and model parameters using adaptive search strategies via an adaptive hybrid optimization module (116);
segmenting regions of interest from the medical image data based on the optimized adaptive hybrid via a segmentation module (118);
analysing the segmented regions and detect the presence of disease via a disease detection module (120);
classifying the detected disease into multiple categories via a disease classification module (122);
evaluating the performance of medical image analysis results via a performance evaluation module (124);
transmitting segmented images, detected diseases, classified disease categories, and evaluated performances to the user device (102) via an output module (126); and
displaying segmented images, detected diseases, classified disease categories, and evaluated performances on the user interface (104) of the user device (102).