Intracranial hemorrhage detection device

Abstract

The embodiment of the present application relates to the technical field of measurement for diagnostic purposes, and particularly relates to an intracranial hemorrhage detection device, which comprises a seat body, a containing part forming a containing space for containing a patient's cranium, a headgear arranged in the containing space and capable of being filled with liquid dielectric and deformed under pressure, a signal emission and collection assembly for emitting microwave signals to the headgear and receiving microwave signals from the headgear, so as to determine an intracranial hemorrhage condition according to the emitted microwave signals and the received microwave signals, and a mounting assembly arranged to integrally mount the containing part and the signal emission and collection assembly on the seat body. The embodiment of the present application integrally mounts the containing part and the signal emission and collection assembly on the seat body through the mounting assembly, so that the two main components, the containing part and the signal emission and collection assembly, are compactly arranged together, space is saved, and thus the volume of the intracranial hemorrhage detection device can be reduced.

Description

Technical Field

[0001] Embodiments of this application relate to the field of measurement technology for diagnostic purposes, and particularly to an intracranial hemorrhage detection device. Background Technology

[0002] This section provides background information relevant to this application only and does not necessarily constitute prior art.

[0003] Intracranial hemorrhage is a common acute and critical illness in clinical practice. During the diagnosis process, it is necessary to clarify the condition and provide treatment as soon as possible to avoid delaying the "golden treatment time." Therefore, it is necessary to design a reliable intracranial hemorrhage detection device to accurately assess the patient's condition.

[0004] Currently, intracranial hemorrhage detection devices typically collect microwave signals from the patient's head to determine the extent of intracranial hemorrhage. However, existing intracranial hemorrhage detection devices still have many shortcomings. Summary of the Invention

[0005] A brief overview of this application is provided below to offer a basic understanding of certain aspects thereof. It should be understood that this overview is not an exhaustive summary of the application. It is not intended to identify key or essential parts of the application, nor is it intended to limit its scope. Its purpose is merely to present certain concepts in a simplified form as a prelude to the more detailed description that follows.

[0006] Embodiments of this application provide an intracranial hemorrhage detection device, which may include: a base, a receiving part, a headgear, a signal transmission and acquisition component, and a mounting component. The receiving part forms a receiving space for accommodating a patient's cranium; the headgear is disposed in the receiving space, configured to be filled with a liquid dielectric, and deformable under pressure; the signal transmission and acquisition component is used to transmit microwave signals to and receive microwave signals from the headgear, thereby determining the intracranial hemorrhage status based on the transmitted and received microwave signals; the mounting component is configured to integrate and mount the receiving part and the signal transmission and acquisition component onto the base.

[0007] The intracranial hemorrhage detection device of this application integrates the housing and the signal transmission and acquisition component into the base body through the mounting assembly, thereby compactly arranging the two main components together, saving space, and thus reducing the size of the intracranial hemorrhage detection device.

[0008] These and other advantages of this application will become more apparent from the following detailed description of preferred embodiments in conjunction with the accompanying drawings. Attached Figure Description

[0009] To further illustrate the above and other advantages and features of this application, the specific embodiments of this application will be described in more detail below with reference to the accompanying drawings. The drawings, together with the following detailed description, are included in and form a part of this specification. Elements having the same function and structure are indicated by the same reference numerals. It should be understood that these drawings only depict typical examples of this application and should not be considered as limiting the scope of this application.

[0010] Figure 1 This is a schematic diagram of the intracranial hemorrhage detection device according to an embodiment of this application, wherein the shell and medium container are omitted. Figure 2 This shows from another perspective Figure 1 The intracranial hemorrhage detection device shown; Figure 3 This is a schematic diagram of the structure of the receiving portion according to an embodiment of this application; Figure 4 This shows from another perspective Figure 3 The accommodating part shown; Figure 5 This is an exploded view of an intracranial hemorrhage detection device according to an embodiment of this application; Figure 6 This is a schematic diagram of a port extension according to an embodiment of this application; Figure 7 This is a schematic diagram of the intracranial hemorrhage detection device according to an embodiment of this application, where the processor and other structures are omitted. Figure 8 This is a schematic diagram of the spatial feature vector corresponding to an image determined according to the method of the embodiments of this application; Figure 9 This is a schematic diagram showing the spatial distribution of the cosine similarity between the semantic vector and the spatial feature vector of the image, determined by the method according to the embodiments of this application, in the image. Figure 10 This is a schematic diagram of the bleeding area of ​​an image determined by the method according to the embodiments of this application; Figure 11 It is a brain image obtained from microwave signals before noise is filtered out; Figure 12 The image is a brain image obtained by filtering out noise from a microwave signal based on the method provided in the embodiments of this application. Figure 13 This is a schematic diagram of microwave signals corresponding to target brain tissue at different depths, determined by the method according to embodiments of this application; Figure 14 This is a schematic diagram showing the distribution of samples of different cranial tissues in the frequency domain feature space, as determined according to embodiments of this application. Figure 15This is a comparative schematic diagram showing the spatial focusing response of a microwave signal after beamforming processing according to the method of the embodiments of this application, and the direct superposition response of a microwave signal without beamforming processing. Figure 16 This is a schematic diagram of the original time-domain signal of interference clutter without stripping the matching medium between the antenna array and the brain; Figure 17 This is a schematic diagram of the target time-domain characteristic signal after removing interference clutter from the matching medium between the antenna array and the brain according to the method of the embodiment of this application; Figure 18 This is a schematic diagram of cranial imaging results obtained without removing interference clutter from the matching medium in the time domain; Figure 19 This is a schematic diagram of the brain imaging results obtained after removing interference clutter from the matching medium in the time domain. Figure 20 This is a schematic diagram of cranial imaging results obtained without utilizing a standardized grid space; Figure 21 This is a schematic diagram of cranial imaging results obtained according to a standardized grid space in an embodiment of this application; Figure 22 This is a schematic diagram showing the result of independently encoding the feature information of the cranium according to an embodiment of this application; Figure 23 This is a schematic diagram showing the result of single encoding of the characteristic information of the cranium; Figure 24 This is a schematic diagram showing the result of training the encoding process according to the method provided in the embodiments of this application; Figure 25 This is a schematic diagram of clutter region features and bleeding region features obtained from the encoding process after adversarial training according to an embodiment of this application.

[0011] It should be noted that the accompanying drawings are not necessarily drawn to scale, but are shown only in a schematic manner without affecting the reader's understanding.

[0012] Explanation of reference numerals in the attached figures: 100. Intracranial hemorrhage detection device; 10. Receiving part; 11. Mounting receiving part; 111. Peripheral part; 1110. Plane; 1111. Opening; 1112. Peripheral mounting hole; 112. End; 113. Head cover mounting part; 1130. Groove; 1131. Guide groove; 1132. Inner liner positioning part; 114. Antenna mounting part; 1140. Mounting groove; 1141. Extension part; 1142. Connector; 1143. Clearance hole; 12. Shell connecting part; 120. Shell clearance groove; 13. Neck support part; 14. Mounting mating part; 141. Mounting main body part; 142. Reinforcing part; 1421. First reinforcing part; 1422. Second reinforcing part; 143. First connecting mating part; 144. Second connecting mating part; 15. Liquid inlet / outlet positioning part; 151. Opening; 152. Limiting channel; 20. Headgear; 21. Headgear body; 22. First headgear mounting part; 221. Guide part; 222. Headgear mounting hole; 23. Second headgear mounting part; 24. Liquid inlet / outlet components; 25. Exhaust component; 31. Vector network analyzer; 310. Side of analyzer; 311. First heat dissipation hole; 32. Port expansion component; 320. Port expansion body; 3201. Main surface; 3202. Side; 321. First connector; 322. Second connector; 33. Antenna; 331. Wire connector; 34. Signal transmission line group; 341. First signal transmission line group; 3411. First signal transmission line; 34111. First extension section; 34112. Bend section; 34113. Second extension section; 342. Second signal transmission line group; 3421. Second signal transmission line; 34211. Third extension section; 34212. Ring section; 34213. Fourth extension section; 41. First mounting component; 411. First mounting piece; 412. Auxiliary mounting piece; 4121. Main body; 4122. Connecting part; 42. Second mounting piece; 43. Third mounting piece; 44. Fourth mounting piece; 45. Reinforcing member; 50. Dielectric charging and discharging pressurization assembly; 51. Dielectric container; 52. Inlet and outlet pipelines; 53. Exhaust pipeline; 54. Drive unit; 55. Pressure measuring unit; 56. Valve; 57. Pressure measuring pipeline; 60. Lining; 61. Lining positioning and mating part; 62. Lining clearance groove; 71. Base; 711. Bottom cover; 712. Drain port; 713. Drain hole; 714. Second heat dissipation hole; 72. Housing; 720. Housing heat dissipation hole; 721. Main housing; 7210. Main housing heat dissipation hole; 722. Front housing; 723. Rear cover; 73. Processor; 74. Fan; 75. Pillow; 76. Handle; 77. Operating component; 78. Communication interface; 79. USB splitter; 200. Bleeding area; 301. Interference noise of the matching medium; 302. Microwave signal of cranial tissue in the original time domain signal; 303. Time domain truncation window; 304. Target time domain characteristic signal. Detailed Implementation

[0013] Exemplary embodiments of this application will be described below with reference to the accompanying drawings. For clarity and brevity, not all features of actual implementations are described in the specification. However, it should be understood that many implementation-specific decisions must be made in the development of any such actual embodiment to achieve the developer's specific goals, such as complying with constraints related to the system and business, and these constraints may vary depending on the implementation. Furthermore, it should be understood that while development work can be very complex and time-consuming, such development work is merely a routine task for those skilled in the art who benefit from the content of this application.

[0014] It should also be noted that, in order to avoid obscuring this application with unnecessary details, only the equipment structure and / or processing steps closely related to the solution according to this application are shown in the accompanying drawings, while other details that are not closely related to this application are omitted.

[0015] It should be noted that, unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning as understood by a person with ordinary skills in the field to which this application pertains.

[0016] In the description of the embodiments of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0017] In related technologies, intracranial hemorrhage detection devices have many components, which often results in a large size of the device and reduces its portability.

[0018] To address the aforementioned technical problems, embodiments of this application provide an intracranial hemorrhage detection device. See also... Figure 1 and Figure 2 , Figure 1 This is a schematic diagram of the intracranial hemorrhage detection device according to an embodiment of this application, wherein the shell and medium container are omitted. Figure 2 This shows from another perspective Figure 1The intracranial hemorrhage detection device shown is described. The intracranial hemorrhage detection device 100 of this application includes: a base 71, a receiving portion 10, a headgear 20, a signal transmission and acquisition component, and a mounting component. The receiving portion 10 forms a receiving space for accommodating a patient's cranium; the headgear 20 is disposed in the receiving space, configured to be filled with a liquid dielectric, and deformable under pressure; the signal transmission and acquisition component is used to transmit microwave signals to and receive microwave signals from the headgear 20, thereby determining the intracranial hemorrhage status based on the transmitted and received microwave signals; the mounting component is configured to integrate the receiving portion 10 and the signal transmission and acquisition component into the base 71.

[0019] The intracranial hemorrhage detection device 100 of this application integrates the receiving part 10 and the signal transmission and acquisition component into the base 71 by means of an installation component, so that the two main components, the receiving part 10 and the signal transmission and acquisition component, are compactly arranged together, saving space and thus reducing the size of the intracranial hemorrhage detection device 100.

[0020] Furthermore, in the embodiments of this application, by setting up a headgear 20, filling the headgear 20 with a dielectric material, and applying pressure to the headgear 20 to allow it to expand and fit the patient's skull, it can adapt to the shape of different patients' skulls. Relying on the flexible deformation and fluid adaptive properties of the headgear 20, it closely fits the contour of the patient's skull, achieving a gapless fit and wrapping, which is beneficial to improving the transmission efficiency of microwave signals, thereby improving the quality of transmitted or received microwave signals.

[0021] In some embodiments, the signal transmission and acquisition assembly may include: a vector network analyzer 31, a port extender 32, and a plurality of antennas 33; the vector network analyzer 31 is configured to transmit microwave signals to the port extender 32, and to receive microwave signals from the port extender 32, and to analyze the received microwave signals; the port extender 32 is configured to extend the port of the vector network analyzer 31, receive microwave signals transmitted by the vector network analyzer 31, and transmit the microwave signals to one antenna 33; and receive corresponding microwave signals from another antenna 33, and transmit the microwave signals to the vector network analyzer 31; the antenna 33 is disposed on the outside of the headgear 20 in the receiving portion 10, and is configured to receive microwave signals from the port extender 32 and transmit the microwave signals to the headgear 20; or, receive microwave signals transmitted by another antenna 33 from the headgear 20 and transmit the microwave signals to the port extender 32.

[0022] In such an embodiment, by providing the port extension 32, the vector network analyzer 31 can be connected to multiple pairs of antennas 33 to transmit and receive microwave signals, thereby increasing the number of antennas 33 and improving the accuracy of detection.

[0023] In some embodiments, the signal transmission and acquisition device further includes: a signal transmission line group 34 for connecting each antenna 33 to the port extension member 32, and connecting the port extension member 32 to the vector network analysis member 31.

[0024] In some embodiments, the mounting components include: a first mounting component 41 configured to integrate the receiving portion 10, the port extension 32, and the vector network analyzer 31 onto the base 71; a second mounting component 42 and a third mounting component 43 configured to fix the receiving portion 10 relative to the base 71 at a predetermined distance in the height direction.

[0025] In this embodiment, the first mounting component 41 integrates the receiving portion 10, the port extension component 32, and the vector network analysis component 31 into the base 71, which helps to save installation space and reduce the overall size of the intracranial hemorrhage detection device 100. Furthermore, fixing the receiving portion 10 relative to the base 71 at a predetermined distance in the height direction allows for space to be reserved for the installation of the antenna 33.

[0026] In some embodiments, the predetermined spacing can be determined by those skilled in the art based on the actual situation.

[0027] In some embodiments, the first mounting assembly 41 includes: a first mounting member 411 disposed on the base 71, a port extension member 32 and a vector network analyzer 31 mounted opposite each other on both sides of the first mounting member 411, a receiving portion 10 connected to the first mounting member 411 on the side where the port extension member 32 is located, and the port extension member 32 disposed between the receiving portion 10 and the vector network analyzer 31; and an auxiliary mounting member 412 disposed on the base 71 and connected to the first mounting member 411, and configured to clamp the vector network analyzer 31 between the auxiliary mounting member 412 and the first mounting member 411.

[0028] In this embodiment, since the receiving part 10 is connected to the first mounting member 411 on the side where the port extension member 32 is located, the vector network analyzer 31 and the port extension member 32 are mounted opposite each other on the two side surfaces of the first mounting member 411. The port extension member 32 is disposed between the receiving part 10 and the vector network analyzer 31, so that the receiving part 10, the port extension member 32, and the vector network analyzer 31 can be arranged sequentially at intervals, thereby facilitating the arrangement of the signal transmission line group 34 between the receiving part 10 and the port extension member 32, and between the port extension member 32 and the vector network analyzer 31. Since a head cover 20 is also provided inside the receiving part 10, placing the vector network analyzer 31 and the port extension member 32 on one side of the receiving part 10, rather than at the bottom, helps to reduce the height of the receiving part 10 and prevents the patient's head from being too high after entering the head cover 20, thus affecting comfort. Furthermore, the auxiliary mounting component 412 is provided to clamp the vector network analyzer 31 between the auxiliary mounting component 412 and the first mounting component 411. This limiting method is more reliable and stable, and can prevent the vector network analyzer 31 from moving.

[0029] In some embodiments, the first mounting member 411 is a metal plate extending in a direction perpendicular to the base 71.

[0030] In some embodiments, the first mounting member 411 and the auxiliary mounting member 412 are configured to provide a height-direction gap between the port extension member 32 and the vector network analyzer 31 and the base 71. In such an embodiment, because there is a height-direction gap between the vector network analyzer 31 and the port extension member 32 and the base 71, damage to the vector network analyzer 31 and the port extension member 32 from prolonged immersion in the liquid dielectric can be avoided in the event of a liquid dielectric leak.

[0031] In some embodiments, the auxiliary mounting member 412 includes: a main body portion 4121 configured to conform to the surface of the vector network analyzer 31 away from the first mounting member 411 and having a flange bent toward the first mounting member 411 to clamp and limit the vector network analyzer 31; and a connecting portion 4122 configured to connect to the flange of the main body portion 4121 and to the first mounting member 411 to connect the main body portion 4121 and the first mounting member 411, thereby clamping the vector network analyzer 31 between the main body portion 4121 and the first mounting member 411.

[0032] In this embodiment, the vector network analyzer 31 can be mounted on the first mounting member 411 without the need for mounting holes or mounting members on the vector network analyzer 31 itself. Furthermore, by providing the main body 4121 to adhere to the surface of the vector network analyzer 31 that is away from the first mounting member 411, and by providing a flange that folds towards the first mounting member 411, multiple surfaces of the vector network analyzer 31 can be limited, thereby restricting the movement of the vector network analyzer 31 in various directions.

[0033] In some embodiments, the second mounting member 42 and the third mounting member 43 are disposed on the base 71; the side of the receiving portion 10 facing the port extension member 32 is connected to the second mounting member 42, and the side of the receiving portion 10 away from the port extension member 32 is connected to the third mounting member 43. In such an embodiment, both sides of the receiving portion 10 are connected to mounting members respectively, which can improve the stability of the receiving portion 10 and also allow the height of the receiving portion 10 to be set more reasonably.

[0034] See Figure 3 and Figure 4 , Figure 3 This is a schematic diagram of the structure of the receiving portion according to an embodiment of this application. Figure 4 This shows from another perspective Figure 3 The accommodating portion is shown. In some embodiments, the accommodating portion 10 includes: a mounting accommodating portion 11, a neck support portion 13, and a mounting mating portion 14; the mounting accommodating portion 11 forms an accommodating space having an opening for the patient's head to enter and exit, the mounting accommodating portion 11 is also configured to mount a headgear 20 in the accommodating space, and is configured to mount an antenna 33; the neck support portion 13 is connected to the opening of the mounting accommodating portion 11 for supporting the patient's neck; the mounting mating portion 14 is disposed on the side of the mounting accommodating portion 11 opposite to the opening, and is configured to cooperate with a first mounting member 411 and a second mounting member 42 to connect the mounting accommodating portion 11 to the first mounting member 411 and the second mounting member 42.

[0035] In this embodiment, by providing the mounting fitting part 14 to cooperate with the mounting components of the intracranial hemorrhage detection device 100, the mounting receiving part 11 is fixedly mounted on the base 71 of the intracranial hemorrhage detection device 100. Thus, the receiving part 10, as well as the headgear 20 and antenna 33 mounted on the receiving part 10, can be fixedly mounted relative to the base 71 of the intracranial hemorrhage detection device 100, thereby improving the overall structural stability of the intracranial hemorrhage detection device 100 without the need for more complex mounting and fixing structures.

[0036] In some embodiments, the neck support 13 is disposed above and connected to the third mounting member 43, thereby providing stable support for the patient's neck by the third mounting member 43.

[0037] In some embodiments, the mounting mating portion 14 includes: a mounting body portion 141 disposed on the mounting receiving portion 11; a reinforcing portion 142 disposed on the mounting body portion 141 for increasing the strength of the mounting body portion 141; a first connecting mating portion 143 disposed on the mounting body portion 141 and extending toward the first mounting member 411; and a second connecting mating portion 144 disposed on the mounting body portion 141 and extending in a direction perpendicular to the extending direction of the first connecting mating portion 143; the first connecting mating portion 143 is configured to engage with a fastener passing through the first mounting member 411 to connect the mounting body portion 141 to the first mounting member 411; and the second connecting mating portion 144 is configured to engage with a fastener passing through the second mounting member 42 to connect the mounting body portion 141 to the second mounting member 42.

[0038] In this embodiment, the mounting body 141 provides a base for the connection of the first connecting mating part 143 and the second connecting mating part 144, making the connection between the mounting receiving part 11 and the mounting assembly more stable. Furthermore, the reinforcement part 142 increases the strength of the mounting body 141, which also helps to improve the stability of the connection between the mounting receiving part 11 and the mounting assembly. The first connecting mating part 143 extends towards the first mounting member 411 and has a certain length, thus providing space for the port extension 32 disposed between the mounting receiving part 11 and the first mounting member 411. Moreover, since the antenna 33 and the headgear 20 are mounted in the receiving part 10, the stability requirements for the receiving part 10 are higher. Through the above connection method, the stability of the receiving part 10 can be improved.

[0039] In some embodiments, there are multiple mounting body portions 141, which are arranged to be connected in sequence to form a square. A first connecting mating portion 143 is disposed on a set of opposite mounting body portions 141, and a second connecting mating portion 144 is disposed on another set of opposite mounting body portions 141.

[0040] In this embodiment, the mounting body portions 141 are sequentially connected to form a square, which enhances the strength of the mounting body portions 141. The first connecting mating portion 143 connects the mounting body portion 141 to the first mounting member 411 from two opposite sides of the mounting body portion 141, thereby increasing the connection strength between the mounting body portion 141 and the first mounting member 411; the second connecting mating portion 144 connects the mounting body portion 141 to the second mounting member 42 from the other two opposite sides of the mounting body portion 141, thereby increasing the connection strength between the mounting body portion 141 and the second mounting member 42.

[0041] In some embodiments, there are multiple second mounting members 42, which are disposed opposite to each other on both sides of the mounting body portion 141 to improve the stability of the receiving portion 10.

[0042] In some embodiments, there are two second mounting members 42, which are disposed opposite to each other on both sides of the mounting body portion 141.

[0043] In some embodiments, the mounting body 141 is configured as four interconnected connecting plates, and the first connecting mating part 143 and the second connecting mating part 144 are configured as a plurality of connecting posts.

[0044] In some embodiments, the reinforcing portion 142 includes: a first reinforcing portion 1421, through which a set of opposing mounting body portions 141 are connected; and a second reinforcing portion 1422, through which another set of opposing mounting body portions 141 are connected; and the first reinforcing portion 1421 and the second reinforcing portion 1422 are configured to be perpendicular to each other and connected.

[0045] In such an embodiment, reinforcement portions 142 are provided in both directions, connecting the two opposing sets of mounting main body portions 141 to each other. The first reinforcement portion 1421 and the second reinforcement portion 1422 are also connected to each other, which can distribute the force on the mounting main body portion 141 and provide support for the mounting main body portion 141, thereby greatly improving the strength of the mounting main body portion 141.

[0046] In some embodiments, the first reinforcing part 1421 is configured to be connected to the first connecting mating part 143, and the second reinforcing part 1422 is configured to be connected to the second connecting mating part 144.

[0047] In such an embodiment, the first reinforcing part 1421 is connected to the first connecting mating part 143, and the second reinforcing part 1422 is connected to the second connecting mating part 144. This can improve the connection strength at the connection positions of the first reinforcing part 1421 and the first connecting mating part 143, and the second reinforcing part 1422 and the second connecting mating part 144, thereby further improving the strength of the mounting body part 141.

[0048] In some embodiments, the receiving portion 10 further includes: a liquid inlet / outlet positioning portion 15, which is disposed in the mounting receiving portion 11 and connected to the mounting mating portion 14, and a liquid inlet / outlet portion 24 disposed on the side of the mounting receiving portion 11 opposite to the opening for the patient's brain to enter and exit, and configured to position the headgear 20.

[0049] In such an embodiment, the liquid inlet / outlet positioning part 15 positions the liquid inlet / outlet part 24 of the head cover 20, thereby preventing the liquid inlet / outlet part 24 of the head cover 20 from shifting.

[0050] In some embodiments, the inlet / outlet positioning portion 15 is configured to communicate with the receiving space and extend in a predetermined direction away from the mounting receiving portion 11. Furthermore, one end of the inlet / outlet positioning portion 15 away from the mounting receiving portion 11 is configured to form an opening 151. The inlet / outlet component 24 of the head sleeve 20 is configured to extend through the inlet / outlet positioning portion 15 and from the opening 151 to the outside of the inlet / outlet positioning portion 15. The inlet / outlet positioning portion 15 is connected to the mounting body portion 141.

[0051] In this embodiment, the inlet / outlet positioning part 15 can form a channel connecting the receiving space of the receiving part 10 with the external space, for positioning and guiding the inlet / outlet liquid component 24 of the head cover 20. Furthermore, the inlet / outlet positioning part 15 is connected to the mounting body part 141, which can further improve the strength of the mounting body part 141.

[0052] In some embodiments, the predetermined direction is set toward the drain port 712 of the intracranial hemorrhage detection device 100, and the drain port 712 is disposed on the base 71 of the intracranial hemorrhage detection device 100.

[0053] In such an embodiment, the inlet / outlet component 24 of the headgear 20 can be guided above the drain port 712 provided on the seat 71, so that when the inlet / outlet component 24 leaks, the leaked liquid can be discharged through the drain port 712.

[0054] In some embodiments, the inlet / outlet positioning part 15 is disposed at the bottom of the mounting and receiving part 11, thereby facilitating the guidance of the inlet / outlet 24 to a position close to the drain port 712.

[0055] In some embodiments, the liquid inlet / outlet positioning part 15 is configured to form a limiting channel 152, which is configured to communicate with the opening 151 and the receiving space of the liquid inlet / outlet positioning part 15 and extends in the direction of the mounting mating part 14.

[0056] In such an embodiment, the liquid inlet / outlet positioning part 15 also has a limiting channel 152 that communicates with the opening 151 and the accommodating space. When the head cover 20 is installed into the accommodating space, the liquid inlet / outlet part 24 of the head cover 20 can move within the limiting channel 152 to facilitate the installation of the head cover 20.

[0057] In some embodiments, the first reinforcing part 1421 is provided as a plurality of parts, and the liquid inlet / outlet positioning part 15 is provided to connect the plurality of first reinforcing parts 1421.

[0058] In this embodiment, the liquid inlet / outlet positioning part 15 is connected to the mounting body part 141 and also connects to a plurality of first reinforcing parts 1421. That is, the liquid inlet / outlet positioning part 15 connects the plurality of first reinforcing parts 1421 provided on the mounting body part 141, thereby further improving the strength of the mounting body part 141.

[0059] See Figure 5 , Figure 5 This is an exploded view of an intracranial hemorrhage detection device according to an embodiment of this application. In some embodiments, the intracranial hemorrhage detection device 100 further includes a housing 72, which cooperates with the receiving portion 10 and the base 71 to cover the receiving portion 10 and the signal transmission and acquisition assembly, thereby improving aesthetics and providing protection for the signal transmission and acquisition assembly.

[0060] In some embodiments, the receiving portion 10 further includes a shell connecting portion 12, which is disposed in the mounting receiving portion 11 and configured to connect to the opening of the mounting receiving portion 11 for the patient's head to enter and exit, for connecting with the shell 72 to press the headgear 20 between the shell 72 and the shell connecting portion 12 to prevent the headgear 20 from rotating or falling off. Furthermore, in such embodiments, the shell connecting portion 12, the neck support portion 13, the mounting mating portion 14, and the inlet / outlet positioning portion 15 can be reasonably distributed on both sides of the mounting receiving portion 11.

[0061] In some embodiments, the mounting accommodating portion 11 includes a peripheral portion 111, an end portion 112, a plurality of antenna mounting portions 114, and a head cover mounting portion 113. The peripheral portion 111 is connected to the end portion 112 to form an accommodating space. The head cover mounting portion 113 is used to mount the head cover 20 in the accommodating space. Each antenna mounting portion 114 is used to mount an antenna 33 facing the head cover 20 on the peripheral portion 111.

[0062] In this embodiment, by providing the antenna mounting part 114 and the headgear mounting part 113, the headgear 20 can be mounted on the receiving part 10 and the antenna 33 can be mounted facing the headgear 20, thereby enabling the antenna 33 to transmit microwave signals to the headgear 20 and receive microwave signals from the headgear 20. This is beneficial for adapting the headgear 20 to the shape of different patients' skulls and improving the transmission efficiency of microwave signals.

[0063] In some embodiments, the antenna mounting portion 114 forms a plurality of mounting slots 1140, which communicate with the receiving space; the antenna 33 is mounted in each mounting slot 1140. In such an embodiment, since the mounting slots 1140 communicate with the receiving space, the antenna 33 can directly face the headgear 20, so that after the headgear 20 is pressurized and expanded, it can simultaneously fit against the patient's skull and the antenna 33, thereby improving the transmission efficiency of microwave signals.

[0064] In some embodiments, the mounting slots 1140 are arranged at equal intervals along the circumferential direction of the periphery 111, so that the multiple antennas 33 can also be arranged at equal intervals along the circumferential direction of the periphery 111. This allows for more comprehensive transmission and reception of microwave signals from different directions of the patient's brain, which is more conducive to accurately obtaining images of the brain.

[0065] In some embodiments, the number of mounting slots 1140 and antennas 33 can be 16.

[0066] In some embodiments, the surface of the periphery 111 facing the headgear 20 includes a plurality of planes 1110 connected circumferentially, each plane 1110 forming an opening 1111 communicating with the mounting groove 1140, and the radiating port surface of the antenna 33 being flush with the plane 1110 containing the opening 1111. In such an embodiment, by making the plane 1110 flush with the radiating port surface of the corresponding antenna 33, it is beneficial to reduce microwave signal loss and improve the microwave signal reception quality.

[0067] In some embodiments, the antenna mounting portion 114 includes an extension portion 1141 extending outward from the periphery of the opening 1111 and a connector 1142 connected to the extension portion 1141. The connector 1142 is configured to connect the antenna 33 to the antenna mounting portion 114. The extension portion 1141 forms a clearance hole 1143 for the wire connector 331 of the antenna 33 to pass through. Since the extension portion 1141 extends outward from the periphery of the opening 1111, the antenna 33 can be mounted in the mounting groove 1140 on the inner side of the periphery 111 without obstructing the radiating port surface of the antenna 33, thereby affecting the transmission and reception of microwave signals. At the same time, by forming a clearance hole 1143 in the extension portion 1141, the wire connector 331 of the antenna 33 can extend to the outside through the clearance hole 1143, thereby realizing the transmission of microwave signals.

[0068] See also Figure 5 In some embodiments, the headgear 20 includes: a headgear body 21 configured to be filled with a liquid dielectric and deformable under pressure to allow the patient's brain to enter the headgear body 21 and conform to the patient's brain after deformation; the liquid dielectric is configured to match the impedance of the antenna 33 of the intracranial hemorrhage detection device 100 with that of human brain tissue; a first headgear mounting fitting part 22 connected to the headgear body 21 and configured to cooperate with the headgear mounting part 113 to mount the headgear body 21 into the receiving space; a second headgear... The second headgear mounting fitting part 23 is connected to the headgear body 21. The shell 72 is detachably connected to the shell connecting part 12 to press the second headgear mounting fitting part 23 between the shell 72 and the shell connecting part 12. The liquid inlet and outlet part 24 is in fluid communication with the headgear body 21 and is used to allow liquid dielectric to enter and exit the headgear body 21. The venting part 25 is provided on the headgear body 21 and is used to vent the air when the headgear body 21 is filled with liquid using the liquid inlet and outlet part 24, and to allow the liquid to flow out from the venting part 25 when the headgear body 21 is filled with liquid.

[0069] In this embodiment, by providing a headgear body 21 and a first headgear mounting fitting part 22 connected to the headgear body 21, the headgear body 21 can be filled with a liquid dielectric that facilitates impedance matching and deformed by inward pressure, allowing the patient's brain to enter the headgear body 21 and fit against the patient's brain after deformation, thereby improving the transmission efficiency of microwave signals; and by setting the first headgear mounting fitting part 22 to cooperate with the receiving part 10 to install the headgear body 21 in the receiving part 10, the movement of the headgear body 21 is prevented from affecting the transmission efficiency of microwave signals.

[0070] In some embodiments, the headgear 20 is made of a flexible material so that it can deform under pressure to match the shape of the patient's skull.

[0071] In some embodiments, the headgear 20, when filled with liquid dielectric, is not circular to match the shape of the patient's skull. Specifically, when the headgear 20 is installed in the receiving portion 10, the length of the headgear 20 in the height direction is greater than its length in the horizontal direction.

[0072] In some embodiments, the headgear mounting portion 113 is connected to the end portion 112 on the inner side of the peripheral portion 111.

[0073] In some embodiments, the headgear mounting portion 113, the peripheral portion 111, and the end portion 112 together form a groove 1130. The first headgear mounting mating portion 22 is configured to be able to fit into the groove 1130, and the headgear body 21 can cover the groove 1130. In such an embodiment, by enabling the first headgear mounting mating portion 22 to fit into the groove 1130 formed by the receiving portion 10, the first headgear mounting mating portion 22 is prevented from detaching from the receiving portion 10. At the same time, since the headgear body 21 can cover the groove 1130, the aesthetics are improved.

[0074] In some embodiments, the headgear mounting portion 113 is configured to also form a guide groove 1131, and the first headgear mounting mating portion 22 is configured to form a guide portion 221. The guide portion 221 is configured to slide in the guide groove 1131, so that the first headgear mounting mating portion 22 can be embedded in the groove 1130. In such an embodiment, since both the headgear body 21 and the first headgear mounting mating portion 22 are made of flexible material, it is difficult to directly embed the first headgear mounting mating portion 22 into the groove 1130. By configuring the guide portion 221 to cooperate with the guide groove 1131, and by pushing the guide portion 221 to slide in the guide groove 1131, the first headgear mounting mating portion 22 can be embedded into the groove 1130.

[0075] In some embodiments, the guide portion 221 protrudes from the first headgear mounting and mating portion 22 to facilitate the application of force.

[0076] In some embodiments, the headgear body 21 may abut against the headgear mounting portion 113 of the receiving portion 10 to prevent the headgear body 21 from moving toward the end portion 112, thereby avoiding interference with the detection of intracranial hemorrhage.

[0077] In some embodiments, the headgear body 21 is bonded to the first headgear mounting mating part 22.

[0078] In some embodiments, the periphery 111 is further configured to form a periphery mounting hole 1112, and the first headgear mounting fitting part 22 forms a headgear mounting hole 222. A positioning member passes through the headgear mounting hole 222 of the first headgear mounting fitting part 22 and the periphery mounting hole 1112 of the periphery 111, thereby mounting the first headgear mounting fitting part 22 onto the periphery 111. In this embodiment, mounting the first headgear mounting fitting part 22 onto the periphery 111 using a positioning member ensures both the fixation of the headgear 20 and facilitates the replacement of the headgear 20.

[0079] In some embodiments, the peripheral mounting hole 1112 corresponds to the guide groove 1131. In such an embodiment, by configuring the guide portion 221 to slide in the guide groove 1131 of the receiving portion 10, the peripheral mounting hole 1112 can be aligned with the head cover mounting hole 222 formed by the first head cover mounting mating portion 22 of the head cover 20, thereby facilitating the replacement of the head cover 20.

[0080] In some embodiments, the positioning element may be a positioning pin.

[0081] In some embodiments, the number of headgear mounting holes 222 and guide portions 221 are the same, and the position of each headgear mounting hole 222 is spaced apart from a corresponding guide portion 221 along the extending direction of the first headgear mounting mating portion 22. In such an embodiment, when the guide portion 221 slides to the bottom in the guide groove 1131, the headgear mounting hole 222 can be aligned with the peripheral mounting hole 1112 of the receiving portion 10, thereby simplifying the assembly of the first headgear mounting mating portion 22 and the receiving portion 10.

[0082] In some embodiments, the guide portion 221 is located at the end of the first headgear mounting and fitting portion 22 away from the headgear body 21, and the guide groove 1131 and the recess 1130 have the same depth. When the guide portion 221 slides to the bottom in the guide groove 1131, the first headgear mounting and fitting portion 22 also reaches the bottom of the recess 1130, so as to facilitate the assembly of the first headgear mounting and fitting portion 22 with the receiving portion 10.

[0083] In some embodiments, the second headgear mounting mating part 23 is connected to the headgear body 21 on the side away from the first headgear mounting mating part 22.

[0084] In some embodiments, the headgear body 21 is flush with the outer surface of the first headgear mounting mating part 22; the thickness of the first headgear mounting mating part 22 is less than the thickness of the headgear body 21; the inlet / outlet liquid component 24 is connected to the side of the bottom of the headgear body 21 and extends inside the first headgear mounting mating part 22 toward the side away from the second headgear mounting mating part 23.

[0085] In such an embodiment, it is beneficial for the headgear body 21 and the first headgear mounting mating part 22 to fit snugly against the inner wall of the receiving part 10, while the liquid inlet and outlet parts 24 can be led outward without occupying the space at the bottom of the receiving part 10 for mounting the antenna 33.

[0086] In some embodiments, the venting member 25 is disposed on the top of the headgear body 21 and at the end of the headgear body 21 away from the first headgear mounting mating part 22. In such an embodiment, since the liquid inlet / outlet member 24 is disposed at the bottom of one end of the headgear body 21 and the venting member 25 is disposed at the top of the other end of the headgear body 21, it is convenient to vent the liquid when filling the headgear body 21 with liquid using the liquid inlet / outlet member 24. This allows the liquid to be smoothly filled into the headgear body 21 by venting the liquid through the liquid inlet / outlet member 24, and the headgear body 21 can be filled with liquid dielectric, thereby improving the transmission efficiency of microwave signals.

[0087] In some embodiments, a shell relief groove 120 is formed at the top of the shell connecting portion 12 to allow the exhaust member 25 of the headgear 20 to pass through. The exhaust member 25 extends beyond the receiving portion 10 through the shell relief groove 120 and then extends along the periphery 111 toward the end portion 112. The shell relief groove 120 can limit the exhaust member 25, preventing it from moving or shifting, and ensuring that the exhaust member 25 is in the highest position, thereby preventing air residue in the headgear body 21.

[0088] In some embodiments, the end portion 112 of the receiving portion 10 is configured to form an opening so that the liquid inlet / outlet member 24 of the head cover 20 can extend from the receiving space to the external space through the opening.

[0089] In some embodiments, the intracranial hemorrhage detection device 100 may further include: a liner 60 disposed between the end 112 and the headgear 20 to cover the opening of the end 112; the liner 60 is disposed radially inside the headgear mounting portion 113, and the headgear mounting portion 113 is further configured to prevent the liner 60 from detaching.

[0090] In this embodiment, the opening is covered by the inner liner 60, which is beneficial to the aesthetics of the interior of the receiving part 10, and the inner liner 60 is fixed by the head cover mounting part 113, which helps to reduce the installation structure.

[0091] In some embodiments, the headgear mounting portion 113 forms an inner liner positioning portion 1132, and the inner liner 60 forms an inner liner positioning mating portion 61. The inner liner positioning portion 1132 and the inner liner positioning mating portion 61 are configured to engage to position the inner liner 60. In such an embodiment, the inner liner 60 is positioned by the engagement of the inner liner positioning portion 1132 and the inner liner positioning mating portion 61, preventing the inner liner 60 from detaching.

[0092] In some embodiments, the liner positioning mating part 61 is configured as a positioning groove extending along the extension direction of the circumferential part 111; the liner positioning part 1132 is configured as a protrusion extending along the extension direction of the circumferential part 111, and the positioning groove and the protrusion slide into each other to position the liner 60, thereby preventing the liner 60 from falling off. This configuration helps to simplify the assembly of the liner 60.

[0093] In some embodiments, the liner 60 is configured to form a liner clearance groove 62 to make way for the guide portion 221 of the headgear 20, thereby facilitating the engagement of the guide portion 221 with the guide groove 1131, and also enabling the headgear 20 to be disassembled and assembled without removing the liner 60.

[0094] In some embodiments, the liner 60 may be made of the same material as the headgear 20 to improve aesthetics. In some embodiments, both the liner 60 and the headgear 20 may be made of silicone.

[0095] In some embodiments, the intracranial hemorrhage detection device 100 further includes: a dielectric filling and discharging pressurization assembly 50, which is configured to fill the headgear 20 with dielectric or discharge the dielectric in the headgear 20, and pressurize the headgear 20 so that the headgear 20 can expand to fit the patient's brain.

[0096] In this embodiment, by setting up a headgear 20, after the patient's skull enters the receiving part 10, the dielectric filling and pressurizing component 50 fills the headgear 20 with dielectric material and pressurizes the headgear 20 so that it can expand and fit the patient's skull. It can adapt to the shape of different patients' skulls. Relying on the flexible deformation and fluid adaptive characteristics of the headgear 20, it closely fits the contour of the patient's skull, achieving a gapless fit and wrapping, which helps to improve the transmission efficiency of microwave signals and thus improve the quality of microwave signals transmitted or received by the signal transmission and acquisition component.

[0097] In some embodiments, the dielectric filling and pressurizing assembly 50 may include: a dielectric container 51, an inlet / outlet liquid line 52, an outlet liquid line 53, and a drive member 54; the dielectric container 51 is used to contain liquid dielectric; the drive member 54 is used to drive the liquid dielectric to flow between the dielectric container 51 and the headgear 20 via the inlet / outlet liquid line 52, and to pressurize the headgear 20 through the inlet / outlet liquid line 52 after the headgear 20 is filled with liquid dielectric, so that the headgear 20 expands and fits against the skull; when the drive member 54 drives the liquid dielectric to flow into the headgear 20, the outlet liquid line 53 is used to discharge gas from the headgear 20; when the drive member 54 pressurizes the headgear 20, the outlet liquid line 53 is disconnected. In such an embodiment, liquid can be smoothly fed into and pressurized into the headgear 20.

[0098] In some embodiments, the drive element 54 is a pump.

[0099] In some embodiments, the inlet / outlet pipe 52 is used to connect the inlet / outlet component 24 of the headgear 20 to the medium container 51, and the outlet pipe 53 is used to connect the outlet component 25 of the headgear 20 to the medium container 51.

[0100] In some embodiments, the dielectric charging and discharging pressurization assembly 50 may further include: a liquid detection element, a pressure measuring element 55, and a valve 56. The liquid detection element is used to detect liquid in the exhaust pipe 53 to determine the filling amount of the headgear 20; the pressure measuring element 55 is used to measure the pressure inside the headgear 20; the valve 56 is disposed in the exhaust pipe 53 and is configured to disconnect the exhaust pipe 53 when the liquid detection element detects liquid in the exhaust pipe 53, so as to pressurize the headgear 20 using the drive element 54.

[0101] In this embodiment, since the exhaust vent 25 is located at the top, when the headgear 20 is filled with dielectric, the dielectric will enter the exhaust pipe 53. When the liquid detection device detects the presence of liquid in the exhaust pipe 53, it indicates that the headgear 20 is filled with dielectric. At this time, after disconnecting the exhaust pipe 53 through the valve 56, the drive vent 54 can be used to pressurize the headgear 20, thereby causing the headgear 20 to expand and fit against the brain. The pressure measuring device 55 is used to measure the pressure inside the headgear 20, so that the drive vent 54 can be stopped from continuing to pressurize based on the pressure value measured by the pressure measuring device 55, so that the pressure on the patient's brain is within an appropriate range.

[0102] In some embodiments, the liquid detection element may be disposed in the exhaust pipe 53.

[0103] In some embodiments, the dielectric charging and discharging pressurization assembly 50 may further include: a pressure measuring line 57 in fluid communication with the exhaust line 53 upstream of the valve 56; and a pressure measuring element 55 disposed on the pressure measuring line 57. By providing the pressure measuring line 57, the pressure inside the head sleeve 20 can be measured when the exhaust line 53 is disconnected from the medium container 51.

[0104] In some embodiments, the inlet / outlet component 24 is quickly connected to the inlet / outlet pipeline 52, the vent component 25 is quickly connected to the vent pipeline 53, and the inlet / outlet pipeline 52 and the vent pipeline 53 are quickly connected to the medium container 51 respectively.

[0105] In some embodiments, the mounting assembly may further include a fourth mounting member 44, connected to the top of the first mounting member 411, for mounting the valve 56 and the pressure measuring element 55. Since the height of the receiving portion 10 is higher than that of the first mounting member 411, mounting the valve 56 and the pressure measuring element 55 on the fourth mounting member 44 not only makes efficient use of space but also facilitates the connection of the valve 56 and the pressure measuring element 55 to the exhaust pipe 53.

[0106] See Figure 6 , Figure 6 This is a schematic diagram of a port expansion component according to an embodiment of this application. In some embodiments, the port expansion component 32 includes a port expansion body 320, two first connectors 321 connected to the port expansion body 320, and a plurality of second connectors 322; the two first connectors 321 are used to connect to a vector network analyzer 31 via a signal transmission line group 34 to receive microwave signals transmitted by the vector network analyzer 31 and to transmit microwave signals to the vector network analyzer 31; each second connector 322 is used to connect to a corresponding antenna 33 via the signal transmission line group 34 to transmit microwave signals from the vector network analyzer 31 to the antenna 33 or to receive corresponding microwave signals from the antenna 33; the two first connectors 321 can be connected to any two different second connectors 322 respectively.

[0107] In such an embodiment, by providing port extensions 32 with two first connectors 321 and multiple second connectors 322, the ports of the vector network analyzer 31 are effectively expanded, thereby enabling communication connections with more antennas 33.

[0108] See Figure 7 , Figure 7This is a schematic diagram of the intracranial hemorrhage detection device according to an embodiment of this application, omitting structures such as the processor. In some embodiments, the port expansion body 320 includes two main surfaces 3201 (i.e., the two surfaces with the largest area) arranged opposite each other and four side surfaces 3202; wherein the two opposite side surfaces 3202 are parallel to each other, and the two adjacent side surfaces 3202 are perpendicular to each other; the two main surfaces 3201 face the receiving part 10 and the vector network analyzer 31 respectively; two first connectors 321 are respectively disposed at two vertices of the port expansion body 320; a plurality of second connectors 322 are respectively disposed on the four side surfaces 3202, and the number of second connectors 322 on each side surface 3202 is equal.

[0109] In this embodiment, the two main surfaces 3201 of the port expansion body 320 are shielded by the first mounting member 411 and the receiving portion 10, while the four sides 3202 of the port expansion body 320 are not shielded. Multiple second connectors 322 are positioned on the four unshielded sides 3202 of the port expansion body 320, and two first connectors 321 are positioned at the unshielded vertices of the port expansion body 320, facilitating the arrangement of the signal transmission line group 34. Furthermore, the two first connectors 321 positioned at the two vertices of the port expansion body 320 make way for the multiple second connectors 322 positioned on the sides 3202, preventing interference between the signal transmission lines; the multiple second connectors 322 are respectively positioned on the four sides 3202, which helps save space.

[0110] In some embodiments, the signal transmission line group 34 includes: four first signal transmission line groups 341, each of which is respectively connected to a plurality of second connectors 322 disposed on a side 3202 and a corresponding antenna 33; and a second signal transmission line group 342 for connecting the first connectors 321 and the vector network analyzer 31.

[0111] In some embodiments, each first signal transmission line group 341 includes a plurality of first signal transmission lines 3411, and the number of first signal transmission lines 3411 in each first signal transmission line group 341 is equal; the first signal transmission lines 3411 of the four first signal transmission line groups 341 are configured to be centrally symmetrical about the center point of the port expansion body 320.

[0112] In this embodiment, four first signal transmission line groups 341 are respectively disposed on the four sides 3202 of the port expansion body 320, and are centrally symmetrical about the center point of the port expansion body 320. This arrangement allows the multiple first signal transmission lines 3411 to be evenly distributed around the port expansion body 320 without interfering with each other, and can be correspondingly connected to the antenna 33 arranged in the circumferential direction of the receiving portion 10. Furthermore, this arrangement of the first signal transmission line groups 341 is aesthetically pleasing.

[0113] In some embodiments, each first signal transmission line 3411 includes: a first extension section 34111, a bent section 34112, and a second extension section 34113; one end of the first extension section 34111 is detachably connected to a second connector 322 disposed on any side 3202, and the other end is connected to the bent section 34112, and the first extension section 34111 is configured to extend in a direction perpendicular to and away from the side 3202; one end of the bent section 34112 is connected to the first extension section 34111, and the other end is connected to the second extension section 34113, and the bent section 34112 is configured to extend in a bent manner; one end of the second extension section 34113 is connected to the bent section 34112, and the other end is detachably connected to the antenna 33, and the second extension section 34113 is configured to extend along the periphery 111 of the receiving portion 10.

[0114] In this embodiment, since the volume of the port extension 32 is smaller than that of the receiving portion 10, the second connector 322 disposed on the side 3202 of the port extension 32 is still some distance away from the periphery 111 of the receiving portion 10. The first extension segment 34111 extends perpendicularly to and away from the side 3202 where the second connector 322 is located, allowing the first signal transmission line 3411 to extend closer to the periphery 111 of the receiving portion 10. The bending segment 34112 is configured to extend in a curved manner so that the first signal transmission line 3411 can be bent. The first signal transmission line 3411 extends to the periphery 111 of the receiving portion 10, and the curved arrangement of the first signal transmission line 3411 allows space for other components located nearby, such as the pressure measuring pipe 57 located at the top of the receiving portion 10 and the liquid inlet / outlet positioning portion 15 located at the bottom of the receiving portion 10; the second extension segment 34113 of each first signal transmission line 3411 extends along the periphery 111 of the receiving portion 10 and is parallel to each other, which not only simplifies the wiring, but also ensures that adjacent first signal transmission lines 3411 are spaced apart and not pressed together, thus avoiding interference with microwave signal transmission.

[0115] In some embodiments, the number of second connectors 322 disposed on each side 3202 of the port extension body 320 is 4, and the number of first signal transmission lines 3411 in each first signal transmission line group 341 is 4.

[0116] In some embodiments, the bent section 34112 of the first signal transmission line 3411 is configured to be bent in the direction of the central axis of the side 3202 where the second connector 322 is located, which is perpendicular to it; and the first signal transmission line 3411 is configured to be symmetrical about the central axis of the side 3202 where the second connector 322 is located, which is perpendicular to it.

[0117] In such an embodiment, since the bent sections 34112 of the first signal transmission lines 3411 disposed on each side 3202 are bent in a direction perpendicular to the central axis of the corresponding side 3202, the multiple first signal transmission lines 3411 disposed on each side 3202 can be disposed more compactly, thereby leaving space for the placement of other components.

[0118] In some embodiments, the second signal transmission line group 342 includes two second signal transmission lines 3421, each second signal transmission line 3421 including a third extension section 34211, a ring section 34212, and a fourth extension section 34213; the third extension section 34211 is connected to the first connector 321 at one end and to the ring section 34212 at the other end, and the third extension section 34211 is configured to extend away from the first connector 321; the ring section 34212 is connected to the third extension section 34211 at one end and to the fourth extension section 34213 at the other end, and the ring section 34212 is configured to bend away from the port extension body 320; the fourth extension section 34213 is connected to the ring section 34212 at one end and to the vector network analyzer 31 at the other end, and the fourth extension section 34213 is configured to extend horizontally.

[0119] In such an embodiment, the annular segment 34212 bends away from the port extension body 320, thus bypassing the first mounting member 411 between the port extension 32 and the vector network analyzer 31, thereby achieving a connection with the vector network analyzer 31.

[0120] In some embodiments, the intracranial hemorrhage detection device may further include: a processor 73, which is communicatively connected to a signal transmission and acquisition component, for receiving microwave signals from the brain acquired by the signal transmission and acquisition component and processing the microwave signals.

[0121] In some embodiments, the processor is disposed on the side of the auxiliary mounting component 412 opposite to the vector network analyzer 31.

[0122] In this embodiment, since the processor 73 is mounted on the side of the auxiliary mounting component 412 opposite to the vector network analyzer 31, the processor 73 is also separated from the base 71, avoiding contamination by leaked dielectric. At the same time, the processor 73, the vector network analyzer 31, and the port expansion component 32 are placed close together, which is conducive to wiring and makes the layout of the entire intracranial hemorrhage detection device 100 more compact.

[0123] In some embodiments, the vector network analyzer 31 is arranged parallel to the port expansion body 320; the two opposing analyzer sides 310 of the vector network analyzer 31 located in the vertical plane are parallel to the two opposing sides 3202 of the port expansion body 320 located in the vertical plane, and the two opposing analyzer sides 310 of the vector network analyzer 31 located in the vertical plane are provided with first heat dissipation holes 311 for heat dissipation. In such an embodiment, since the two opposing analyzer sides 310 of the vector network analyzer 31 located in the vertical plane do not face the port expansion body 320 and the receiving portion 10, airflow is facilitated, thereby improving heat dissipation.

[0124] In some embodiments, a fan is provided inside the vector network analyzer 31 to force air to flow through the first heat dissipation hole 311 to dissipate heat from the vector network analyzer 31.

[0125] In some embodiments, the housing 72 forms two sets of oppositely arranged heat dissipation holes 720, which face the first heat dissipation holes 311 on both sides of the vector network analyzer 31, for airflow, thereby facilitating heat dissipation of the vector network analyzer 31.

[0126] In some embodiments, the intracranial hemorrhage detection device 100 may further include: a plurality of fans 74 disposed inside the housing 72 and facing the housing heat dissipation hole 720, for driving ambient air into the housing 72, and through the first heat dissipation hole 311 into the vector network analyzer 31 to dissipate heat from the vector network analyzer 31 before leaving through the other side housing heat dissipation hole 720.

[0127] In some embodiments, the housing 72 may include a main housing 721, a front housing 722, and a rear cover 723. The main housing 721 is detachably connected to the base 71, the front housing 722 is detachably connected to the receiving portion 10, and the rear cover 723 is detachably connected to the main housing 721. The dielectric receiving member 51 is detachably mounted on the rear cover 723. In such an embodiment, dividing the housing 72 into a main housing 721, a front housing 722, and a rear cover 723 facilitates the assembly of the housing 72 and also facilitates the removal of the dielectric receiving member 51 for dielectric replacement.

[0128] In some embodiments, the side of the main housing 721 opposite to the receiving portion 10 is recessed toward the receiving portion 10, thereby forming a space for receiving the media receiving member 51; the rear cover 723 is L-shaped and is detachably connected to the recess of the main housing 721 for installing the media receiving member 51.

[0129] In some embodiments, the main housing 721 forms a handle 76 above the recess to facilitate the transfer of the intracranial hemorrhage detection device 100.

[0130] In some embodiments, the main housing 721 is further provided with a heat dissipation hole 7210 below the recessed area for dissipating heat from the processor 73.

[0131] In some embodiments, the front shell 722 is detachably connected to the shell connecting portion 12 of the receiving portion 10 to press the second headgear mounting mating portion 23 between the shell 72 and the shell connecting portion 12, preventing the headgear 20 from rotating or falling off.

[0132] In some embodiments, the housing 72 may also include a pillow portion 75, detachably connected to the neck support portion 13, for providing support to the patient's neck to improve aesthetics.

[0133] In some embodiments, the mounting assembly further includes a reinforcement 45 for engaging with the headrest 75 to provide support.

[0134] In some embodiments, the base 71 is provided with an opening and a bottom cover 711 for opening or closing the opening. The opening is located directly below the liquid inlet / outlet positioning part 15, thereby facilitating the disassembly and assembly of the liquid inlet / outlet pipe 52 and the liquid inlet / outlet part 24 by opening the bottom cover 711.

[0135] In some embodiments, the opening of the base 71 is located between the two second mounting members 42 and on the side of the first mounting member 411 facing the receiving portion 10, so as not to affect the overall installation strength.

[0136] In some embodiments, the bottom cover 711 is hollowed out, and the drain port 712 is formed on the bottom cover 711. This facilitates the discharge of leakage at the connection between the inlet / outlet pipe 52 and the inlet / outlet component 24, thereby preventing the leaked liquid dielectric from causing mold growth or damage to the signal transmission and acquisition components. At the same time, it can also dissipate heat from the processor 73, port expansion component 32 and vector network analysis component 31, which helps to prevent the processor 73, port expansion component 32 and vector network analysis component 31 from getting too hot.

[0137] In some embodiments, the base 71 is provided with a drain hole 713 below the connection between the drive member 54 and the inlet / outlet pipe 52 and the exhaust pipe 53, for draining liquid in case of leakage.

[0138] In some embodiments, the intracranial hemorrhage detection device 100 may further include an operating element 77 and a plurality of communication interfaces 78, disposed on the side of the main housing 721 opposite to the receiving portion 10 and located below the rear cover 723. Since the processor 73 is also disposed on the side opposite to the receiving portion 10, placing the operating element 77 and the plurality of communication interfaces 78 at the rear of the main housing 721 below the rear cover 723 facilitates wiring. The operating element 77 may be a button or a touch screen.

[0139] In some embodiments, the intracranial hemorrhage detection device 100 may further include: a USB splitter 79, disposed on the side of the base 71 opposite to the receiving portion 10 of the processor 73, for connecting to multiple communication interfaces 78 to expand the communication interfaces of the processor 73. A second heat dissipation hole 714 is provided below the USB splitter 79 on the base 71 for heat dissipation of the USB splitter 79.

[0140] In some embodiments, the driver 54 and the USB splitter 79 are disposed on the side of the base 71 away from the receiving portion 10 to make efficient use of space.

[0141] The inventors of this application have discovered that the existing methods for determining the state of intracranial hemorrhage based on microwave signals have poor accuracy and reliability in determining the results of intracranial hemorrhage detection, and are difficult to accurately, comprehensively and quantitatively reflect the actual situation of intracranial hemorrhage.

[0142] In some embodiments, the processor 73 is configured to: receive microwave signals of the brain acquired by the signal transmission and acquisition component; filter out noise from the microwave signals and normalize the noise-filtered microwave signals to determine the normalized microwave signals; determine the characteristic information of the brain based on the normalized microwave signals; reconstruct an image of the brain based on the characteristic information of the brain, the image providing spatial location information, morphological information, and energy intensity information of the hemorrhage area of ​​the brain; determine the category of the microwave signals of the brain based on the characteristic information of the brain; and determine the characteristic attributes of the hemorrhage area of ​​the brain based on the image and the category of the microwave signals of the brain.

[0143] Images of the brain can provide quantitative spatial information such as the location, morphology, and energy intensity of the hemorrhage area. However, due to the lack of pathological semantic information guiding whether bleeding has occurred, the hemorrhage area is easily confused with background clutter. The category of microwave signals in the brain can provide pathological semantic information regarding whether bleeding has occurred, but it only serves as a qualitative judgment, lacking both spatial and quantitative information. In this embodiment, by jointly determining the characteristic attributes of the hemorrhage area based on both the image and the category, the category semantics guide the precise localization of the hemorrhage area in the image. This allows the detection of hemorrhage areas with weak signals that might otherwise be overlooked. The spatial information of the image supplements the quantifiable information of spatial location, morphology, and energy intensity of the category discrimination. The two complement and corroborate each other, resulting in higher sensitivity for detecting this small target, the hemorrhage area. The detection results can comprehensively, accurately, and quantitatively reflect the actual hemorrhage situation in the brain. Furthermore, the processor 73 first performs noise filtering and normalization processing on the acquired microwave signal, which can filter out background clutter to a certain extent and obtain a microwave signal with a high signal-to-noise ratio. As a result, the characteristic information of the cranium determined based on the microwave signal with a high signal-to-noise ratio, as well as the cranium image reconstructed based on the cranium characteristic information and the category of the cranium microwave signal determined, are more accurate and reliable.

[0144] In some embodiments, the feature information of the cranium may be, for example, a multi-dimensional intermediate feature representation of the electromagnetic scattering characteristics of cranial tissue extracted from microwave signals after filtering and normalization.

[0145] In some embodiments, the category of the microwave signal of the brain can be, for example, a qualitative judgment result based on the characteristic information of the brain regarding whether the brain is bleeding (and the nature of the bleeding). For example, the category can be a semantic label or category marker used to indicate health or bleeding (and further distinguish the bleeding subtype).

[0146] In some embodiments, spatial location information indicates the location of the hemorrhage area within the brain.

[0147] In some embodiments, morphological information represents the shape, size, and extent of the bleeding.

[0148] In some embodiments, energy intensity information represents the intensity of scattered energy in the bleeding area.

[0149] In some embodiments, the characteristic attributes of the hemorrhage area in the brain can be, for example, a complete and quantifiable attribute description used to determine the hemorrhage and provide information on "hemorrhage location, hemorrhage morphology, and hemorrhage energy intensity".

[0150] In some embodiments, the processor 73 is specifically configured to determine the characteristic attributes of the hemorrhage area of ​​the brain by: determining the semantic vector of the category based on the category of the microwave signal of the brain; determining the hemorrhage area features of the image based on the semantic vector of the category and the image; and determining the characteristic attributes of the hemorrhage area of ​​the brain based on the semantic vector of the category and the hemorrhage area features of the image.

[0151] In such embodiments, compared to judging the hemorrhage status of the brain solely based on images or solely based on text categories, determining the characteristic attributes of the hemorrhage area of ​​the brain by jointly determining the semantic vector of the category and the hemorrhage area features of the image can achieve a unity of spatial accuracy and semantic interpretability of the hemorrhage detection results, thereby comprehensively, accurately and quantitatively reflecting the true hemorrhage status of the brain.

[0152] In some embodiments, the processor 73 is specifically configured to determine the semantic vector of a category by: determining a text label for a category based on the category of microwave signals from the brain; determining a fixed-dimensional semantic vector based on the text label of the category; and performing feature space alignment on the fixed-dimensional semantic vector to determine the semantic vector of the category.

[0153] In such an embodiment, since the semantic vector is aligned with the feature space, the semantic vector and the spatial feature vector of the image are in the same space, which provides the conditions for subsequent similarity calculation.

[0154] In some embodiments, the processor 73 is specifically configured to determine the hemorrhage region features of the image by: determining the spatial feature vector corresponding to the reconstructed cranial image; determining the cosine similarity between the semantic vector and the spatial feature vector of the image based on the semantic vector and the image; determining the feature similarity distribution between the semantic vector and the spatial feature vector based on the cosine similarity; determining the matching degree between the semantic vector and the spatial feature vector based on the feature similarity distribution; determining the hemorrhage region of the image and the spatial location of the hemorrhage region in the image based on the matching degree; and determining the hemorrhage region features of the cranial image based on the hemorrhage region of the image and the spatial location of the hemorrhage region in the image.

[0155] In such an embodiment, by determining the cosine similarity between the semantic vector and the spatial feature vector of the image, the high-dimensional features of the microwave signal can be expressed more clearly, thereby accurately determining the bleeding area of ​​the image and the spatial location of the bleeding area in the image.

[0156] In some embodiments, the feature similarity distribution between semantic vectors and spatial feature vectors can be the spatial location distribution of the cosine similarity between semantic vectors and spatial feature vectors in the image.

[0157] In some embodiments, when determining the bleed region of an image, regions with a matching degree value greater than or equal to a predetermined threshold can be identified as bleed regions of the image. It is understood that those skilled in the art are aware of the value of the predetermined threshold, and this application does not limit it.

[0158] See Figures 8 to 10 , Figure 8 This is a schematic diagram of the spatial feature vector corresponding to an image determined according to the method of the embodiments of this application. Figure 9 This is a schematic diagram showing the spatial distribution of the cosine similarity between the semantic vector and the spatial feature vector of the image, determined by the method according to embodiments of this application, in the image. Figure 10 This is a schematic diagram of the bleeding area of ​​an image determined according to the method of an embodiment of this application. Figure 8 In the diagram, the vertical axis on the right represents the magnitude of the spatial feature vector. For example... Figures 8 to 10 As shown, by gradually determining the spatial feature vector, semantic vector, and the cosine similarity and feature similarity distribution of the spatial feature vector, as well as the matching degree between the semantic vector and the spatial feature vector, the bleeding region in the image is accurately located, thereby enabling the acquisition of the bleeding region features of the image.

[0159] In some embodiments, the processor 73 is specifically configured to determine the characteristic attributes of the hemorrhage region of the brain by: concatenating the semantic vector and the hemorrhage region features of the image along the channel dimension to determine the joint feature vector of the hemorrhage region; determining the spatial location attribute, morphological attribute, and energy intensity attribute of the hemorrhage region based on the joint feature vector; and determining the characteristic attributes of the hemorrhage region of the brain based on the semantic vector and the spatial location attribute, morphological attribute, and energy intensity attribute of the hemorrhage region.

[0160] In such an embodiment, by concatenating the semantic vector with the hemorrhage region features of the image along the channel dimension to form a joint feature vector, it is possible to simultaneously fuse category semantic information and image spatial information, thereby more accurately determining the characteristic attributes of the hemorrhage region of the brain.

[0161] In some embodiments, the processor 73 is configured to store a preset number of cranial microwave signals from healthy samples, which are pre-acquired using the signal transmission and acquisition component of the intracranial hemorrhage detection device of this application; the processor 73 is specifically configured to filter out noise from the microwave signals and normalize the noise-filtered microwave signals in the following manner: determining the noise-filtered microwave signals based on the cranial microwave signals acquired by the signal transmission and acquisition component and the cranial microwave signals from the preset number of healthy samples stored in the processor 73; and determining the normalized microwave signals based on the noise-filtered microwave signals.

[0162] In such an embodiment, since the cranial microwave signal of a healthy sample can reflect the background interference information generated by the inherent layered structure of the skull, scalp, etc., the cranial microwave signal of a healthy sample can be used as a reference to filter out electromagnetic reflection clutter generated by the layered structure of the skull, scalp, etc. in the collected cranial microwave signal, thereby improving the signal-to-noise ratio of the microwave signal. By normalizing the microwave signal after filtering out noise, the amplitude shift caused by non-target factors can be eliminated, and the microwave scattering parameters can be mapped to a uniform numerical range.

[0163] In some embodiments, multiple antennas 33 of the signal transmission and acquisition component are arranged along the same circumference in the receiving portion 10. All antennas 33 are collectively referred to as a transceiver antenna array. An antenna 33 for transmitting microwave signals and an antenna 33 for receiving microwave signals are collectively referred to as a pair of transceiver antenna combinations.

[0164] In some embodiments, the processor 73 is specifically configured to determine the noise-filtered microwave signal by: determining the time-domain mean of the brain microwave signal of the healthy sample for each transceiver channel of the transceiver antenna array based on the brain microwave signal of the healthy sample stored in the processor 73, and determining the baseline mean signal corresponding to the transceiver channel based on the time-domain mean; determining the centered healthy sample matrix based on the brain microwave signal of the healthy sample and the baseline mean signal; performing singular value decomposition on the centered healthy sample matrix and determining the eigenvectors corresponding to the first N principal components, and determining the background clutter subspace corresponding to the transceiver channel based on the eigenvectors; wherein N is a preset number of principal components; converting the brain microwave signal acquired by the signal transmission and acquisition component to a time-domain signal, and determining the centered target microwave signal based on the baseline mean signal; determining the estimated clutter component in the target microwave signal based on the centered target microwave signal and the background clutter subspace; and determining the noise-filtered microwave signal based on the centered target microwave signal and the estimated clutter component.

[0165] In this embodiment, the processor 73 stores a preset number of cranial microwave signals from healthy samples and determines the time-domain mean of the cranial microwave signals of the healthy samples on each transceiver channel. This allows it to further obtain a baseline mean signal reflecting the static scattering response of normal cranial tissue. Furthermore, based on the cranial microwave signals of the healthy samples and the baseline mean signal, a centered healthy sample matrix is ​​determined. By performing singular value decomposition on the centered healthy sample matrix, the high-dimensional healthy sample data can be compressed, and principal component features characterizing strong static structures such as the skull and tissue boundaries can be extracted. By extracting the feature vectors corresponding to the first N principal components to construct a background clutter subspace, the distribution pattern of background clutter in the feature space can be accurately characterized, providing a physically meaningful projection basis for subsequent clutter filtering. By centering the acquired microwave signals and projecting them onto the background clutter subspace, components in the microwave signals that are consistent with the background clutter distribution can be accurately separated, i.e., clutter components can be estimated. This avoids the accidental rejection of weak target signals that overlap with the effective signal in frequency band or time delay by traditional time window or frequency window filtering methods, thereby improving the accuracy of clutter estimation. By subtracting the estimated clutter component from the centered target microwave signal, the dominant background clutter can be accurately removed in the time domain, thereby improving the signal-to-noise ratio of the microwave signal.

[0166] Furthermore, because different transceiver channels correspond to different antenna spatial locations, the distance between the transmitting and receiving antennas, the thickness of the skull or tissues the electromagnetic waves pass through, and the anatomical structures they pass through are all asymmetrical. Therefore, the background clutter of each transceiver channel has its own unique time delay, amplitude, and space-frequency structure. By establishing a dedicated background clutter subspace for each transceiver channel, it is possible to adapt to the asymmetrical scattering path differences caused by different antenna spatial locations, accurately match and filter out the background clutter unique to each transceiver channel, thereby achieving precise filtering of background clutter across the entire array.

[0167] See Figure 11 and Figure 12 , Figure 11 The brain image is obtained based on the microwave signal before noise is filtered out. Figure 12 The image is a cranial image obtained from a microwave signal after noise has been filtered out using the method provided in the embodiments of this application. Figure 11 In the 200-square-meter hemorrhage area before noise removal, the characteristics of the hemorrhage target (such as blood cell signals) are severely masked by background clutter, making effective identification impossible; Figure 12 In this embodiment, after filtering out noise using the method provided in this application, background clutter at location 200 in the hemorrhage area is effectively suppressed, making the echo signal of the blood cells in the hemorrhage area stand out and clearly showing a high-brightness energy convergence point. This indicates that the method in this application embodiment can significantly improve the signal-to-noise ratio of microwave signals, achieving precise localization and visualization of the intracranial hemorrhage area.

[0168] In some embodiments, N can be selected from a value range of 1 to 10, where N is a positive integer.

[0169] When N is too small, for example, when N is 1, clutter from the skull and scalp cannot be adequately filtered out, resulting in a low improvement in the signal-to-noise ratio of the microwave signal. When N is too large, for example, when N is greater than 10, the background clutter subspace may overstep its boundaries and include components that should belong to the valid hemorrhage signal, causing the valid hemorrhage signal to be filtered out along with the background clutter. In some embodiments, the value of N can be 2, 3, 4, or 5. In such embodiments, when N is 2, 3, 4, or 5, filtering can adequately remove the dominant background clutter without intruding into the valid signal subspace, thus preserving the valid hemorrhage signal and achieving the optimal balance between filtering clutter and preserving the valid signal.

[0170] In some embodiments, the specific value of N can be the minimum N value required for the sum of the energies of the first N singular values ​​to reach a preset proportion of the total energy, and the preset proportion can be 85%-95%. In such embodiments, it is possible to ensure that effective bleeding signals are preserved while sufficiently filtering out background clutter.

[0171] In some embodiments, the processor 73 is specifically configured to determine the estimated clutter component in the target microwave signal by projecting the centered target microwave signal onto the background clutter subspace to determine the estimated clutter component in the target microwave signal.

[0172] In some embodiments, the processor 73 is specifically configured to determine the normalized microwave signal in the following manner: based on the microwave signal after noise removal, determine the amplitude of the microwave signal and determine the maximum absolute value of the amplitude in the frequency dimension; based on the maximum absolute value and a preset constant, determine the normalization denominator; based on the microwave signal after noise removal and the normalization denominator, determine the normalized microwave signal.

[0173] In this embodiment, by employing the maximum absolute amplitude normalization method, the microwave signal can be strictly mapped to a preset amplitude range, unifying the dimensions of each transmitting and receiving channel and preventing strong channel signals from drowning out weak channel signals. By determining the normalized microwave signal based on the microwave signal after noise removal and the normalization denominator, the relative amplitude ratio between different frequency points of the microwave signal can be preserved. This, in turn, preserves important pathological discrimination features such as the zero-point characteristics and phase structure of the microwave signal, which helps to obtain characteristic information of the brain using the normalized microwave signal.

[0174] In some embodiments, the preset constant is a very small positive number introduced to prevent the normalization denominator from being zero.

[0175] In some embodiments, the preset constant can be 10. -8 Up to 10 -6 Preferably, the preset constant can be 10. -6 This prevents numerical overflow caused by the normalization denominator being zero, while avoiding interference with the normalization results.

[0176] In some embodiments, the processor 73 is specifically configured to determine the characteristic information of the cranium by: determining the time domain characteristics of the normalized microwave signal based on the normalized microwave signal; determining the frequency domain characteristics of the normalized microwave signal based on the normalized microwave signal; determining the spatial domain characteristics of the normalized microwave signal based on the normalized microwave signal; and determining the characteristic information of the cranium based on the time domain characteristics, frequency domain characteristics, and spatial domain characteristics.

[0177] In such an embodiment, by extracting the time-domain features, frequency-domain features, and spatial-domain features of the microwave signal respectively, the electromagnetic scattering characteristics of the microwave signal in the cranial tissue can be expressed from multiple dimensions, thereby reflecting the characteristic information of the cranium more comprehensively.

[0178] In some embodiments, the processor 73 is specifically configured to determine the time-domain characteristics of the normalized microwave signal by: determining the echo delay of the normalized microwave signal based on the normalized microwave signal; determining the pulse peak amplitude of the normalized microwave signal based on the normalized microwave signal; determining the waveform symmetry of the normalized microwave signal based on the normalized microwave signal; and determining the time-domain characteristics of the normalized microwave signal based on the echo delay, pulse peak amplitude, and waveform symmetry.

[0179] In such an embodiment, by determining the echo delay, pulse peak amplitude, and waveform symmetry of the microwave signal, the scattering response pattern of the hemorrhage area in the brain over time can be reflected, thereby improving the ability of the subsequently determined brain feature information to express the location and intensity of the hemorrhage area in the brain tissue.

[0180] See Figure 13 , Figure 13 This is a schematic diagram of microwave signals corresponding to target brain tissue at different depths, determined according to the method of embodiments of this application. In some embodiments, the echo delay represents the occurrence time of the scattering response and is used to reflect the depth location information of the scatterer. Figure 13 As shown in the figure, based on the three microwave signal curves at different depths, it can be seen that as the depth of the target brain tissue increases within the brain, the timing of its echo peak appearance shifts accordingly. Specifically, at a target depth of 10 mm, the corresponding echo peak appearance time is 8 ns; at a target depth of 25 mm, the corresponding echo peak appearance time is 16 ns; and at a target depth of 45 mm, the corresponding echo peak appearance time is 27 ns. The depth of the target brain tissue and the corresponding echo peak appearance time exhibit a clear monotonic correspondence, indicating that the depth location of the target brain tissue within the brain can be determined based on the echo delay. Therefore, by extracting the echo delay as a temporal feature, the ability to express the spatial location of the hemorrhage area within the brain can be improved, and the delay information can be directly converted into depth information of the hemorrhage area.

[0181] In some embodiments, the peak pulse amplitude represents the intensity of the scattering response. Hemorrhages in the brain produce strong scattering because the dielectric constant and conductivity of blood are significantly higher than those of normal brain tissue.

[0182] In some embodiments, waveform symmetry represents the shape of the scattering response, wherein the slope ratio of the left and right edges of the envelope reflects the interface structure of the scatterer and the dispersion / loss characteristics of the medium, and can be used to distinguish between scattering from a single scatterer and scattering from a multilayer interface.

[0183] In some embodiments, the processor 73 is specifically configured to determine the frequency domain characteristics of the normalized microwave signal by: performing a short-time Fourier transform on the normalized microwave signal to determine the time-frequency distribution of the normalized microwave signal; determining the power spectral density distribution of the normalized microwave signal based on the time-frequency distribution; determining the frequency domain energy concentration of the normalized microwave signal based on the time-frequency distribution; and determining the frequency domain characteristics of the normalized microwave signal based on the power spectral density distribution and the frequency domain energy concentration.

[0184] In such an embodiment, by performing a short-time Fourier transform on the microwave signal and determining its power spectral density distribution and frequency domain energy concentration, the scattering energy distribution pattern of the hemorrhage area in the brain in the frequency dimension can be reflected, thereby improving the ability of the subsequently determined brain feature information to express the differences in dielectric properties of the hemorrhage area.

[0185] See Figure 14 , Figure 14 This is a schematic diagram showing the distribution of samples of different cranial tissues in the frequency domain feature space, as determined according to embodiments of this application. It illustrates the distribution of samples of normal tissue, ischemic tissue, edematous tissue, and hemorrhagic tissue in the frequency domain feature space, respectively. Figure 14 The horizontal axis represents the characteristic frequency corresponding to the power spectral density distribution, and the vertical axis represents the frequency domain energy concentration. As shown in the figure, the samples of the four tissue types are clustered with clear boundaries between clusters. Hemorrhagic tissue is located in the region with the lowest characteristic frequency and the highest frequency domain energy concentration; edematous tissue and ischemic tissue are located in regions with lower characteristic frequencies and higher frequency domain energy concentrations, respectively; and normal tissue is located in the region with the highest characteristic frequency and the lowest frequency domain energy concentration. The distribution pattern of these four tissue types is consistent with their dielectric properties: hemorrhagic tissue has the highest dielectric property, and its scattered echo energy concentrates towards lower frequencies, thus resulting in the lowest characteristic frequency and the highest frequency domain energy concentration for hemorrhagic tissue; conversely, normal tissue has the lowest dielectric property, and its scattered echo energy concentrates towards higher frequencies, thus resulting in the highest characteristic frequency and the lowest frequency domain energy concentration for normal tissue. Therefore, the method provided in this application embodiment can effectively express the differences in dielectric properties of different cranial tissues as their positional distribution differences in the frequency domain feature space by determining the power spectral density distribution and frequency domain energy concentration of microwave signals. This significantly improves the ability to express the differences in dielectric properties of different cranial tissues and provides a clear physical basis for determining the category of microwave signals.

[0186] In some embodiments, the processor 73 is specifically configured to determine the spatial characteristics of the normalized microwave signal by: determining the spatial distribution of the normalized microwave signal in each receiving channel based on the normalized microwave signal; performing beamforming processing on the normalized microwave signal based on the spatial distribution to determine the spatial focusing response of the normalized microwave signal; determining the scattering intensity of the normalized microwave signal in each spatial region of the brain based on the spatial focusing response; and determining the spatial characteristics of the normalized microwave signal based on the spatial focusing response and the scattering intensity.

[0187] In such an embodiment, by performing beamforming processing on the microwave signal and determining the scattering intensity of the microwave signal in various spatial regions of the cranium, the scattering distribution pattern of the hemorrhage area in the cranium in the spatial dimension can be reflected, thereby improving the ability of the subsequently determined cranium feature information to locate the spatial position of the hemorrhage area.

[0188] In some embodiments, spatial focusing response refers to the response value at each spatial location within the imaging area, obtained by applying corresponding time delay compensation to the microwave signals of each channel based on the antenna spatial location corresponding to each receiving channel and then coherently superimposing them; the response values ​​at all spatial locations together constitute the spatial focusing response.

[0189] See Figure 15 , Figure 15 This is a comparative schematic diagram showing the spatial focusing response of a microwave signal after beamforming processing according to the method of this application, and the direct superposition response of a microwave signal without beamforming processing. Figure 15 The horizontal axis represents the cross-section along the bleed region, and the vertical axis represents the value of the scattered energy response intensity at each location in the imaging space, mapped to the 0-1 interval after normalization. As shown in the figure, the curve representing the spatial focusing response of the microwave signal after beamforming fully illustrates the distribution pattern of scattered energy along the cross-section of the bleed region, i.e., in the spatial dimension. However, the curve representing the direct superposition response of the microwave signal without beamforming cannot effectively reflect the distribution pattern of scattered energy in the spatial dimension due to energy dispersion and waveform roughness.

[0190] In some embodiments, the processor 73 is specifically configured to reconstruct an image of the brain by: stripping away interference clutter from the matching medium between the transceiver antenna array and the brain based on the brain's characteristic information, and determining a target temporal feature signal containing only brain tissue; determining a multidimensional spatial grid coordinate matrix representing the spatial geometry of the transceiver antenna array and the average dielectric properties of the brain based on the spatial geometry of the transceiver antenna array and the average dielectric properties of the brain; determining the transmission distance and delay time of the microwave signal propagating in each pair of transceiver antennas to each grid point based on the target temporal feature signal and the multidimensional spatial grid coordinate matrix; and performing multi-frequency, multi-antenna confocal energy superposition and attenuation weighted compensation on the target temporal feature signal at each grid point based on the transmission distance and delay time to determine an image of the brain.

[0191] In this embodiment, by truncating the interface reflection clutter of the matching medium in the time domain and based on the mapping relationship between the preset grid space and the antenna propagation path, fast confocal superposition and geometric attenuation compensation of multi-frequency and multi-antenna signals are realized. This significantly improves the image reconstruction speed in the actual detection process and greatly enhances the spatial resolution of the target image, providing a geometric benchmark for subsequently determining the feature attributes of the bleeding area.

[0192] In some embodiments, the processor 73 is specifically configured to determine the target temporal feature signal containing only brain tissue by: determining the thickness of the matching medium between the antenna transmitting and receiving microwave signals and the scalp of the brain based on the scattering signal from the antenna's reflection port, and obtaining the dielectric constant of the matching medium; determining the transmission time of the electromagnetic wave through the matching medium based on the thickness and dielectric constant of the matching medium; converting the brain's feature information from the frequency domain to the time domain using an inverse Fourier transform to obtain a time-domain microwave signal; determining the parameter configuration of a preset window function based on the transmission time to determine the target window function; and determining the target temporal feature signal containing only brain tissue based on the target window function and the time-domain microwave signal.

[0193] In such an embodiment, since the matching medium is the region through which electromagnetic waves pass first in the time domain, as long as the transmission time of the electromagnetic waves through the matching medium is determined, the target time domain feature signal containing only brain tissue can be determined based on the characteristic information of the cranium and the transmission time. This greatly filters out and completely removes the influence of the matching medium on the microwave signal in the time domain, making the hemorrhage area displayed in the final imaging result clearer and the pixel clutter less.

[0194] See Figure 16 and Figure 17 , Figure 16 This is a schematic diagram of the original time-domain signal of interference clutter without stripping the matching medium between the antenna array and the brain. Figure 17This is a schematic diagram of the target time-domain characteristic signal after removing interference clutter from the matching medium between the antenna array and the brain according to the method of embodiments of this application. Figure 16 As can be seen, the original time-domain signal contains interference clutter 301 from the matched medium and microwave signals 302 from the brain tissue; from Figure 17 As can be seen from the method of this embodiment, the interference clutter 301 of the matching medium on one side of the time-domain truncated window 303 has been removed, and the target time-domain feature signal 304 only contains the microwave signal of the cranial tissue on the other side of the time-domain truncated window 303. Compared with the microwave signal 302 of the cranial tissue in the original time-domain signal, the microwave signal of the cranial tissue represented by the target time-domain feature signal 304 after removing the interference clutter 301 of the matching medium is clearer.

[0195] See Figure 18 and Figure 19 , Figure 18 This is a schematic diagram of cranial imaging results obtained without removing interference clutter from the matching medium in the time domain; Figure 19 This is a schematic diagram of the brain imaging results obtained after removing interference clutter from the matching medium in the time domain. Figure 18 and Figure 19 The magnified image shows the bleeding area. As can be seen from the image, the imaging quality is higher after removing the interference clutter from the matching medium. The bleeding area in the imaging result is clearer, and there are fewer clutter points in the pixels.

[0196] In some embodiments, the processor 73 is specifically configured to determine the multidimensional spatial grid coordinate matrix by: obtaining the initial values ​​of the radius and angle of the transceiver antenna array and the average dielectric constant of electromagnetic waves propagating in the cranium; determining the spatial coordinate position of each antenna based on the initial values ​​of the radius and angle of the transceiver antenna array; determining the grid points of the imaging region based on the spatial coordinate positions of each antenna; and generating a multidimensional spatial grid coordinate matrix representing the spatial geometry and the average dielectric properties of the cranium based on the grid points of the imaging region and the average dielectric constant.

[0197] In this embodiment, by introducing the physical topology parameters of the transceiver antenna array to establish a standardized grid space, a precise geometric reference can be provided for the subsequent confocal energy superposition process, effectively preventing imaging distortion caused by the stretching and deformation of the headgear 20; when generating the multidimensional spatial grid coordinate matrix, the average dielectric constant of electromagnetic waves propagating in the cranium can be considered, which can avoid the estimation deviation of wave velocity caused by dielectric properties, ensuring the accuracy of subsequent time delay alignment and preventing defocusing or offset in imaging.

[0198] See Figure 20 and Figure 21 , Figure 20 This is a schematic diagram of cranial imaging results obtained without utilizing a standardized grid space. Figure 21This is a schematic diagram of cranial imaging results obtained according to a standardized grid space in an embodiment of this application. Figure 20 and Figure 21 The image shows the hemorrhage area in the brain. As shown in the figure, the brain imaging results obtained by utilizing the standardized grid space of this application embodiment, i.e., the multi-dimensional spatial grid coordinate matrix, are more realistic and the location of the hemorrhage area is more accurate.

[0199] In some embodiments, the processor 73 is specifically configured to determine the transmission distance of each pair of transceiver antennas at each grid point by: traversing each frequency sampling point in the full frequency domain based on the characteristic information of the cranium, and determining the spatial wavenumber corresponding to each frequency point, wherein the full frequency domain is the full frequency domain of the microwave signal frequency band acquired by the signal transmission and acquisition component; determining the transmission distance of the microwave signal propagating in each pair of transceiver antennas to each grid point by traversing each pair of transceiver antennas and using a multi-dimensional spatial grid coordinate matrix, based on the average dielectric constant of the electromagnetic wave propagating in the cranium and the spatial wavenumber corresponding to each frequency point; determining the propagation speed of the microwave in the cranium based on the average dielectric constant, and determining the delay time of the microwave signal propagating in each pair of transceiver antennas to each grid point based on the transmission distance and the propagation speed.

[0200] In such an embodiment, by determining the propagation path of each pair of transceiver antennas in the grid space and determining the spatial wavenumber corresponding to each frequency point in the full frequency domain, the phase change of microwaves in brain tissue can be accurately captured, thereby effectively correcting the signal delay error caused by multi-layer complex reflections; by using the spatial grid method, the path relationship between each grid coordinate and the antenna can be determined in advance, thereby improving the imaging speed in actual imaging.

[0201] In some embodiments, the full frequency range is from 0.5 GHz to 2.5 GHz.

[0202] In some embodiments, the processor 73 is specifically configured to determine an image of the intracranial tissue by: performing time-delay alignment on a target temporal feature signal containing only brain tissue based on the transmission distance and delay time of each pair of transceiver antennas at each grid point, and the average dielectric constant of electromagnetic waves propagating in the brain, to determine the initial signal strength of each pair of transceiver antennas at each grid point; determining an attenuation compensation weighting value for the initial signal strength at each grid point based on the transmission distance; determining a signal strength map based on the initial signal strength and the attenuation compensation weighting value; and mapping the signal strength map to a spatial grid corresponding to a multidimensional spatial grid coordinate matrix to determine an image of the intracranial tissue.

[0203] In this embodiment, since the target time-domain feature signal is obtained from the frequency-domain feature information through inverse Fourier transform, it contains scattering information in the entire frequency domain. Therefore, performing time delay alignment and attenuation compensation weighting on the target time-domain feature signal is actually coherently superimposing the scattering information of these microwave signals of different frequencies in the spatial domain, thereby ensuring high image resolution and improving the accuracy of imaging results. By implementing gain weighting on the energy contribution of different antenna channels according to the transmission distance of each pair of transceiver antennas at each grid point, the energy attenuation defect of microwaves when propagating to deep layers in lossy brain media is compensated for, thereby improving the spatial resolution of the image.

[0204] In some embodiments, the processor 73 is specifically configured to determine the category of the microwave signal of the brain by: determining the clutter region features and hemorrhage region features of the brain based on the feature information of the brain; determining the decoupled hemorrhage region features through adversarial learning based on the clutter region features and the hemorrhage region features; and determining the category of the microwave signal of the brain based on the decoupled hemorrhage region features.

[0205] In such an embodiment, clutter region features and hemorrhage region features are extracted from the feature information of the cranium, which can separate the two types of features in the coding space. By applying decoupling constraints to clutter region features and hemorrhage region features through adversarial learning, residual clutter components in hemorrhage region features can be suppressed, thereby improving the accuracy of microwave signal category determination.

[0206] In some embodiments, the processor 73 is specifically configured to determine the clutter region features and hemorrhage region features of the cranium by encoding the cranium feature information toward the clutter information to determine the clutter region features in the feature information; and encoding the cranium feature information toward the hemorrhage information to determine the hemorrhage region features in the feature information.

[0207] See Figure 22 and Figure 23 , Figure 22 This is a schematic diagram showing the result of independently encoding the feature information of the cranium according to an embodiment of this application. Figure 23 This is a schematic diagram illustrating the result of single encoding of the cranial feature information. As can be seen from the diagram, in such an embodiment, the clutter signal and hemorrhage signal obtained by single encoding of the feature information overlap and are difficult to distinguish. However, the method according to the embodiments of this application independently encodes the cranial feature information, which enables the clutter region features representing background clutter scattering and the hemorrhage region features representing hemorrhage region scattering to be clustered separately in the encoding space. This avoids the overlap of clutter signals and hemorrhage signals in single encoding, thereby providing a basis for subsequent decoupling of the two features.

[0208] In some embodiments, the processor 73 is specifically configured to determine the decoupled bleed region features by: determining a feature correlation measure between the clutter region features and the bleed region features based on the clutter region features and the bleed region features; determining an adversarial loss function based on the feature correlation measure, wherein the adversarial loss function is used to constrain the bleed region features and the clutter region features to be independent of each other in the feature space; performing adversarial training on the encoding process based on the adversarial loss function, so that the clutter region features and the bleed region features are orthogonal to each other; and determining the decoupled bleed region features based on the encoding process after adversarial training.

[0209] In such an embodiment, by constructing an adversarial loss function to impose orthogonality constraints on clutter region features and bleeding region features, the background scattering component represented by clutter region features in the encoded output bleeding region features can be excluded; through the adversarial training mechanism, the encoding process focuses on modeling its corresponding feature space during the game, thereby improving the ability of the decoupled bleeding region features to distinguish the bleeding state.

[0210] See Figure 24 and Figure 25 , Figure 24 This is a schematic diagram showing the result of training the encoding process according to the method provided in the embodiments of this application. Figure 25 This is a schematic diagram of clutter region features and bleeding region features obtained through the adversarial training encoding process according to an embodiment of this application. Figure 24 As shown, with the increase in adversarial training rounds, the feature correlation between the hemorrhage region features and the clutter region features gradually decreases, while the accuracy of category judgment gradually increases. Figure 25 As shown, after adversarial training of the encoding process, clutter region features and bleeding region features are orthogonally separated, which facilitates the separation of decoupled bleeding region features.

[0211] In some embodiments, the processor 73 is specifically configured to determine the category of the microwave signal of the brain by: determining a logical value of the bleeding category through linear transformation based on the bleeding region characteristics of the decoupled target region; determining the probability of bleeding based on the logical value; and determining the category of the microwave signal of the brain based on the probability of bleeding.

[0212] In such an embodiment, by performing a linear transformation on the decoupled hemorrhage region features and mapping them to a probability distribution, the hemorrhage region features can be transformed into a quantifiable basis for classifying the category; since the hemorrhage region features have been freed from clutter interference through adversarial learning, the hemorrhage probability can more accurately reflect the true hemorrhage state of the brain.

[0213] Regarding the embodiments of this application, it should also be noted that, without conflict, the embodiments of this application and the features in the embodiments can be combined with each other to obtain new embodiments.

[0214] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. The scope of protection of this application shall be determined by the scope of the claims.

Claims

1. A device for detecting intracranial hemorrhage, characterized in that, include: seat body; The receiving section forms a space to accommodate the patient's skull; A headgear, disposed in the receiving space, is configured to be used to fill a liquid dielectric and to be deformable under pressure; The signal transmission and acquisition component is used to transmit microwave signals to the headgear and receive microwave signals from the headgear, thereby determining the intracranial hemorrhage situation based on the transmitted and received microwave signals. The mounting components are configured to integrate the receiving portion and the signal transmission and acquisition components into the base.

2. The apparatus according to claim 1, characterized in that, The signal transmission and acquisition component includes: Vector network analyzer, port expansion unit, and multiple antennas; The vector network analyzer is configured to send microwave signals to the port extender, receive microwave signals from the port extender, and analyze the received microwave signals. The port extender is configured to extend the port of the vector network analyzer, receive the microwave signal sent by the vector network analyzer, and transmit the microwave signal to one of the antennas; and receive a corresponding microwave signal from the other antenna and transmit the microwave signal to the vector network analyzer. The antenna is disposed on the outside of the headgear in the receiving portion and is configured to receive microwave signals from the port extension and transmit the microwave signals to the headgear; or, receive microwave signals emitted by another antenna from the headgear and transmit the microwave signals to the port extension.

3. The detection device according to claim 2, characterized in that, The installation components include: A first mounting component is configured to integrate the receiving portion, the port extension, and the vector network analyzer into the base; A second mounting member and a third mounting member are configured to fix the receiving portion relative to the seat body at a predetermined distance in the height direction.

4. The detection device according to claim 3, characterized in that, The first installation component includes: A first mounting component is disposed on the base body, the port expansion component and the vector network analyzer are mounted opposite each other on both sides of the first mounting component, the receiving portion is connected to the first mounting component on the side where the port expansion component is located, and the port expansion component is disposed between the receiving portion and the vector network analyzer; An auxiliary mounting component is disposed on the base and connected to the first mounting component, and is configured to clamp the vector network analyzer between the auxiliary mounting component and the first mounting component.

5. The detection device according to claim 4, characterized in that, The auxiliary mounting components include: The main body is configured to fit against the surface of the vector network analyzer that is away from the first mounting member, and has a flange that bends toward the first mounting member to clamp and limit the vector network analyzer. A connecting portion is configured to connect to the flange of the main body and to the first mounting member, thereby connecting the main body and the first mounting member and clamping the vector network analyzer between the main body and the first mounting member.

6. The detection device according to claim 4, characterized in that, The second mounting component and the third mounting component are disposed on the base body; The side of the receiving portion facing the port extension is connected to the second mounting member, and the side of the receiving portion away from the port extension is connected to the third mounting member.

7. The detection device according to claim 6, characterized in that, The receiving part includes a mounting receiving part, a neck support part, and a mounting mating part; The mounting and receiving part forms the receiving space, the receiving space having an opening for the patient's brain to enter and exit, the mounting and receiving part is also configured to mount the headgear in the receiving space, and configured to mount the antenna; The neck support is connected to the opening of the mounting and receiving part and is used to support the patient's neck; The mounting fitting part is disposed on the side of the mounting receiving part opposite to the opening, and is configured to cooperate with the first mounting member and the second mounting member to connect the mounting receiving part with the first mounting member and the second mounting member.

8. The apparatus according to claim 7, characterized in that, The neck support is disposed above the third mounting member and is connected to the third mounting member.

9. The detection device according to claim 8, characterized in that, The mounting and fitting part includes: The main mounting part is disposed in the mounting receiving part; A reinforcing part is provided on the mounting body to improve the strength of the mounting body; A first connecting and mating part is disposed on the mounting body part and extends toward the first mounting member; The second connecting and mating part is disposed on the mounting body part and is configured to extend in a direction perpendicular to the extending direction of the first connecting and mating part; The first connecting part is configured to engage with a fastener passing through the first mounting member to connect the mounting body part to the first mounting member; the second connecting part is configured to engage with a fastener passing through the second mounting member to connect the mounting body part to the second mounting member.

10. The detection device according to claim 9, characterized in that, There are multiple second mounting components, which are disposed opposite to each other on both sides of the mounting body.

11. The detection device according to any one of claims 1-10, characterized in that, Also includes: The processor is communicatively connected to the signal transmission and acquisition component and is used to receive and process the microwave signals of the brain acquired by the signal transmission and acquisition component.

12. The detection device according to claim 11, characterized in that, The processor is configured as follows: Receives microwave signals from the brain acquired by the signal transmitting and acquiring component; The noise of the microwave signal is filtered out, and the microwave signal after noise filtering is normalized to determine the normalized microwave signal. Based on the normalized microwave signal, the characteristic information of the cranium is determined; Based on the characteristic information of the cranium, an image of the cranium is reconstructed, and the image provides spatial location information, morphological information and energy intensity information of the hemorrhage area of ​​the cranium; Based on the characteristic information of the cranium, the category of microwave signals of the cranium is determined; Based on the image and the type of microwave signal from the brain, the characteristic attributes of the hemorrhage area in the brain are determined.

13. The detection device according to claim 12, characterized in that, The processor is configured to store a preset number of cranial microwave signals from healthy samples, which are pre-acquired using the signal transmission and acquisition component. The processor is specifically configured to filter out noise from the microwave signal and normalize the noise-filtered microwave signal in the following manner: Based on the microwave signal of the brain acquired by the signal transmission and acquisition component and the microwave signal of the brain of a preset number of healthy samples stored in the processor, the microwave signal after noise filtering is determined. Based on the microwave signal after noise removal, the normalized microwave signal is determined.

Images