A breast detection system based on DOT

Abstract

The embodiment of the present application provides a breast detection system based on DOT, which relates to the technical field of medical equipment. The system includes a probe assembly, a detection unit assembly, a light source, an acquisition interface and a computer; the probe assembly includes multiple probes, the detection unit assembly includes multiple detection units, and the detection units collect optical signals; the light source is respectively connected to the multiple probes; the acquisition interface is respectively connected to the multiple detection units and the light source, and the light source synchronization signal is sent to the acquisition interface; the computer includes a neural network chip and a processing chip, the processing chip is connected to the acquisition interface, and the neural network chip is connected to the processing chip. The system can achieve the technical effect of improving the detection index of breast detection.

Description

Technical Field

[0001] The present application relates to the technical field of medical equipment, and in particular to a DOT-based breast detection system. Background Art

[0002] At present, diffuse optical tomography, also known as diffuse optical tomography (Diffuse Optical Tomography or Optical Diffusion Tomography, DOT / ODT), is a three-dimensional functional imaging method for thick tissues that uses near-infrared light (600-900nm) to irradiate and collect data. Its purpose is to use highly sensitive near-infrared photon detection instruments and image reconstruction technology based on the biological tissue photon transport model to reconstruct the three-dimensional distribution of optical characteristic parameters inside the tissue by collecting the time, space and spectral distribution information of multi-point surface scattered light in the tissue, and to associate it with the physiological state of the tissue (hemoglobin concentration and oxygen saturation, etc.).

[0003] In the prior art, detection devices or equipment based on DOT technology mostly use the absorption spectrum difference given by the appropriate near-infrared light band in breast tissue, calculate the optical amplitude and phase data received by the detector after the light is scattered in the tissue according to the radiation transfer equation, and construct the spatial distribution of breast tissue to obtain the optical information inside the tissue (mainly including the distribution of oxygenated and deoxygenated hemoglobin). Existing detection devices or equipment based on DOT technology have defects. Whether it is forward calculation or reverse solution, since the reconstruction algorithm is pathologically distributed, the stability and universality of various algorithms used in the two major processes have their own optimal situations, which leads to the deviation of the results from the expected results caused by the differences in the individual subjects in the actual calculation process. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a DOT-based breast detection system, which can achieve the technical effect of improving the detection indicators of breast detection.

[0005] The embodiment of the present application provides a DOT-based breast detection system, including a probe assembly, a detection unit assembly, a light source, an acquisition interface, and a computer;

[0006] The probe assembly includes a plurality of probes, the detection unit assembly includes a plurality of detection units, the plurality of probes transmit detection signals to the internal tissue of the object to be detected, and the detection units collect optical signals;

[0007] The light sources are respectively connected to the multiple probes;

[0008] The acquisition interface is connected to the multiple detection units and the light source respectively, and the light source synchronization signal is sent to the acquisition interface;

[0009] The computer includes a neural network chip and a processing chip, the processing chip is connected to the acquisition interface, and the neural network chip is connected to the processing chip.

[0010] Furthermore, the light source is a high-frequency modulated light source.

[0011] Furthermore, the acquisition interface is a parallel channel digital acquisition interface.

[0012] Furthermore, the probe assembly includes two to one hundred probes.

[0013] Furthermore, the detection unit assembly includes two to one hundred detection units.

[0014] Furthermore, the number of the probes in the probe assembly is the same as the number of the detection units in the detection unit assembly.

[0015] Furthermore, the computer also includes a storage module, and the storage module is connected to the processing chip.

[0016] Furthermore, the computer also includes a display device, and the display device is connected to the processing chip.

[0017] Furthermore, the acquisition interface includes a plurality of detection data acquisition terminals, and the plurality of detection data acquisition terminals are respectively connected to the plurality of detection units.

[0018] Furthermore, the system also includes a power module, and the power module is connected to the light source and the computer respectively.

[0019] Other features and advantages disclosed in the present application will be described in the following description, or some features and advantages can be inferred or determined without doubt from the description, or can be learned by implementing the above-mentioned technology disclosed in the present application.

[0020] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A structural block diagram of a DOT-based breast detection system provided in an embodiment of the present application;

[0023] Figure 2 A structural block diagram of a computer provided in an embodiment of the present application;

[0024] Figure 3 A schematic diagram of a process of a DOT-based breast detection method provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of a process for obtaining one-dimensional data results provided in an embodiment of the present application;

[0026] Figure 5 A network architecture diagram of a DOT-based breast detection provided in an embodiment of the present application;

[0027] Figure 6 A structural block diagram of a neural network module provided in an embodiment of the present application;

[0028] Figure 7 A structural block diagram of a DOT-based breast detection device provided in an embodiment of the present application;

[0029] Figure 8 A structural block diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0031] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0032] The embodiment of the present application provides a breast detection system based on DOT, which can be applied to tumor detection of breast tissue; the breast detection system based on DOT uses a neural network to take breast tissue optical data as input data, which is input into the neural network after pre-processing such as correction to obtain a one-dimensional data result, and then splices the one-dimensional data result with breast lesion data, and finally classifies the splicing result according to a fully connected layer with three groups to obtain a classification result, which includes a classification orientation of benign / malignant breast tumors; thus, the breast detection method based on DOT can bypass the complicated algorithm design of forward and reverse solution by applying artificial intelligence, and directly obtain the final detection result from the optical data of breast tissue combined with the breast lesion data, thereby avoiding the defects of direct calculation of DOT technology, and improving the technical effect of the detection index of breast detection while ensuring the detection sensitivity.

[0033] See also Figure 1 to Figure 2 , Figure 1 A structural block diagram of a DOT-based breast detection system provided in an embodiment of the present application, Figure 2 Structural block diagram of a computer provided in an embodiment of the present application. The DOT-based breast detection system includes a probe assembly 41, a detection unit assembly 42, a light source 43, an acquisition interface 44 and a computer 45.

[0034] Exemplarily, the probe assembly 41 includes a plurality of probes, and the detection unit assembly 42 includes a plurality of detection units. The plurality of probes transmit detection signals to the internal tissue of the object to be detected, and the detection units collect optical signals.

[0035] Exemplarily, the light source 43 is connected to a plurality of probes respectively.

[0036] Exemplarily, the collection interface 44 is connected to a plurality of detection units and the light source 43 respectively, and the light source 43 sends synchronization signals to the collection interface.

[0037] Exemplarily, the computer 45 includes a neural network chip 451 and a processing chip 452 , the processing chip 452 is connected to the acquisition interface 44 , and the neural network chip 451 is connected to the processing chip 452 .

[0038] Exemplarily, the light source 43 is a high-frequency modulated laser source.

[0039] Exemplarily, the acquisition interface 44 is a parallel channel digital acquisition interface.

[0040] In some embodiments, the probe assembly 41 includes ten probes, and the detection unit assembly 42 includes ten detection units.

[0041] Exemplarily, the computer 45 further includes a storage module 453 and a display device 454 , and the processing chip 452 is connected to the storage module 453 and the display device 454 , respectively.

[0042] Exemplarily, the probe assembly 41 includes two to one hundred probes.

[0043] Exemplarily, the detection unit assembly 42 includes two to one hundred detection units.

[0044] Exemplarily, the number of probes in the probe assembly 41 is the same as the number of detection units in the detection unit assembly 42 .

[0045] Exemplarily, the computer 45 further includes a storage module 453 , which is connected to the processing chip 452 .

[0046] Exemplarily, the computer 45 further includes a display device 454 , which is connected to the processing chip 452 .

[0047] Exemplarily, the acquisition interface 44 includes a plurality of detection data acquisition terminals, and the plurality of detection data acquisition terminals are respectively connected to the plurality of detection units.

[0048] Exemplarily, the DOT-based breast detection system further includes a power module, which is connected to the light source and the computer respectively.

[0049] See also Figure 3 , Figure 3 A schematic flow chart of a DOT-based breast detection method provided in an embodiment of the present application includes the following steps:

[0050] S100: Acquire breast tissue optical data, breast lesion data, patient clinical information and patient information, wherein the breast tissue optical data includes optical amplitude data and optical phase data.

[0051] In some embodiments, breast tissue optical data is obtained by an opalescence super machine; illustratively, the optical module in the opalescence super machine provides multiple light source ends and multiple detection ends at two different wavelengths, and can obtain matrix data of multi-wavelength emission and multi-wavelength reception, wherein the matrix data includes multiple optical amplitude data and multiple optical phase data.

[0052] For example, the opalescence ultrasound machine is a dual-mode diagnostic technology device that uses the DOT optical principle and ultrasound. It first uses B-ultrasound structural diagnosis to find out the location, size and basic shape of lesions in the breast, and then uses the DOT optical system for intelligent analysis. It can detect the blood oxygen content and hemoglobin content of the tumor, which is convenient for benign and malignant screening and treatment. It can track and follow up the same tumor and monitor changes in the disease.

[0053] Exemplarily, the breast lesion data includes information on breast lesions, including size information (length, width) and location information (depth, offset) of breast tumors, totaling 4 data; optionally, breast tissue optical data, breast lesion data plus the patient's age, a total of 725 breast data can be obtained.

[0054] S200: Inputting the optical amplitude data and the optical phase data into a preset neural network to obtain a one-dimensional data result.

[0055] For example, neural networks are applications of artificial intelligence technology; neural networks are also called convolutional neural networks (CNN), which are a type of feedforward neural networks that include convolutional calculations and have a deep structure, and are one of the representative algorithms of deep learning. Neural networks have representation learning capabilities and can perform shift-invariant classification on input information according to their hierarchical structure, so they are also called "shift-invariant artificial neural networks (SIANN)".

[0056] Neural networks are constructed by imitating the visual perception mechanism of biological organisms and can perform supervised and unsupervised learning. The convolution kernel parameter sharing within the hidden layer and the sparsity of the inter-layer connections enable the neural network to learn grid-like topology features such as pixels and audio with a smaller amount of computation, with stable results and no additional feature engineering requirements for the data.

[0057] By inputting optical amplitude data and optical phase data into a preset neural network, the preset neural network is trained to obtain a one-dimensional data result; thereby, the DOT technology can be avoided, whether it is forward calculation or reverse solution, the stability and universality of various algorithms used in the two major processes have their own optimal situations, which leads to the problem of deviation between the results and expectations caused by the differences in the individual subjects in the actual calculation process; at the same time, the problem of the existing DOT technology directly calculating and solving through optical data is avoided, and the tedious calculation process is avoided. Under the premise of ensuring the detection sensitivity, the technical effect of the detection indicators of breast detection is improved.

[0058] S300: performing a one-dimensional first-order splicing operation on the one-dimensional data result, the breast lesion data, the patient clinical information and the patient information to obtain a splicing result.

[0059] S400: Classifying the splicing result according to the fully connected layer having three groups to obtain the classification result, wherein the classification result includes the classification orientation of benign / malignant breast tumors.

[0060] In some embodiments, the one-dimensional data result and the breast lesion data are concatenated, and then passed through three groups of fully connected layers and Dropout, and finally the probability of benign or malignant is output.

[0061] In some embodiments, the DOT-based breast detection method finally outputs a probability value, which is in the interval [0,1]. If the value is greater than 0.5, it is judged as malignant, otherwise it is benign. This refers to the benign / malignant nature of breast tumors. Due to physiological mechanisms, malignant tumors have richer blood supply.

[0062] In some real-time methods, the AI ​​network can ultimately have two different output forms, one is a two-category judgment of benign and malignant, and the other is a graded judgment of the degree of malignancy (which can be multi-level, such as 4 levels: benign, partially benign, partially malignant, and malignant).

[0063] Optionally, the breast lesion data includes the size and depth of the lesion; the patient's clinical information includes one or more of blood test items, physiological period, pregnancy status and breastfeeding status; and the patient information includes the patient's gender and age.

[0064] In some implementation scenarios, the DOT-based breast detection method uses a neural network to take breast tissue optical data as input data, which is input into the neural network after preprocessing such as correction to obtain a one-dimensional data result, and then the one-dimensional data result is spliced ​​with the breast lesion data, and finally the spliced ​​result is classified according to a fully connected layer with three groups to obtain a classification result, which includes the classification orientation of benign / malignant breast tumors; thus, the DOT-based breast detection method can bypass the complicated algorithm design of forward and reverse solutions by applying artificial intelligence, and obtain the final detection result directly from the breast tissue optical data combined with the breast lesion data, thereby avoiding the defects of direct calculation of the DOT technology, and improving the technical effect of the detection indicators of breast detection while ensuring the detection sensitivity.

[0065] See also Figure 4 , Figure 4 A schematic diagram of a process for obtaining a one-dimensional data result provided in an embodiment of the present application; the step of inputting optical amplitude data and optical phase data into a preset neural network to obtain a one-dimensional data result includes:

[0066] S210: performing dimension conversion on the optical data of the breast tissue, converting the optical amplitude data and the optical phase data into a two-dimensional array including three channels;

[0067] S220: performing a two-dimensional convolution operation according to the two-dimensional array;

[0068] S230: Perform N levels of convolution operations on the two-dimensional array after the two-dimensional convolution operation to obtain a one-dimensional data result, wherein the input object of the convolution operation at each level is the downsampling result of the feature map output by the convolution operation at the previous level, and the convolution operation at each level includes multiple convolution processes.

[0069] Exemplarily, the above process is a method for obtaining one-dimensional data results through a neural network.

[0070] See also Figure 5 , Figure 5 A network architecture diagram of DOT-based breast detection provided in an embodiment of the present application.

[0071] In some embodiments, the optical data is sent to a neural network, and a specific example is as follows: first, a reshape operation is performed to convert the one-dimensional data into three-dimensional data; second, four sets of convolution operations are performed, and a pooling is inserted in the middle to control the data size; finally, a global pooling operation is performed to convert the data into a one-dimensional data result, that is, the final convolution result is obtained.

[0072] In some embodiments, the convolution process includes a convolution layer with a convolution kernel size of 3×3 and an activation layer.

[0073] In some embodiments, the downsampling result is obtained by a 3×2 maximum pooling layer operation.

[0074] In some embodiments, the final one-dimensional data result of the convolution is obtained using a two-dimensional global maximum pooling operation.

[0075] In some embodiments, the final one-dimensional convolution result and the lesion information data are subjected to a one-dimensional first-order splicing operation.

[0076] In some implementations, the concatenated result is classified using three groups of fully connected layers, wherein each group of fully connected layers is processed using a 50% dropout layer in the middle.

[0077] In some implementations, the classification result obtained based on the fully connected layer represents the benign or malignant classification orientation of this embodiment.

[0078] Exemplarily, the step of inputting the optical amplitude data and the optical phase data into a preset neural network to obtain a one-dimensional data result includes:

[0079] Through the two-dimensional global maximum pooling operation, a one-dimensional data result is obtained.

[0080] See also Figure 6 , Figure 6 A structural block diagram of a DOT-based breast detection device provided in an embodiment of the present application, the DOT-based breast detection device includes:

[0081] An acquisition module 100 is used to acquire breast tissue optical data, breast lesion data, patient clinical information and patient information, wherein the breast tissue optical data includes optical amplitude data and optical phase data;

[0082] A neural network module 200, used for inputting the optical amplitude data and the optical phase data into a preset neural network to obtain a one-dimensional data result;

[0083] A splicing module 300 is used to perform a one-dimensional first-order splicing operation on the one-dimensional data result and the breast lesion data, the patient clinical information and the patient information to obtain a splicing result;

[0084] The classification module 400 is used to classify the splicing result according to the three groups of fully connected layers to obtain the classification result, which includes the classification orientation of benign / malignant breast tumors.

[0085] See also Figure 7 , Figure 7 This is a structural block diagram of a neural network module provided in an embodiment of the present application. The neural network module includes:

[0086] The conversion unit 210 is used to perform dimension conversion on the optical data of the breast tissue, and convert the optical amplitude data and the optical phase data into a two-dimensional array including three channels;

[0087] A two-dimensional convolution unit 220, configured to perform a two-dimensional convolution operation according to the two-dimensional array;

[0088] The N-level convolution unit 230 is used to perform N-level convolution operations on the two-dimensional array after the two-dimensional convolution operation to obtain a one-dimensional data result, wherein the input object of the convolution operation at each level is the downsampling result of the feature map output by the convolution operation at the previous level, and the convolution operation at each level includes multiple convolution processes.

[0089] Exemplarily, the downsampling result is obtained by a 3×2 maximum pooling layer operation.

[0090] Exemplarily, the neural network module is also used to obtain a one-dimensional data result through a two-dimensional global maximum pooling operation.

[0091] It should be understood that Figure 6The DOT-based breast detection device and Figure 7 The neural network module shown is similar to Figure 3 and Figure 4 The method embodiments shown correspond to each other and will not be described again here to avoid repetition.

[0092] This application also provides an electronic device, see Figure 8 , Figure 8 A structural block diagram of a device provided in an embodiment of the present application. The electronic device may include a processor 510, a communication interface 520, a memory 530 and at least one communication bus 540. Among them, the communication bus 540 is used to realize the direct connection and communication of these components. Among them, the communication interface 520 of the electronic device in the embodiment of the present application is used to communicate signaling or data with other node devices. The processor 510 can be an integrated circuit chip with signal processing capabilities.

[0093] The processor 510 mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor 510 can also be any conventional processor, etc.

[0094] The memory 530 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 530 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 510, the electronic device can execute the above-mentioned Figure 3 to Figure 4 The method embodiment involves various steps.

[0095] Optionally, the electronic device may further include a storage controller and an input / output unit.

[0096] The memory 530, storage controller, processor 510, peripheral interface, input and output unit components are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses 540. The processor 510 is used to execute executable modules stored in the memory 530, such as software function modules or computer programs included in the electronic device.

[0097] The input and output unit is used to provide users with the task creation and to create a start optional time period or preset execution time for the task to realize the interaction between the user and the server. The input and output unit can be, but is not limited to, a mouse and a keyboard.

[0098] Understandably, Figure 8 The structure shown is for illustration only, and the electronic device may also include Figure 8 More or fewer components as shown, or with Figure 8 Different configurations shown. Figure 8 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0099] An embodiment of the present application further provides a storage medium having instructions stored thereon. When the instructions are run on a computer, the computer program is executed by a processor to implement the method described in the method embodiment. To avoid repetition, the method will not be described here.

[0100] The present application also provides a computer program product, which, when executed on a computer, enables the computer to execute the method described in the method embodiment.

[0101] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0103] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0104] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A breast detection system based on DOT, characterized in that: The system includes a probe assembly, a detection unit assembly, a light source, an acquisition interface and a computer; The probe assembly includes a plurality of probes, the detection unit assembly includes a plurality of detection units, and the detection units collect optical signals; The light sources are respectively connected to the multiple probes; The acquisition interface is connected to the multiple detection units and the light source respectively, and the light source synchronization signal is sent to the acquisition interface; The computer includes a neural network chip and a processing chip, the processing chip is connected to the acquisition interface, and the neural network chip is connected to the processing chip; wherein the DOT-based breast detection system is used for: Acquiring breast tissue optical data, breast lesion data, patient clinical information and patient information, wherein the breast tissue optical data includes optical amplitude data and optical phase data; Inputting the optical amplitude data and the optical phase data into a preset neural network to obtain a one-dimensional data result; Performing a one-dimensional first-order splicing operation on the one-dimensional data result, the breast lesion data, the patient clinical information, and the patient information to obtain a splicing result; The splicing result is classified according to the fully connected layer with three groups to obtain the classification result, which includes the classification orientation of benign / malignant breast tumors.

2. The DOT-based breast detection system according to claim 1, characterized in that: The light source is a high-frequency modulated light source.

3. The DOT-based breast detection system according to claim 1, characterized in that: The acquisition interface is a parallel channel digital acquisition interface.

4. The DOT-based breast detection system according to claim 1, characterized in that: The probe assembly includes two to one hundred probes.

5. The DOT-based breast detection system according to claim 1, characterized in that: The detection unit assembly includes two to one hundred detection units.

6. The DOT-based breast detection system according to claim 4 or 5, characterized in that: The number of the probes in the probe assembly is the same as the number of the detection units in the detection unit assembly.

7. The DOT-based breast detection system according to claim 1, characterized in that: The computer further includes a storage module connected to the processing chip.

8. The DOT-based breast detection system according to claim 1 or 7, characterized in that: The computer further includes a display device connected to the processing chip.

9. The DOT-based breast detection system according to claim 1, characterized in that: The acquisition interface includes a plurality of detection data acquisition terminals, and the plurality of detection data acquisition terminals are respectively connected to the plurality of detection units.

10. The DOT-based breast detection system according to claim 1, characterized in that: The system further comprises a power supply module, and the power supply module is connected to the light source and the computer respectively.

Images