Three-chamber data acquisition method, probe and acquisition system

Abstract

The three-chamber data obtaining method comprises the steps that multiple sets of training data are obtained, each set of training data comprises three-chamber data and electrical data, obtained in the same sampling period, of a collection area of biological tissue, and the three-chamber data comprises the extracellular interstitial volume fraction, the cell volume fraction and the blood vessel volume fraction of all voxel points in the collection area; the electrical data is related to the electrical impedance of the biological tissue; utilizing multiple groups of training data to train a calculation model, so that the calculation model can realize mapping between the electrical data and the three-room data; acquiring electrical data of a target area of the biological tissue, wherein the target area and the acquisition area are the same in size and shape; and inputting the obtained electrical data of the target area into the trained calculation model to obtain three-room data of the target area. According to the acquisition method, the three-room data can be directly acquired through the electrical data, and the complexity of three-room data acquisition is reduced. The invention also provides a probe and a three-chamber data acquisition system.

Description

Technical Field

[0001] The present invention relates to the medical field, and in particular to a method, a probe and a system for acquiring three-chamber data. Background Art

[0002] In the medical field, the combined measurement of electrical signals and magnetic resonance imaging is essential for research and diagnosis. Electrical impedance tomography (EIT), as a modern imaging method, has been widely used in the field of biomedical imaging by sending current in the body and measuring the voltage distribution to reconstruct images of internal structures. Magnetic resonance imaging (MRI) can provide high-resolution three-chamber data, which includes the volume fractions of the extracellular space, cell tissue, and vascular compartment. This information is essential for accurately monitoring the diffusion state of tracers and their relationship with tissue anatomical structures. The combination of electrical impedance tomography and magnetic resonance imaging can achieve multimodal imaging of biological tissues. Multimodal imaging provides complementary information through different imaging modes, which can more comprehensively and accurately evaluate the structure, function or metabolic state of the human body, and further improve the accuracy of diagnosis and research.

[0003] At present, the acquisition of three-chamber data mainly relies on magnetic resonance imaging technology. However, magnetic resonance imaging has many limitations, such as high cost and cumbersome and complicated image acquisition process. In addition, the electrical signals in biological tissues change very quickly. If you want to synchronously collect electrical signals and three-chamber data while keeping the biological tissues in the same physiological state, the operation difficulty will be greatly increased, which will not only increase the complexity of data acquisition, but also make it difficult to ensure the stability and accuracy of the data obtained. Summary of the invention

[0004] The object of the present invention is to provide a method for acquiring three-chamber data, which can directly obtain the three-chamber data through electrical data and reduce the complexity of acquiring the three-chamber data.

[0005] Another object of the present invention is to provide a probe capable of introducing a tracer while acquiring electrical data of a collection region, so as to acquire three-chamber data of the same collection region within the same sampling period.

[0006] Another object of the present invention is to provide a three-chamber data acquisition system, which can directly obtain the three-chamber data through electrical data, thereby reducing the complexity of three-chamber data acquisition.

[0007] The method for acquiring three-chamber data provided by the present invention comprises: acquiring multiple groups of training data, wherein each group of training data comprises three-chamber data and electrical data of a collection area of ​​biological tissue acquired within the same sampling period, the three-chamber data comprises the extracellular space volume fraction, the cell volume fraction and the blood vessel volume fraction of each voxel point in the collection area, and the electrical data is related to the electrical impedance of the biological tissue; training a computing model using the multiple groups of training data so that the computing model can realize mapping between the electrical data and the three-chamber data; acquiring electrical data of a target area of ​​the biological tissue, the target area having the same size and shape as the collection area; and inputting the acquired electrical data of the target area into the trained computing model to obtain the three-chamber data of the target area.

[0008] By training the computational model, the mapping between the electrical data collected from the acquisition area and the three-chamber data is achieved, so that the three-chamber data of the target area can be obtained by inputting the electrical data obtained from the target area into the computational model. This method can directly obtain the three-chamber data through the electrical data, reducing the complexity of acquiring the three-chamber data.

[0009] In another exemplary embodiment of the method for acquiring three-chamber data, the method for acquiring each set of training data includes: introducing a tracer for magnetic resonance imaging into a collection area of ​​biological tissue, performing magnetic resonance imaging on the collection area in the same sampling period, acquiring electrical data of the collection area through a probe located in the collection area, and obtaining three-chamber data according to the magnetic resonance imaging result. This facilitates achieving that each set of training data comes from the same collection area in the same sampling period.

[0010] In another exemplary embodiment of the method for acquiring three-chamber data, the loss function of the calculation model is expressed by formula (1):

[0011] L(θ)=λ a L a +λ b L b +λ∥θ∥ 2 Formula (1)

[0012] in,

[0013] a is the volume fraction of the extracellular space,

[0014] b is the cell volume fraction,

[0015] L(θ) is the loss function of the computational model, where θ is the training parameter of the computational model.

[0016] λ a and λ b are the dynamic weights for a and b respectively,

[0017] L a and Lb are the mean square error losses for a and b respectively,

[0018] λ is the regularization strength hyperparameter,

[0019] ∥θ∥ 2 is the regularization term, expressed by formula (2):

[0020]

[0021] Among them, θ j is the jth training parameter of the calculation model.

[0022] In another exemplary embodiment of the method for acquiring three-chamber data, the dynamic weight λ a and λ b They are respectively expressed by formula (3) and formula (4):

[0023]

[0024] in,

[0025] ∈ is a constant,

[0026] L a and L b They are respectively shown in formula (5) and formula (6):

[0027]

[0028] N is the number of training data sets,

[0029] a i is the output value of the extracellular space volume fraction predicted by the calculation model,

[0030] is the true value of the extracellular space volume fraction, obtained from the three-chamber data of the training data, b i is the output value of the cell volume fraction predicted by the calculation model,

[0031] is the true value of the cell volume fraction, obtained from the three-chamber data of the training data.

[0032] The present invention also provides a probe. The probe is configured to introduce a tracer into the collection area and obtain electrical data of the collection area when the probe is located in the collection area. The probe can introduce the tracer while obtaining the electrical data of the collection area, so as to obtain three-chamber data of the same collection area in the same sampling period.

[0033] In another schematic embodiment of the probe, the probe includes a probe body, several isolation pipes, several electrodes arranged on the surface of the probe body, several wires and a processing module. The probe body is provided with a through hole for introducing a tracer into the collection area when the probe body is located in the collection area. Several isolation pipes are passed through the probe body and extend along the length direction of the probe body. Several electrodes are arranged to form a plurality of layer arrays perpendicular to the length direction, and are configured to be able to obtain electrical signals by means of excitation measurement. Each wire is passed through an isolation pipe. Each electrode is connected to the processing module via a wire. The processing module can process the acquired electrical signal into electrical data, and can transmit the electrical data to the computing model. By integrating the electrode into the probe body, it is beneficial to reduce the volume of the probe and improve the stability of data acquisition.

[0034] In another exemplary embodiment of the probe, a plurality of electrodes are arranged to form three mutually parallel layer arrays, each layer array includes four electrodes evenly distributed along the circumference of the probe body, and the electrodes in each layer array are aligned with the electrodes at corresponding positions in the adjacent layer array along the length direction, thereby facilitating the improvement of the accuracy of data collection.

[0035] In another exemplary embodiment of the probe, the probe body is made of alumina ceramics, and the surface of the probe body is covered with a polyethylene glycol coating, thereby reducing the risk of probe breakage, reducing the immune response and inflammatory response of tissue to the probe, and improving the stability of the probe.

[0036] In another exemplary embodiment of the probe, the isolation channel is made of copper, and each electrode is a circular copper sheet welded to the surface of the probe body, thereby facilitating stable collection and transmission of electrical signals.

[0037] The present invention also provides a three-chamber data acquisition system. The three-chamber data acquisition system includes a calculation module, and the calculation module stores a trained calculation model. The three-chamber data acquisition system can directly obtain the three-chamber data through electrical data, reducing the complexity of data acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The following drawings are only used to schematically illustrate and explain the present invention, and do not limit the scope of the present invention.

[0039] Figure 1 The present invention is a flow chart of a schematic implementation of a method for acquiring three-chamber data.

[0040] Figure 2 The present invention is a flowchart of an exemplary implementation of a method for acquiring training data.

[0041] Figure 3 A schematic diagram illustrating the sampling area.

[0042] Figure 4 and Figure 5 A schematic diagram for explaining the structure of the probe.

[0043] Figure 6 A schematic diagram for illustrating electrical data.

[0044] Figure 7 A schematic diagram for explaining the acquired three-chamber data.

[0045] Description of symbols

[0046] 10 probes

[0047] 11Probe body

[0048] 111 through hole

[0049] 12 Isolation Pipeline

[0050] 13 electrodes

[0051] 14 wires

[0052] 15 Processing Modules

[0053] 20 computing modules

[0054] S Collection Area

[0055] L length direction. DETAILED DESCRIPTION

[0056] In order to have a clearer understanding of the technical features, purposes and effects of the invention, the specific embodiments of the invention are now described with reference to the accompanying drawings, in which the same reference numerals represent the same parts.

[0057] In this document, “exemplary” means “serving as an example, instance or illustration”, and any diagram or implementation described in this document as “exemplary” should not be interpreted as a more preferred or more advantageous technical solution.

[0058] Figure 1 FIG. 1 is a flow chart of an exemplary implementation of a method for acquiring three-chamber data. Figure 1 In an exemplary embodiment, the method for acquiring three-chamber data includes S10 to S40.

[0059] S10: Acquire multiple sets of training data, wherein each set of training data includes three-chamber data and electrical data of a collection area S of biological tissue acquired in the same sampling period, the three-chamber data includes the extracellular space volume fraction, the cell volume fraction and the blood vessel volume fraction of each voxel point in the collection area S, and the sum of the three-chamber data of each voxel point is 1. The electrical data is related to the electrical impedance of the biological tissue.

[0060] The three-chamber data is obtained, for example, through the results of magnetic resonance imaging of biological tissues, and the electrical data is obtained, for example, by collecting electrical signals from biological tissues. The electrical signals of biological tissues (such as the brain) change rapidly, so magnetic resonance imaging and collecting electrical signals need to be performed within the same sampling period to ensure that the three-chamber data and electrical data used as training data are data obtained when the biological tissues are in the same physiological state. The time span of the sampling period can be determined according to the type of biological tissue, such as a few seconds. The electrical signal is, for example, the potential signal of the biological tissue, and the electrical data is, for example, the potential difference between two collection points, which is related to the electrical impedance of the biological tissue. It is well known to those skilled in the art that electrical tomography of biological tissues can be performed using these electrical data.

[0061] Methods for obtaining training data include: Figure 2 As shown in the flowchart, Figure 2 In the illustrated exemplary embodiment, the method for acquiring each set of training data includes S11 to S13.

[0062] S11: Introduce a tracer for magnetic resonance imaging into a collection area S of biological tissue. The collection area S is, for example, a cubic area with a side length of 3 cm. Figure 3 The tracer is, for example, Figure 3 As shown, the tracer is introduced into the collection area S of the biological tissue through the probe 10 located in the collection area. However, it is not limited thereto. In other exemplary embodiments, the tracer can also be introduced into the collection area S of the biological tissue through other pathways. Due to the diffusion of the tracer, the collection area S is a diffusion space centered on the needle tip of the probe. For the convenience of calculation, the collection area S can be simplified to a cubic area centered on the needle tip of the probe, whose center line coincides with the axis of the probe.

[0063] S12: Perform magnetic resonance imaging of the collection area S during the same sampling period, and obtain electrical data of the collection area S through the probe 10 located in the collection area S. In an illustrative embodiment, after the tracer is introduced into the collection area S, the operator performs magnetic resonance imaging of the collection area S, and at the same time, collects electrical signals through the electrodes integrated on the probe 10, for example, by means of excitation measurement, and converts the electrical signals into electrical data. The excitation measurement method uses a pair of adjacent electrodes as excitation electrodes and the remaining electrodes as measurement electrodes to obtain electrical data of the collection area. In other illustrative embodiments, the excitation measurement method may also use a pair of relative electrodes as excitation electrodes. It should be noted that a pair of relative electrodes are two electrodes that are in relative positions among all electrodes.

[0064] S13: Obtain three-chamber data according to the magnetic resonance imaging results. The three-chamber data can be obtained from the magnetic resonance imaging image according to the method disclosed in patent CN114646913B. In this way, multiple sets of training data can be obtained, and each set of training data comes from the same acquisition area in the same sampling period.

[0065] S20: Train a computational model using multiple sets of training data, so that the computational model can achieve mapping between electrical data and three-chamber data.

[0066] Multiple sets of training data are input into the computational model to obtain the mapping relationship between the electrical data and the three-chamber data through training. The amount of training data can be determined according to the type of biological tissue.

[0067] In an exemplary embodiment, the loss function of the computational model is represented by equation (1):

[0068] L(θ)=λ a L a +λ b L b +λ∥θ∥ 2 Formula (1)

[0069] in,

[0070] L(θ) is the loss function of the computational model, where θ is the training parameter of the computational model;

[0071] λ is the regularization strength hyperparameter;

[0072] ∥θ∥ 2 is the regularization term, expressed by formula (2):

[0073]

[0074] Among them, θ j is the jth training parameter of the calculation model;

[0075] a is the volume fraction of the extracellular space;

[0076] b is the cell volume fraction;

[0077] λ a and λ b are the dynamic weights for a and b respectively. In an exemplary embodiment, the dynamic weight λ a and λ b They are respectively expressed by formula (3) and formula (4):

[0078]

[0079] Among them, ∈ is a constant;

[0080] La and L b are the mean square error losses for a and b respectively. In an exemplary embodiment, L a and L b They are respectively shown in formula (5) and formula (6):

[0081]

[0082] Where N is the number of training data sets,

[0083] a i is the output value of the extracellular space volume fraction predicted by the calculation model,

[0084] is the true value of the extracellular space volume fraction, obtained from the three-chamber data of the training data,

[0085] b i is the output value of the cell volume fraction predicted by the calculation model,

[0086] is the true value of the cell volume fraction, obtained from the three-chamber data of the training data.

[0087] In other exemplary embodiments, the computing model may also use other loss functions. Through the constraints of the above loss functions, the computing model can converge quickly to complete the training.

[0088] S30: Acquire electrical data of a target area of ​​biological tissue, the target area having the same size and shape as the acquisition area S. The method for acquiring electrical data of the target area is the same as the method for acquiring electrical data of the acquisition area S, and will not be repeated here. It should be noted that the process of acquiring electrical data of the target area does not require the introduction of a tracer. In addition, the relative position of the target area and the probe should also be the same as the relative position of the acquisition area S and the probe.

[0089] S40: Input the acquired electrical data into the trained computing model to obtain the three-chamber data of the target area.

[0090] By training the computational model, the mapping between the electrical data collected from the acquisition area and the three-chamber data is realized, so that the three-chamber data of the target area can be obtained by inputting the electrical data obtained from the target area into the computational model. This method can directly obtain the three-chamber data through electrical data, reducing the complexity of obtaining the three-chamber data.

[0091] The present invention also provides a probe 10 . Figure 4 and Figure 51 is a schematic diagram for explaining the structure of the probe. The probe 10 is configured to be able to introduce a tracer and obtain electrical data of a collection area. The probe can introduce a tracer while obtaining electrical data of a collection area, so as to obtain three-chamber data of the same collection area in the same sampling period.

[0092] The probe 10 includes a probe body 11 , a plurality of isolation pipes 12 , a plurality of electrodes 13 disposed on the surface of the probe body 11 , a plurality of wires 14 and a processing module 15 .

[0093] The probe body 11 is provided with a through hole 111 for introducing a tracer into the collection area S when the probe body is located in the collection area S. However, it is not limited to this. In other exemplary embodiments, the probe body can also introduce a tracer into the collection area S in other ways. The probe body 11 is made of alumina ceramics, and the surface of the probe body 11 is covered with a polyethylene glycol coating. Alumina ceramics have good insulation properties and mechanical strength and are not easy to break, thereby helping to reduce the risk of breakage of the probe. The polyethylene glycol coating can reduce the immune response and inflammatory response of biological tissues to the probe and improve the stability of the probe.

[0094] A plurality of isolation pipes 12 penetrate the probe body 11 and extend along a length direction L of the probe body 11 .

[0095] Several electrodes 13 are arranged to form multiple layer arrays perpendicular to the length direction L, and can obtain electrical signals such as potential signals by means of excitation measurement. In the exemplary embodiment, the electrodes 13 are arranged in three layer arrays, each of which includes four electrodes 13 ( Figure 4 and Figure 5 Only one of them is schematically marked in the figure), the electrodes 13 in each layer array are aligned with the electrodes 13 at the corresponding position in the adjacent layer array along the length direction L to avoid the reduction of the accuracy of the edge area of ​​the acquisition area in the electrical impedance distribution reconstruction. In other exemplary embodiments, the electrodes 13 can be arranged in other numbers of layer arrays, and the number of electrodes 13 in each layer array can also be other numbers.

[0096] Each electrode 13 is a circular copper sheet welded to the surface of the probe body 11. Each electrode 13 is, for example, a 10-micron copper sheet to ensure high-quality signal acquisition and imaging and good long-term biological environment stability. Figure 5 As shown, the circular sheet electrode 13 is integrated into the probe body 11, which can reduce the size of the probe along the direction perpendicular to the length, and can reduce the size of the wound during use.

[0097] Each wire 14 ( Figure 4 and Figure 5The electrodes 13 are connected to the processing module 15 via a wire 14. The isolation channel 12 is made of copper, for example, and runs through the entire probe body 11, thereby reducing external interference and ensuring stable transmission of electrical signals.

[0098] The processing module 15 can process the collected electrical signals into electrical data and can transmit the electrical data to the computing model. In an exemplary embodiment, the processing module 15 obtains the electrical signals, such as potential signals, collected by each electrode 13 through each wire 14, obtains electrical data, such as voltage values, through processing, and transmits the electrical data to the computing model, such as through electrical connection.

[0099] The present invention also provides a system for acquiring three-chamber data. The system for acquiring three-chamber data includes a computing module 20. The computing module 20 stores a trained computing model. The computing module 20 is, for example, electrically connected to the processing module 15 to receive electrical data and input the electrical data into the computing model. The system for acquiring three-chamber data can directly obtain three-chamber data through electrical data, thereby reducing the complexity of acquiring three-chamber data.

[0100] The following is a specific example of how to obtain three-chamber data using a three-chamber data acquisition system. In the actual use of the three-chamber data acquisition system, there is no need to perform magnetic resonance imaging on the target area, nor is there any need to introduce a tracer into the target area. Instead, the probe is used to obtain the electrical data of the target area and input it into the calculation model stored in the calculation module 20 for mapping. Therefore, in actual use, the probe can be as follows: Figure 4 and Figure 5 The probe 10 shown may also be another probe that does not have the through hole 111 .

[0101] The biological tissue is the brainstem region. A probe 10 is inserted into the target area of ​​the brainstem region. The probe 10 is integrated with 12 electrodes 13, which are arranged in three layer arrays, for example, named layer arrays A, B and C. The electrodes 13 in each layer array are named, for example, electrodes A1 to A4, B1 to B4 and C1 to C4. An excitation measurement method is adopted. First, two adjacent electrodes 13, for example, A1 and A2 are used as excitation electrodes, and the remaining 10 electrodes 13 are used as measurement electrodes. During the excitation measurement process, an excitation current is passed through electrodes A1 and A2, and the processing module 15 collects 10 potential signals output by the remaining 10 electrodes. After processing, 9 voltage values, that is, 9 electrical data, are obtained. By analogy, A2 and A3, A3 and A4, A4 and A1, B1 and B2... are switched in turn as excitation electrodes to complete a complete excitation measurement process. This process obtains 108 electrical data, that is, electrical data, such as Figure 6 shown. Figure 6The horizontal axis is the serial number of the electrical data, and the vertical axis is the voltage in mV.

[0102] The probe transmits the acquired electrical data in the brainstem area to the computing module 20. After receiving the electrical data, the computing module 20 inputs the data into the trained computing model. The computing model calculates the following: Figure 7 Three-chamber data are shown. Figure 7 In the figure, from left to right are the volume fraction distribution of the extracellular space, the volume fraction distribution of cells, and the volume fraction distribution of blood vessels in the brainstem region. In each voxel point, the sum of the volume fraction of the extracellular space, the volume fraction of cells, and the volume fraction of blood vessels is 1.

[0103] It should be understood that although this specification is described according to various embodiments, not every embodiment contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

[0104] The series of detailed descriptions listed above are only specific descriptions of feasible embodiments of the present invention. They are not intended to limit the scope of protection of the present invention. Any equivalent implementation scheme or changes that do not deviate from the technical spirit of the present invention, such as combination, division or repetition of features, should be included in the scope of protection of the present invention.

Claims

1. A method for acquiring three-chamber data, characterized in that: include: Acquire multiple sets of training data, wherein each set of training data includes three-chamber data and electrical data of a collection area of ​​biological tissue acquired in the same sampling period, the three-chamber data includes the extracellular space volume fraction, the cell volume fraction and the blood vessel volume fraction of each voxel point in the collection area, and the electrical data is related to the electrical impedance of the biological tissue; Using the plurality of sets of the training data to train a computing model, so that the computing model can achieve mapping between the electrical data and the three-chamber data; Acquiring electrical data of a target area of ​​biological tissue, the target area having the same size and shape as the acquisition area; and The electrical data of the target area obtained is input into the trained calculation model to obtain the three-chamber data of the target area.

2. The method for acquiring three-chamber data according to claim 1, characterized in that: The method for obtaining each group of training data includes: Introducing a tracer for magnetic resonance imaging into the collection area of ​​biological tissue, Performing magnetic resonance imaging on the acquisition area during the same sampling period, and acquiring electrical data of the acquisition area through a probe located in the acquisition area, and The three-chamber data are obtained according to magnetic resonance imaging results.

3. The method for acquiring three-chamber data according to claim 1, characterized in that: The loss function of the computational model is expressed by formula (1): L(θ)=λ a L a +λ b L b +λ∥θ∥ 2 formula(1) in, a is the volume fraction of the extracellular space, b is the cell volume fraction, L(θ) is the loss function of the computing model, where θ is the training parameter of the computing model, λ a and λ b are the dynamic weights for a and b respectively, L a and L b are the mean square error losses for a and b respectively, λ is the regularization strength hyperparameter, ∥θ∥ 2 is the regularization term, expressed by formula (2): Among them, θ j is the jth training parameter of the computing model.

4. The method for acquiring three-chamber data according to claim 3, characterized in that: Dynamic weight λ a and λ b They are respectively expressed by formula (3) and formula (4): in, ∈ is a constant, L a and L b They are respectively shown in formula (5) and formula (6): in, N is the number of training data sets, a i is the output value of the extracellular space volume fraction predicted by the computational model, is the true value of the extracellular space volume fraction, obtained from the three-chamber data of the training data, b u is the output value of the cell volume fraction predicted by the computational model, is the true value of the cell volume fraction, obtained from the three-chamber data in the training data.

5. A probe, characterized in that The probe is configured to introduce a tracer into the collection region (S) and acquire electrical data of the collection region (S) when the probe is located in the collection region (S).

6. The probe according to claim 5, characterized in that: The probe comprises: A probe body (11) is provided with a through hole (111) for introducing a tracer into the collection area (S) when the probe body (11) is located in the collection area. A plurality of isolation pipes (12) are embedded in the probe body (11), A plurality of electrodes (13) are arranged on the surface of the probe body (11), wherein the plurality of electrodes (13) are arranged to form a plurality of layer arrays perpendicular to the length direction (L) of the probe body (11), and are configured to obtain electrical signals by means of excitation measurement. a plurality of wires (14), each of the wires (14) passing through one of the isolation pipes (12) and electrically connected to one of the electrodes (13); and A processing module (15), each of the electrodes (13) is connected to the processing module (15) via a wire (14), and the processing module (15) is capable of processing the acquired electrical signal into the electrical data and transmitting the electrical data to the calculation model.

7. The probe according to claim 6, characterized in that A plurality of the electrodes (13) are arranged to form three mutually parallel layer arrays, each of the layer arrays comprising four electrodes (13) uniformly distributed along the circumference of the probe body (11), and the electrodes (13) in the three layer arrays are aligned along the length direction (L).

8. The probe according to claim 6, characterized in that The probe body (11) is made of alumina ceramics, and the surface of the probe body (11) is covered with a polyethylene glycol coating.

9. The probe according to claim 6, characterized in that The isolation channel (12) is made of copper, and each of the electrodes (13) is a circular copper sheet welded to the surface of the probe body (11).

10. A three-chamber data acquisition system, comprising a computing module (20), wherein the computing module (20) stores a trained computing model as described in any one of claims 1 to 4.

Images