SYSTEM FOR DETERMINING AND PREDICTING SCATTERING COEFFICIENTS OF MYOCARDIUM TISSUE IN NEAR-INFRARED-BAND FOR IN-VIVO COMMUNICATIONS

Abstract

ABSTRACT SYSTEM FOR DETERMINING AND PREDICTING SCATTERING COEFFICIENTS OF MYOCARDIUM TISSUE IN NEAR-INFRARED-BAND FOR IN-VIVO COMMUNICATIONS A system(100) for determining and predicting scattering coefficients of myocardium tissue in near infrared band for in-vivo communications comprises data acquisition module(102), theoretical modeling module(104), machine learning module(106), prediction module(108), and output module(110). The data acquisition module (102) collects initial biological data and input features on myocardial tissue, including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm. The theoretical modeling module(104) estimates initial scattering coefficients based on these features. The machine learning module(106) trains one or more machine learning models using input data from the data acquisition module(102) and initial scattering coefficients from the theoretical modeling module(104). The prediction module(108) processes new biological data to extract features and predict scattering coefficients, indicating abnormalities; and the output module(110) generates an output on a user interface based on the predicted coefficients, highlighting potential issues like myocardial infarction, ischemia, or fibrosis.

Specification

Description:FIELD OF DISCLOSURE
The disclosure relates to diagnostic and health monitoring technologies.
DEFINITIONS
Myocardium: The term 'Myocardium' mentioned herein in the disclosure refers to the muscular layer of the heart, responsible for contracting and pumping blood throughout the body. It is located between the outer layer (epicardium) and the inner layer (endocardium) of the heart. The myocardium is composed primarily of cardiac muscle cells, which are specialized to work continuously and rhythmically. Its health is crucial for effective heart function.
BACKGROUND
The background information herein below relates to the disclosure but is not necessarily prior art.
Non-invasive diagnostic methods are crucial in modern medicine, offering a means to evaluate physiological and pathological conditions without the need for surgical intervention. These techniques, which include imaging modalities like MRI, CT scans, and NIR spectroscopy, are valued for their ability to provide critical insights into patient health while minimizing risk and discomfort. According to recent studies, non-invasive methods are preferred in over 70% of diagnostic procedures due to their safety profile and patient compliance.
In the realm of cardiac care, non-invasive techniques are particularly vital for monitoring heart health and diagnosing conditions such as myocardial infarction, ischemia, and heart failure. Current methods for assessing myocardial tissue, especially using NIR spectroscopy, focus on measuring scattering properties to infer tissue characteristics. Despite their utility, these methods often encounter significant limitations, including poor resolution and inaccurate estimations due to the complexity of light-tissue interactions.
Current systems rely heavily on traditional algorithms and empirical models, which frequently fall short of accurately capturing the scattering behaviors of myocardial tissue. These limitations result in suboptimal diagnostic accuracy and reduced effectiveness in real-time monitoring.
Therefore, there is a need for a system for determining and predicting scattering coefficients of myocardium tissue in near-infrared-band for in-vivo communications that alleviates the aforementioned drawbacks.
OBJECTS
Some of the objects of the disclosure, which at least one embodiment herein satisfies, are as follows:
It is an object of the disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
An object of the disclosure is to provide a system for determining and predicting scattering coefficients of myocardium tissue in near-infrared-band for in-vivo communications.
An object of the disclosure is to develop a robust theoretical-modelling module for accurate estimation of scattering coefficients based on the refractive indices and physical properties of myocardium tissue.
Another object of the disclosure is to implement and optimize machine learning models to enhance the prediction of scattering coefficients and identify non-linear relationships effectively.
Still, another object of the disclosure is to create a real-time monitoring application that integrates with implantable devices for continuous assessment of myocardial tissue health.
Yet another object of the disclosure is to employ advanced data augmentation techniques to generate synthetic datasets that expand the predictive capabilities of the model across various conditions.
Another object of the disclosure is to establish a comprehensive validation framework that cross-validates scattering coefficient estimates against theoretical models and experimental data using various performance metrics.
Still, another object of the disclosure is to develop predictive analytics capabilities for assessing cardiac disease progression by analyzing temporal changes in scattering coefficients.
Yet another object of the disclosure is to design the system for compatibility with 6G-enabled smart hospitals for integration with other health monitoring systems.
Another object of the disclosure is to incorporate uncertainty quantification techniques in the validation module to assess variability in predictions and enhance reliability.
Still, another object of the disclosure is to develop mechanisms for continuous learning and adaptation in machine learning models to maintain prediction accuracy over time.
Yet another object of the disclosure is to enhance overall patient care by providing timely and accurate assessments of myocardial health for early diagnosis and intervention.
Another object of the disclosure is to minimize false positives and negatives in scattering coefficient predictions, ensuring reliable diagnostics in clinical settings.
Still, another object of the disclosure is to support ongoing research in cardiac health by providing a framework for exploring new models in scattering coefficient analysis.
Yet another object of the disclosure is to foster collaboration between cardiologists, data scientists, and biomedical engineers for a comprehensive approach to cardiac diagnostics.
Another object of the disclosure is to make advanced cardiac monitoring technologies more accessible to a broader range of healthcare facilities, including smaller clinics.
Still, another object of the disclosure is to provide training resources for healthcare professionals to enhance their ability to interpret scattering coefficients and make informed decisions.
Yet another object of the disclosure is to design a user-friendly interface that facilitates ease of use for healthcare providers and seamless integration into existing workflows.
Other objects and advantages of the disclosure will be more apparent from the following description, which is not intended to limit the scope of the disclosure.
SUMMARY
The present disclosure envisages a system for determining and predicting scattering coefficients of myocardium tissue in near-infrared-band for in-vivo communications.
The system comprises a data acquisition module, a theoretical modeling module, a machine learning module, a prediction module, and an output module.
The data acquisition module is configured to collect initial biological data on myocardial tissue, including input features including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm.
The theoretical modeling module is configured to estimate initial scattering coefficients of the myocardial tissue in the NIR band ranging from 600-900 nm based on the scatterer radius, the refractive indices, and the volume fraction of the myocardial tissue.
The machine learning module is configured to receive the input features including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm from the data acquisition module and the initial scattering coefficients from the theoretical-modeling module, as input data, and further configured to train one or more machine learning models using the input data.
The prediction module is configured to receive new biological data of myocardium tissue and further configured to implement the one or more trained machine learning models on the new biological data of myocardium tissue to extract input features and predict the scattering coefficients for the new biological data of myocardium tissue in the NIR band ranging from 600-900 nm based on the extracted input features, wherein the predicted scattering coefficients indicating abnormalities in tissue properties.
The output module is configured to receive the predicted scattering coefficients from the prediction module and generate an output on a user interface indicating abnormalities in tissue properties including myocardial infarction, ischemia, or fibrosis.
In an embodiment, the system is configured to comprise one or more machine learning models including support vector machines, linear regression, polynomial regression, gradient boost, and artificial neural network (ANN).
In an embodiment, the system further comprises a data augmentation module configured to generate synthetic datasets for wavelengths and tissue characteristics not originally present in the initial biological data, wherein the data augmentation module generates the synthetic datasets by varying input parameters including tissue refractive index, scatterer size, and wavelength to predict scattering coefficients for biological tissues under different conditions.
In an embodiment, the prediction module is configured to employ the one or more machine learning models to capture non-linear trends in scattering coefficients across the 600-900 nm wavelength range.
In an embodiment, the system includes an application configured to continuously monitor cardiac health using implantable devices for providing real-time data to the prediction module for the calculation and prediction of myocardial tissue scattering coefficients.

In an embodiment, the application includes personalized treatment planning by integrating scattering coefficient data with patient-specific metrics to optimize therapeutic interventions.

In an embodiment, the system is configured to integrate with 6G-enabled smart hospitals, and with other health monitoring systems to provide comprehensive cardiac diagnostics and real-time monitoring capabilities.
In an embodiment, the system is further configured to include a validation module configured to cross-validate estimated coefficients against theoretical models generated by the theoretical modeling module and evaluates model performance using metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R2R^2R2 Score.
In an embodiment, the validation module is configured to include the use of clinical trials to independently verify the accuracy and reliability of the scattering coefficient predictions in real-world scenarios.

In an embodiment, the machine learning module is configured to implement iterative learning techniques to refine the estimation of scattering coefficients based on real-time biological feedback from in-vivo monitoring systems.

In an embodiment, the data acquisition module is further configured to operate in the terahertz (THz) range, enabling non-invasive signal propagation and tissue analysis with low photon energy, ensuring patient safety.
The present disclosure also envisages a method for determining and predicting scattering coefficients of myocardium tissue in near-infrared-band for in-vivo communications. The method comprises the following steps:
• collecting, by a data acquisition module, initial biological data on myocardial tissue, including input features such as scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm;
• estimating, by a theoretical modeling module, initial scattering coefficients of the myocardial tissue in the NIR band ranging from 600-900 nm based on the scatterer radius, refractive indices, and volume fraction of the myocardial tissue;
• training, by a machine learning module, one or more machine learning models using input features, including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm, along with the initial scattering coefficients;
• receiving, by a prediction module, new biological data of myocardial tissue, extracting input features from the new biological data, and predicting the scattering coefficients for the new biological data in the NIR band based on the extracted input features using the trained machine learning models; and
• generating, by an output module, an output on a user interface indicating abnormalities in tissue properties, including myocardial infarction, ischemia, or fibrosis, based on the predicted scattering coefficients.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
A system for determining and predicting scattering coefficients of myocardium tissue in near-infrared-band for in-vivo communications of the disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates a block diagram representing a system for determining and predicting scattering coefficients of myocardium tissue in near-infrared-band for in-vivo communications in accordance with one embodiment of the disclosure;
Figure 2 illustrates a schematic representation of human myocardium tissue; and
Figure 3A illustrates a graph showing the Scattering Coefficient of Myocardium Tissue for Different Sizes (Length of the Myofibrils) in accordance with one embodiment of the disclosure;
Figure 3B illustrates a graph showing Actual Vs Predicted Scattering Coefficient using Linear Regression in accordance with one embodiment of the disclosure;
Figure 3C illustrates a graph showing Actual Vs Predicted Scattering Coefficient using Polynomial Regression in accordance with one embodiment of the disclosure;
Figure 3D illustrates a graph showing Actual Vs Predicted Scattering Coefficient using Gradient Boost Regression in accordance with one embodiment of the disclosure;
Figure 3E illustrates a graph showing Actual Vs Predicted Scattering Coefficient using ANN in accordance with one embodiment of the disclosure; and
Figure 4 illustrates a method for determining and predicting scattering coefficients of myocardium tissue in near-infrared-band for in-vivo communications in accordance with one embodiment of the disclosure.

LIST OF REFERENCE NUMERALS
100 - System
102 - Data acquisition module
104 - Theoretical modelling module
106 - Machine learning module
108 - Prediction module
110 - Output module
112 - Data augmentation module
114 - Validation module
A Collagen Fibrils
B Mean Fibrils Displacement
C Interstitial Space
D Incident Terahertz Signal
DETAILED DESCRIPTION
Embodiments, of the disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the disclosure to the person skilled in the art. Numerous details are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail.
The terminology used, in the disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the disclosure. As used in the disclosure, the forms "a," "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "including," and "having," are open-ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
When an element is referred to as being "engaged to," "connected to," or "coupled to" another element, it may be directly engaged, connected, or coupled to the other element. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed elements.
Non-invasive diagnostic methods play a crucial role in modern medicine by enabling the assessment of physiological and pathological conditions without surgery, with techniques like MRI, CT scans, and NIR spectroscopy being particularly valued for their safety and patient compliance, preferred in over 70% of procedures. In cardiac care, these methods are essential for monitoring heart health and diagnosing conditions such as myocardial infarction and heart failure. However, current NIR spectroscopy approaches face challenges due to poor resolution and inaccuracies in light-tissue interaction estimations, often relying on traditional algorithms that fail to effectively capture myocardial tissue scattering behaviors. This highlights the need for improved systems to accurately determine and predict scattering coefficients of myocardial tissue in the NIR band for better in-vivo diagnostics.
To address the issues of the existing systems and methods, the disclosure envisages a system (hereinafter referred to as "system 100") for determining and predicting scattering coefficients of myocardium tissue in near infrared band for in-vivo communications in accordance with one embodiment of the disclosure. The system (100) will now be described with reference to Figure 1 and Figure 2. Figure 3 illustrates a method for determining and predicting scattering coefficients of myocardium tissue in near infrared band for in-vivo communications in accordance with one embodiment of the disclosure ((hereinafter referred to as "method 200").
Referring to Figure 1, the system (100) comprises a data acquisition module (102), a theoretical modeling module (104), a machine learning module (106), a prediction module (108), and an output module (110). The data acquisition module (102) collects essential biological parameters of the myocardial tissue, specifically focusing on scatterer radius, refractive indices, volume fraction, and wavelength within the NIR range of 600-900 nm. This foundational data is then fed into the theoretical modeling module (104), which utilizes these parameters to estimate the initial scattering coefficients of the tissue, forming a critical basis for subsequent analysis. The machine learning module (106) receives both the input features and the initial scattering coefficients, leveraging this data to train various machine learning models, thus enhancing predictive accuracy. Upon acquiring new biological data, the prediction module (108) applies the trained models to extract relevant input features and predict scattering coefficients for this fresh dataset, enabling the identification of potential abnormalities in tissue properties. Finally, the output module (110) compiles the predicted coefficients and presents findings on a user interface, alerting users to any detected anomalies such as myocardial infarction, ischemia, or fibrosis, thereby facilitating timely clinical interventions.
In an embodiment of the machine learning module (106), the one or more machine learning models include support vector machines, linear regression, polynomial regression, gradient boost, and artificial neural network (ANN).
In an embodiment, the system (100) can further comprise a data augmentation module (112) configured to generate synthetic datasets for wavelengths and tissue characteristics not originally present in the initial biological data, wherein the data augmentation module (112) generates the synthetic datasets by varying input parameters including tissue refractive index, scatterer size, and wavelength to predict scattering coefficients for biological tissues under different conditions.
In an embodiment, the system (100) can further comprise a prediction module (108) configured to employ the one or more machine learning models to capture non-linear trends in scattering coefficients across the 600-900 nm wavelength range.
In an embodiment, the system (100) can include an application configured to continuously monitor cardiac health using implantable devices for providing real-time data to the prediction module (108) for calculation and prediction of myocardial tissue scattering coefficients.
In an embodiment, the application can include personalized treatment planning by integrating scattering coefficient data with patient-specific metrics to optimize therapeutic interventions.
In an embodiment, the system (100) can be configured to integrate with 6G-enabled smart hospitals, and with other health monitoring systems to provide comprehensive cardiac diagnostics and real-time monitoring capabilities.
In an embodiment, the system (100) can further comprise a validation module (114) configured to cross-validate estimated coefficients against theoretical models generated by the theoretical modelling module (104) and evaluates model performance using metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R2R^2R2 Score.
In an embodiment, the validation module (114) is further configured to include the use of clinical trials to independently verify the accuracy and reliability of the scattering coefficient predictions in real-world scenarios.
In an embodiment, the machine learning module (106) is configured to implement iterative learning techniques to refine the estimation of scattering coefficients based on real-time biological feedback from in-vivo monitoring systems.
In an embodiment of the data acquisition module (102), the data acquisition module (102) is further configured to operate in the terahertz (THz) range, enabling non-invasive signal propagation and tissue analysis with low photon energy, ensuring patient safety.
Figure 2 depicts a schematic representation of human myocardium tissue. The tissue consists various collagen fibrils (A) with interstitial space (C) between them. The mean fibrils displacement (B) denotes average distance between fibrils (A) .A terahertz signal (D) is incident on the myocardium tissue to determin the refractive indices and scattering coefficient of the myocardium tissue. In a preferred embodiment of the disclosure, a single cardiac cell, known as cardiomyocyte, consisting of a number of myofibrils suspended in sarcoplasm as shown in Figure 2 is considered for testing the models employed by the machine learning module (106). A considerable mismatch in refractive indices between myofibrils and ground substance, sarcoplasm, makes the system turbid, i.e., causes multiple scattering and poor transmittance of propagating light. The available scattering model, as shown in Figure 2 is tested considering the features enlisted in Table 1.
Table 1: Refractive Index of Myocardium Tissue
Description Notation/Values
Wavelength (nm) 600-900 nm
Refractive index of sarcoplasm 1.35
Refractive index of myofibril 1.53
Volume fraction of sarcoplasm 𝑓𝑓sarco= 0.875
Volume fraction of myofibrils
(cylinders) 𝑓𝑓cyl = 1- 𝑓𝑓sarco = 0.126
Radius of the particle (r) 1 μ𝑚𝑚
The average refractive index n0
Refractive index of scatterers ns
Relative refractive index m= ns/n0
Wavelength of the signal in vacuum λ0=𝑐𝑐/𝑓𝑓
Estimation of the scattering coefficient using the machine learning models to determine the scattering losses experienced by the signal while passing through the scattering model as shown in Figure 2, is done using equation 1. The scattering coefficient 𝜇𝜇𝜇𝜇 [cm−1] of the cardiomyocyte is determined by the following expression:



where 𝜌𝜌𝜇𝜇 is the volume density of the scatterers and 𝜎𝜎𝜇𝜇 = 𝑄𝑄𝜇𝜇 ∗ 𝐴𝐴𝜇𝜇 is the effective cross-section [cm2] of the scattering geometry, 𝑄𝑄𝜇𝜇 is the scattering efficiency and 𝐴𝐴 is the geometric cross-section of the scatterer.
In another embodiment, the obtained results are validated using cross-validation techniques.
Figure 3A illustrates a graph showing the Scattering Coefficient of Myocardium Tissue for Different Sizes (Length of the Myofibrils) in accordance with one embodiment of the disclosure. This figure shows the variation of the scattering coefficient for different frequencies. It is observed that the scattering coefficient is significantly large, beginning with 2200 [𝑐𝑚-1] for 600 nm and gradually reducing to 1580 [𝑐𝑚-1] at 900 𝑛𝑚 for the length of the myofibril of 2 𝜇𝑚. As the length of the myofibril increases the magnitude of the scattering coefficient drastically reduces. For the myofibril length of 10𝜇𝑚, the scattering coefficient has a value of 420 [𝑐𝑚-1] at 600 𝑛𝑚 and it decreases to 380 [𝑐𝑚-1] at 900 𝑛𝑚. This finding indicates that scattering is significantly high in the NIR band as a result has a reduced penetration depth and decreased image contrast. Accordingly, for a given length of the myofibril, it is recommended NIR signals in 900 nm wavelength are suitable as they have lesser scattering losses compared to other wavelength bands.
Figure 3B illustrates a graph showing Actual Vs Predicted Scattering Coefficient using Linear Regression in accordance with one embodiment of the disclosure. The graph illustrates the results of using a Linear Regression Model to forecast scattering coefficients based on frequencies. Beginning from 600 nm data sets and extending up to 900 nm THz and extending to 500 THz. The model assumes a straight-line relationship between wavelength and scattering coefficient, with the line's slope indicating how much the coefficient changes for each wavelength unit.
Figure 3C illustrates a graph showing Actual Vs Predicted Scattering Coefficient using Polynomial Regression in accordance with one embodiment of the disclosure. The graph shows the data predictions made by training the Polynomial Regression model from 600-900 𝑛𝑚 and extending it to 1000 𝑛𝑚. The Polynomial Regression model captures the nonlinear relationship between wavelength and Scattering Coefficient through a quadratic equation, a polynomial with degree 2. Despite being a linear regression method due to its linearity in coefficients, Polynomial Regression can model nonlinear data, giving the plot its distinctive curved shape.
Figure 3D illustrates a graph showing Actual Vs Predicted Scattering Coefficient using Gradient Boost Regression in accordance with one embodiment of the disclosure. The graph shows data extrapolation in order to improve prediction accuracy.
Figure 3E illustrates a graph showing Actual Vs Predicted Scattering Coefficient using ANN in accordance with one embodiment of the disclosure. This graph illustrates the profound impact of Artificial Neural Network (ANN) modeling on broadening the insights obtained from a dataset. By harnessing the collaborative strength of interconnected nodes, akin to a synchronized team effort, the ANN enhances predictive accuracy. In contrast to other methods, ANNs excel at modeling nonlinear relationships, making them well-suited for extrapolation tasks. ANNs are configured to enable analyzing of complex datasets, detecting subtle patterns, and generating highly accurate predictions.
In an embodiment of the disclosure, the machine learning module 106 is further configured to perform data augmentation to obtain values of scattering coefficients in wavelength band beyond 900 nm. In the figures 3A, 3B, 3C, 3D and 3E the portion between 900 and 1000 𝑛𝑚 depicts the predicted values of the scattering coefficient obtained using the machine learning models. It is seen that linear regression and ANN are performing better compared to polynomial regression and gradient boosting.

Table 2 gives the respective performance metrics indicating machine learning can serve as a better tool for exploring unknown data in case of non-availability.
Linear Regression Polynomial Regression Gradient Boost ANN
Metrics Values Values Values Values
MAE 0.00073252 0.00009972 0.00043321 0.00011652
MSE 0.00000113 0.00000004 0.00000150 0.00000004
RMSE 0.00106435 0.00019544 0.00122496 0.00020988
𝑅𝑅2 Score 0.98238456 0.99940604 0.97666722 0.99931505

Figure 4 depicts the steps involved in method (200) for determining and predicting scattering coefficients of myocardium tissue in near infrared band for in-vivo communications. The order in which method 200 is described is not intended to be construed as a limitation, and any number of the described method steps may be combined in any order to implement method 200, or an alternative method. Furthermore, method 200 may be implemented by processing resource or computing device(s) through any suitable hardware, non-transitory machine-readable medium/instructions, or a combination thereof. The method 200 comprises the following steps:
At step 202, the method (200) includes collecting, by a data acquisition module (102), initial biological data on myocardial tissue, including input features such as scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm;
At step 204, the method (200) includes estimating, by a theoretical modeling module (104), initial scattering coefficients of the myocardial tissue in the NIR band ranging from 600-900 nm based on the scatterer radius, refractive indices, and volume fraction of the myocardial tissue;
At step 206, the method (200) includes training, by a machine learning module (106), one or more machine learning models using input features, including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm, along with the initial scattering coefficients;
At step 208, the method (200) includes receiving, by a prediction module (108), new biological data of myocardial tissue, extracting input features from the new biological data, and predicting the scattering coefficients for the new biological data in the NIR band based on the extracted input features using the trained machine learning models; and
At step 210, the method (200) includes generating, by an output module (100), an output on a user interface indicating abnormalities in tissue properties, including myocardial infarction, ischemia, or fibrosis, based on the predicted scattering coefficients.
The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or codes on a computer-readable medium. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. For example, due to the nature of software, functions described above can be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment but are interchangeable. Such variations are not to be regarded as a departure from the disclosure, and all such modifications are considered to be within the scope of the disclosure.
TECHNICAL ADVANCEMENTS
The disclosure described herein above has several technical advantages including, but not limited to, the realization of a system for determining and predicting scattering coefficients of myocardium tissue in near infrared band for in-vivo communications, that:
• facilitates continuous monitoring of myocardial tissue through integration with implantable devices, allowing for timely interventions and personalized patient care, further augmented by 6G technology for high-speed data transmission;
• enables real-time monitoring of scattering coefficients to assess therapeutic interventions, optimizing treatment plans based on patient-specific responses;
• improves classification accuracy by integrating support vector machines (SVMs), refining the model's ability to identify complex boundaries in scattering coefficient data;
• offers non-invasive, real-time monitoring of cardiac health, potentially reducing reliance on costly imaging techniques and interventions for overall cost savings in healthcare delivery;
• facilitates better management of cardiac conditions through early detection and ongoing monitoring, leading to significant long-term cost savings for patients and healthcare systems;
• minimizes integration costs and facilitates widespread adoption by ensuring compatibility with existing health IT infrastructures, including electronic health records (EHRs) and telemedicine platforms;
• supports the growth of telehealth services by providing real-time data, fostering new business models for remote cardiac health monitoring and management;
• allows for the export of advanced diagnostic technologies as healthcare systems worldwide adopt innovative solutions;
• enhances community health and productivity by improving cardiac health, leading to reduced absenteeism and positively impacting local economies;
• promotes improved patient outcomes through early detection of myocardial abnormalities, allowing timely interventions and reducing severe cardiac event rates;
• optimizes healthcare resource allocation by focusing on patients requiring immediate attention based on predictive analytics, streamlining operations, and reducing waste;
• supports personalized treatment planning by integrating scattering coefficient data with patient-specific metrics, enhancing treatment efficacy and adherence while lowering long-term chronic disease management costs;
• informs further research and development opportunities in cardiac health by generating robust data, opening avenues for new therapeutic innovations; and
• differentiates healthcare providers in the market by implementing advanced diagnostic technologies, attracting more patients, and improving market share in a competitive landscape.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
The use of the expression "at least" or "at least one" suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation. , Claims:WE CLAIM:
1. A system (100) for determining and predicting scattering coefficients of myocardium tissue in near infrared (NIR) band for in-vivo communications, comprising:
• a data acquisition module (102) configured to collect initial biological data on myocardial tissue, including input features including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm;
• a theoretical modelling module (104) configured to estimate initial scattering coefficients of the myocardial tissue in the NIR band ranging from 600-900 nm based on the scatterer radius, the refractive indices, and the volume fraction of the myocardial tissue;
• a machine learning module (106) configured to receive the input features including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm from the data acquisition module (102) and the initial scattering coefficients from the theoretical-modeling module (104), as input data, and further configured to train one or more machine learning models using the input data;
• a prediction module (108) configured to receive new biological data of myocardium tissue, and further configured to implement the one or more trained machine learning models on the new biological data of myocardium tissue to extract input features and predict the scattering coefficients for the new biological data of myocardium tissue in the NIR band ranging from 600-900 nm based on the extracted input features, wherein the predicted scattering coefficients indicating abnormalities in tissue properties; and
• an output module (110) configured to receive the predicted scattering coefficients from the prediction module (108) and generate an output on a user interface indicating abnormalities in tissue properties including myocardial infarction, ischemia, or fibrosis.
2. The system (100) as claimed in claim 1, wherein said one or more machine learning models include support vector machines, linear regression, polynomial regression, gradient boost, and artificial neural network (ANN).
3. The system (100) as claimed in claim 1, further comprises a data augmentation module (112) configured to generate synthetic datasets for wavelengths and tissue characteristics not originally present in the initial biological data, wherein the data augmentation module (112) generates the synthetic datasets by varying input parameters including tissue refractive index, scatterer size, and wavelength to predict scattering coefficients for biological tissues under different conditions.
4. The system (100) as claimed in claim 1, wherein the prediction module (108) is configured to employ the one or more machine learning models to capture non-linear trends in scattering coefficients across the 600-900 nm wavelength range.
5. The system (100) as claimed in claim 1, wherein the system (100) includes an application configured to continuously monitor cardiac health using implantable devices for providing real-time data to the prediction module (108) for calculation and prediction of myocardial tissue scattering coefficients.
6. The system (100) as claimed in claim 5, wherein said application includes personalized treatment planning by integrating scattering coefficient data with patient-specific metrics to optimize therapeutic interventions.
7. The system (100) as claimed in claim 1, wherein the system (100) is configured to integrate with 6G-enabled smart hospitals, and with other health monitoring systems to provide comprehensive cardiac diagnostics and real-time monitoring capabilities.
8. The system (100) as claimed in claim 1, wherein the system (100) is further configured to include a validation module (114) configured to cross-validate estimated coefficients against theoretical models generated by the theoretical modelling module (104) and evaluates model performance using metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R2R^2R2 Score.
9. The system (100) as claimed in claim 8, wherein said validation module (114) is configured to include the use of clinical trials to independently verify the accuracy and reliability of the scattering coefficient predictions in real-world scenarios.
10. The system (100) as claimed in claim 1, wherein the machine learning module (106) is configured to implement iterative learning techniques to refine the estimation of scattering coefficients based on real-time biological feedback from in-vivo monitoring systems.
11. The system (100) as claimed in claim 1, wherein the data acquisition module (102) is further configured to operate in the terahertz (THz) range, enabling non-invasive signal propagation and tissue analysis with low photon energy, ensuring patient safety
12. A method (200) for determining and predicting scattering coefficients of myocardium tissue in near infrared (NIR) band for in-vivo communications, comprising the following steps:
• collecting, by a data acquisition module (102), initial biological data on myocardial tissue, including input features such as scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm;
• estimating, by a theoretical modeling module (104), initial scattering coefficients of the myocardial tissue in the NIR band ranging from 600-900 nm based on the scatterer radius, refractive indices, and volume fraction of the myocardial tissue;
• training, by a machine learning module (106), one or more machine learning models using input features, including scatterer radius, refractive indices, volume fraction, and wavelength of operation in the NIR range of 600-900 nm, along with the initial scattering coefficients;
• receiving, by a prediction module (108), new biological data of myocardial tissue, extracting input features from the new biological data, and predicting the scattering coefficients for the new biological data in the NIR band based on the extracted input features using the trained machine learning models; and
• generating, by an output module (100), an output on a user interface indicating abnormalities in tissue properties, including myocardial infarction, ischemia, or fibrosis, based on the predicted scattering coefficients.

Dated this 21st day of November, 2024

_______________________________
MOHAN RAJKUMAR DEWAN, IN/PA - 25
OF R. K. DEWAN & CO.
AUTHORIZED AGENT OF APPLICANT

TO,
THE CONTROLLER OF PATENTS
THE PATENT OFFICE, CHENNAI

Documents