A method for electrical impedance cancer detection based on frequency domain information enhancement

Abstract

The present invention discloses an electrical impedance cancer detection method based on frequency domain information enhancement, the method comprising the following steps: S1: obtaining an electrical impedance signal in a patient's body by electrical impedance imaging technology; S2: using discrete cosine transform to convert the signal into a frequency domain representation and perform frequency domain enhancement; S3: inputting the frequency domain enhanced features into a model, combining the frequency domain information and global dependency, processing the frequency domain enhanced features to obtain a global feature matrix; S4: inputting the global feature matrix into a classifier for cancer detection, and providing corresponding detection results. The present invention performs frequency domain conversion on a time domain signal, inputs the frequency domain enhanced features into a network model, combines the frequency domain information and global dependency to obtain a global matrix feature, and inputs the feature into a classifier for cancer detection, thereby improving the robustness of frequency domain data and enhancing the application effect of electrical impedance signals in cancer detection.

Description

Technical Field

[0001] The present invention relates to the field of cancer detection, and in particular to an electrical impedance cancer detection method based on frequency domain information enhancement. Background Art

[0002] Cancer is one of the leading causes of death worldwide, and early detection and treatment are crucial for improving patient survival. Traditional cancer detection methods have limitations, including high cost, radiation exposure risks, and insufficient sensitivity for early detection. Therefore, the development of new cancer detection technologies is crucial. The electrical impedance cancer detection method based on frequency domain information enhancement offers a new solution for cancer detection due to its non-invasive and simple operation. The rapid development of deep learning technology is enabling accurate cancer diagnosis results.

[0003] In the prior art, Chinese patent publication number CN117481630A discloses a "breast cancer detection method based on bioelectrical impedance analysis." This method uses bioelectrical impedance analysis technology to extract electrical signal data from normal and malignant breast tissue samples, thereby improving breast cancer detection. However, this method mainly relies on the detection of a single cancer and cannot detect multiple cancers through frequency domain information, which makes the application of electrical impedance signals in cancer detection have certain limitations.

[0004] Therefore, it is urgent to design an electrical impedance cancer detection method based on frequency domain information enhancement to solve the problems existing in the above-mentioned existing technologies. Summary of the Invention

[0005] The purpose of the present invention is to provide an electrical impedance cancer detection method based on frequency domain information enhancement. By performing frequency domain conversion on the time domain signal, the features after frequency domain enhancement are input into the network model, and the global matrix features are obtained by combining the frequency domain information and the global dependency relationship. Finally, the global matrix features are input into the classifier for cancer detection, which effectively improves the robustness of the frequency domain data, thereby improving the application effect of the electrical impedance signal in cancer detection.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A first aspect of the present invention provides a method for electrical impedance cancer detection based on frequency domain information enhancement, the method comprising the following steps:

[0008] S1: Obtain the electrical impedance signal in the patient's body through electrical impedance imaging technology and preprocess it;

[0009] S2: Perform frequency domain conversion on the preprocessed time domain signal, use discrete cosine transform to convert the signal into frequency domain representation and perform frequency domain enhancement;

[0010] S3: Inputting the frequency-domain enhanced features into an improved network model, wherein the improved network model combines frequency-domain information and global dependencies, and processes the frequency-domain enhanced features to obtain a final global feature matrix;

[0011] S4: The final global feature matrix is ​​input into the classifier, and the output is calculated by the fully connected layer. The output is then converted into a probability value through a function, which can determine whether cancer exists and give the corresponding detection results.

[0012] As an embodiment of the present application, step S1 specifically includes:

[0013] S11: Electrical impedance tomography (EIT) involves injecting current into the human body and recording reflected signals at different electrode locations. These signals reflect the electrical conductivity of different tissues in the body and contain amplitude and phase information in the time domain. These signals are expressed as complex numbers, including real resistance and imaginary reactance. The calculation formula is as follows:

[0014]

[0015] in, Represents the total impedance that changes with time; Resistance value changing with time; Indicates the reactance value that changes with time; It is an imaginary unit, which represents the difference between the reactance part and the resistance part; Used to control the weight or influence between reactance and resistance; Indicates the phase, the phase information of the current or voltage that changes with time;

[0016] S12: Perform preliminary denoising on the signal by applying a low-pass filter to remove high-frequency noise and retain the low-frequency components of the signal. The formula of the filtered signal is expressed as:

[0017]

[0018] in, represents the denoised signal; Represents the original electrical impedance signal; represents the impulse response of the filter; Indicates the adjustment parameters of the filter; controls the frequency response of the filter;

[0019] S13: Remove baseline drift by subtracting the mean from the signal to ensure that the mean of the signal is close to zero. The calculation formula is as follows:

[0020]

[0021] in, represents the signal after removing the baseline drift; represents the denoised signal; represents the mean of the signal multiplied by the intensity or offset used to control for baseline drift removal;

[0022] S14: Normalize the signal to have zero mean and unit variance to ensure that the signals are compared on the same scale. The normalization formula is as follows:

[0023]

[0024] in, represents the normalized signal; represents the signal after removing the baseline drift, represents the mean of the normalized signal; represents the standard deviation of the normalized signal; Represents new coefficients that control normalization.

[0025] As an embodiment of the present application, the step S2 of converting the signal into a frequency domain representation using discrete cosine transform specifically includes:

[0026] A discrete cosine transform is performed on the time domain signal. The discrete cosine transform can effectively extract the frequency component of the signal and convert the time domain signal into a frequency domain signal. The specific formula is as follows:

[0027]

[0028] in, is the transformed frequency domain signal; is the normalized time domain signal; is the time domain signal weighting coefficient; is the frequency coefficient, which represents the discrete cosine transform of the signal at different frequencies; is the length of the signal; is the frequency domain index after transformation; is the index of the time domain signal; is a newly added coefficient; it is used to adjust the magnitude of the final output to control the overall scaling of the overall result.

[0029] As an embodiment of the present application, the frequency domain enhancement in step S2 specifically includes:

[0030] In the frequency domain, the low-frequency part of the signal contains useful biological information. Enhancing the low-frequency part in the frequency domain can further enhance the effective characteristics of the signal. The formula of the enhanced frequency domain signal is as follows:

[0031]

[0032] in, represents the enhanced frequency domain signal; It represents the overall gain factor multiplied by the amplitude part of the frequency domain signal in frequency; is a gain function used to adjust the gain of different frequency components; is the phase part corresponding to the frequency; It is a phase offset parameter used to adjust the signal phase to avoid phase distortion caused by gain adjustment.

[0033] As an embodiment of the present application, step S3 specifically includes:

[0034] S31: Inputting the frequency domain enhanced signal into the network model to process the frequency domain signal;

[0035] S32: Extract frequency domain features through the network model, and obtain the global feature matrix after completing global dependency modeling.

[0036] As an embodiment of the present application, the extraction of frequency domain features in step S32 specifically includes:

[0037] S3211: Signal enhanced from the frequency domain using four-layer convolution Four levels of frequency domain features are extracted from the convolution layer. Each layer of convolution can gradually extract more complex frequency domain features to help the model better understand the signal pattern. The specific formula is as follows:

[0038]

[0039]

[0040]

[0041]

[0042] in, is the output after the first layer of convolution operation, is the first layer 1x1 convolution kernel, is the signal after frequency domain enhancement, It is the bias term of the first convolution layer, which controls the offset of the model; is the output after the second layer of convolution operation, is the 2x2 convolution kernel of the second layer, It is the bias term of the second layer of convolution, which controls the offset of the model; is the output after the third layer of convolution operation, is the 3x3 convolution kernel of the third layer, It is the bias term of the third convolution layer, which controls the offset of the model; is the output after the 4th layer of convolution operation, is the 4x4 convolution kernel of the 4th layer, It is the bias term of the 4th convolution layer, which controls the offset of the model;

[0043] S3212: After four layers of convolution, the feature map obtained is the deepest output. To further improve the expressiveness of the model and reduce information redundancy, a pooling-based feature aggregation method is used to integrate these frequency domain features. The formula is as follows:

[0044]

[0045] in, is the feature map after aggregation; It is the feature map output after four layers of convolution.

[0046] As an embodiment of the present application, obtaining the global feature matrix after completing the global dependency modeling in step S32 specifically includes:

[0047] S3221: The pooled features are input to the global dependency modeling layer, where the self-attention mechanism is used to calculate the dependency between features. The formula is as follows:

[0048]

[0049] in, is the feature after pooling; Weight matrices representing queries, keys, and values, which are learned parameters obtained through training; Bias items representing queries, keys, and values;

[0050] S3222: Use a self-attention mechanism to calculate the correlation between the query and the key. The attention weight of each feature is obtained by the dot product of the query and the key. The specific formula is as follows:

[0051]

[0052] in, Represents the attention weight, which includes the dependencies between features. Each feature is weighted according to its relevance to other features. Represents the query vector of the input features at the current time step; is the vector obtained after transposition; Indicates the dimension of the key vector, used for normalization, is an additional bias term;

[0053] S3223: After the attention score is calculated, multiple attention weights are weighted and summed with the value matrix. The formula is as follows:

[0054]

[0055] in, is the global feature matrix after weighted summation; is the calculated attention weight; is a matrix of values.

[0056] As an embodiment of the present application, in step S4, the final global feature matrix is ​​input into the classifier, and the output obtained by the fully connected layer calculation specifically includes:

[0057] The global feature matrix obtained by weighted summation is used as the input of the classifier. After a flattening operation, it is input into a classifier and the output is calculated through the fully connected layer. The formula is as follows:

[0058]

[0059]

[0060] in, It is a flattening operation, in which the multi-scale fused features are flattened into a one-dimensional vector; is the output of the fully connected layer; is the weight matrix of the fully connected layer; is the weight matrix of the fully connected layer; is the bias term.

[0061] As an embodiment of the present application, in step S4, the output is converted into a probability value by a function, which can determine whether cancer exists and provide corresponding detection results, specifically including:

[0062] The output of the fully connected layer is converted into a probability value through a function for classification, and the probability of each category is obtained by calculation. The specific calculation formula is:

[0063]

[0064] in, It is The probability value of a class; the calculation method is based on the adjustment of given features and parameters; and is the modified input feature; and It is an adjustable parameter used to control the impact of features on the final result; Indicates the number of categories.

[0065] The beneficial effects of the present invention are:

[0066] (1) The present invention obtains electrical signal data of cancer tissue through bioelectrical impedance imaging technology, and preprocesses and enhances the acquired electrical impedance signal in the frequency domain, including denoising, baseline drift correction, and standardization steps, thereby effectively improving the signal quality and being able to efficiently extract features from the electrical impedance signal, thereby mining potential cancer features. Compared with traditional cancer detection methods, the present invention does not require invasive operations such as puncture or surgery, thus achieving non-invasive cancer detection.

[0067] (2) The present invention uses discrete cosine transform to convert the preprocessed time domain signal into frequency domain representation and enhance the frequency domain features, thereby improving the effect of frequency domain feature extraction. The enhanced frequency domain features are input into the network model for feature extraction, and the frequency domain features are gradually extracted through four layers of convolution. After four layers of convolution, the features are aggregated using pooling operations to improve the expressive ability of the model and reduce information redundancy. The pooled features are then input into the global dependency modeling layer, and the self-attention mechanism is used to calculate the dependency between features, thereby enhancing the model's attention to key information. Finally, the similarity between the query and the key is calculated, and the weighted summation with the value matrix is ​​performed to obtain the final global feature matrix for further cancer detection and classification tasks. Through the above steps, the robustness to frequency domain data can be effectively improved, thereby improving the application effect of electrical impedance signals in cancer detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 Schematic diagram of a signal collection method for an electrical impedance cancer detection method based on frequency domain information enhancement provided in an embodiment of the present invention;

[0069] Figure 2 A flow chart of a signal processing method for an electrical impedance cancer detection method based on frequency domain information enhancement provided in an embodiment of the present invention;

[0070] Figure 3 The figure is a flow chart of signal feature extraction for an electrical impedance cancer detection method based on frequency domain information enhancement provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0072] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0073] In the present invention, unless otherwise specified or limited, the terms "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can mean fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two elements or interaction between two elements, unless otherwise specified. Those skilled in the art will be able to understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0074] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme in which A and B are satisfied at the same time. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0075] Reference Figures 1 to 3 In a first aspect, the present invention provides a method for detecting cancer by electrical impedance based on frequency domain information enhancement, the method comprising the following steps:

[0076] S1: Obtain the electrical impedance signal in the patient's body through electrical impedance imaging technology and preprocess it;

[0077] S2: Perform frequency domain conversion on the preprocessed time domain signal, use discrete cosine transform to convert the signal into frequency domain representation and perform frequency domain enhancement;

[0078] S3: Inputting the frequency-domain enhanced features into an improved network model, wherein the improved network model combines frequency-domain information and global dependencies, and processes the frequency-domain enhanced features to obtain a final global feature matrix;

[0079] S4: The final global feature matrix is ​​input into the classifier, and the output is calculated by the fully connected layer. The output is then converted into a probability value through a function, which can determine whether cancer exists and give the corresponding detection results.

[0080] Specifically, the present invention obtains the electrical impedance signal in the patient's body through electrical impedance imaging technology, pre-processes the signal, and converts the time domain signal into a frequency domain representation through a discrete cosine transform. After enhancing the frequency domain features, it is input into the improved network model. The improved network model combines frequency domain information and global dependencies, processes the features after frequency domain enhancement to obtain the final global feature matrix; the final global feature matrix is ​​input into the classifier, and the output is obtained by calculation through the fully connected layer, and then the output is converted into a probability value through a function, which can determine whether cancer exists and give corresponding detection results, providing more accurate cancer detection support.

[0081] like Figure 2 As shown, as an embodiment of the present application, step S1 specifically includes:

[0082] S11: Electrical impedance tomography (EIT) involves injecting current into the human body and recording reflected signals at different electrode locations. These signals reflect the electrical conductivity of different tissues in the body and include amplitude and phase information in the time domain. These signals are usually expressed in complex form, including real resistance and imaginary reactance. The calculation formula is as follows:

[0083]

[0084] in, Represents the total impedance that changes with time; Resistance value changing with time; Indicates the reactance value that changes with time; It is an imaginary unit, which represents the difference between the reactance part and the resistance part; Used to control the weight or influence between reactance and resistance; Indicates the phase, the phase information of the current or voltage that changes with time;

[0085] S12: Since the electrical impedance signal is easily interfered by noise, it is necessary to perform preliminary denoising on the signal and apply a low-pass filter to remove high-frequency noise and retain the low-frequency components of the signal. The formula of the filtered signal is expressed as:

[0086]

[0087] in, represents the denoised signal; Represents the original electrical impedance signal; represents the impulse response of the filter; Indicates the adjustment parameters of the filter; controls the frequency response of the filter;

[0088] S13: The impedance signal may experience baseline drift due to equipment errors or external interference, affecting the analysis results. Baseline drift is removed by subtracting the mean from the signal to ensure that the mean of the signal is close to zero. The calculation formula is as follows:

[0089]

[0090] in, Represents the signal after low-pass filtering and removal of baseline drift; represents the denoised signal; represents the mean of the signal multiplied by the intensity or offset used to control for baseline drift removal;

[0091] S14: To prevent the amplitude differences of the signal at different time points from affecting subsequent analysis, the signal needs to be normalized to have zero mean and unit variance, ensuring that the signals are compared on the same scale. The normalization formula is as follows:

[0092]

[0093] in, represents the normalized signal; represents the signal after removing the baseline drift, represents the mean of the normalized signal; represents the standard deviation of the normalized signal; Represents new coefficients that control normalization.

[0094] Specifically, the present invention obtains electrical signal data of cancer tissue through bioelectrical impedance imaging technology, and then preprocesses the acquired electrical impedance signal, including denoising, baseline drift correction, and standardization steps, which effectively improves the signal quality and can efficiently extract features in the electrical impedance signal, thereby discovering potential cancer characteristics; compared with traditional cancer detection methods, the present invention does not require invasive operations such as puncture or surgery, and realizes non-invasive cancer detection.

[0095] As an embodiment of the present application, the step S2 of converting the signal into a frequency domain representation using discrete cosine transform specifically includes:

[0096] A discrete cosine transform is performed on the time domain signal. The discrete cosine transform can effectively extract the frequency component of the signal and convert the time domain signal into a frequency domain signal. The specific formula is as follows:

[0097]

[0098] in, is the transformed frequency domain signal; is the normalized time domain signal; is the time domain signal weighting coefficient; is the frequency coefficient, which represents the discrete cosine transform of the signal at different frequencies; is the length of the signal; is the frequency domain index after transformation; is the index of the time domain signal; is a newly added coefficient; it is used to adjust the magnitude of the final output to control the overall scaling of the overall result.

[0099] As an embodiment of the present application, the frequency domain enhancement in step S2 specifically includes:

[0100] In the frequency domain, the low-frequency part of the signal usually contains useful biological information. Enhancing the low-frequency part in the frequency domain can further enhance the effective characteristics of the signal. The formula of the enhanced frequency domain signal is as follows:

[0101]

[0102] in, represents the enhanced frequency domain signal; It represents the overall gain factor multiplied by the amplitude part of the frequency domain signal in frequency; It is a gain function, which is used to adjust the gain of different frequency components. The gain of the low-frequency part is higher, while the gain of the high-frequency part is lower. is the phase part corresponding to the frequency; It is a phase offset parameter used to adjust the signal phase to avoid phase distortion caused by gain adjustment.

[0103] Specifically, after preliminary denoising, baseline drift removal and normalization, a clear electrical impedance signal is obtained; a discrete cosine transform is performed on the standardized time domain signal to extract the frequency component, and the frequency domain signal is enhanced to further improve the effective features in the signal, thereby discovering potential cancer characteristics.

[0104] As an embodiment of the present application, step S3 specifically includes:

[0105] S31: Inputting the frequency domain enhanced signal into the network model to process the frequency domain signal;

[0106] S32: Extract frequency domain features through the network model, and obtain the global feature matrix after completing global dependency modeling.

[0107] like Figure 3 As shown, as an embodiment of the present application, the extraction of frequency domain features in step S32 specifically includes:

[0108] S3211: Signal enhanced from the frequency domain using four-layer convolution Four levels of frequency domain features are extracted from the convolution layer. Each layer of convolution can gradually extract more complex frequency domain features to help the model better understand the signal pattern. The specific formula is as follows:

[0109]

[0110]

[0111]

[0112]

[0113] in, is the output after the first layer of convolution operation, is the first layer 1x1 convolution kernel, is the signal after frequency domain enhancement, It is the bias term of the first convolution layer, which controls the offset of the model; is the output after the second layer of convolution operation, is the 2x2 convolution kernel of the second layer, It is the bias term of the second layer of convolution, which controls the offset of the model; is the output after the third layer of convolution operation, is the 3x3 convolution kernel of the third layer, It is the bias term of the third convolution layer, which controls the offset of the model; is the output after the 4th layer of convolution operation, is the 4x4 convolution kernel of the 4th layer, It is the bias term of the 4th convolution layer, which controls the offset of the model;

[0114] S3212: After four layers of convolution, the feature map obtained is the deepest output. To further improve the expressiveness of the model and reduce information redundancy, a pooling-based feature aggregation method is used to integrate these frequency domain features. The formula is as follows:

[0115]

[0116] in, is the feature map after aggregation; It is the feature map output after four layers of convolution.

[0117] As an embodiment of the present application, obtaining the global feature matrix after completing the global dependency modeling in step S32 specifically includes:

[0118] S3221: The pooled features are input to the global dependency modeling layer, where the self-attention mechanism is used to calculate the dependency between features. The formula is as follows:

[0119]

[0120] in, is the feature after pooling; Weight matrices representing queries, keys, and values, which are learned parameters obtained through training; Bias items representing queries, keys, and values;

[0121] S3222: A self-attention mechanism is used to calculate the correlation between the query and the key. The attention weight of each feature can be obtained by taking the dot product of the query and the key. The specific formula is as follows:

[0122]

[0123] in, Represents the attention weight, which includes the dependencies between features. Each feature is weighted according to its relevance to other features. Represents the query vector of the input features at the current time step; yes The column vector obtained after transposition changes from a column vector to a row vector; Indicates the dimension of the key vector, used for normalization, It is an additional bias term, the calculated similarity can be adjusted, and the feature has a greater influence in the calculation;

[0124] S3223: After the attention score is calculated, the next step is to perform a weighted summation of multiple attention weights and the value matrix. The formula is as follows:

[0125]

[0126] in, is the global feature matrix after weighted summation; is the calculated attention weight; is a matrix of values.

[0127] Specifically, the frequency-domain enhanced signal is input into the network model and normalized to ensure that the data is further processed at the same scale. Then, the frequency-domain features are extracted through the network model, and more complex features are extracted layer by layer to help the model better understand the pattern of the signal. Each layer of convolution gradually extracts frequency-domain features. After four layers of convolution, the features are aggregated using pooling operations to improve the expressive power of the model and reduce information redundancy. Next, the pooled features are input into the global dependency modeling layer, and the self-attention mechanism is used to calculate the dependency between features to enhance the model's attention to key information. By calculating the similarity between the query and the key and weighted summing it with the value matrix, the final global feature matrix is ​​obtained for further cancer detection and classification tasks.

[0128] As an embodiment of the present application, step S4 inputs the final global feature matrix into the classifier, and the output obtained by the fully connected layer calculation specifically includes:

[0129] The global feature matrix obtained by weighted summation is used as the input of the classifier. After a flattening operation, it is input into a classifier and the output is calculated through the fully connected layer. The formula is as follows:

[0130]

[0131]

[0132] in, It is a flattening operation, in which the multi-scale fused features are flattened into a one-dimensional vector, ready to enter the fully connected layer; is the weight matrix of the fully connected layer; is the output of the fully connected layer; is the weight matrix of the fully connected layer; is the bias term.

[0133] As an embodiment of the present application, in step S4, the output is converted into a probability value by a function, which can determine whether cancer exists and provide corresponding detection results, specifically including:

[0134] The output of the fully connected layer is converted into a probability value through a function for classification, and the probability of each category is obtained by calculation. The specific calculation formula is:

[0135]

[0136] in, It is The probability value of a class; the calculation method is based on the adjustment of given features and parameters; and is the modified input feature; and It is an adjustable parameter used to control the impact of features on the final result; Indicates the number of categories.

[0137] Specifically, the global feature matrix obtained through weighted summation is input into the classifier. After flattening, it is input into the fully connected layer for calculation to obtain the classifier output. A function is then used to convert the fully connected layer output into a probability value for each category. Based on the features and the adjustment of adjustable parameters, the probability of each category is calculated, thus achieving cancer classification detection.

[0138] The above descriptions are merely some preferred embodiments of the present disclosure and illustrate the underlying technical principles. Those skilled in the art should understand that the scope of the invention encompassed by the embodiments of the present disclosure is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for electrical impedance cancer detection based on frequency domain information enhancement, characterized in that: The method comprises the following steps: S1: Obtain the electrical impedance signal in the patient's body through electrical impedance imaging technology and preprocess it; S2: Perform frequency domain conversion on the preprocessed time domain signal, use discrete cosine transform to convert the signal into frequency domain representation and perform frequency domain enhancement; S3: Inputting the frequency-domain enhanced features into an improved network model, wherein the improved network model combines frequency-domain information and global dependencies, and processes the frequency-domain enhanced features to obtain a final global feature matrix; S4: The final global feature matrix is ​​input into the classifier, and the output is calculated by the fully connected layer. The output is then converted into a probability value through a function to determine whether cancer exists and give the corresponding detection result; The step S2 of converting the signal into a frequency domain representation using discrete cosine transform specifically includes: A discrete cosine transform is performed on the time domain signal. The discrete cosine transform can effectively extract the frequency component of the signal and convert the time domain signal into a frequency domain signal. The specific formula is as follows: in, is the transformed frequency domain signal; is the normalized time domain signal; is the time domain signal weighting coefficient; is the frequency coefficient, which represents the discrete cosine transform of the signal at different frequencies; is the length of the signal; is the frequency domain index after transformation; is the index of the time domain signal; It is a newly added coefficient; it is used to adjust the amplitude of the final output and control the overall scaling of the overall result; The frequency domain enhancement in step S2 specifically includes: In the frequency domain, the low-frequency part of the signal contains useful biological information. Enhancing the low-frequency part in the frequency domain can further enhance the effective characteristics of the signal. The formula of the enhanced frequency domain signal is as follows: in, represents the enhanced frequency domain signal; It represents the overall gain factor multiplied by the amplitude part of the frequency domain signal in frequency; is a gain function used to adjust the gain of different frequency components; is the phase part corresponding to the frequency; It is the phase offset parameter, which is used to adjust the signal phase to avoid phase distortion caused by gain adjustment; Signal enhanced from the frequency domain using four layers of convolution The four-level frequency domain features are extracted from the equation. The specific formula is as follows: in, is the output after the first layer of convolution operation, is the first layer 1x1 convolution kernel, is the signal after frequency domain enhancement, It is the bias term of the first convolution layer, which controls the offset of the model; is the output after the second layer of convolution operation, is the 2x2 convolution kernel of the second layer, It is the bias term of the second layer of convolution, which controls the offset of the model; is the output after the third layer of convolution operation, is the 3x3 convolution kernel of the third layer, It is the bias term of the third convolution layer, which controls the offset of the model; is the output after the 4th layer of convolution operation, is the 4x4 convolution kernel of the 4th layer, It is the bias term of the 4th convolution layer, which controls the offset of the model.

2. The electrical impedance cancer detection method based on frequency domain information enhancement according to claim 1, characterized in that: The step S1 specifically includes: S11: Electrical impedance tomography (EIT) involves injecting current into the human body and recording reflected signals at different electrode locations. These signals reflect the electrical conductivity of different tissues in the body and contain amplitude and phase information in the time domain. These signals are expressed as complex numbers, including real resistance and imaginary reactance. The calculation formula is as follows: in, Represents the total impedance that changes with time; Resistance value changing with time; Indicates the reactance value that changes with time; It is an imaginary unit, which represents the difference between the reactance part and the resistance part; Used to control the weight or influence between reactance and resistance; Indicates the phase, the phase information of the current or voltage that changes with time; S12: Perform preliminary denoising on the signal by applying a low-pass filter to remove high-frequency noise and retain the low-frequency components of the signal. The formula of the filtered signal is expressed as: in, represents the denoised signal; Represents the original electrical impedance signal; represents the impulse response of the filter; Indicates the adjustment parameters of the filter; controls the frequency response of the filter; S13: Remove baseline drift by subtracting the mean from the signal to ensure that the mean of the signal is close to zero. The calculation formula is as follows: in, represents the signal after removing the baseline drift; represents the denoised signal; represents the mean of the signal multiplied by the intensity or offset used to control for baseline drift removal; S14: Normalize the signal to have zero mean and unit variance to ensure that the signals are compared on the same scale. The normalization formula is as follows: in, represents the normalized signal; represents the signal after removing the baseline drift, represents the mean of the normalized signal; represents the standard deviation of the normalized signal; Represents new coefficients that control normalization.

3. The electrical impedance cancer detection method based on frequency domain information enhancement according to claim 1, characterized in that: The step S3 specifically includes: S31: Inputting the frequency domain enhanced signal into the network model to process the frequency domain signal; S32: Extract frequency domain features through the network model, and obtain the global feature matrix after completing global dependency modeling.

4. The electrical impedance cancer detection method based on frequency domain information enhancement according to claim 3, characterized in that: The extraction of frequency domain features in step S32 specifically includes: S3211: Each convolution layer can gradually extract more complex frequency domain features to help the model better understand the signal pattern; S3212: After four layers of convolution, the feature map obtained is the deepest output. To further improve the expressiveness of the model and reduce information redundancy, a pooling-based feature aggregation method is used to integrate these frequency domain features. The formula is as follows: in, is the aggregated feature; It is the feature map output after four layers of convolution.

5. The electrical impedance cancer detection method based on frequency domain information enhancement according to claim 4, characterized in that: After completing the global dependency modeling in step S32, the global feature matrix is ​​obtained, which specifically includes: S3221: The aggregated features are input to the global dependency modeling layer, where the self-attention mechanism is used to calculate the dependency between features. The formula is as follows: in, is the feature after pooling; Weight matrices representing queries, keys, and values, which are learned parameters obtained through training; Bias items representing queries, keys, and values; S3222: Use a self-attention mechanism to calculate the correlation between the query and the key. The attention weight of each feature is obtained by the dot product of the query and the key. The specific formula is as follows: in, Represents the attention weight, which includes the dependencies between features. Each feature is weighted according to its relevance to other features. Represents the query vector of the input features at the current time step; is the vector obtained after transposition; Indicates the dimension of the key vector, used for normalization, is an additional bias term; S3223: After the attention score is calculated, multiple attention weights are weighted and summed with the value matrix. The formula is as follows: in, is the global feature matrix after weighted summation; is the calculated attention weight; is a matrix of values.

6. The electrical impedance cancer detection method based on frequency domain information enhancement according to claim 5, characterized in that: In step S4, the final global feature matrix is ​​input into the classifier, and the output obtained by the fully connected layer calculation specifically includes: The global feature matrix obtained by weighted summation is used as the input of the classifier. After a flattening operation, it is input into a classifier and the output is calculated through the fully connected layer. The formula is as follows: in, It is a flattening operation, in which the multi-scale fused features are flattened into a one-dimensional vector; is the weight matrix of the fully connected layer; is the weight matrix of the fully connected layer; is the bias term; is the output of the fully connected layer.

7. The electrical impedance cancer detection method based on frequency domain information enhancement according to claim 6, characterized in that: In step S4, the output is converted into a probability value through a function, which can determine whether cancer exists and provide corresponding detection results, including: The output of the fully connected layer is converted into a probability value through a function for classification, and the probability of each category is obtained by calculation. The specific calculation formula is: in, It is The probability value of a class; the calculation method is based on the adjustment of given features and parameters; and is the modified input feature; and It is an adjustable parameter used to control the impact of features on the final result; Indicates the number of categories.

Images