A SYSTEM FOR CHARACTERIZING DIELECTRIC PROPERTIES OF OVINE HEART TISSUES AND A METHOD THEREOF

Abstract

ABSTRACT A SYSTEM FOR CHARACTERIZING DIELECTRIC PROPERTIES OF OVINE HEART TISSUES AND A METHOD THEREOF The present disclosure envisages a system for characterizing dielectric properties of ovine heart tissues. The system includes a terahertz (THz) wave generator (102), a biological tissue sample holder (104), a detector (106), a data acquisition module (108), a machine learning module (110), a traditional analytical module (112), a processing module (114), and a validation module (116). The terahertz (THz) wave generator (102) configured to produce electromagnetic waves in the frequency range of 0.1 THz to 10 THz. The detector (106) configured to detect THz signals that have either transmitted through or reflected from said ovine heart tissues. The data acquisition module (108) configured to collect THz data on THz transmission and reflection from said ovine heart tissues. The machine learning module (110) configured to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data.

Specification

Description:FIELD
The present disclosure relates to the field of electronics and communication engineering.
More particularly, the present disclosure discloses a system for characterizing dielectric properties of ovine heart tissues and a method thereof.
DEFINITIONS
As used in the present disclosure, the following term is generally intended to have the meaning as set forth below, except to the extent that the context in which it is used to indicate otherwise.
3-Debye model - The 3-Debye model refers to a theoretical approach used to describe the frequency-dependent dielectric response of materials, particularly their dielectric relaxation behavior. The 3-Debye model includes three Debye relaxation processes to account for multiple mechanisms of dielectric relaxation, each with a different characteristic relaxation time and amplitude.
Linear Regression - Linear regression refers to the statistical technique used to model the relationship between dependent variables (dielectric properties) and independent variables (such as temperature, frequency, material composition, etc.). Linear regression can be used to predict dielectric behavior at different temperatures, frequencies, or material compositions.
Polynomial Regression - Polynomial regression refers to a mathematical model that fits a polynomial equation to the relationship between the dielectric constant (or other dielectric parameters) and influencing variables, such as frequency, temperature, or material composition. Polynomial regression is particularly useful when there is a need to fit data that shows curved or complex behavior.
Gradient Boosting - The term "Gradient Boosting" refers to enhancing predictive models for analyzing and predicting material behaviors, especially those involving dielectric constants, polarization, or conductivity.
K-nearest neighbors - K-nearest neighbors (KNN) are typically related to the use of machine learning algorithms, particularly the K-nearest neighbors' algorithm, to predict or classify dielectric materials' behaviors based on their features.
The above definitions are in addition to those expressed in the art.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
Nano sensor networks are emerging as pivotal tools in healthcare, offering the potential for real-time monitoring, diagnostics, and treatment delivery at the molecular level. These networks consist of interconnected nano sensors that can detect various biological markers, chemicals, and environmental changes, leading to enhanced patient care and management. Nano sensors are mainly designed to detect minute concentrations of biological substances, allowing for high sensitivity in monitoring physiological changes. Their small size enables interactions at the nanoscale, making them capable of detecting biomarkers that might be overlooked by larger sensors. However, these nano sensor technologies may suffer from calibration issues and sensor drift over time, leading to inaccuracies in measurements. Regular calibration and maintenance can be resource-intensive and may not always be feasible in clinical settings. The deployment of nano sensors in healthcare raises ethical and regulatory concerns related to patient privacy, data security, and the accuracy of health monitoring. Traditional regulatory frameworks may not adequately address the unique challenges posed by nano sensor technology.
Traditional analytical models, such as the three-pole Debye model, primarily provide dielectric property data only up to 20 GHz. This limitation restricts their applicability in fields requiring analysis at higher frequencies, such as THz imaging and communications. Biological tissues can exhibit different dielectric behaviors at higher frequencies, and traditional methods fail to account for this critical variation. The reliance on traditional models often results in a lack of accuracy in predictions, especially when dealing with complex biological tissues. Analytical models may oversimplify the intricate behaviors of biological materials, leading to discrepancies between predicted and actual dielectric properties. The three-pole Debye model, while useful, may not capture all the nuances of tissue dielectric behavior, particularly in the THz range.
Therefore, there is felt a need for a system for characterizing the dielectric properties of ovine heart tissues and a method thereof that alleviates the aforementioned drawbacks.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
It is an object of the present disclosure, to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
An object of the present disclosure is to provide a system for characterizing dielectric properties of ovine heart tissues.
Another object of the present disclosure is to provide a system that enhances the accuracy of predicting the dielectric properties of cardiac tissues.
Still another object of the present disclosure is to provide a system that allows for non-invasive monitoring of cardiac tissue and other biological tissues within the human body.
Yet another object of the present disclosure is to provide a system that intends for in-vivo monitoring, particularly within the scope of 6G healthcare applications.
Still another object of the present disclosure is to provide a system that addresses the lack of high-frequency data.
Yet another object of the present disclosure is to provide a system that enhances patient care and advances 6G healthcare applications.
Still another object of the present disclosure is to provide a method for characterizing the dielectric properties of ovine heart tissues.
Other objects and advantages of the present disclosure will be more apparent from the following description when read in conjunction with the accompanying figures, which are not intended to limit the scope of the present disclosure.
SUMMARY
The present disclosure envisages a system for characterizing the dielectric properties of ovine heart tissues. The system includes a terahertz (THz) wave generator, a biological tissue sample holder, a detector, a data acquisition module, a machine learning module, a traditional analytical module, a processing module, and a validation module.
The terahertz (THz) wave generator is configured to produce electromagnetic waves in the frequency range of 0.1 THz to 10 THz. The biological tissue sample holder is configured to securely hold said ovine heart tissues during characterization. The biological tissue sample holder includes a temperature control unit to maintain said ovine heart tissues at physiological temperatures during characterization to ensure accurate dielectric property measurements.
The detector is operatively coupled to said terahertz (THz) wave generator to detect THz signals that have either transmitted through or reflected from said ovine heart tissues. In an embodiment, the detector is a time-domain spectroscopic detector capable of detecting both transmitted and reflected THz signals, providing enhanced sensitivity for characterizing thin tissue samples.
The machine learning module is configured to train and implement a plurality of machine learning models to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data. The machine learning module comprises said plurality of machine learning models including Linear Regression, Polynomial Regression, Gradient Boosting, and K-nearest neighbors, to predict dielectric properties that have been trained using large datasets of terahertz frequency response data from said ovine heart tissues. The dielectric properties, including permittivity and conductivity, of said ovine heart tissues are predicted at specific frequencies within the terahertz range including 0.5 THz, 1 THz, and 3 THz.
In an embodiment, the machine learning models are trained using a dataset comprising THz frequency data and corresponding known dielectric properties of said ovine heart tissues, allowing for accurate predictions across the THz spectrum.
The traditional analytical module is configured to implement a three-pole Debye model and integrate with said machine learning models to generate dielectric properties of said ovine heart tissues in the terahertz frequency range of 500 MHz to 20 GHz.
The processing module is configured to combine said predicted dielectric properties from said machine learning module and said generated dielectric properties from said traditional analytical module to provide real-time dielectric characterization of said ovine heart tissues at terahertz frequencies 0.1 THz to 10 THz. The processing module is further configured to dynamically adjust the weighting between said machine learning module and said traditional analytical module based on the quality of the THz data received, optimizing the accuracy of the real-time dielectric characterization.
The validation module is configured to validate said dielectric characterization of said ovine heart tissues by means of curve fitting technique and a mathematical model to compare said dielectric characterization with experimental data within the 20 GHz to 10 THz range to ensure their accuracy and reliability for medical applications.
In an embodiment, the mathematical model implemented by said validation module includes a Monte Carlo simulation or other statistical methods to estimate the uncertainty in the dielectric characterization and ensure reliability for medical applications.
The system further comprises a calibration module and a visualization interface. The calibration module is configured to ensure consistent and reliable THz data acquisition by compensating for environmental conditions and sample variability during measurements. The visualization interface is configured to display predicted permittivity and conductivity values of said ovine heart tissues as a function of terahertz frequency in real time.
The present disclosure envisages a method for characterizing the dielectric properties of ovine heart tissues. The method includes the following steps:
• producing, by a terahertz (THz) wave generator, electromagnetic waves in the frequency range of 0.1 THz to 10 THz;
• holding, by a biological tissue sample holder, to securely hold said ovine heart tissues during characterization;
• detecting, by a detector, by coupling said terahertz (THz) wave generator to detect THz signals that have either transmitted through or reflected from said ovine heart tissues;
• collecting, by a data acquisition module, THz data on THz transmission and reflection from said ovine heart tissues;
• training and implementing, by a machine learning module, a plurality of machine learning models to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data;
• implementing, by a traditional analytical module, a three-pole Debye model and integrating with said machine learning models to generate dielectric properties of said ovine heart tissues in the terahertz frequency range of 500 MHz to 20 GHz;
• combining, by a processing module, said predicted dielectric properties from said machine learning module and said generated dielectric properties from said traditional analytical module to provide real-time dielectric characterization of said ovine heart tissues at terahertz frequencies 0.1 THz to 10 THz; and
• validating, by a validation module, said dielectric characterization of said ovine heart tissues by means of curve fitting technique and a mathematical model to compare said dielectric characterization with experimental data within the 20 GHz to 10 THz range to ensure their accuracy and reliability for medical applications.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
A system for characterizing dielectric properties of ovine heart tissues of the present disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates a block diagram of a system for characterizing dielectric properties of ovine heart tissues, in accordance with the present disclosure;
Figures 2(a) and (b) illustrate the simulation results for the Polynomial Fit by Origin based on the experimental data from the myocardium tissue in terms of permittivity, frequency, and conductivity, in accordance with the present disclosure;
Figures 3(a) and (b) illustrate the simulation results depicting linear fit by origin in terms of permittivity, conductivity, and frequency, in accordance with the present disclosure;
Figures 4 (a) and (b) illustrate the simulation results depicting 3-Pole Debye Fit by Origin in terms of permittivity, conductivity and frequency, in accordance with the present disclosure;
Figures 5 (a), (b), (c) and (d) illustrate the exemplary simulation results of Polynomial Regression, Gradient Boosting, KNN, and Linear Regression, in accordance with the present disclosure; and
Figure 6 illustrates a method for characterizing dielectric properties of ovine heart tissues, in accordance with the present disclosure.
LIST OF REFERENCE NUMERALS
100 - System
102 - Terahertz (THz) wave generator
104 - Biological tissue sample holder
106 - Detector
108 - Data acquisition module
110 - Machine learning module
112 - Traditional analytical module
114 - Processing module
116 - Validation module
600 - Method
DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawings.
Embodiments are provided so as to thoroughly and fully convey the scope of the present 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 present 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 present 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 present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present 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 present 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.
Nano sensor networks are emerging as pivotal tools in healthcare, offering the potential for real-time monitoring, diagnostics, and treatment delivery at the molecular level. These networks consist of interconnected nano sensors that can detect various biological markers, chemicals, and environmental changes, leading to enhanced patient care and management. Nano sensors are mainly designed to detect minute concentrations of biological substances, allowing for high sensitivity in monitoring physiological changes. Their small size enables interactions at the nanoscale, making them capable of detecting biomarkers that might be overlooked by larger sensors. However, these nano sensor technologies may suffer from calibration issues and sensor drift over time, leading to inaccuracies in measurements. Regular calibration and maintenance can be resource-intensive and may not always be feasible in clinical settings. The deployment of nano sensors in healthcare raises ethical and regulatory concerns related to patient privacy, data security, and the accuracy of health monitoring. Traditional regulatory frameworks may not adequately address the unique challenges posed by nano sensor technology.
Traditional analytical models, such as the three-pole Debye model, primarily provide dielectric property data only up to 20 GHz. This limitation restricts their applicability in fields requiring analysis at higher frequencies, such as THz imaging and communications. Biological tissues can exhibit different dielectric behaviors at higher frequencies, and traditional methods fail to account for this critical variation. The reliance on traditional models often results in a lack of accuracy in predictions, especially when dealing with complex biological tissues. Analytical models may oversimplify the intricate behaviors of biological materials, leading to discrepancies between predicted and actual dielectric properties. The three-pole Debye model, while useful, may not capture all the nuances of tissue dielectric behavior, particularly in the THz range.
In order to address the aforementioned problems, the present disclosure envisages a system (hereinafter referred to as "system 100") for characterizing dielectric properties of ovine heart tissues and a method (hereinafter referred to as "method 600") for characterizing dielectric properties of ovine heart tissues. The system 100 and the method 600 are now being described with reference to Figure 1 to Figure 6.
Figure 1 illustrates a system for characterizing dielectric properties of ovine heart tissues. The system includes a terahertz (THz) wave generator (102), a biological tissue sample holder (104), a detector (106), a data acquisition module (108), a machine learning module (110), a traditional analytical module (112), a processing module (114), and a validation module (116).
The terahertz (THz) wave generator (102) is configured to produce electromagnetic waves in the frequency range of 0.1 THz to 10 THz. The biological tissue sample holder (104) is configured to securely hold said ovine heart tissues during characterization. The biological tissue sample holder (104) includes a temperature control unit to maintain said ovine heart tissues at physiological temperatures during characterization to ensure accurate dielectric property measurements.
The detector (106) is operatively coupled to said terahertz (THz) wave generator (102) to detect THz signals that have either transmitted through or reflected from said ovine heart tissues. In an embodiment, the detector (106) is a time-domain spectroscopic detector capable of detecting both transmitted and reflected THz signals, providing enhanced sensitivity for characterizing thin tissue samples.
The machine learning module (110) is configured to train and implement a plurality of machine learning models (110a) to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data. The machine learning module (100) comprises said plurality of machine learning models (110a) including Linear Regression, Polynomial Regression, Gradient Boosting, and K-nearest neighbors, to predict dielectric properties that have been trained using large datasets of terahertz frequency response data from said ovine heart tissues. The dielectric properties, including permittivity and conductivity, of said ovine heart tissues are predicted at specific frequencies within the terahertz range including 0.5 THz, 1 THz, and 3 THz.
In an embodiment, the machine learning models (112a) are trained using a dataset comprising THz frequency data and corresponding known dielectric properties of said ovine heart tissues, allowing for accurate predictions across the THz spectrum.
The traditional analytical module (112) is configured to implement a three-pole Debye model (112a) and integrate with said machine learning models (110a) to generate dielectric properties of said ovine heart tissues in the terahertz frequency range of 500 MHz to 20 GHz.
The traditional analytical module (112) used in the present disclosure is the 3-pole Debye model.

The parameters obtained from the 3-debye model are shown in Table 1:

The processing module (144) is configured to combine said predicted dielectric properties from said machine learning module (110) and said generated dielectric properties from said traditional analytical module (112) to provide real-time dielectric characterization of said ovine heart tissues at terahertz frequencies 0.1 THz to 10 THz. The processing module (144) is further configured to dynamically adjust the weighting between said machine learning module (110) and said traditional analytical module (112) based on the quality of the THz data received, optimizing the accuracy of the real-time dielectric characterization.
The validation module (116) is configured to validate said dielectric characterization of said ovine heart tissues by means of curve fitting technique and a mathematical model to compare said dielectric characterization with experimental data within the 20 GHz to 10 THz range to ensure their accuracy and reliability for medical applications.
In an embodiment, the mathematical model implemented by said validation module (116) includes a Monte Carlo simulation or other statistical methods to estimate the uncertainty in the dielectric characterization and ensure reliability for medical applications.
In an exemplary embodiment, the system 100 is implemented on the cardiac tissues having dielectric properties beyond 20 GHz, which is crucial for in vivo wireless nano sensor networks operating in the terahertz band (0.1 to 10 THz). These networks are essential for monitoring internal health parameters and rely on accurate knowledge of channel conditions to develop efficient MAC and routing protocols. The present disclosure significantly enhances the accuracy and scope of predicting dielectric properties of biological tissues and introduces new applications in the fields of biomedical sensing and advanced communication technologies.
In an embodiment, the system 100 in the present disclosure develops nano-scale sensors that operate at terahertz frequencies allowing for non-invasive monitoring of cardiac and other biological tissues in vivo. The present disclosure enables precise, continuous health monitoring, reducing the need for invasive procedures and improving patient comfort and care.
Figures 2 (a) and (b) illustrate the simulation results for the Polynomial Fit by Origin in terms of permittivity, frequency, and conductivity, in accordance with the present disclosure. The simulation results are obtained based on the experimental data from the myocardium tissue for the frequency range of 500 MHz to 20 GHz.
Figures 3 (a) and (b) illustrate the simulation results depicting linear fit by origin in terms of permittivity, conductivity, and frequency, in accordance with the present disclosure.
Figures 4 (a) and (b) illustrate the simulation results depicting 3-Pole Debye Fit by Origin in terms of permittivity, conductivity, and frequency, in accordance with the present disclosure. The 3-Debye model predicts the dielectric properties of cardiac tissues in the terahertz frequency range. This enhances the accuracy and reliability of dielectric property predictions, leveraging the strengths of both analytical and machine learning methodologies.
The results of the performance metrics, obtained from fitting the models in simulations are displayed in below Tables 2 and 3:
Table 2. Permittivity vs Frequency (Fitting by Origin)
Fitting Model Residual Sum of Squares R-square Adjusted R-square
Polynomial Fit 477.2478 0.941 0.9397
Linear Fit 648.4197 0.9198 0.9190
3-Pole Debye Fit 87.2284 0.9892 0.9882

Table 3. Conductivity vs Frequency (Fitting by Origin)
Fitting Model Residual Sum of Squares R-square Adjusted R-square
Polynomial Fit 18.3215 0.9953 0.9952
Linear Fit 65.2328 0.9833 0.9832
3-Pole Debye Fit 17.5047 0.9955 0.9951
Figures 5 (a), (b), (c) and (d) illustrate the exemplary simulation results of Polynomial Regression, Gradient Boosting, KNN, and Linear Regression, in accordance with the present disclosure. The performance metrics employed in this study include Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (Coefficient of Determination). The results of these performance metrics, obtained from using machine learning models to predict the real and imaginary parts of in-vivo permittivity, are shown in below tables 4 and 5:
Table 4. Permittivity vs Frequency
ML Model MSE RMSE MAE R- Square
Gradient Boosting 0.0009 0.0300 0.0193 0.9999
k-NN 0.8832 0.2972 0.1337 0.9988
Linear Regression 6.4199 2.5337 1.9091 0.9198
Polynomial Regression 4.7252 2.1737 1.6721 0.9409


Table 5. Conductivity vs Frequency
ML Model MSE RMSE MAE R- Square
Gradient Boosting 7.1854 0.0084 0.0051 0.9999
k-NN 0.0585 0.2419 0.0751 0.9984
Linear Regression 0.6468 0.8036 0.7131 0.9833
Polynomial Regression 0.1814 0.4259 0.3501 0.9953
Figure 6 illustrates a method for characterizing dielectric properties of ovine heart tissues. The order in which method 600 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 500, or an alternative method. Furthermore, method 500 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 includes the following steps:
At step 602, the method 600 includes producing, by a terahertz (THz) wave generator (102), electromagnetic waves in the frequency range of 0.1 THz to 10 THz.
At step 604, the method 600 includes holding, by a biological tissue sample holder (104), to securely hold said ovine heart tissues during characterization.
At step 606, the method 600 includes detecting, by a detector (106), by coupling said terahertz (THz) wave generator (102) to detect THz signals that have either transmitted through or reflected from said ovine heart tissues.
At step 608, the method 600 includes collecting, by a data acquisition module (108), THz data on THz transmission and reflection from said ovine heart tissues.
At step 610, the method 600 includes training and implementing, by a machine learning module (110), a plurality of machine learning models (110a) to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data.
At step 612, the method 600 includes implementing, by a traditional analytical module (112), a three-pole Debye model (112a) and integrate with said machine learning models (110a) to generate dielectric properties of said ovine heart tissues in the terahertz frequency range of 500 MHz to 20 GHz.
At step 614, the method 600 includes combining, by a processing module (144), said predicted dielectric properties from said machine learning module (110) and said generated dielectric properties from said traditional analytical module (112) to provide real-time dielectric characterization of said ovine heart tissues at terahertz frequencies 0.1 THz to 10 THz.
At step 616, the method 600 includes validating, by a validation module (116), said dielectric characterization of said ovine heart tissues by means of curve fitting technique and a mathematical model to compare said dielectric characterization with experimental data within the 20 GHz to 10 THz range to ensure their accuracy and reliability for medical applications.
At step 618, the method 600 includes ensuring, by a calibration module (118), consistent and reliable THz data acquisition by compensating for environmental conditions and sample variability during measurements.
At step 620, the method 600 includes displaying, by a visualization interface (120), predicted permittivity and conductivity values of said ovine heart tissues as a function of terahertz frequency in real time.
In an operative configuration, the system (100) for characterizing dielectric properties of ovine heart tissues. The system (100) comprises a terahertz (THz) wave generator (102) configured to produce electromagnetic waves in the frequency range of 0.1 THz to 10 THz. The biological tissue sample holder (104) is configured to securely hold said ovine heart tissues during characterization. The detector (106) is operatively coupled to said terahertz (THz) wave generator (102) to detect THz signals that have either transmitted through or reflected from said ovine heart tissues. The data acquisition module (108) is configured to collect THz data on THz transmission and reflection from said ovine heart tissues. The machine learning module (110) is configured to train and implement a plurality of machine learning models (110a) to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data. The traditional analytical module (112) is configured to implement a three-pole Debye model (112a) and integrate with said machine learning models (110a) to generate dielectric properties of said ovine heart tissues in the terahertz frequency range of 500 MHz to 20 GHz. The processing module (144) configured to combine said predicted dielectric properties from said machine learning module (110) and said generated dielectric properties from said traditional analytical module (112) to provide real-time dielectric characterization of said ovine heart tissues at terahertz frequencies 0.1 THz to 10 THz. The validation module (116) is configured to validate said dielectric characterization of said ovine heart tissues by means of curve fitting technique and a mathematical model to compare said dielectric characterization with experimental data within the 20 GHz to 10 THz range to ensure their accuracy and reliability for medical applications.
Advantageously, the system 100 for characterizing dielectric properties of ovine heart tissues offers several significant advantages, particularly by integrating the machine learning module (110) and the three-pole Debye model (112a), the system achieves higher prediction accuracy compared to using either approach alone. This combined methodology allows for more reliable predictions of key dielectric properties such as permittivity and conductivity, particularly in the terahertz range where traditional models may fall short. This hybrid approach leverages the strengths of machine learning, such as pattern recognition from empirical data, and the predictive power of the Debye model, improving overall model robustness and ensuring greater precision in the results.
The processing module (144) facilitates real-time analysis of dielectric properties by combining predictions from the machine learning models with those from the traditional analytical module. This real-time capability is crucial for time-sensitive applications such as in vivo monitoring, dynamic tissue characterization, or on-the-fly medical decision-making, allowing for faster and more responsive diagnostic or therapeutic interventions.
The validation module (116) plays a crucial role in ensuring the reliability and accuracy of the predicted dielectric properties. By employing curve fitting and comparing results with experimental data across the 20 GHz to 10 THz range, the system minimizes potential errors and ensures that the dielectric characterizations are scientifically validated and suitable for clinical or biomedical use. This enhances the credibility of the predictions, making the system suitable for medical-grade applications where accuracy is paramount.
The system's data acquisition module (108) and detector (106) ensure a comprehensive collection of terahertz data, capturing both transmission and reflection signals from ovine heart tissues. This dual-signal acquisition increases the system's ability to characterize the tissues under a variety of conditions and provides a more complete dielectric profile. This feature is particularly advantageous for complex biological tissues, where multiple electromagnetic interactions occur, necessitating a detailed data capture process.
The ability to predict dielectric properties in the THz range opens new possibilities for medical applications, such as high-frequency diagnostics, non-invasive cardiac monitoring, and terahertz-based therapies.
The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the present 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 present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCEMENTS
The present disclosure described herein above has several technical advantages including, but not limited to, the realization of a system for characterizing dielectric properties of ovine heart tissues that:
• enhances the accuracy of predicting the dielectric properties of cardiac tissues;
• non-invasive monitoring of cardiac tissue;
• enhances patient comfort and care;
• enables precise and continuous health monitoring;
• assists in the early detection and diagnosis of medical conditions; and
• improves the efficiency and reliability of remote health monitoring systems.
The aspect 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 reveal 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.
Any discussion of devices, articles or the like that has been included in this specification is solely for the purpose of providing a context for the disclosure. It is not to be taken as an admission that any or all of these matters form a part of the prior art base or were common general knowledge in the field relevant to the disclosure as it existed anywhere before the priority date of this application.
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 characterizing dielectric properties of ovine heart tissues, said system (100) comprising:
• a terahertz (THz) wave generator (102) configured to produce electromagnetic waves in the frequency range of 0.1 THz to 10 THz;
• a biological tissue sample holder (104) configured to securely hold said ovine heart tissues during characterization;
• a detector (106) operatively coupled to said terahertz (THz) wave generator (102) to detect THz signals that have either transmitted through or reflected from said ovine heart tissues;
• a data acquisition module (108) configured to collect THz data on THz transmission and reflection from said ovine heart tissues;
• a machine learning module (110) configured to train and implement a plurality of machine learning models (110a) to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data;
• a traditional analytical module (112) configured to implement a three-pole Debye model (112a) and integrate with said machine learning models (110a) to generate dielectric properties of said ovine heart tissues in the terahertz frequency range of 500 MHz to 20 GHz;
• a processing module (144) configured to combine said predicted dielectric properties from said machine learning module (110) and said generated dielectric properties from said traditional analytical module (112) to provide real-time dielectric characterization of said ovine heart tissues at terahertz frequencies 0.1 THz to 10 THz; and
• a validation module (116) configured to validate said dielectric characterization of said ovine heart tissues by means of curve fitting technique and a mathematical model to compare said dielectric characterization with experimental data within the 20 GHz to 10 THz range to ensure their accuracy and reliability for medical applications.

2. The system (100) as claimed in claim 1, said system (110) further comprises:
• a calibration module (118) configured to ensure consistent and reliable THz data acquisition by compensating for environmental conditions and sample variability during measurements; and
• a visualization interface (120) configured to display predicted permittivity and conductivity values of said ovine heart tissues as a function of terahertz frequency in real time.
3. The system (100) as claimed in claim 1, wherein said biological tissue sample holder (104) includes a temperature control unit to maintain said ovine heart tissues at physiological temperatures during characterization to ensure accurate dielectric property measurements.
4. The system (100) as claimed in claim 1, wherein said detector (106) is a time-domain spectroscopic detector capable of detecting both transmitted and reflected THz signals, providing enhanced sensitivity for characterizing thin tissue samples.
5. The system (100) as claimed in claim 1, wherein said machine learning module (100) comprises said plurality of machine learning models (110a) including Linear Regression, Polynomial Regression, Gradient Boosting, and K-nearest neighbors, to predict dielectric properties that have been trained using large datasets of terahertz frequency response data from said ovine heart tissues.
6. The system (100) as claimed in claim 1, wherein said machine learning models (112a) are trained using a dataset comprising THz frequency data and corresponding known dielectric properties of said ovine heart tissues, allowing for accurate predictions across the THz spectrum.
7. The system (100) as claimed in claim 1, wherein said dielectric properties, including permittivity and conductivity, of said ovine heart tissues are predicted at specific frequencies within the terahertz range including 0.5 THz, 1 THz, and 3 THz.
8. The system (100) as claimed in claim 1, wherein said mathematical model implemented by said validation module (116) includes a Monte Carlo simulation or other statistical methods to estimate the uncertainty in the dielectric characterization and ensure reliability for medical applications.
9. The system (100) as claimed in claim 1, wherein said processing module (144) is configured to dynamically adjust the weighting between said machine learning module (110) and said traditional analytical module (112) based on the quality of the THz data received, optimizing the accuracy of the real-time dielectric characterization.
10. A method for characterizing dielectric properties of ovine heart tissues, said method comprises the following steps:
• producing, by a terahertz (THz) wave generator (102), electromagnetic waves in the frequency range of 0.1 THz to 10 THz;
• holding, by a biological tissue sample holder (104), to securely hold said ovine heart tissues during characterization;
• detecting, by a detector (106), by coupling said terahertz (THz) wave generator (102) to detect THz signals that have either transmitted through or reflected from said ovine heart tissues;
• collecting, by a data acquisition module (108), THz data on THz transmission and reflection from said ovine heart tissues;
• training and implementing, by a machine learning module (110), a plurality of machine learning models (110a) to predict dielectric properties from said ovine heart tissues, including permittivity and conductivity, based on said collected THz data;
• implementing, by a traditional analytical module (112), a three-pole Debye model (112a) and integrating with said machine learning models (110a) to generate dielectric properties of said ovine heart tissues in the terahertz frequency range of 500 MHz to 20 GHz;
• combining, by a processing module (144), said predicted dielectric properties from said machine learning module (110) and said generated dielectric properties from said traditional analytical module (112) to provide real-time dielectric characterization of said ovine heart tissues at terahertz frequencies 0.1 THz to 10 THz; and
• validating, by a validation module (116), said dielectric characterization of said ovine heart tissues by means of curve fitting technique and a mathematical model to compare said dielectric characterization with experimental data within the 20 GHz to 10 THz range to ensure their accuracy and reliability for medical applications.
11. The method as claimed in claim 10, wherein said method further comprises:
• ensuring, by a calibration module (118), consistent and reliable THz data acquisition by compensating for environmental conditions and sample variability during measurements; and
• displaying, by a visualization interface (120), predicted permittivity and conductivity values of said ovine heart tissues as a function of terahertz frequency in real time.
Dated this 15th day of November, 2024

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

TO,
THE CONTROLLER OF PATENTS
THE PATENT OFFICE, CHENNAI

Documents