Cervical degeneration intelligent diagnosis method, system and equipment based on deep learning

Abstract

The invention provides a cervical degeneration intelligent diagnosis method, system and device based on deep learning and a computer readable storage medium. The intelligent diagnosis method for cervical degeneration based on deep learning comprises the following steps: acquiring a cervical vertebra side X-ray image; inputting the cervical vertebra side position X-ray image into a preset cervical vertebra degeneration intelligent diagnosis model, and outputting a cervical vertebra degeneration diagnosis result; wherein the cervical degeneration diagnosis result comprises normality, intervertebral space stenosis, physiological curvature change and osteophyte; the physiological curvature change comprises normal physiological curvature, physiological curvature straightening and physiological curvature reverse arching. According to the embodiment of the invention, the cervical degeneration diagnosis can be more accurately carried out.

Description

Technical Field

[0001] The present application relates to the field of cervical degeneration diagnosis, and in particular to a deep learning-based intelligent diagnosis method, system, device and computer-readable storage medium for cervical degeneration. Background Art

[0002] At present, the diagnosis of cervical degeneration in related technologies is mainly based on: using a feature recognition module to recognize various CT image features of the current cervical degenerative disease patients and visualize them in the form of text options.

[0003] However, this method is based on three-dimensional CT images and cannot accurately diagnose cervical degeneration.

[0004] Therefore, how to diagnose cervical degeneration more accurately is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] The embodiments of the present application provide a deep learning-based intelligent diagnosis method, system, device and computer-readable storage medium for cervical vertebra degeneration, which can more accurately diagnose cervical vertebra degeneration.

[0006] In a first aspect, an embodiment of the present application provides an intelligent diagnosis method for cervical degeneration based on deep learning, comprising:

[0007] Obtain lateral X-ray images of the cervical spine;

[0008] Input the lateral X-ray image of the cervical spine into the preset intelligent diagnosis model of cervical degeneration, and output the diagnosis result of cervical degeneration;

[0009] Among them, the diagnostic results of cervical degeneration include: normal, intervertebral disc stenosis, changes in physiological curvature and osteophytes; changes in physiological curvature include: normal physiological curvature, straightening of physiological curvature and reverse arch of physiological curvature.

[0010] Optionally, the processing flow of the cervical vertebra degeneration intelligent diagnosis model includes:

[0011] The lateral X-ray image of the cervical spine is passed through a 3x3 convolutional layer to capture the local features of the image;

[0012] The average pooling layer is used to downsample the convolutional feature map.

[0013] Optionally, after downsampling the convolutional feature map using an average pooling layer, the following steps are also included:

[0014] In module stage2, the downsampling unit and the basic unit are stacked once each;

[0015] In module stage3, the downsampling unit is stacked once and the basic unit is stacked three times to enhance the learning ability of features;

[0016] In module stage4, the downsampling unit and the basic unit are stacked once each.

[0017] Optionally, also include:

[0018] A 1x1 convolutional layer is used for cross-channel feature fusion and dimensionality reduction;

[0019] The global pooling layer reduces the spatial dimension of the feature map to a single value to capture the global information of the entire feature map;

[0020] The fully connected layer receives the feature vector from the global pooling layer and outputs a predicted value;

[0021] Among them, the 3x3 convolution layer and the 1x1 convolution layer respectively introduce the Mish activation function.

[0022] Optionally, obtain a lateral x-ray of the cervical spine, including:

[0023] The patient's head should be kept in a neutral position, with both eyes looking straight ahead and the lower jaw slightly retracted, so that the midsagittal plane of the head and neck is parallel to the camera stand panel;

[0024] The patient's shoulders should be lowered to avoid covering the cervical spine area with the shoulders;

[0025] Determine the center position of the cervical spine and ensure that the cervical spine is completely within the X-ray irradiation field;

[0026] The center line is aligned with the midpoint of the cervical spine to ensure the clarity of the lateral image of the cervical spine;

[0027] Operate X-ray equipment, perform exposure and take pictures, and obtain lateral X-ray images of the cervical spine;

[0028] Check whether the X-ray image is clear and the cervical spine structure is intact, and save the image after confirming that it is correct;

[0029] Image processing was performed to adjust the contrast and brightness of the lateral X-ray images of the cervical spine.

[0030] Optionally, before inputting the lateral X-ray image of the cervical spine into the preset intelligent diagnosis model for cervical degeneration, the method further includes:

[0031] Acquire a cervical spine lateral X-ray image dataset;

[0032] Mark the degeneration location and type in the lateral X-ray image of the cervical spine, and save the marking results in a txt file;

[0033] The lateral cervical spine X-ray images and their corresponding txt texts were shuffled and divided into training set, validation set, and test set in a ratio of 6:2:2;

[0034] Model training was performed based on the training set, validation set, and test set to obtain an intelligent diagnostic model for cervical vertebrae degeneration.

[0035] Optionally, during model training, set the training batch_size to 32;

[0036] Set the initial learning rate to 1e-4, and add a learning rate decay strategy. Every 5000 iterations, the learning rate decays to 0.9 of the previous learning rate.

[0037] Set the optimizer to Adam optimizer;

[0038] Set the loss function to DICEloss;

[0039] The training set and validation set were validated once every 1000 iterations. The early stopping method was used to determine the stopping time of network training, and an intelligent diagnosis model for cervical degeneration was obtained.

[0040] In a second aspect, the embodiment of the present application provides an intelligent diagnosis system for cervical degeneration based on deep learning, including:

[0041] An image acquisition module, used for acquiring a lateral X-ray image of the cervical spine;

[0042] The cervical degeneration diagnosis module is used to input the cervical lateral X-ray image into the preset cervical degeneration intelligent diagnosis model and output the cervical degeneration diagnosis result;

[0043] Among them, the diagnostic results of cervical degeneration include: normal, intervertebral disc stenosis, changes in physiological curvature and osteophytes; changes in physiological curvature include: normal physiological curvature, straightening of physiological curvature and reverse arch of physiological curvature.

[0044] 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;

[0045] When the processor executes the computer program instructions, an intelligent diagnosis method for cervical vertebrae degeneration based on deep learning is implemented.

[0046] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement an intelligent diagnostic method for cervical vertebrae degeneration based on deep learning.

[0047] The deep learning-based intelligent diagnosis method, system, device and computer-readable storage medium for cervical vertebra degeneration of the embodiments of the present application can diagnose cervical vertebra degeneration more accurately.

[0048] The deep learning-based intelligent diagnostic method for cervical degeneration includes:

[0049] Obtain lateral X-ray images of the cervical spine;

[0050] Input the lateral X-ray image of the cervical spine into the preset intelligent diagnosis model of cervical degeneration, and output the diagnosis result of cervical degeneration;

[0051] Among them, the diagnostic results of cervical degeneration include: normal, intervertebral disc stenosis, changes in physiological curvature and osteophytes; changes in physiological curvature include: normal physiological curvature, straightening of physiological curvature and reverse arch of physiological curvature. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] 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.

[0053] Figure 1 It is a flowchart of an intelligent diagnosis method for cervical vertebra degeneration based on deep learning provided by an embodiment of the present application;

[0054] Figure 2 is a schematic diagram of cervical vertebra degeneration types provided by an embodiment of the present application;

[0055] Figure 3 This is a schematic diagram of the network structure of an intelligent diagnostic model for cervical vertebra degeneration provided by an embodiment of the present application;

[0056] Figure 4 It is a structural schematic diagram of a deep learning-based intelligent diagnosis system for cervical vertebra degeneration provided by an embodiment of the present application;

[0057] Figure 5 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, system, device and computer-readable storage medium for intelligent diagnosis of cervical vertebra degeneration based on deep learning. The following first introduces the intelligent method for intelligent diagnosis of cervical vertebra degeneration based on deep learning provided by the embodiments of the present application.

[0061] Figure 1 FIG. 1 is a flow chart of an intelligent diagnosis method for cervical vertebra degeneration based on deep learning provided by an embodiment of the present application. Figure 1 As shown, the intelligent diagnosis method for cervical degeneration based on deep learning includes:

[0062] S101, obtaining a lateral X-ray image of the cervical spine;

[0063] S102, inputting the lateral X-ray image of the cervical spine into a preset intelligent diagnosis model for cervical degeneration, and outputting a diagnosis result for cervical degeneration;

[0064] Among them, the diagnostic results of cervical degeneration include: normal, intervertebral disc stenosis, changes in physiological curvature and osteophytes; changes in physiological curvature include: normal physiological curvature, straightening of physiological curvature and reverse arch of physiological curvature.

[0065] Figure 2 is a schematic diagram of cervical vertebra degeneration types provided by an embodiment of the present application;

[0066] Figure 3 It is a schematic diagram of the network structure of an intelligent diagnostic model for cervical vertebra degeneration provided by an embodiment of the present application.

[0067] In one embodiment, the processing flow of the cervical vertebra degeneration intelligent diagnosis model includes:

[0068] The lateral X-ray image of the cervical spine is passed through a 3x3 convolutional layer to capture the local features of the image;

[0069] The average pooling layer is used to downsample the convolutional feature map.

[0070] In one embodiment, after downsampling the convolutional feature map using an average pooling layer, the method further includes:

[0071] In module stage2, the downsampling unit and the basic unit are stacked once each;

[0072] In module stage3, the downsampling unit is stacked once and the basic unit is stacked three times to enhance the learning ability of features;

[0073] In module stage4, the downsampling unit and the basic unit are stacked once each.

[0074] In one embodiment, it further includes:

[0075] A 1x1 convolutional layer is used for cross-channel feature fusion and dimensionality reduction;

[0076] The global pooling layer reduces the spatial dimension of the feature map to a single value to capture the global information of the entire feature map;

[0077] The fully connected layer receives the feature vector from the global pooling layer and outputs a predicted value;

[0078] Among them, the 3x3 convolution layer and the 1x1 convolution layer respectively introduce the Mish activation function.

[0079] In one embodiment, obtaining a lateral X-ray image of the cervical spine includes:

[0080] The patient's head should be kept in a neutral position, with both eyes looking straight ahead and the lower jaw slightly retracted, so that the midsagittal plane of the head and neck is parallel to the camera stand panel;

[0081] The patient's shoulders should be lowered to avoid covering the cervical spine area with the shoulders;

[0082] Determine the center position of the cervical spine and ensure that the cervical spine is completely within the X-ray irradiation field;

[0083] The center line is aligned with the midpoint of the cervical spine to ensure the clarity of the lateral image of the cervical spine;

[0084] Operate X-ray equipment, perform exposure and take pictures, and obtain lateral X-ray images of the cervical spine;

[0085] Check whether the X-ray image is clear and the cervical spine structure is intact, and save the image after confirming that it is correct;

[0086] Image processing was performed to adjust the contrast and brightness of the lateral X-ray images of the cervical spine.

[0087] In one embodiment, before inputting the lateral X-ray image of the cervical spine into the preset intelligent diagnosis model of cervical degeneration, the method further includes:

[0088] Acquire a cervical spine lateral X-ray image dataset;

[0089] Mark the degeneration location and type in the lateral X-ray image of the cervical spine, and save the marking results in a txt file;

[0090] The lateral cervical spine X-ray images and their corresponding txt texts were shuffled and divided into training set, validation set, and test set in a ratio of 6:2:2;

[0091] Model training was performed based on the training set, validation set, and test set to obtain an intelligent diagnostic model for cervical vertebrae degeneration.

[0092] In one embodiment, during the model training process, the batch_size of the training is set to 32;

[0093] Set the initial learning rate to 1e-4, and add a learning rate decay strategy. Every 5000 iterations, the learning rate decays to 0.9 of the previous learning rate.

[0094] Set the optimizer to Adam optimizer;

[0095] Set the loss function to DICEloss;

[0096] The training set and validation set were validated once every 1000 iterations. The early stopping method was used to determine the stopping time of network training, and an intelligent diagnosis model for cervical degeneration was obtained.

[0097] Figure 4 It is a structural diagram of an intelligent diagnosis system for cervical degeneration based on deep learning provided by an embodiment of the present application.

[0098] The deep learning-based intelligent diagnosis system for cervical degeneration includes:

[0099] An image acquisition module 401 is used to acquire a lateral X-ray image of the cervical spine;

[0100] The cervical degeneration diagnosis module 402 is used to input the cervical lateral X-ray image into a preset cervical degeneration intelligent diagnosis model and output the cervical degeneration diagnosis result;

[0101] Among them, the diagnostic results of cervical degeneration include: normal, intervertebral disc stenosis, changes in physiological curvature and osteophytes; changes in physiological curvature include: normal physiological curvature, straightening of physiological curvature and reverse arch of physiological curvature.

[0102] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown.

[0103] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0104] Specifically, the processor 501 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.

[0105] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 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. Where appropriate, the memory 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the electronic device. In a particular embodiment, the memory 502 may be a non-volatile solid-state memory.

[0106] In one embodiment, the memory 502 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.

[0107] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any one of the deep learning-based intelligent diagnosis methods for cervical vertebrae degeneration in the above-mentioned embodiments.

[0108] In one example, the electronic device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0109] The communication interface 503 is mainly used to implement communication between various modules, systems, units and / or devices in the embodiments of the present application.

[0110] Bus 510 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 510 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.

[0111] In addition, in combination with the deep learning-based intelligent diagnosis method for cervical degeneration 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 deep learning-based intelligent diagnosis methods for cervical degeneration in the above embodiments is implemented.

[0112] 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.

[0113] 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.

[0114] 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 systems. 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.

[0115] The above reference is according to the method of the embodiment of the present application, the flow chart of system (system) and computer program product and / or block diagram and describe various aspects of the present application.It should be understood that each square frame in the flow chart and / or block diagram and the combination of each square frame in the flow chart and / or block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of general-purpose computer, special-purpose computer or other programmable data processing system, to produce a kind of machine, so that these instructions executed by the processor of computer or other programmable data processing system enable the realization of the function / action specified in one or more square frames of flow chart and / or block diagram.Such processor can be but not limited to general-purpose processor, special-purpose processor, special application processor or field programmable logic circuit.It can also be understood that each square frame in the block chart and / or flow chart and the combination of square frames in the block chart and / or flow chart can also be realized by the special-purpose hardware that performs the specified function or action, or can be realized by the combination of special-purpose hardware and computer instructions.

[0116] 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 deep learning-based intelligent diagnosis method for cervical vertebra degeneration, characterized in that: include: Obtain lateral X-ray images of the cervical spine; Input the lateral X-ray image of the cervical spine into the preset intelligent diagnosis model of cervical degeneration, and output the diagnosis result of cervical degeneration; Among them, the diagnostic results of cervical degeneration include: normal, intervertebral disc stenosis, changes in physiological curvature and osteophytes; changes in physiological curvature include: normal physiological curvature, straightening of physiological curvature and reverse arch of physiological curvature.

2. The deep learning-based intelligent diagnosis method for cervical vertebra degeneration according to claim 1 is characterized in that: The processing flow of the intelligent diagnosis model for cervical degeneration includes: The lateral X-ray image of the cervical spine is passed through a 3x3 convolutional layer to capture the local features of the image; The average pooling layer is used to downsample the convolutional feature map.

3. The deep learning-based intelligent diagnosis method for cervical vertebra degeneration according to claim 2 is characterized in that: After downsampling the convolutional feature map using the average pooling layer, it also includes: In module stage2, the downsampling unit and the basic unit are stacked once each; In module stage3, the downsampling unit is stacked once and the basic unit is stacked three times to enhance the learning ability of features; In module stage4, the downsampling unit and the basic unit are stacked once each.

4. The deep learning-based intelligent diagnosis method for cervical vertebra degeneration according to claim 3 is characterized in that: Also includes: A 1x1 convolutional layer is used for cross-channel feature fusion and dimensionality reduction; The global pooling layer reduces the spatial dimension of the feature map to a single value to capture the global information of the entire feature map; The fully connected layer receives the feature vector from the global pooling layer and outputs a predicted value; Among them, the 3x3 convolution layer and the 1x1 convolution layer respectively introduce the Mish activation function.

5. The deep learning-based intelligent diagnosis method for cervical vertebra degeneration according to claim 4 is characterized in that: Obtain lateral x-rays of the cervical spine, including: The patient's head should be kept in a neutral position, with both eyes looking straight ahead and the lower jaw slightly retracted, so that the midsagittal plane of the head and neck is parallel to the camera stand panel; The patient's shoulders should be lowered to avoid covering the cervical spine area with the shoulders; Determine the center position of the cervical spine and ensure that the cervical spine is completely within the X-ray irradiation field; The center line is aligned with the midpoint of the cervical spine to ensure the clarity of the lateral image of the cervical spine; Operate X-ray equipment, perform exposure and take pictures, and obtain lateral X-ray images of the cervical spine; Check whether the X-ray image is clear and the cervical spine structure is intact, and save the image after confirming that it is correct; Image processing was performed to adjust the contrast and brightness of the lateral X-ray images of the cervical spine.

6. The deep learning-based intelligent diagnosis method for cervical vertebra degeneration according to claim 1, characterized in that: Before inputting the lateral X-ray image of the cervical spine into the preset intelligent diagnosis model of cervical degeneration, the method further includes: Acquire a cervical spine lateral X-ray image dataset; Mark the degeneration location and type in the lateral X-ray image of the cervical spine, and save the marking results in a txt file; The lateral cervical spine X-ray images and their corresponding txt texts were shuffled and divided into training set, validation set, and test set in a ratio of 6:2:2; Model training was performed based on the training set, validation set, and test set to obtain an intelligent diagnostic model for cervical vertebrae degeneration.

7. The deep learning-based intelligent diagnosis method for cervical vertebra degeneration according to claim 6, characterized in that: During model training, set the training batch_size to 32; Set the initial learning rate to 1e-4, and add a learning rate decay strategy. Every 5000 iterations, the learning rate decays to 0.9 of the previous learning rate. Set the optimizer to Adam optimizer; Set the loss function to DICEloss; The training set and validation set were validated once every 1000 iterations. The early stopping method was used to determine the stopping time of network training, and an intelligent diagnosis model for cervical degeneration was obtained.

8. An intelligent diagnosis system for cervical degeneration based on deep learning, characterized in that: The system comprises: An image acquisition module, used for acquiring a lateral X-ray image of the cervical spine; The cervical degeneration diagnosis module is used to input the cervical lateral X-ray image into the preset cervical degeneration intelligent diagnosis model and output the cervical degeneration diagnosis result; Among them, the diagnostic results of cervical degeneration include: normal, intervertebral disc stenosis, changes in physiological curvature and osteophytes; changes in physiological curvature include: normal physiological curvature, straightening of physiological curvature and reverse arch of physiological curvature.

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 deep learning-based intelligent diagnosis method for cervical vertebrae degeneration 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 intelligent diagnosis method for cervical vertebrae degeneration as described in any one of claims 1 to 7.

Images