Reconstruction Method, Device, Medium and Near-Infrared Brain Functional Imaging System for Diffuse Optical Tomography

Abstract

The present application discloses a reconstruction method, device, medium and near-infrared brain function imaging system for diffuse light tomography, wherein the reconstruction method for diffuse light tomography includes using a processor: based on the measurement data of each measurement position of a high-density measurement array arranged on the surface of the object to be measured, forming a one-dimensional measurement data sequence with a predetermined measurement position order; based on the one-dimensional measurement data sequence with the predetermined measurement position order, performing a coarse reconstruction to obtain 3D input data so that it is aligned with the spatial resolution of the ground truth reconstructed image; using the 3D input data as input and as a constraint condition, using a conditional variational autoencoder to reconstruct the spatial distribution of optical parameters in the object to be measured.

Description

Technical Field

[0001] The present application belongs to the field of medical artificial intelligence, and in particular relates to a reconstruction method, device, medium and near-infrared brain function imaging system for diffuse light tomography. Background Art

[0002] Early diagnosis and treatment assessment of brain diseases are particularly important. Functional brain imaging techniques, including functional magnetic resonance imaging (fMRI), electrophysiological imaging (EEG), magnetoencephalography (MEG), and functional near-infrared spectroscopy (fNIRS), can quantitatively image the spatiotemporal state of brain activity, providing important reference for the early diagnosis and treatment of brain diseases. fNIRS, as an emerging functional brain imaging technology, offers advantages such as low cost, high portability, non-invasiveness, and the absence of ionizing radiation. It is suitable for large-scale clinical screening and daily monitoring and assessment of patients with brain diseases.

[0003] However, the development of near-infrared functional brain imaging technology is still constrained by several factors. On the one hand, the layered structure of the brain makes the detection of the cerebral cortex susceptible to physiological interference from superficial tissues. On the other hand, the strong scattering properties of internal brain tissues make photons prone to random migration during transmission within the tissues, resulting in severe ill-posedness in functional brain imaging. Even small noise levels can cause large fluctuations in the imaging results, affecting their credibility. To address these issues, diffuse optical tomography (DOT) eliminates physiological interference from superficial tissues by designing alternating detection channels and provides depth-resolved information. This can alleviate the ill-posedness of the inverse problem to a certain extent, but its imaging accuracy still needs to be improved. Summary of the Invention

[0004] In response to the above-mentioned technical problems existing in the prior art, the present application provides a reconstruction method, device, medium and near-infrared brain functional imaging system for diffuse optical tomography, which can establish a mapping relationship from the sensor domain to the reconstructed image domain through a conditional autoencoder, and realize a gradually refined reconstruction method by forming a one-dimensional measurement data sequence with a predetermined measurement bit order based on the measurement data, roughly reconstructing to obtain 3D input data, and adding constraints in the model inference stage, thereby improving the accuracy of the reconstructed spatial distribution of optical parameters in the body to be measured.

[0005] According to a first embodiment of the present application, a reconstruction method for diffuse optical tomography is provided, the reconstruction method comprising: using a processor: forming a one-dimensional measurement data sequence in a predetermined measurement position order based on measurement data of each measurement position of a high-density measurement array arranged on the surface of the object to be measured; performing a coarse reconstruction based on the one-dimensional measurement data sequence in the predetermined measurement position order to obtain 3D input data so that it is aligned with the spatial resolution of the ground truth reconstructed image; and using the 3D input data as input and as a constraint condition, using a conditional variational autoencoder to reconstruct the spatial distribution of optical parameters in the object to be measured.

[0006] According to a second embodiment of the present application, a reconstruction device for diffuse optical tomography is provided. The reconstruction device includes at least a processor and a memory. The memory stores computer-executable instructions. When the processor executes the computer-executable instructions, it performs the above-mentioned reconstruction method for diffuse optical tomography.

[0007] According to the third embodiment of the present application, a near-infrared brain function imaging system is provided, comprising a near-infrared optical data acquisition device and a reconstruction device for diffuse light tomography; wherein the near-infrared optical data acquisition device is used to acquire near-infrared data of an object; and the reconstruction device is used to execute the above-mentioned reconstruction method for diffuse light tomography using the near-infrared data.

[0008] According to a fourth aspect of the present application, there is provided a non-transitory computer-readable storage medium storing a program, wherein the program causes a processor to execute the operations of the above-mentioned reconstruction method for diffuse optical tomography.

[0009] Compared with the prior art, the embodiments of the present application have the following advantages:

[0010] The reconstruction method for diffuse light tomography provided in each embodiment of the present application integrates the measurement data of each measurement position of a high-density measurement array arranged on the surface of the object to be measured to form a one-dimensional measurement data sequence with a predetermined measurement position order, so that the conditional variational autoencoder used in the subsequent model inference stage can extract the spatial distribution semantics that characterize the relative positional relationship between the measurement position and the object to be measured. Therefore, in the model inference stage, richer features can be extracted by combining the arrangement of each transmitting position and receiving position in the high-density measurement array. The extracted spatial distribution semantics are also strongly correlated with the reconstruction process, which can alleviate the ill-posedness problem of the solution caused by the lack of feature semantics in the inverse problem of diffuse light tomography reconstruction, thereby improving the accuracy of the reconstructed spatial distribution of optical parameters in the object to be measured. Furthermore, compared with directly reconstructing the one-dimensional measurement data sequence, by first roughly reconstructing the one-dimensional measurement data sequence into 3D input data that matches the spatial resolution of the ground truth reconstructed image, the feature semantics input to the conditional variational autoencoder can be further enriched, the ill-posedness problem of the solution during reconstruction by the conditional variational autoencoder can be alleviated, and the accuracy of the reconstructed spatial distribution of optical parameters in the body to be measured can be improved; in the model inference stage, the mapping relationship from the sensor domain to the reconstructed image domain is established by using the conditional autoencoder, and the accuracy of the reconstruction results obtained by the conditional autoencoder is improved by adding constraints. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0012] Figure 1 A flowchart showing a reconstruction method for diffuse optical tomography provided by an embodiment of the present application is shown;

[0013] Figure 2 A schematic diagram illustrating a reconstruction method for diffuse optical tomography provided by an embodiment of the present application, wherein a diagram illustrating measurement of a surface of an object to be measured using a high-density measurement array is shown;

[0014] Figure 3 A schematic diagram illustrating a high-density measurement array in a reconstruction method for diffuse optical tomography provided in an embodiment of the present application;

[0015] Figure 4 A schematic diagram illustrating a training process in a reconstruction method for diffuse optical tomography provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the technical solution of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and specific embodiments, but are not intended to limit the present application.

[0017] The words "first", "second" and similar terms used in this application do not indicate any order, quantity or importance, but are only used to distinguish. The words "include" or "comprises" and similar terms used in this application mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of covering other elements. In this application, the arrows shown in the figures of each step are only examples of the execution order, not limitations. The technical solution of this application is not limited to the execution order described in the embodiments. The steps in the execution order can be combined, decomposed, or swapped, as long as the logical relationship of the execution content is not affected.

[0018] All terms used in this application (including technical or scientific terms) have the same meaning as understood by a person of ordinary skill in the art to which this application belongs, unless otherwise specifically defined. It should also be understood that terms defined in common dictionaries, for example, should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein. Techniques and devices known to a person of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques and devices should be considered part of the specification.

[0019] In this application, the arrows shown in the figures of each step are only examples of the execution order, not limitations. The technical solution of this application is not limited to the execution order described in the embodiments. The various steps in the execution order can be combined for execution, can be decomposed for execution, and can be swapped in order, as long as it does not affect the logical relationship of the execution content.

[0020] See also Figure 1 FIG. 1 is a flowchart of a reconstruction method for diffuse optical tomography provided by an embodiment of the present disclosure. The reconstruction method includes executing S101 to S103 by a processor, wherein:

[0021] S101: Based on the measurement data of each measurement position of the high-density measurement array arranged on the surface of the object to be measured, a one-dimensional measurement data sequence with a predetermined measurement position order is formed.

[0022] S102: Based on the one-dimensional measurement data sequence in a predetermined measurement position order, perform a coarse reconstruction to obtain 3D input data so as to align the spatial resolution of the 3D input data with the spatial resolution of the ground truth reconstructed image.

[0023] S103: Using the 3D input data as input and as constraints, a conditional variational autoencoder is used to reconstruct the spatial distribution of optical parameters in the body under test.

[0024] The following is a detailed description of the above steps.

[0025] With respect to S101, the object to be measured may be a living organism, a specific organ of a living organism, or a non-living object, such as a head or abdomen of a subject. The high-density measurement array may be a high-density arrangement measurement array, which may be understood as a measurement array that satisfies predetermined high-density arrangement conditions. The high-density arrangement conditions may include, for example, that the interval between measurement positions in the measurement array is less than a predetermined interval, and that the number of measurement positions is greater than a predetermined number.

[0026] In some embodiments, the measurement data of the measurement position can be collected by a measurement device deployed at the measurement position. The measurement device has a probe capable of emitting or receiving near-infrared light. By deploying the probe of the measurement device at each measurement position of a high-density measurement array, the measurement data can be collected.

[0027] It should be noted that the "one-dimensional" in the one-dimensional measurement data sequence represents a single data dimension, which can be understood as the properties of the near-infrared light collected at the corresponding measurement position, such as the intensity variation data of the near-infrared light. In other words, the "one-dimensional" in the one-dimensional measurement data sequence does not represent a spatial dimension. For example, a one-dimensional measurement data sequence can be represented as the intensity variation data corresponding to each measurement position arranged in sequence.

[0028] For example, a schematic diagram of measuring the surface of an object to be measured using a high-density measurement array can be shown as follows: Figure 2 As shown, Figure 2 In the embodiment, the object to be measured is the head of the subject, and a high-density measurement array is deployed on the head of the subject, so as to achieve high-density acquisition of measurement data. After the measurement data are acquired, a one-dimensional measurement data sequence with a predetermined measurement bit order can be formed based on the acquired measurement data, so as to reconstruct the spatial distribution of optical parameters in the object to be measured through subsequent model inference steps.

[0029] In some embodiments, the high-density measurement array may include transmission bits and receiving bits arranged in sequence; the one-dimensional measurement data sequence of the predetermined measurement bit order includes measurement data corresponding to multiple transmission bits spliced in sequence, each transmission bit has at least one target receiving bit and forms a measurement channel with it, and the measurement data corresponding to each transmission bit includes the measurement data collected by each target receiving bit it has.

[0030] Among them, the transmitting position can be used to deploy the transmitting probe of the measuring equipment, and the receiving position can be used to deploy the receiving probe of the measuring equipment. The transmitting probe can transmit near-infrared light to the object to be measured, and the receiving probe can receive the near-infrared light emitted from the object to be measured.

[0031] For example, the schematic diagram of the high-density measurement array can be as follows: Figure 3 As shown, Figure 3 In the figure, the 13 red dots represent the 13 transmitting positions in the high-density measurement array, and the 12 green dots represent the 12 receiving positions in the high-density measurement array. Taking transmitting position A in the first row and first column and receiving position B in the first row and second column as examples, the measurement data corresponding to transmitting position A includes the data collected by its receiving position B for transmitting position A. In other words, the near-infrared light emitted by the transmitting probe of the measuring device at transmitting position A is emitted from the object to be measured and collected by the receiving probe deployed at receiving position B. The collected measurement data can be used as the measurement data of measurement channel AB corresponding to transmitting position A (or receiving position B).

[0032] In some other embodiments, the one-dimensional measurement data sequence of the predetermined measurement bit order includes measurement data corresponding to multiple receiving bits spliced in sequence, that is, the one-dimensional measurement data sequence can be obtained by splicing the measurement data corresponding to multiple receiving bits in sequence.

[0033] In some embodiments, the target receiving bit of each transmitting bit includes several receiving bits whose distance from it meets a preset distance condition; the measurement data corresponding to each transmitting bit is obtained by sequentially splicing the measurement data collected by each target receiving bit for it according to the predetermined serial number of each target receiving bit in the high-density measurement array.

[0034] For any transmitted bit, the received bits in the high-density measurement array can be divided into several categories according to the distance from the transmitted bit, and the target received bit can be some of the received bits, such as the closest category 2 or category 3 received bits.

[0035] For example, taking the target receiving bit as the three types of receiving bits closest to the transmitting bit as an example, Figure 3 For the transmitted bit U in the example, the received bits can be divided into 6 categories according to the distance between each received bit and the transmitted bit U. From near to far, they are received bits P and V, received bits L and R, received bits F and X, received bits H and N, received bits B and T, and received bits D and J. Therefore, the 3 categories of received bits with the closest distance can be selected as the target received bits, that is, the received bits P and V, received bits L and R, and received bits F and X can be selected as the target received bits corresponding to the transmitted bit U.

[0036] In some embodiments, the measurement data in the one-dimensional measurement data sequence with a predetermined measurement bit order are arranged following the predetermined measurement bit order.

[0037] For example, the transmitting probes deployed at the transmitting positions can be sequentially activated, and the receiving probes deployed at the corresponding target receiving positions can collect measurement data at the corresponding times. The measurement data collected by the receiving probes deployed at each target receiving position are sequentially concatenated according to the predetermined sequence number of each target receiving position in the high-density measurement array to generate a one-dimensional measurement data sequence.

[0038] Still Figure 3 As an example of the high-density measurement array in the example, the predetermined serial numbers corresponding to the measurement bits can be Figure 3 As shown in A to Y, when splicing the measurement data in sequence, the measurement data of each target receiving position can be spliced in the order of the serial number. The measurement data sequence corresponding to the transmission position U is FLPRVX (i.e., the measurement data corresponding to each target receiving position). The one-dimensional measurement data sequence can be obtained by splicing the measurement data sequences of each transmission position. For example, according to the measurement position order of ACEGIKMOQSUWY, the measurement data corresponding to each transmission position are spliced in sequence.

[0039] In some other embodiments, in a one-dimensional measurement data sequence with a predetermined measurement position order, the measurement data may also be arranged in association with its position indication information, where the position indication information indicates the measurement position order.

[0040] Among them, the position indication information can be, for example, the coordinates, serial number, etc. of the corresponding measurement position. By directly adding the position indication information to the one-dimensional measurement data sequence, the relative position relationship between each measurement position and the object to be measured can be explicitly expressed, so that the corresponding feature semantics can be extracted more directly in the subsequent model reasoning stage.

[0041] In this way, the measurement data with spatial distribution semantics are spliced together in the above manner to obtain a one-dimensional measurement data sequence with a predetermined measurement position order, or position indication information is directly added to the one-dimensional measurement data sequence, so that the conditional variational autoencoder used in the subsequent model inference stage can extract the spatial distribution semantics that characterize the relevant positional relationship between the measurement position and the object to be measured, so that in the model inference stage, richer features can be extracted in combination with the arrangement of each transmitting position and receiving position in the high-density measurement array, and the extracted spatial distribution semantics are also strongly related to the reconstruction process, which can alleviate the ill-posedness problem of the solution caused by the lack of feature semantics in the inverse problem of diffuse optical tomography reconstruction, and improve the accuracy of the reconstructed spatial distribution of optical parameters in the object to be measured.

[0042] In some embodiments, when verifying the splicing effect of a one-dimensional measurement data sequence, the following test groups may be set:

[0043] Group 1: According to the randomly generated measurement position order, the measurement data of each measurement position are spliced to generate a one-dimensional measurement data sequence.

[0044] Group 2: According to the predetermined measurement position sequence described in the above embodiment, the measurement data of each measurement position are spliced to generate a one-dimensional measurement data sequence.

[0045] Group 3: According to the predetermined measurement position sequence described in the above embodiment, the measurement data of the target receiving positions that meet the preset distance conditions are selected and spliced to generate a one-dimensional measurement data sequence.

[0046] When selecting indicators for evaluating image reconstruction effects, indicators such as SSIM (Structural Similarity Index), PSNR (Peak Signal-to-Noise Ratio), CNR (Contrast-to-Noise Ratio), R value (Pearson Correlation Coefficient, also known as Pearson correlation coefficient), Jaccard index, and MAE (Mean Absolute Error) can be selected. The definitions, calculation methods, and meanings of the above indicators are known to those skilled in the art and are not detailed here.

[0047] In some embodiments, a phantom with multiple targets scattered in a medium at a depth of 3 cm or even 5 cm was used as the reconstruction object, with optical parameter data at various locations in the phantom's space serving as ground truth. Using the same high-density measurement array, the reconstruction results of the images obtained by inputting each set of one-dimensional measurement data sequences into the same model were verified. This demonstrated that, compared to the randomly generated measurement position sequence containing spatially distributed semantics in Group 1, a predetermined measurement position sequence in Group 3 provided better reconstruction results. Furthermore, it was demonstrated that, compared to Group 2, where measurement data from target receiving positions meeting a preset distance condition were stitched together, Group 3 provided better reconstruction results by increasing feature semantic density and reducing noise input.

[0048] With respect to S102, the rough reconstruction can be understood as the process of converting a one-dimensional measurement data sequence into 3D input data with the same spatial resolution as the ground truth reconstructed image, which can be achieved through a pre-trained U-Net, GAN or other model with upsampling function, or can also be achieved through an interpolation algorithm, deconvolution algorithm or other algorithm with upsampling function. The ground truth reconstructed image represents the real spatial distribution of optical parameters in the body to be measured, which is also the desired reconstruction target of diffuse optical tomography. The spatial resolution of the ground truth reconstructed image can be, for example, 2mm, 3mm, 5mm, etc. The size of the 3D input data obtained after rough reconstruction also matches the size of the ground truth reconstructed image, thereby facilitating the subsequent use of the conditional variational autoencoder for corresponding reconstruction processing.

[0049] In some embodiments, when performing coarse reconstruction on a one-dimensional measurement data sequence based on a predetermined measurement bit order, a pre-trained model with an upsampling module may be used to perform coarse reconstruction on the one-dimensional measurement data sequence to obtain 3D input data.

[0050] In this way, compared with directly reconstructing the one-dimensional measurement data sequence, by first roughly reconstructing the one-dimensional measurement data sequence into 3D input data that matches the spatial resolution of the ground truth reconstructed image, the feature semantics input to the conditional variational autoencoder can be enriched, the ill-posedness problem of the solution during reconstruction of the conditional variational autoencoder can be alleviated, and the accuracy of the reconstructed spatial distribution of optical parameters in the body to be measured can be improved.

[0051] Regarding S103, the spatial distribution of optical parameters in the object to be measured can be understood as optical parameters at various locations in the object to be measured space, such as near-infrared light related parameters at various locations in the object to be measured space. The model architecture of the conditional variational autoencoder includes an encoder and a decoder.

[0052] The architecture of the encoder and decoder may be a multi-layer perceptron (MLP) including a fully connected layer, a convolutional neural network (CNN) including a convolutional layer, a Transformer with serialized data processing capabilities, or the like.

[0053] In some embodiments, when the 3D input data is used as input and as a constraint, a conditional variational autoencoder is used to reconstruct the spatial distribution of optical parameters in the body under test, the following steps A1 to A3 may be performed:

[0054] A1: Based on the 3D input data, an encoder is used to extract measurement domain feature information, and sample feature information in the latent space that satisfies a first preset distribution is extracted.

[0055] Here, the first preset distribution may be a Gaussian distribution.

[0056] In some embodiments, when extracting sampling feature information in the latent space that satisfies the first preset distribution, the sampling feature information in the latent space that satisfies the multi-dimensional Gaussian distribution can be extracted based on the 3D input data using a trained priori network.

[0057] like Figure 2 As shown, the one-dimensional measurement data sequence can obtain 3D input data after rough reconstruction. The 3D input data is input into the trained priori network, and the sampling feature information in the latent space that satisfies the multi-dimensional Gaussian distribution can be extracted through the priori network.

[0058] Among them, the prior network can be a deep learning model including multiple continuously stacked convolution modules, which can extract feature representations of multiple dimensions layer by layer through continuously stacked convolution modules, so that sampling feature information in the latent space that satisfies the multi-dimensional Gaussian distribution can be extracted through the prior network.

[0059] In some embodiments, the number of dimensions in the multidimensional Gaussian distribution can be 2 to 6. When the multidimensional Gaussian distribution includes at least 4 dimensions, the attributes corresponding to each dimension in the multidimensional Gaussian distribution include the position of the activation area, the shape of the activation area, the number of activation areas, and the activation degree of the activation area.

[0060] In this way, the activation area is described by four dimensions: the position of the activation area, the shape of the activation area, the number of activation areas, and the activation degree of the activation area, so that the feature semantics of the sampled feature information in the latent space can fully express the properties of the activation area; on the other hand, the Gaussian distribution dimension of 2-6 also avoids the poor reconstruction effect caused by too few dimensions and the more complicated model training and use caused by too many dimensions, taking into account both reconstruction effect and reconstruction efficiency.

[0061] In some embodiments, the encoder may include multiple continuously stacked convolution modules, and an attention mechanism may be introduced in the convolution module. By introducing the attention mechanism, an attention weight matrix that has a strong correlation with tissue depth can be obtained, so that the measurement domain feature information extracted by the encoder contains feature semantics that are strongly correlated with tissue depth. This can be used as a constraint condition during decoding processing to improve the accuracy of the final reconstruction result.

[0062] A2: Fusing the measurement domain feature information and the sampling feature information to obtain fused feature information.

[0063] In some embodiments, when the measurement domain characteristic information and the sampling characteristic information are fused, the measurement domain characteristic information and the sampling characteristic information may be cascaded to obtain fused characteristic information.

[0064] Wherein, when cascading, the measurement domain characteristic information and the sampling characteristic information may be cascaded according to the channel dimension.

[0065] In some embodiments, when fusing the measurement domain characteristic information and the sampling characteristic information, the fusion of the measurement domain characteristic information and the sampling characteristic information may also be achieved through weighted summation or the like. The embodiments of the present disclosure do not limit the specific fusion method.

[0066] A3: The fused feature information is decoded into the spatial distribution of optical parameters in the body to be measured through a decoder.

[0067] Here, the fused characteristic information obtained by fusing the measurement domain characteristic information and the sampling characteristic information can be input into the decoder to obtain the spatial distribution of optical parameters in the body to be measured output by the decoder.

[0068] When the decoder decodes the fused feature information, the measurement domain feature information in the fused feature information may be used as a constraint condition to constrain the decoder's decoding of the sampling feature information in the fused feature information.

[0069] In this way, by introducing the measurement domain feature information extracted by the encoder from the 3D input data, the sampling feature information in the latent space that satisfies the multidimensional Gaussian distribution is constrained, which can not only give full play to the feature semantic expression ability of the multidimensional Gaussian distribution, but also take into account the accuracy of reconstructing the spatial distribution of optical parameters in the body to be measured.

[0070] In some embodiments, the conditional variational autoencoder is trained through the following first training process, which may include the following steps B1-B2:

[0071] B1: Using the posterior network, we extract embedded features from the ground truth reconstructed image.

[0072] Here, the posterior network may have the same network architecture as the a priori network, or may include a more complex network architecture than the a priori network, that is, the network performance of the posterior network may be the same as the network performance of the a priori network, or may be stronger than the network performance of the a priori network.

[0073] B2: Utilizing the embedded features to adjust parameters of the encoder and the decoder, and coordinating with the 3D input data to adjust parameters of the prior network.

[0074] For example, the training process can be shown as Figure 4 As shown, Figure 4In the posterior network, the embedded features from the ground truth reconstructed image can be extracted and used to participate in the subsequent parameter adjustment. The specific parameter adjustment method will be introduced below and will not be elaborated here.

[0075] In some embodiments, the prior network is trained via the following second training process, which may include the following steps C1 to C3:

[0076] C1: Roughly reconstruct the sample one-dimensional measurement data sequence to obtain the sample 3D input data.

[0077] C2: The sample 3D input data and the ground truth reconstructed image are concatenated along the channel dimension and fed into the posterior network to extract the baseline sampling feature information containing the embedded features of the ground truth reconstructed image.

[0078] Here, by concatenating the sample 3D input data and the ground truth reconstructed image along the channel dimension, an input content containing both the feature semantics of the measurement data and the feature semantics of the reconstruction result can be obtained. After feeding the corresponding input content into the posterior network, the baseline sampling feature information containing both the feature semantics of the measurement data and the feature semantics of the reconstruction result can be extracted.

[0079] In this way, since the benchmark sampling feature information contains the embedded features of the ground truth reconstructed image, that is, it contains the feature semantics of the reconstruction result corresponding to the reconstruction target, it can be used as a reference target in the training process.

[0080] C3: Parameter adjustment of the prior network is performed using the sample sampling feature information corresponding to the sample one-dimensional measurement data sequence and the reference sampling feature information corresponding to the ground truth reconstructed image.

[0081] In some embodiments, when adjusting the parameters of the prior network, the KL loss function can be used to determine the distribution deviation between the sample sampling feature information and the reference sampling feature information, and the parameters of the prior network can be adjusted according to the distribution deviation.

[0082] Here, since the baseline sampling feature information contains the feature semantics of the reconstruction result corresponding to the reconstruction target, the parameters of the prior network are adjusted according to the distribution deviation between the sample sampling feature information and the baseline sampling feature information, so that the sampling feature information output by the prior network can be closer to the reconstruction target, thereby improving the accuracy of the spatial distribution of the optical parameters subsequently reconstructed by the decoder.

[0083] Furthermore, when the parameters of the a priori network are adjusted, the parameters of the a posteriori network may also be adjusted synchronously, that is, the parameters of the a priori network and the a posteriori network may be adjusted simultaneously.

[0084] The posterior network may be a pre-trained deep learning model, and when adjusting the parameters of the prior network, the network parameters of the posterior network may also be fine-tuned.

[0085] In some embodiments, both the prior network and the posterior network are untrained deep learning models. During the second training process, parameters of the prior network and the posterior network can be adjusted simultaneously.

[0086] In some embodiments, the training process of the encoder and the decoder may include the following steps D1 to D5:

[0087] D1: Roughly reconstruct the sample one-dimensional measurement data sequence to obtain the sample 3D input data.

[0088] Here, the sample one-dimensional measurement data sequence can be obtained by collecting the sample to be tested through a high-density measurement array. The spatial distribution of optical parameters in the sample to be tested is pre-set, so the pre-set spatial distribution of optical parameters in the sample to be tested can be used as the ground truth to reconstruct the image (reconstruction target).

[0089] D2: Based on the sample 3D input data, an encoder is used to extract sample measurement domain feature information, and sample sampling feature information in a latent space that satisfies a first preset distribution is extracted.

[0090] Here, the first preset distribution may be a multi-dimensional Gaussian distribution. For other related descriptions of the first preset distribution, reference may be made to the above related content and will not be repeated here.

[0091] D3: Fusing the sample measurement domain feature information and the sample sampling feature information to obtain sample fusion feature information.

[0092] Here, when the sample measurement domain feature information and the sample sampling feature information are fused, the sample measurement domain feature information and the sample sampling feature information may be cascaded according to a channel dimension to obtain sample fusion feature information.

[0093] D4: The sample fusion feature information is decoded into the spatial distribution of the sample optical parameters in the body to be tested through a decoder.

[0094] Here, the sample fusion characteristic information obtained by fusing the sample measurement domain characteristic information and the sample sampling characteristic information can be input into the decoder to obtain the spatial distribution of the sample optical parameters in the body to be measured output by the decoder.

[0095] When the decoder decodes the sample fusion feature information, the sample measurement domain feature information in the sample fusion feature information may be used as a constraint condition to constrain the decoder's decoding of the sample sampling feature information in the sample fusion feature information.

[0096] D5: Using the MSE loss function to determine the deviation between the spatial distribution of the sample optical parameters and the ground truth reconstructed image, and adjusting the parameters of the encoder and the decoder according to the deviation.

[0097] Here, the ground truth reconstructed image is the reconstruction target, and the spatial distribution of the sample optical parameters is the reconstruction result output by the decoder. The deviation between the current reconstruction result and the reconstruction target is determined by the MSE loss function. The parameters of the encoder and the decoder can be adjusted according to the deviation to reduce the deviation between the reconstruction result and the reconstruction target, thereby continuously improving the reconstruction effect.

[0098] The reconstruction method for diffuse light tomography provided in each embodiment of the present application integrates the measurement data of each measurement position of a high-density measurement array arranged on the surface of the object to be measured to form a one-dimensional measurement data sequence with a predetermined measurement position order, so that the conditional variational autoencoder used in the subsequent model inference stage can extract the spatial distribution semantics that characterize the relative positional relationship between the measurement position and the object to be measured. Therefore, in the model inference stage, richer features can be extracted by combining the arrangement of each transmitting position and receiving position in the high-density measurement array. The extracted spatial distribution semantics are also strongly correlated with the reconstruction process, which can alleviate the ill-posedness problem of the solution caused by the lack of feature semantics in the inverse problem of diffuse light tomography reconstruction, thereby improving the accuracy of the reconstructed spatial distribution of optical parameters in the object to be measured. Furthermore, compared with directly reconstructing the one-dimensional measurement data sequence, by first roughly reconstructing the one-dimensional measurement data sequence into 3D input data that matches the spatial resolution of the ground truth reconstructed image, the feature semantics input to the conditional variational autoencoder can be further enriched, the ill-posedness problem of the solution during reconstruction by the conditional variational autoencoder can be alleviated, and the accuracy of the reconstructed spatial distribution of optical parameters in the body to be measured can be improved; in the model inference stage, the mapping relationship from the sensor domain to the reconstructed image domain is established by using the conditional autoencoder, and the accuracy of the reconstruction results obtained by the conditional autoencoder is improved by adding constraints.

[0099] In some embodiments of the present application, a reconstruction device for diffuse optical tomography is provided, wherein the reconstruction device includes at least a processor and a memory, wherein the memory stores computer-executable instructions, and when the processor executes the computer-executable instructions, it performs the reconstruction method for diffuse optical tomography described in any embodiment of the present application.

[0100] The processor may be a processing device including one or more general-purpose processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, the processor may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor that runs other instruction sets, or a processor that runs a combination of instruction sets. The processor may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a system on a chip (SoC), etc.

[0101] In some embodiments of the present application, a near-infrared brain function imaging system is provided, comprising a near-infrared optical data acquisition device and a reconstruction device for diffuse light tomography; wherein the near-infrared optical data acquisition device is used to acquire near-infrared data of an object; and the reconstruction device is used to use the near-infrared data to execute the reconstruction method for diffuse light tomography described in any embodiment of the present application.

[0102] This application describes various operations or functions that can be implemented as software code or instructions or defined as software code or instructions. Such content can be source code or differential code ("incremental" or "patch" code) that can be directly executed ("object" or "executable" form). Software code or instructions can be stored in a computer-readable storage medium and, when executed, can cause a machine to perform the described functions or operations, and include any mechanism for storing information in a form accessible to a machine (e.g., a computing device, an electronic system, etc.), such as recordable or non-recordable media (e.g., read-only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, etc.).

[0103] The exemplary methods described herein can be at least partially machine- or computer-implemented. In some embodiments, a computer-readable storage medium stores computer program instructions that, when executed by a processor, cause the processor to perform the reconstruction method for diffuse optical tomography described in various embodiments of the present invention.

[0104] Implementations of such methods may include software code, such as microcode, assembly language code, high-level language code, and the like. Various software programming techniques may be used to create various programs or program modules. For example, program portions or program modules may be designed using or with the aid of Java, Python, C, C++, assembly language, or any other known programming language. One or more of such software portions or modules may be integrated into a computer system and / or computer-readable media. Such software code may include computer-readable instructions for performing the various methods. The software code may form part of a computer program product or computer program module. Furthermore, in an example, the software code may be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer-readable media, such as during execution or at other times. Examples of such tangible computer-readable media may include, but are not limited to, hard disks, removable disks, removable optical disks (e.g., optical disks and digital video disks), magnetic cassettes, memory cards or sticks, random access memory (RAM), read-only memory (ROM), and the like.

[0105] Furthermore, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present application with equivalent elements, modifications, omissions, combinations (e.g., solutions that intersect various embodiments), adaptations, or changes. The elements of the claims are to be interpreted broadly based on the language employed in the claims and are not limited to the examples described in this specification or during the prosecution of the application, which examples are to be construed as non-exclusive. Therefore, it is intended that this specification and examples be considered merely as examples, with the true scope and spirit being indicated by the following claims and their full scope of equivalents.

[0106] The above description is intended to be illustrative and not restrictive. For example, the above examples (or one or more of their embodiments) may be used in combination with each other. For example, a person of ordinary skill in the art may use other embodiments when reading the above description. In addition, in the above detailed description, various features may be grouped together to simplify the application. This should not be interpreted as an intention that a disclosed feature that is not claimed for protection is essential to any claim. On the contrary, the subject matter of the present application may have less than all the features of a particular disclosed embodiment. Thus, the claims are incorporated herein into the detailed description as examples or embodiments, with each claim independently serving as a separate embodiment, and it is contemplated that these embodiments may be combined with each other in various combinations or arrangements. The scope of the present application should be determined with reference to the appended claims and the full scope of equivalents to which such claims are entitled.

[0107] The above embodiments are merely exemplary embodiments of the present application and are not intended to limit the scope of the present application. The scope of protection of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and scope of protection of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the scope of protection of the present application.

Claims

1. A reconstruction method for diffuse light tomography, characterized in that: The reconstruction method includes, using a processor: Based on the measurement data of each measurement position of the high-density measurement array arranged on the surface of the object to be measured, a one-dimensional measurement data sequence of a predetermined measurement position order is formed; Based on a one-dimensional measurement data sequence with a predetermined measurement position order, a coarse reconstruction is performed to obtain 3D input data so that the spatial resolution is aligned with the ground truth reconstructed image; The 3D input data is used as input and as a constraint condition, and a conditional variational autoencoder is used to reconstruct the spatial distribution of optical parameters in the body to be measured.

2. The reconstruction method according to claim 1, characterized in that The high-density measurement array includes transmission bits and reception bits that are sequentially spaced apart; The one-dimensional measurement data sequence of the predetermined measurement bit order includes measurement data corresponding to multiple transmission bits spliced in sequence, each transmission bit has at least one target receiving bit and forms a measurement channel with it, and the measurement data corresponding to each transmission bit includes the measurement data collected for each target receiving bit it has.

3. The reconstruction method according to claim 2, characterized in that: The target receiving bit of each transmitting bit includes a plurality of receiving bits whose distances therefrom meet a preset distance condition; The measurement data corresponding to each transmitting bit is obtained by sequentially splicing the measurement data collected by each target receiving bit according to the predetermined sequence number of each target receiving bit in the high-density measurement array.

4. The reconstruction method according to claim 1, characterized in that: The 3D input data is used as input and as a constraint condition, and a conditional variational autoencoder is used to reconstruct the spatial distribution of optical parameters in the body to be measured, specifically including: Based on the 3D input data, using an encoder to extract measurement domain feature information, and extracting sampling feature information in a latent space that satisfies a first preset distribution; fusing the measurement domain feature information and the sampling feature information to obtain fused feature information; The fused feature information is decoded into the spatial distribution of optical parameters in the body to be measured by a decoder.

5. The reconstruction method according to claim 4, characterized in that: Extracting sampling feature information in a latent space that satisfies a first preset distribution based on the 3D input data specifically includes: Based on the 3D input data, a trained priori network is used to extract sampling feature information in a latent space that satisfies a multi-dimensional Gaussian distribution.

6. The reconstruction method according to claim 5, characterized in that: The number of dimensions in the multidimensional Gaussian distribution is 2-6; When the multidimensional Gaussian distribution includes at least four dimensions, the attributes corresponding to each dimension in the multidimensional Gaussian distribution include: The location of the activation area, the shape of the activation area, the number of activation areas, and the degree of activation of the activation area.

7. The reconstruction method according to claim 5, characterized in that: The conditional variational autoencoder is trained through the following first training process, which includes: Using the posterior network, we extract embedded features from the ground truth reconstructed image; Parameters of the encoder and the decoder are adjusted using the embedded features, and parameters of the prior network are adjusted in coordination with the 3D input data.

8. The reconstruction method according to claim 7, characterized in that: The prior network is trained through the following second training process, which specifically includes: Roughly reconstruct the sample one-dimensional measurement data sequence to obtain the sample 3D input data; Concatenating the sample 3D input data and the ground truth reconstructed image along the channel dimension and feeding them into the posterior network to extract reference sampled feature information containing embedded features of the ground truth reconstructed image; The parameters of the prior network are adjusted using the sample sampling feature information corresponding to the sample one-dimensional measurement data sequence and the reference sampling feature information corresponding to the ground truth reconstructed image.

9. The reconstruction method according to claim 8, characterized in that: Parameter adjustment is performed on the prior network, specifically including: The KL loss function is used to determine the distribution deviation between the sample sampling feature information and the reference sampling feature information, and the parameters of the prior network are adjusted according to the distribution deviation.

10. The reconstruction method according to claim 7, characterized in that: The training process of the encoder and the decoder includes: Roughly reconstruct the sample one-dimensional measurement data sequence to obtain the sample 3D input data; Based on the sample 3D input data, extracting sample measurement domain feature information using an encoder, and extracting sample sampling feature information in a latent space that satisfies a first preset distribution; Fusing the sample measurement domain feature information and the sample sampling feature information to obtain sample fusion feature information; The sample fusion feature information is decoded into the spatial distribution of the sample optical parameters in the body to be tested by a decoder; The MSE loss function is used to determine the deviation between the spatial distribution of the sample optical parameters and the ground truth reconstructed image, and the parameters of the encoder and the decoder are adjusted according to the deviation.

11. The reconstruction method according to claim 1, characterized in that: In a one-dimensional measurement data sequence with a predetermined measurement position order: the measurement data are arranged in accordance with the predetermined measurement position order; or, the measurement data are arranged in association with their position indication information, where the position indication information indicates the measurement position order.

12. A reconstruction device for diffuse optical tomography, characterized in that: The reconstruction device comprises at least a processor and a memory, wherein the memory stores computer-executable instructions, and the processor executes the reconstruction method for diffuse optical tomography according to any one of claims 1 to 11 when executing the computer-executable instructions.

13. A near-infrared brain function imaging system, characterized in that: It includes a near-infrared optical data acquisition device and a reconstruction device for diffuse light tomography; wherein, The near-infrared optical data acquisition device is used to collect near-infrared data of the object; The reconstruction device is configured to execute the reconstruction method for diffuse optical tomography according to any one of claims 1 to 11 using the near-infrared data.

14. A non-transitory computer-readable storage medium storing a program, characterized in that: The program causes the processor to perform the operations of the reconstruction method for diffuse optical tomography according to any one of claims 1 to 11.

Images