Fat quantification method and device

Abstract

The invention relates to a fat quantification method and device, and belongs to the technical field of medical treatment. The fat quantification method comprises the following steps: acquiring a scanning image of a to-be-detected part; based on the scanning image, determining a fat area and a soft tissue area of the to-be-detected part; based on the scanning image, determining an attenuation coefficient of the to-be-detected part, the attenuation coefficient indicating an attenuation degree of the scanning ray in a process of scanning the to-be-detected part; and determining the fat content of the to-be-detected part based on the attenuation coefficient of the to-be-detected part, the fat region and the soft tissue region. According to the method, an accurate fat quantification result can be obtained while the injury to a human body is reduced.

Description

Technical Field

[0002] The present invention relates to the field of medical technology, and particularly to a method and device for fat quantification. Background Art

[0004] Fat quantification plays a crucial role in multiple medical fields such as metabolic disorders, cardiovascular risk assessment, and cancer research. Non-invasive and accurate measurement of fat content in human tissues is crucial for disease diagnosis, determining treatment plans, and health monitoring.

[0005] Existing imaging methods, such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging), can represent fat content alternatively through parameters such as ray attenuation or relaxation characteristics. However, due to the influence of partial volume effects, tissue heterogeneity, etc. in these imaging methods, and the lack of standardized calculation methods, their quantification accuracy is usually low, and accurate fat content cannot be obtained.

[0006] The methods described in this section are not necessarily methods that have been previously envisioned or adopted. Unless otherwise specified, no method described in this section should be considered a related art solely because it is included in this section. Similarly, unless otherwise specified, the problems mentioned in this section should not be considered to have been recognized in any related art. Summary of the Invention

[0008] In view of this, according to the first aspect of the present disclosure, a method for fat quantification is proposed, including: obtaining a scanned image of a part to be detected; determining a fat region and a soft tissue region of the part to be detected based on the scanned image; determining an attenuation coefficient of the part to be detected based on the scanned image, where the attenuation coefficient indicates the attenuation degree of the scanned ray during the scanning of the part to be detected; and determining the fat content of the part to be detected based on the attenuation coefficient, fat region, and soft tissue region of the part to be detected.

[0009] According to the second aspect of the present disclosure, a device for fat quantification is proposed, including: an acquisition module for obtaining a scanned image of a part to be detected; a region determination module for determining a fat region and a soft tissue region of the part to be detected based on the scanned image; an attenuation coefficient determination module for determining an attenuation coefficient of the part to be detected based on the scanned image, where the attenuation coefficient indicates the attenuation degree of the scanned ray during the scanning of the part to be detected; and a fat content determination module for determining the fat content of the part to be detected based on the attenuation coefficient, fat region, and soft tissue region of the part to be detected.

[0010] According to one or more embodiments of the present disclosure, scanned images can be used to accurately determine the fat content of the part to be detected, and it can be applicable to different parts and different imaging modalities. Through non-invasive detection methods, while reducing the damage to the human body, accurate fat quantification results are obtained, improving the accuracy of the detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings, so that those of ordinary skill in the art can more clearly understand the above and other features and advantages of the present invention. In the drawings:

[0013] Figure 1 is a schematic flowchart of a fat quantification method according to some embodiments of the present disclosure;

[0014] Figure 2 is a schematic flowchart of determining a fat region and a soft tissue region according to some embodiments of the present disclosure;

[0015] Figure 3 is a schematic flowchart of determining the attenuation coefficient of the part to be detected according to some embodiments of the present disclosure;

[0016] Figure 4 is a schematic flowchart of determining the fat content of the part to be detected according to some embodiments of the present disclosure;

[0017] Figure 5 is a schematic block diagram of a fat quantification device according to some embodiments of the present disclosure;

[0018] Figure 6 is a schematic block diagram of a computing device according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to have a clearer understanding of the technical features, objectives, and effects of the present invention, the specific embodiments of the present invention will now be described with reference to the accompanying drawings. In the figures, the same reference numerals denote the same parts.

[0021] In this document, "schematic" means "serving as an example, instance, or illustration", and any illustration or embodiment described as "schematic" in this document should not be construed as a more preferred or more advantageous technical solution.

[0022] For the sake of simplicity of the drawings, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product. Additionally, for the sake of simplicity and ease of understanding of the drawings, in some figures, only one of the components with the same structure or function is schematically shown, or only one of them is labeled.

[0023] In this document, "a" not only means "only one", but can also mean "more than one". In this document, "first", "second", etc. are only used to distinguish from each other, rather than indicating their importance, order, and the prerequisite for each other's existence, etc.

[0024] Fat quantification plays a crucial role in many medical fields such as metabolic disorders, cardiovascular risk assessment, and cancer research. Accurate non-invasive measurement of fat content in human tissues is crucial for disease diagnosis, treatment plan determination, and health monitoring.

[0025] Existing imaging methods, such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging), can alternatively represent fat content through parameters such as ray attenuation or relaxation characteristics. However, these imaging methods are often affected by partial volume effects, tissue heterogeneity, etc., and lack standardized calculation methods. Their quantification accuracy is usually low, and accurate fat content cannot be obtained. For example, for CT, fat content can be alternatively represented by CT value, also known as Hounsfield - Units (HU for short). However, CT can usually only make indirect estimates, and this representation method also depends on some predefined thresholds. For example, if the CT value of the liver is greater than a predetermined threshold, fatty liver is considered. This may lead to its inability to fully identify the differences between different humans or different tissues and cannot obtain accurate fat quantification results. For MRI, it can distinguish between fat and water, but this detection method is easily restricted by technology. For example, the detection results may be affected by interference factors such as sensitivity artifacts. In addition, it may also be affected by motion sensitivity.

[0026] In the prior art, in order to obtain accurate fat quantification results, usually only invasive biopsy can be used to directly analyze the fat content through histological analysis. However, since this method is invasive, it poses certain risks to the human body and is not suitable for routine monitoring and large-scale applications.

[0027] Therefore, the fat quantification method provided by the present disclosure can be used. This method is non-invasive and can be applied to different parts and different imaging methods. After obtaining the scanned image of the part to be detected, the accurate fat content of this part can be analyzed based on the scanned image, reducing the damage to the human body while obtaining accurate fat quantification results and improving the accuracy of the detection results.

[0028] The exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0029] An embodiment of the present disclosure provides a fat quantification method. Refer to Figure 1 , the fat quantification method 100 includes steps 110 to 140.

[0030] Step 110, obtaining a scanned image of the part to be detected.

[0031] Step 120, based on the scanned image, determining the fat region and soft tissue region of the part to be detected.

[0032] Step 130, based on the scanned image, determining the attenuation coefficient of the part to be detected. The attenuation coefficient indicates the attenuation degree of the scanning ray during the scanning of the part to be detected.

[0033] Step 140, based on the attenuation coefficient, fat region and soft tissue region of the part to be detected, determining the fat content of the part to be detected.

[0034] In step 110, a scanned image of any part to be detected in the human body (such as: liver, pancreas, muscle, etc.) can be obtained. The scanned image can be obtained by a variety of imaging methods, for example, it can be obtained by CT, DECT (Dual-Energy CT, abbreviated as dual-energy CT), etc. This fat quantification method can be applied to images generated by a variety of imaging methods, can adapt to different usage scenarios, and greatly improves the versatility.

[0035] In some embodiments, in order to improve the accuracy of the analysis results, a standardized protocol for obtaining images can be formulated in advance, such as some standardized CT image acquisition methods, using a pre-determined resolution during imaging, etc. When performing step 110, referring to these standardized protocols, which facilitates the subsequent processing process and improves the accuracy of the analysis results.

[0036] Since in the scanned image, different structures in human tissues (such as: fat, soft tissue, bone, etc.) will show different display effects, therefore, in step 120, the different regions of the part to be detected can be determined according to the obtained scanned image. Among them, fat and soft tissue have a relatively important impact on the determination of fat content. Therefore, in step 120, the fat region and soft tissue region of the part to be detected can be determined.

[0037] In some embodiments, step 120 includes: based on the scanned image, using an artificial intelligence algorithm to segment the part to be detected to obtain the fat region and soft tissue region.

[0038] In this step, an artificial intelligence algorithm can be used to segment the part to be detected into predefined regions, such as dividing it into a fat region, a soft tissue region, other component regions, etc. In one example, a pre-trained image processing model can be used to segment the scanned image. During the training process, the model optimizes the segmentation performance by learning the relationship between image features and tissue categories. During the segmentation process, the scanned image can be preprocessed, including operations such as removing background noise, adjusting image contrast, and normalization. After that, feature extraction can be further performed, which is used as the input of the image processing model, and the image processing model outputs the segmentation result.

[0039] By using an artificial intelligence-driven algorithm to achieve the segmentation of the part to be detected, the robustness and repeatability of the segmentation process can be enhanced, making it applicable to different usage scenarios.

[0040] In some embodiments, referring to Figure 2 , step 120 includes steps 210 to 220.

[0041] Step 210, based on the scanned image, determine the Hounsfield Unit of the part to be detected.

[0042] Step 220, according to the Hounsfield Unit of the part to be detected, determine the fat region and soft tissue region of the part to be detected.

[0043] The Hounsfield Unit (HU) is a measurement unit used to represent the relative density of human tissues or organs in computed tomography scan images. For CT images, it can also be referred to as the CT value.

[0044] The following takes the scanned image as a CT image as an example for illustration:

[0045] For different tissue regions of the human body, they usually have different CT values in CT images. For example, the CT value of fat is about -50HU to -100HU, the CT value of muscle is about +40HU to +50HU, and the CT value of bone has a large range of variations with different densities of bone. The CT value of normal bone is usually between +700HU and +3000HU.

[0046] Therefore, the CT value (i.e., the Hounsfield Unit) of the part to be detected can be obtained from the scanned image, and further, based on the CT values at different positions, the fat region and soft tissue region can be segmented. In some embodiments, steps 210 and 220 can also be implemented in combination with an artificial intelligence algorithm. For example, an artificial intelligence algorithm can be used to determine the fat region and soft tissue region according to the Hounsfield Unit of the part to be detected.

[0047] In some embodiments, referring to Figure 3, step 130 includes steps 310 to 320.

[0048] Step 310, based on the scanned image, determine the Hounsfield unit of the part to be detected.

[0049] Step 320, based on the predetermined attenuation coefficient and the Hounsfield unit of the part to be detected, determine the attenuation coefficient of the part to be detected. The predetermined attenuation coefficient indicates the attenuation coefficient of water.

[0050] In the embodiments herein, the attenuation coefficient is the linear attenuation coefficient of the substance, which can indicate the attenuation degree of the scanning ray during the scanning of the part to be detected. Taking CT scanning as an example, the attenuation coefficient can directly reflect the attenuation degree of the X-ray. When calculating the attenuation coefficient of the part to be detected, the attenuation coefficient corresponding to the Hounsfield unit of the part to be detected can be calculated based on the predetermined attenuation coefficient, that is, the attenuation coefficient of water.

[0051] Similar to step 210, in step 310, the Hounsfield unit of the part to be detected can also be determined according to the scanned image.

[0052] In some embodiments, step 320 includes:

[0053] Determine the attenuation coefficient of the part to be detected according to the following formula:

[0054]

[0055] where, is the attenuation coefficient of the part to be detected, is the Hounsfield unit of the part to be detected, is the predetermined attenuation coefficient.

[0056] After obtaining the attenuation coefficient of the part to be detected, the fat content of the part to be detected can be further calculated according to the attenuation coefficient and the distributions of the fat area and the soft tissue area obtained in step 120.

[0057] In some embodiments, referring to Figure 4 , step 140 includes steps 410 to 420.

[0058] Step 410, based on the attenuation coefficient, fat area and soft tissue area of the part to be detected, determine the correspondence between the attenuation coefficient of the part to be detected and the fat attenuation coefficient and the soft tissue attenuation coefficient. The fat attenuation coefficient indicates the attenuation coefficient of the fat area. The soft tissue attenuation coefficient indicates the attenuation coefficient of the soft tissue area.

[0059] Step 420, based on the correspondence, determine the fat content of the part to be detected.

[0060] The attenuation coefficient of each part can be regarded as a linear combination of the contributions of the attenuation coefficient of fat and the attenuation coefficient of soft tissue. Therefore, in step 410, the attenuation coefficient of the part to be detected can be expressed as a combination between the attenuation coefficient of the fat region and the attenuation coefficient of the soft tissue in this part.

[0061] In some embodiments, step 410 includes:

[0062] Determine the corresponding relationship between the attenuation coefficient of the part to be detected, the attenuation coefficient of fat, and the attenuation coefficient of soft tissue according to the following formula:

[0063] ,

[0064] where, is the attenuation coefficient of the part to be detected, is the attenuation coefficient of fat, is the attenuation coefficient of soft tissue, is the fat content of the part to be detected.

[0065] In the formula, the attenuation coefficient of fat and the attenuation coefficient of soft tissue can be determined according to the typical values of normal people. The typical values of the attenuation coefficient of fat and the typical values of the attenuation coefficient of soft tissue can be obtained from the existing knowledge in this field and will not be elaborated here.

[0066] In some embodiments, it can also be adjusted according to different humans or different parts. For example, for the elderly and children, different adjustments can be made based on the typical values; for different parts on the same human body, different adjustments can also be made based on the typical values. In one example, continuing to take the scanned image as a CT image to illustrate the adjustment process, taking the attenuation coefficient of fat as an example, part or all of the regions can be selected in the fat region obtained in step 120. As described above, there is a specific relationship between the CT value and the attenuation coefficient. For example, it can be expressed by the formula above. Therefore, according to this formula, can be set as the CT value of this selected region, and is set as . According to the CT value of this selected region in the CT image, the adjusted attenuation coefficient of fat can be calculated to achieve the adjustment for different humans or different parts. Similarly, part or all of the regions can be selected in the soft tissue region obtained in step 120, and according to the CT value of this selected region in the CT image, the adjusted attenuation coefficient of soft tissue can be calculated to achieve the adjustment for different humans or different parts. By adjusting the attenuation coefficient of fat and the attenuation coefficient of soft tissue Adjustments can be made so that the method can be adjusted according to different tissue characteristics, optimized for different populations, and the accuracy of the analysis results can be improved.

[0067] In some embodiments, step 420 includes:

[0068] Determine the fat content of the part to be detected according to the following formula:

[0069] ,

[0070] where, is the attenuation coefficient of the part to be detected, is the fat attenuation coefficient, is the soft tissue attenuation coefficient, is the fat content of the part to be detected.

[0071] By segmenting the part to be detected to obtain the fat area and the soft tissue area, according to the segmentation result, the attenuation coefficient of the part to be detected is represented by a combination between the fat attenuation coefficient and the soft tissue attenuation coefficient, and by combining the attenuation coefficient with tissue analysis, accurate fat quantification can be achieved.

[0072] In some embodiments, the fat quantification method 100 further includes: generating a fat distribution map of the part to be detected based on the fat content of the part to be detected.

[0073] After obtaining the fat content of the part to be detected, further visualization operations can be performed on it to display the fat distribution of the part to be detected, which is convenient for intuitively observing the fat content. In some embodiments, the fat distribution map may further include content such as the percentage data of the volume and / or mass of the fat in the entire part to be detected, quantitative insights into the local fat content and the whole body fat content, and the comparison results of the fat distribution of the part to be detected with a specific population reference range.

[0074] Based on the same technical concept, an embodiment of the present application provides a fat quantification device. The embodiments of the fat quantification device can refer to the embodiments of the fat quantification method, and the repeated parts will not be described again. Refer to Figure 5 , the fat quantification device 500 includes an acquisition module 510, a region determination module 520, an attenuation coefficient determination module 530, and a fat content determination module 540.

[0075] The acquisition module 510 is used to acquire a scanned image of the part to be detected.

[0076] The region determination module 520 is used to determine the fat region and the soft tissue region of the part to be detected based on the scanned image.

[0077] The attenuation coefficient determination module 530 is configured to determine the attenuation coefficient of the part to be detected based on the scanned image. The attenuation coefficient indicates the attenuation degree of the scanned ray during the scanning of the part to be detected.

[0078] The fat content determination module 540 is configured to determine the fat content of the part to be detected based on the attenuation coefficient of the part to be detected, the fat region, and the soft tissue region.

[0079] The acquisition module 510, the region determination module 520, the attenuation coefficient determination module 530, and the fat content determination module 540 in the fat quantification device 500 may correspond to steps 110 to 140 in the fat quantification method 100. For the sake of brevity, they will not be elaborated here. It should be understood that corresponding to the embodiments of the fat quantification method 100, the embodiments of the fat quantification device 500 may further include more modules.

[0080] It should be noted that the functions of the various modules discussed herein can be divided into multiple modules, and / or at least some functions of multiple modules can be combined into a single module. The specific module that performs an action includes the specific module itself performing the action, or alternatively the specific module calling or otherwise accessing another component or module that performs the action (or performs the action in combination with the specific module). Therefore, the specific module that performs an action may include the specific module itself that performs the action and / or another module that the specific module calls or otherwise accesses and performs the action.

[0081] It should also be understood that various technologies can be described herein in the general context of software-hardware elements or program modules. The various modules described above Figure 5 can be implemented in hardware or in hardware combined with software and / or firmware. For example, these modules can be implemented as computer program code / instructions that are configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these modules can be implemented as hardware logic / circuits. The hardware logic / circuits may include an integrated circuit chip (which includes one or more components such as a processor (e.g., a Central Processing Unit (CPU), a microcontroller, a microprocessor, a Digital Signal Processor (DSP), etc.), a memory, one or more communication interfaces, and / or other circuits), and may optionally execute the received program code and / or include embedded firmware to perform functions.

[0082] An embodiment of the present application provides a computing device 600, as Figure 6 shown. Figure 6An example configuration of a computing device 600 that can be used to implement the fat quantification method 100 described herein is shown. For example, the above-described fat quantification device 500 can be implemented in whole or at least in part by the computing device 600 or a similar device or system.

[0083] The computing device 600 can include at least one processor 605, a memory 607, one or more communication interfaces 602, a display device 601, other input / output (I / O) devices 603, and one or more mass storage devices 606 that can communicate with each other, such as via a bus 604 or other suitable connections. Instructions are stored on the memory 607, and when executed by the processor 605, the instructions cause the processor 605 to execute the fat quantification method as in the above embodiments.

[0084] The computing device 600 can be various different types of devices. Examples of the computing device 600 include, but are not limited to: desktop computers, server computers, laptop or netbook computers, mobile devices (e.g., tablets, cellular or other wireless phones (e.g., smartphones), notepad computers, mobile stations), wearable devices (e.g., glasses, watches), entertainment devices (e.g., entertainment appliances, set-top boxes communicatively coupled to a display device, game consoles), televisions or other display devices, automotive computers, and so on.

[0085] The processor 605 can be a single processing unit or multiple processing units, and all processing units can include a single or multiple computing units or multiple cores. The processor 605 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operation instructions. Among other capabilities, the processor 605 can be configured to obtain and execute computer-readable instructions stored in the memory 607, the mass storage device 606, or other computer-readable media, such as program code of an operating system 608, program code of an application 609, program code of other programs 610, and so on.

[0086] Memory 607 and mass storage device 606 are examples of computer-readable storage media for storing instructions that are executed by processor 605 to implement the various functions described above. For example, memory 607 generally can include both volatile and non-volatile memory (e.g., RAM, ROM, etc.). In addition, mass storage device 606 generally can include a hard disk drive, a solid state drive, removable media, including external and removable drives, memory cards, flash memory, floppy disks, optical disks (e.g., CD, DVD), storage arrays, network attached storage, storage area network, etc. Memory 607 and mass storage device 606 can both be collectively referred to herein as memory or computer-readable storage media, and can be non-transitory media capable of storing computer-readable, processor-executable program instructions as computer program code that can be executed by processor 605 as a particular machine configured to implement the operations and functions described in the examples herein.

[0087] Multiple programs can be stored on mass storage device 606. These programs include operating system 608, one or more application programs 609, other programs 610, and program data 611, and they can be loaded into memory 607 for execution. Examples of such application programs or program modules can include, for example, computer program logic (e.g., computer program code or instructions) for implementing the following components / functions: fat quantification device 500 (including acquisition module 510, region determination module 520, attenuation coefficient determination module 530, and fat content determination module 540), fat quantification method 100 (including any suitable steps of fat quantification method 100), and / or additional embodiments described herein.

[0088] Although illustrated as being stored in memory 607 of computing device 600 in Figure 6 , operating system 608, application programs 609, other programs 610, and program data 611, or portions thereof, can be implemented using any form of computer-readable medium accessible by computing device 600.

[0089] One or more communication interfaces 602 are used to exchange data with other devices, such as via a network, a direct connection, and so on. Such communication interfaces can be one or more of the following: any type of network interface (e.g., network interface card (NIC)), wired or wireless (such as IEEE 802.11 wireless local area network (WLAN)) wireless interface, Worldwide Interoperability for Microwave Access (WiMAX) interface, Ethernet interface, Universal Serial Bus (USB) interface, cellular network interface, BluetoothTM interface, Near Field Communication (NFC) interface, etc. The communication interface 602 can facilitate communication within a variety of network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, and so on. The communication interface 602 can also provide communication with external storage devices (not shown) such as in storage arrays, network-attached storage, storage area networks, and so on.

[0090] In some examples, a display device 601 such as a monitor can be included for displaying information and images to a user. Other I / O devices 603 can be devices that receive various inputs from a user and provide various outputs to the user, and can include touch input devices, gesture input devices, cameras, keyboards, remote controls, mice, printers, audio input / output devices, and so on.

[0091] The techniques described herein can be supported by these various configurations of the computing device 600 and are not limited to the specific examples of the techniques described herein. For example, the functionality can also be implemented in whole or in part on a "cloud" using a distributed system. The cloud includes and / or represents a platform for resources. The platform abstracts the underlying functionality of the hardware (e.g., servers) and software resources of the cloud. Resources can include applications and / or data that can be used when performing computing processing on servers remote from the computing device 600. Resources can also include services provided via the Internet and / or via a subscriber network such as a cellular or Wi-Fi network. The platform can abstract the resources and functionality to connect the computing device 600 with other computer devices. Thus, the implementation of the functionality described herein can be distributed throughout the cloud. For example, the functionality can be implemented partially on the computing device 600 and partially via a platform that abstracts the functionality of the cloud.

[0092] Embodiments of the present application also provide a computer-readable storage medium having instructions stored thereon that, when executed alone or jointly by one or more processors of a computing device, cause the computing device to perform the methods in any of the above embodiments.

[0093] A computer-readable storage medium includes volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. The computer-readable storage medium includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD), or other optical storage devices, magnetic cartridges, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by a computer device.

[0094] An embodiment of the present application further provides a computer program product, including instructions that, when executed alone or jointly by one or more processors of a computing device, cause the computing device to execute the method in any of the above embodiments.

[0095] The above are only embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A fat quantification method, comprising: Obtaining a scanned image of a part to be detected; Based on the scanned image, determining the fat region and soft tissue region of the part to be detected; Based on the scanned image, determining the attenuation coefficient of the part to be detected, where the attenuation coefficient indicates the attenuation degree of the scanning ray during the scanning of the part to be detected; And Based on the attenuation coefficient, fat region, and soft tissue region of the part to be detected, determining the fat content of the part to be detected.

2. The fat quantification method according to claim 1, wherein The determining the fat region and soft tissue region of the part to be detected based on the scanned image includes: Based on the scanned image, using an artificial intelligence algorithm to segment the part to be detected to obtain the fat region and the soft tissue region.

3. The fat quantification method according to claim 1 or 2, wherein The determining the fat region and soft tissue region of the part to be detected based on the scanned image includes: Based on the scanned image, determining the Hounsfield unit of the part to be detected; and According to the Hounsfield unit of the part to be detected, determining the fat region and soft tissue region of the part to be detected.

4. The fat quantification method according to claim 1, wherein, The determining the attenuation coefficient of the part to be detected based on the scanned image includes: Based on the scanned image, determining the Hounsfield unit of the part to be detected; and According to a predetermined attenuation coefficient and the Hounsfield unit of the part to be detected, determining the attenuation coefficient of the part to be detected, where the predetermined attenuation coefficient indicates the attenuation coefficient of water.

5. The fat quantification method according to claim 4, wherein, The determining the attenuation coefficient of the part to be detected according to the predetermined attenuation coefficient and the Hounsfield unit of the part to be detected includes: Determining the attenuation coefficient of the part to be detected according to the following formula: ， Among them, is the attenuation coefficient of the part to be detected, is the Hounsfield unit of the part to be detected, is the predetermined attenuation coefficient.

6. The fat quantification method according to claim 1, wherein, The determining the fat content of the part to be detected based on the attenuation coefficient, fat region, and soft tissue region of the part to be detected includes: Based on the attenuation coefficient, fat region, and soft tissue region of the part to be detected, determining the correspondence between the attenuation coefficient of the part to be detected and the fat attenuation coefficient and soft tissue attenuation coefficient, where the fat attenuation coefficient indicates the attenuation coefficient of the fat region, and the soft tissue attenuation coefficient indicates the attenuation coefficient of the soft tissue region; and Based on the correspondence, determining the fat content of the part to be detected.

7. The fat quantification method according to claim 6, wherein, The determining the correspondence between the attenuation coefficient of the part to be detected and the fat attenuation coefficient and soft tissue attenuation coefficient based on the attenuation coefficient, fat region, and soft tissue region of the part to be detected includes: Determining the correspondence according to the following formula: ， Wherein, is the attenuation coefficient of the part to be detected, is the fat attenuation coefficient, is the soft tissue attenuation coefficient, is the fat content of the part to be detected.

8. The fat quantification method according to claim 7, wherein, The determining the fat content of the part to be detected based on the correspondence includes: Determining the fat content of the part to be detected according to the following formula: ， Wherein, is the attenuation coefficient of the part to be detected, is the fat attenuation coefficient, is the soft tissue attenuation coefficient, is the fat content of the part to be detected.

9. The fat quantification method according to claim 1, further comprising: Based on the fat content of the part to be detected, generating a fat distribution map of the part to be detected.

10. A fat quantification device, comprising: An acquisition module for acquiring a scanned image of a part to be detected; A region determination module for determining the fat region and soft tissue region of the part to be detected based on the scanned image; An attenuation coefficient determination module, configured to determine an attenuation coefficient of the part to be detected based on the scanned image, where the attenuation coefficient indicates an attenuation degree of the scanning ray during scanning of the part to be detected; and a fat content determination module, configured to determine a fat content of the part to be detected based on the attenuation coefficient of the part to be detected, the fat region, and the soft tissue region.

Images