Bone mineral density measurement and osteoporosis diagnosis method and device based on deep learning

Abstract

The invention provides a bone mineral density measurement and osteoporosis diagnosis method and device based on deep learning, equipment and a computer readable storage medium. The method comprises the following steps: acquiring an original spine CT image; preprocessing the original spine CT image to obtain a target spine CT image; inputting the target spine CT image into a preset bone mineral density measurement and osteoporosis diagnosis model, and outputting a bone mineral density value and an osteoporosis diagnosis result; wherein the osteoporosis diagnosis results comprise normality, osteopenia and osteoporosis; the model is obtained through model training and comprises a plurality of DenseNet networks, each DenseNet network is composed of a plurality of dense blocks, the input of each dense block is connected with the output of all the previous dense blocks, dense connection is formed, information and gradient flow is promoted, and gradient disappearance is relieved. According to the embodiment of the invention, the bone mineral density can be measured more accurately, and the type of osteoporosis can be diagnosed.

Description

Technical Field

[0001] The present application belongs to the technical field of osteoporosis, and in particular relates to a bone density measurement and osteoporosis diagnosis method, device, equipment and computer-readable storage medium based on deep learning. Background Art

[0002] Osteoporosis is closely related to population aging. Since 2010, China's population aging has accelerated. According to the published data, an obvious trend can be seen: the population aged 50 and above is increasing rapidly. It is estimated that by 2050, there will be 5.99 million cases of osteoporotic fractures each year.

[0003] Many studies have shown that early intervention in patients at high risk of fracture can significantly reduce the incidence of fractures. Therefore, it is particularly important to screen patients for osteoporosis and assess their fracture risk. Bone density measurement plays a vital role in osteoporosis and fracture risk assessment. Bone density measurement is an internationally recognized diagnostic standard for osteoporosis. Bone density measurement and osteoporosis diagnosis based on X-ray images and CT images are the two most widely used methods in clinical practice.

[0004] Bone density measurement and osteoporosis diagnosis based on X-ray images, although low in cost and radiation dose, cannot directly display the details of the microstructure of osteoporosis and may not be sensitive enough to detect mild osteoporosis.

[0005] Therefore, how to measure bone density more accurately and diagnose the type of osteoporosis is a technical problem that technicians in this field need to solve urgently. Summary of the invention

[0006] The embodiments of the present application provide a bone density measurement and osteoporosis diagnosis method, device, equipment and computer-readable storage medium based on deep learning, which can more accurately measure bone density and diagnose the type of osteoporosis.

[0007] In a first aspect, the present application provides a method for bone density measurement and osteoporosis diagnosis based on deep learning, including:

[0008] Obtain original spinal CT images;

[0009] Preprocessing the original spine CT image to obtain the target spine CT image;

[0010] Input the target spine CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result;

[0011] Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis;

[0012] The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

[0013] Optionally, the original spine CT image is preprocessed to obtain a target spine CT image, including:

[0014] The original spine CT image is cropped and normalized to obtain the target spine CT image.

[0015] Optionally, the original spine CT image is cropped and normalized to obtain a target spine CT image, including:

[0016] Determine the area of ​​interest based on specific tasks and applications;

[0017] Cropping the original spine CT image according to the region of interest to obtain a first spine CT image;

[0018] Normalizing the grayscale of the first spine CT image to obtain a second spine CT image;

[0019] The second spine CT image is spatially normalized by bilinear interpolation to obtain the target spine CT image.

[0020] Optionally, a mapping relationship between bone density values ​​and osteoporosis diagnosis results includes:

[0021] If the bone density value is greater than or equal to 120 mg per cubic centimeter, the osteoporosis diagnosis result is normal;

[0022] If the bone density value is less than or equal to 80 milligrams per cubic centimeter, the osteoporosis diagnosis result is osteoporosis;

[0023] If the bone density value is between 80 and 120 mg / cm3, the osteoporosis diagnosis is osteopenia.

[0024] Optionally, the target spine CT image is input into a preset bone density measurement and osteoporosis diagnosis model to output a bone density value and osteoporosis diagnosis result, including:

[0025] Use Conv-Bn-ReLU to extract features from the target spine CT image to obtain the first feature map;

[0026] Using Dense Block to enhance the features of the first feature map through dense connections to obtain a second feature map;

[0027] The second feature map is resized using the Transition Layer to obtain a third feature map;

[0028] Using multiple Dense Blocks and Conv-Bn-ReLU, feature enhancement and feature extraction are performed on the third feature map to obtain a fourth feature map;

[0029] Based on the fourth characteristic graph, the bone density value and the osteoporosis diagnosis result are output respectively.

[0030] Optionally, based on the fourth characteristic map, a bone density value is output, including:

[0031] Performing a pooling operation on the fourth feature map to obtain a fifth feature map;

[0032] Perform linear transformation on the fifth feature map and output the bone density value.

[0033] Optionally, based on the fourth characteristic graph, an osteoporosis diagnosis result is output, including:

[0034] Performing a pooling operation on the fourth feature map to obtain a fifth feature map;

[0035] Performing a linear transformation on the fifth characteristic map and outputting a bone density value;

[0036] Based on the bone density value and Softmax function, the osteoporosis diagnosis result is output.

[0037] In a second aspect, the present application provides a bone density measurement and osteoporosis diagnosis device based on deep learning, comprising:

[0038] An image acquisition module, used for acquiring original spinal CT images;

[0039] A preprocessing module, used for preprocessing the original spine CT image to obtain a target spine CT image;

[0040] The measurement and diagnosis module is used to input the target spine CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result;

[0041] Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis;

[0042] The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0044] When the processor executes the computer program instructions, a bone density measurement and osteoporosis diagnosis method based on deep learning is implemented.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, a bone density measurement and osteoporosis diagnosis method based on deep learning is implemented.

[0046] The embodiments of the present application provide a deep learning-based bone density measurement and osteoporosis diagnosis method, device, equipment and computer-readable storage medium, which can more accurately measure bone density and diagnose the type of osteoporosis.

[0047] The deep learning-based bone density measurement and osteoporosis diagnosis method includes:

[0048] Obtain original spinal CT images;

[0049] Preprocessing the original spine CT image to obtain the target spine CT image;

[0050] Input the target spine CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result;

[0051] Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis;

[0052] The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 It is a flowchart of a method for bone density measurement and osteoporosis diagnosis based on deep learning provided by an embodiment of the present application;

[0055] Figure 2 It is a flowchart of a method for bone density measurement and osteoporosis diagnosis based on deep learning provided by an embodiment of the present application;

[0056] Figure 3 It is a structural schematic diagram of a bone density measurement and osteoporosis diagnosis device based on deep learning provided by an embodiment of the present application;

[0057] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0058] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0059] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0060] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment and computer-readable storage medium for bone density measurement and osteoporosis diagnosis based on deep learning. The following first introduces the method for bone density measurement and osteoporosis diagnosis based on deep learning provided by the embodiments of the present application.

[0061] Figure 1 and Figure 2 FIG. 1 is a flow chart of a method for bone density measurement and osteoporosis diagnosis based on deep learning provided by an embodiment of the present application. Figure 1As shown, the deep learning-based bone density measurement and osteoporosis diagnosis method includes:

[0062] S101, obtaining an original spinal CT image;

[0063] S102, preprocessing the original spine CT image to obtain a target spine CT image;

[0064] S103, inputting the target spine CT image into a preset bone density measurement and osteoporosis diagnosis model, and outputting a bone density value and an osteoporosis diagnosis result;

[0065] Among them, the diagnosis results of osteoporosis include: normal, osteopenia and osteoporosis; the bone density measurement and osteoporosis diagnosis model are obtained through model training, which includes multiple DenseNet networks, each DenseNet network consists of multiple dense blocks, and the input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

[0066] In one embodiment, preprocessing the original spine CT image to obtain the target spine CT image includes:

[0067] The original spine CT image is cropped and normalized to obtain the target spine CT image.

[0068] In one embodiment, the original spine CT image is cropped and normalized to obtain a target spine CT image, including:

[0069] Determine the area of ​​interest based on specific tasks and applications;

[0070] Cropping the original spine CT image according to the region of interest to obtain a first spine CT image;

[0071] Normalizing the grayscale of the first spine CT image to obtain a second spine CT image;

[0072] The second spine CT image is spatially normalized by bilinear interpolation to obtain the target spine CT image.

[0073] In one embodiment, the mapping relationship between the bone density value and the osteoporosis diagnosis result includes:

[0074] If the bone density value is greater than or equal to 120 mg per cubic centimeter, the osteoporosis diagnosis result is normal;

[0075] If the bone density value is less than or equal to 80 milligrams per cubic centimeter, the osteoporosis diagnosis result is osteoporosis;

[0076] If the bone density value is between 80 and 120 mg / cm3, the osteoporosis diagnosis is osteopenia.

[0077] In one embodiment, the target spine CT image is input into a preset bone density measurement and osteoporosis diagnosis model, and the bone density value and osteoporosis diagnosis result are output, including:

[0078] Use Conv-Bn-ReLU to extract features from the target spine CT image to obtain the first feature map;

[0079] Using Dense Block to enhance the features of the first feature map through dense connections to obtain a second feature map;

[0080] The second feature map is resized using the Transition Layer to obtain a third feature map;

[0081] Using multiple Dense Blocks and Conv-Bn-ReLU, feature enhancement and feature extraction are performed on the third feature map to obtain a fourth feature map;

[0082] Based on the fourth characteristic graph, the bone density value and the osteoporosis diagnosis result are output respectively.

[0083] In one embodiment, outputting a bone density value based on the fourth characteristic map includes:

[0084] Performing a pooling operation on the fourth feature map to obtain a fifth feature map;

[0085] Perform linear transformation on the fifth feature map and output the bone density value.

[0086] In one embodiment, based on the fourth characteristic graph, outputting an osteoporosis diagnosis result includes:

[0087] Performing a pooling operation on the fourth feature map to obtain a fifth feature map;

[0088] Performing a linear transformation on the fifth characteristic map and outputting a bone density value;

[0089] Based on the bone density value and Softmax function, the osteoporosis diagnosis result is output.

[0090] Figure 3 : is a schematic diagram of a bone density measurement and osteoporosis diagnosis device based on deep learning provided by an embodiment of the present application; the bone density measurement and osteoporosis diagnosis device based on deep learning includes:

[0091] An image acquisition module 301 is used to acquire an original spinal CT image;

[0092] A preprocessing module 302 is used to preprocess the original spine CT image to obtain a target spine CT image;

[0093] The measurement and diagnosis module 303 is used to input the target spine CT image into a preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result;

[0094] Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis;

[0095] The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

[0096] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown.

[0097] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0098] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0099] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an electronic device. In a particular embodiment, memory 402 may be a non-volatile solid-state memory.

[0100] In one embodiment, the memory 402 may be a read-only memory (ROM). In one embodiment, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0101] The processor 401 reads and executes computer program instructions stored in the memory 402 to implement any one of the deep learning-based bone density measurement and osteoporosis diagnosis methods in the above embodiments.

[0102] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0103] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0104] Bus 410 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0105] In addition, in combination with the bone density measurement and osteoporosis diagnosis method based on deep learning in the above embodiments, the present application embodiment can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the bone density measurement and osteoporosis diagnosis methods based on deep learning in the above embodiments is implemented.

[0106] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0107] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0108] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0109] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0110] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A bone density measurement and osteoporosis diagnosis method based on deep learning, characterized in that: include: Obtain original spinal CT images; Preprocessing the original spine CT image to obtain the target spine CT image; Input the target spine CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result; Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis; The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

2. The method for bone density measurement and osteoporosis diagnosis based on deep learning according to claim 1, characterized in that: The original spine CT image is preprocessed to obtain the target spine CT image, including: The original spine CT image is cropped and normalized to obtain the target spine CT image.

3. The method for bone density measurement and osteoporosis diagnosis based on deep learning according to claim 2, characterized in that: The original spine CT image is cropped and normalized to obtain the target spine CT image, including: Determine the area of ​​interest based on specific tasks and applications; Cropping the original spine CT image according to the region of interest to obtain a first spine CT image; Normalizing the grayscale of the first spine CT image to obtain a second spine CT image; The second spine CT image is spatially normalized by bilinear interpolation to obtain the target spine CT image.

4. The method for bone density measurement and osteoporosis diagnosis based on deep learning according to claim 1, characterized in that: The mapping relationship between bone density values ​​and osteoporosis diagnosis results includes: If the bone density value is greater than or equal to 120 mg per cubic centimeter, the osteoporosis diagnosis result is normal; If the bone density value is less than or equal to 80 milligrams per cubic centimeter, the osteoporosis diagnosis result is osteoporosis; If the bone density value is between 80 and 120 mg / cm3, the osteoporosis diagnosis is osteopenia.

5. The method for bone density measurement and osteoporosis diagnosis based on deep learning according to claim 1, characterized in that: The target spine CT image is input into the preset bone density measurement and osteoporosis diagnosis model, and the bone density value and osteoporosis diagnosis results are output, including: Use Conv-Bn-ReLU to extract features from the target spine CT image to obtain the first feature map; Using Dense Block to enhance the features of the first feature map through dense connections to obtain a second feature map; The second feature map is resized using the Transition Layer to obtain a third feature map; Using multiple Dense Blocks and Conv-Bn-ReLU, feature enhancement and feature extraction are performed on the third feature map to obtain a fourth feature map; Based on the fourth characteristic graph, the bone density value and the osteoporosis diagnosis result are output respectively.

6. The method for bone density measurement and osteoporosis diagnosis based on deep learning according to claim 5, characterized in that: Based on the fourth characteristic graph, the bone density value is output, including: Performing a pooling operation on the fourth feature map to obtain a fifth feature map; Perform linear transformation on the fifth feature map and output the bone density value.

7. The method for bone density measurement and osteoporosis diagnosis based on deep learning according to claim 6, characterized in that: Based on the fourth characteristic graph, the osteoporosis diagnosis result is output, including: Performing a pooling operation on the fourth feature map to obtain a fifth feature map; Performing a linear transformation on the fifth characteristic map and outputting a bone density value; Based on the bone density value and Softmax function, the osteoporosis diagnosis result is output.

8. A bone density measurement and osteoporosis diagnosis device based on deep learning, characterized in that: The device comprises: An image acquisition module, used for acquiring original spinal CT images; A preprocessing module, used for preprocessing the original spine CT image to obtain a target spine CT image; The measurement and diagnosis module is used to input the target spine CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result; Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis; The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the bone density measurement and osteoporosis diagnosis method based on deep learning as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the deep learning-based bone density measurement and osteoporosis diagnosis method as described in any one of claims 1 to 7.

Images