A cross-terminal adaptive rendering method for telemedicine images

Abstract

The application relates to the technical field of image transmission and rendering, and discloses a cross-terminal adaptive rendering method for remote medical images, which comprises the following steps: acquiring medical image data to be transmitted and acquiring rendering configuration parameters of a target display terminal; dividing the medical image data into multiple transmission rendering units, and extracting pixel feature indexes of each transmission rendering unit in combination with the rendering configuration parameters; respectively identifying potential distortion types of each transmission rendering unit based on the rendering configuration parameters and the pixel feature indexes; formulating a transmission rendering strategy based on the potential distortion types of each transmission rendering unit; and controlling remote transmission and rendering display of the medical image data based on the transmission rendering strategy. The application can reduce local detail weakening caused by insufficient gray scale response of different terminal screens, compression distortion or scaling rendering.

Description

Technical Field

[0001] This application relates to the technical field of image transmission and rendering, specifically to a cross-terminal adaptive rendering method for remote medical images. Background Technology

[0002] Remote medical images are typically viewed on different types of devices. Differences in grayscale response, display size, and other aspects between devices can lead to issues such as merged dark areas, insufficient local contrast, blurred texture details, or over-sharpened edges when viewing the same image on different devices.

[0003] Current remote image display methods often focus on image compression, resolution adjustment, tile loading, or window width and level adjustment, typically treating the image as a whole or reducing image quality only according to network bandwidth and terminal resolution. This approach struggles to maintain the fidelity of grayscale detail-sensitive areas in medical images, especially on ordinary or mobile terminals, where some local grayscale differences are weakened by compression, scaling, or display mapping processes.

[0004] The information disclosed in this background section is intended only to enhance the understanding of the overall background of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] The technical problem to be solved by this application is to overcome the defects of the prior art and provide a cross-terminal adaptive rendering method for remote medical images, which reduces the weakening of local details caused by insufficient grayscale response, compression distortion or scaling rendering of different terminal screens.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution: A cross-terminal adaptive rendering method for remote medical images includes the following steps: Acquire the medical image data to be transmitted and obtain the rendering configuration parameters of the target display terminal; The medical image data is divided into multiple transmission rendering units, and the pixel feature indicators of each transmission rendering unit are extracted in combination with the rendering configuration parameters. Based on the rendering configuration parameters and pixel feature indicators, the potential distortion type of each transmission rendering unit is identified; Develop a transport rendering strategy based on the potential distortion type of each transport rendering unit; The remote transmission and rendering display of the medical image data are controlled and executed based on the transmission and rendering strategy.

[0007] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, wherein: the transmission rendering unit is a local image block obtained by dividing medical image data according to pixel coordinates, and each transmission rendering unit is labeled with the pixel coordinates and pixel signal values ​​of the pixels it contains; any transmission rendering unit corresponds to a continuous display area in the display window of the target display terminal.

[0008] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the rendering configuration parameters include the display window width and display window level of the target display terminal; The pixel feature index includes the pixel value span; the method for extracting the pixel value span of any transmission rendering unit includes: The pixel signal value of each pixel in the transmission rendering unit is truncated based on the display window width and display window level of the target display terminal. Sort the pixel signal values ​​of all pixels in the transmission rendering unit from smallest to largest, and extract the first pixel value and the second pixel value respectively, where the first pixel value is greater than the second pixel value; The difference between the first pixel value and the second pixel value is calculated and used as the pixel value span of the transmission rendering unit.

[0009] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the pixel feature index further includes local detail density; the method for extracting the local detail density of any transmission rendering unit includes: Calculate the pixel gradient magnitude of each pixel in the transmission rendering unit based on the pixel signal value; calculate the average pixel gradient magnitude of all pixels in the transmission rendering unit, and denot it as the reference pixel gradient. A pixel gradient threshold is set based on the reference pixel gradient; if the pixel gradient magnitude of any pixel is greater than the pixel gradient threshold, then the pixel is marked as a detail pixel. The ratio of the total number of detail pixels within a transport rendering unit to the total number of pixels within the transport rendering unit is calculated and used as the local detail density of the transport rendering unit.

[0010] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the rendering configuration parameters further include the display window size and available grayscale levels of the target display terminal; The potential distortion types are divided into grayscale merging distortion and structural detail weakening; Methods for identifying the potential distortion type of any transport rendering unit include: Set a pixel span threshold; if the pixel value span of any transmission rendering unit is greater than the pixel span threshold, then mark the transmission rendering unit as a higher-level unit. For any high-level unit, the pixel signal value of each pixel is mapped to the gray level of the target display terminal; Extract the first reference pixel value, the second reference pixel value, and the third reference pixel value from the higher-level unit; wherein the first reference pixel value is greater than the second reference pixel value, and the second reference pixel value is greater than the third reference pixel value; If any two of the first reference pixel value, the second reference pixel value, and the third reference pixel value are mapped to the same gray level of the target display terminal, then the potential distortion type of the higher-level unit includes gray level merging distortion.

[0011] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the method for mapping the pixel signal value of any pixel in a high-level unit to a gray level of the target display terminal includes: after the truncation process, calculating the difference between the pixel signal value of any pixel and the lower limit of the display, as the pixel offset of the pixel; and mapping the pixel signal value of the pixel to a gray level between 0 and L-1 based on the pixel offset, where L is the number of available gray levels of the target display terminal.

[0012] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the method for identifying the potential distortion type of any transmission rendering unit includes: Set a detail density threshold; if the local detail density of any transfer rendering unit is greater than the detail density threshold, then mark the transfer rendering unit as a high detail unit; For any high detail unit, each pixel is projected onto the display window of the target display terminal according to the display window size, and the projection coordinates of each pixel are recorded; If any two detail pixels in a high detail unit have the same projected coordinates, then the two corresponding detail pixels are marked as coincident detail pixels. The ratio of the number of overlapping detail pixels within a high detail unit to the total number of detail pixels within the high detail unit is calculated as the detail overlap ratio of the high detail unit. If the detail overlap ratio is greater than a preset overlap ratio threshold, the potential distortion type of the high detail unit includes structural detail weakening.

[0013] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the transmission rendering strategy includes assigning a processing priority to each transmission rendering unit; the processing priority includes a first priority, a second priority, and a third priority. If any transmission rendering unit has a potential distortion type that includes structural detail reduction, then its processing priority is the first priority. If the potential distortion type of any transmission rendering unit does not include structural detail weakening but includes grayscale merging distortion, then its processing priority is the second priority. If the potential distortion type of any transmission rendering unit does not include structural detail weakening and grayscale merging distortion, then its processing priority is the third priority.

[0014] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the transmission rendering strategy further includes: if the processing priority of any transmission rendering unit is the first priority, then a reconstruction error threshold is set for the transmission rendering unit; before compressing the transmission rendering unit and sending it to the target display terminal, the encoding fidelity of the compression is controlled so that the reconstruction error of the transmission rendering unit is less than the reconstruction error threshold.

[0015] As a preferred embodiment of the cross-terminal adaptive rendering method for remote medical images described in this application, the transmission rendering strategy further includes: if the processing priority of any transmission rendering unit is the second priority, then when mapping the gray levels of the transmission rendering unit, a local display window width narrowing process is performed; the local display window width narrowing process includes increasing the lower limit of the display and decreasing the upper limit of the display.

[0016] Compared with the prior art, the beneficial effects achieved by this application are as follows: This application enables remote medical image rendering to move beyond simply compressing or enhancing the entire image uniformly. Instead, it allows for differentiated processing based on local image features and the display capabilities of the terminal. For areas with complex textures, dense edges, and significant grayscale variations, it improves grayscale preservation and rendering fidelity. For background or low-information areas, it reduces transmission and rendering resource consumption. This application also minimizes the weakening of local details caused by insufficient grayscale response, compression distortion, or scaling rendering on different terminal screens. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 A flowchart of a cross-terminal adaptive rendering method for remote medical images provided in this application. Detailed Implementation

[0018] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0019] This embodiment introduces a cross-terminal adaptive rendering method for remote medical images, referring to... Figure 1 The method includes the following steps: Acquire the medical image data to be transmitted and obtain the rendering configuration parameters of the target display terminal; In this embodiment, the medical image data is digital image data generated by medical image acquisition equipment, stored or forwarded by an image server, and sent to a remote terminal for browsing and display via a network. The medical image data includes at least an image pixel matrix and the pixel coordinates and pixel signal values ​​of each pixel, and may also include image size, bit depth, frame sequence information, etc. The pixel signal value refers to the image intensity value corresponding to each pixel in the medical image data, used to characterize the grayscale, density, echo intensity, or other imaging response values ​​of that pixel in the acquisition or reconstruction result. It should be noted that the method described in this embodiment is applicable to adaptive processing of single-frame medical image data. If the processing object is an image sequence, the processing method described in this embodiment can be executed sequentially for each frame of medical image data. The target display terminal is a terminal device that receives medical image data and can perform browsing, decoding, grayscale mapping, and display output, such as a diagnostic workstation, computer, tablet terminal, mobile terminal, or remote consultation display device.

[0020] The medical image data is divided into multiple transmission rendering units, and the pixel feature indicators of each transmission rendering unit are extracted in combination with the rendering configuration parameters. The transmission rendering unit is a local image block obtained by dividing medical image data according to pixel coordinates. Each transmission rendering unit is labeled with the pixel coordinates and pixel signal values ​​of the pixels it contains. Any transmission rendering unit corresponds to a continuous display area in the display window of the target display terminal.

[0021] As an optional implementation, the medical image data is divided into multiple transmission rendering units using a regular grid; the different transmission rendering units are evenly distributed and have the same size and shape. Optionally, any transmission rendering unit includes 32×32 or 64×64 pixels, which can avoid excessive computation due to overly dense division of transmission rendering units, while also preventing local details from being smoothed and blurred due to overly coarse division of transmission rendering units.

[0022] The rendering configuration parameters include the display window width and display window level of the target display terminal; The display window width represents the length of the display range of the mapped pixel signal values ​​that the target display terminal can display, and the display window position is used to represent the center position of the display range.

[0023] For example, when the display window width is 400 and the display window level is 40, the target display terminal displays pixel signal values ​​ranging from -160 to 240, where -160 is the lower limit of the pixel signal value and 240 is the upper limit of the pixel signal value. The target display terminal only maps pixel signal values ​​from -160 to 240 to grayscale values ​​and then renders and displays them.

[0024] The pixel feature metrics include pixel value span and local detail density; Methods for extracting the pixel value span of any transmission rendering unit include: The pixel signal value of each pixel in the transmission rendering unit is truncated based on the display window width and display window level of the target display terminal. The truncation process includes: calculating the upper and lower limits of the pixel signal value based on the display window width and display window level of the target display terminal; if the pixel signal value of any pixel is less than the lower limit, then its pixel signal value is updated to the lower limit; if the pixel signal value of any pixel is greater than the upper limit, then its pixel signal value is updated to the upper limit; if the pixel signal value of any pixel is greater than or equal to the lower limit and less than or equal to the upper limit, then its pixel signal value remains unchanged.

[0025] Sort the pixel signal values ​​of all pixels in the transmission rendering unit from smallest to largest, and extract the first pixel value and the second pixel value respectively, where the first pixel value is greater than the second pixel value; The difference between the first pixel value and the second pixel value is calculated and used as the pixel value span of the transmission rendering unit.

[0026] As an optional implementation, the 95th percentile of the pixel signal value is extracted as the first pixel value of the transmission rendering unit, and the 5th percentile of the pixel signal value is extracted as the second pixel value. The pixel value span is used to reflect whether the transmission rendering unit contains a large number of gray levels that need to be maintained; the larger the pixel value span, the more likely the transmission rendering unit is to suffer gray level loss during grayscale mapping.

[0027] Methods for extracting the local detail density of any transport rendering unit include: Calculate the pixel gradient magnitude of each pixel in the transmission rendering unit based on the pixel signal value; calculate the average pixel gradient magnitude of all pixels in the transmission rendering unit, and denot it as the reference pixel gradient. A pixel gradient threshold is set based on the reference pixel gradient; if the pixel gradient magnitude of any pixel is greater than the pixel gradient threshold, then the pixel is marked as a detail pixel. The ratio of the total number of detail pixels within a transport rendering unit to the total number of pixels within the transport rendering unit is calculated and used as the local detail density of the transport rendering unit.

[0028] Optionally, the pixel gradient threshold is set to 1.5 times the reference pixel gradient. The pixel gradient magnitude of each pixel can be calculated using the Sobel or Scharr operator; if the pixel gradient magnitude of any pixel is greater than 1.5 times the reference pixel gradient, it indicates a significant local pixel signal value change at that location. Local detail density characterizes both edge density and texture complexity, reflecting whether the transmission rendering unit is prone to edge blurring, texture smoothing, or detail breakage during compression, scaling, or interpolation.

[0029] Based on the rendering configuration parameters and pixel feature indicators, the potential distortion type of each transmission rendering unit is identified; The rendering configuration parameters also include the display window size of the target display terminal and the number of available gray levels; The display window size represents the pixel width and pixel height of the display window of the target display terminal that can be used to display images; the available gray levels represent the number of gray levels that the target display terminal can stably distinguish in actual display conditions.

[0030] The number of available grayscale levels for a target display terminal can be determined based on its nominal bit depth or system display settings. For example, ordinary mobile terminals, tablets, or office monitors are typically configured with 8-bit grayscale display capability, corresponding to 256 available grayscale levels; professional monitors supporting 10-bit grayscale display output have 1024 available grayscale levels; and professional monitors in medical diagnostic workstations are configured with 12-bit grayscale display capability, with 4096 available grayscale levels.

[0031] The potential distortion types are divided into grayscale merging distortion and structural detail weakening; Methods for identifying the potential distortion type of any transport rendering unit include: Set a pixel span threshold; if the pixel value span of any transmission rendering unit is greater than the pixel span threshold, then mark the transmission rendering unit as a higher-level unit. Optionally, the pixel span threshold is set to 5% of the display window width of the target display terminal; that is, when the pixel value span of the transmission rendering unit is greater than 5% of the display window width, the transmission rendering unit is considered to contain a significant number of gray levels. If the pixel gradient of the entire frame of medical image data is relatively flat, high-level units will not be forcibly drawn.

[0032] For any high-level unit, the pixel signal value of each pixel is mapped to the gray level of the target display terminal; Extract the first reference pixel value, the second reference pixel value, and the third reference pixel value from the higher-level unit; wherein the first reference pixel value is greater than the second reference pixel value, and the second reference pixel value is greater than the third reference pixel value; If any two of the first reference pixel value, the second reference pixel value, and the third reference pixel value are mapped to the same gray level of the target display terminal, then the potential distortion type of the higher-level unit includes gray level merging distortion.

[0033] As an optional implementation, the method for extracting the first reference pixel value, the second reference pixel value, and the third reference pixel value from the high-level unit includes: after the truncation process, sorting the pixel signal values ​​of all pixels in the high-level unit from smallest to largest, and extracting the 90th percentile of the pixel signal value as the first reference pixel value, extracting the 50th percentile of the pixel signal value as the second reference pixel value, and extracting the 10th percentile of the pixel signal value as the third reference pixel value; only when the first reference pixel value, the second reference pixel value, and the third reference pixel value are all mapped to different gray levels of the target display terminal can it be determined that the low, middle, and high gray levels of the high-level unit can be distinguished on the target display terminal, and there is no risk of gray level merging distortion.

[0034] Methods for mapping the pixel signal value of any pixel within a higher-level unit to the grayscale level of the target display terminal include: After the truncation process, the difference between the pixel signal value of any pixel and the lower limit of the display is calculated as the pixel offset of that pixel; based on the pixel offset, the pixel signal value of that pixel is mapped to a gray level between 0 and L-1, where L is the number of available gray levels of the target display terminal.

[0035] For example, if the display window width is 400 and the display window level is 40, then the lower display limit is -160 and the upper display limit is 240. If the available grayscale level L of the target display terminal is 256, then pixel signal values ​​from -160 to 240 will be mapped to 256 grayscale levels from 0 to 255. If the pixel signal value of any pixel is 40, then the pixel offset of the corresponding pixel relative to the lower display limit is 200, and this pixel offset accounts for 0.5 of the display window width. Multiplying 0.5 by the maximum grayscale level 255 and rounding to the nearest integer, we get a grayscale level of 128. Based on the same calculation method, if the pixel signal value is -160, then the grayscale level is 0; if the pixel signal value is 240, then the grayscale level is 255.

[0036] Methods for identifying the potential distortion type of any transport rendering unit include: Set a detail density threshold; if the local detail density of any transfer rendering unit is greater than the detail density threshold, then mark the transfer rendering unit as a high detail unit; Optionally, the detail density threshold is set to 10%; when more than 10% of the pixels in the transmission rendering unit are detail pixels, it contains sufficiently dense structural details and is sensitive to compression or scaling.

[0037] For any high detail unit, each pixel is projected onto the display window of the target display terminal according to the display window size, and the projection coordinates of each pixel are recorded; If any two detail pixels in a high detail unit have the same projected coordinates, then the two corresponding detail pixels are marked as coincident detail pixels. The ratio of the number of overlapping detail pixels within a high detail unit to the total number of detail pixels within the high detail unit is calculated as the detail overlap ratio of the high detail unit. If the detail overlap ratio is greater than a preset overlap ratio threshold, the potential distortion type of the high detail unit includes structural detail weakening.

[0038] Optionally, the overlap ratio threshold is set to 0.15. If multiple detail pixels have the same projection coordinates, it means that these detail pixels will spatially merge within the display window of the target display terminal. When at least 15% of the detail pixels in a high detail unit have the same projection coordinates as other detail pixels, it means that the detail of the high detail unit is significantly weakened after being projected onto the target display terminal.

[0039] For example, if the size of the medical image data is 2048×2048 pixels, and the display window size of the target display terminal is 1024×1024 pixels, then the scaling ratio is 0.5, meaning that one pixel corresponds to only 0.5 pixels on the target display terminal. Let the coordinates of the partial detail pixels within any high detail unit in the medical image data be as follows: , , Projected onto the display window of the target display terminal at a scaling ratio of 0.5, with the projection coordinates rounded to integer positions, the projection coordinates of the aforementioned detail pixels are as follows: , , There are two adjacent detail pixels that are pressed to the same projection coordinate position in the display window.

[0040] Develop a transport rendering strategy based on the potential distortion type of each transport rendering unit; The transmission rendering strategy includes assigning a processing priority to each transmission rendering unit; the processing priority includes a first priority, a second priority, and a third priority; If any transmission rendering unit has a potential distortion type that includes structural detail reduction, then its processing priority is the first priority. If the potential distortion type of any transmission rendering unit does not include structural detail weakening but includes grayscale merging distortion, then its processing priority is the second priority. If the potential distortion type of any transmission rendering unit does not include structural detail weakening and grayscale merging distortion, then its processing priority is the third priority.

[0041] The transmission rendering strategy further includes: if the processing priority of any transmission rendering unit is the first priority, then a reconstruction error threshold is set for that transmission rendering unit; before compressing the transmission rendering unit and sending it to the target display terminal, the encoding fidelity of the compression is controlled so that the reconstruction error of the transmission rendering unit is less than the reconstruction error threshold.

[0042] The transmission end, such as the image server or its nearby edge nodes, is equipped with an encoder. The encoder compresses and encodes each transmission rendering unit and sends it to the target display terminal. The target display terminal is responsible for decoding, grayscale mapping, and final display of the transmission rendering units. Optionally, after compressing and encoding the transmission rendering units, the transmission end performs local decoding on the encoding result before sending to obtain the reconstructed transmission rendering units. The maximum absolute deviation of the pixel signal values ​​of corresponding pixels in the transmission rendering units before and after compression and decoding reconstruction is calculated. If the maximum absolute deviation is greater than or equal to the reconstruction error threshold, the encoding fidelity is increased and compression and encoding are performed again until the maximum absolute deviation is less than the reconstruction error threshold. Optionally, methods to improve encoding fidelity include, but are not limited to, the encoder selecting a smaller quantization step size, a higher quality factor, or using a near-lossless mode for compression and encoding.

[0043] Optionally, a reconstruction error threshold is set based on the pixel gradient threshold. For example, the equivalent pixel spacing when calculating the pixel gradient magnitude is determined and denoted as d; for example, if adjacent pixel difference is used to calculate the pixel gradient magnitude, the comparison involves two adjacent pixels with a spacing of 1 pixel, so d is 1; if center difference is used, then d=2; if the Sobel operator is used, its lateral gradient is essentially a comparison of the weighted signal difference between the left and right neighborhoods, and the two sampling positions are located on the left and right sides of the center pixel, so its equivalent pixel spacing d can be set to 2. The product of the pixel gradient threshold and the equivalent pixel spacing d is calculated as the signal difference threshold; 0.25 to 0.5 times the signal difference threshold is set as the reconstruction error threshold, thereby reducing the probability of smoothing out or falsifying structural details during the compression process.

[0044] The transmission rendering strategy further includes: if the processing priority of any transmission rendering unit is the second priority, then when mapping the gray level of the transmission rendering unit, a local display window width narrowing process is performed; the local display window width narrowing process includes increasing the lower limit of the display and decreasing the upper limit of the display.

[0045] Optionally, when performing local display window narrowing processing on any transmission rendering unit, the lower display limit is increased to its second pixel value, i.e., the 5th percentile of the pixel signal value, and the upper display limit is decreased to its first pixel value, i.e., the 95th percentile of the pixel signal value. Based on the method of mapping pixel signal values ​​to gray levels of the target display terminal described in this embodiment, after increasing the lower display limit and decreasing the upper display limit, the gray level corresponding to each pixel signal value is recalculated. This can widen the gray level difference again in the original merged small gray level differences within the transmission rendering unit (specifically, in the key area where the pixel signal value is located between the first and second pixel values), thereby improving the actual display contrast and reducing the degree of gray level merging distortion.

[0046] The remote transmission and rendering display of the medical image data are controlled and executed based on the transmission and rendering strategy.

[0047] Based on the transmission rendering strategy, the image server and target terminal prioritize the highest priority transmission rendering units to prevent excessive compression and smoothing of structural information of too many detailed pixels, which would be difficult to recover during subsequent grayscale mapping. The image server and target terminal then prioritize the second priority transmission rendering units, and finally the third priority units. Remote images are typically transmitted in chunks, progressively loaded, and viewed in sections. The highest priority is given to transmission rendering units with a risk of weakened structural details, followed by those with a risk of grayscale merging distortion. This ensures that areas within the display window requiring high fidelity are rendered more precisely first, preventing critical detail areas from becoming blurred and having their layers merged before being displayed, while less important areas consume bandwidth and processing resources.

[0048] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0049] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of protection of this application, and these all fall within the scope of protection of this application.

Claims

1. A cross-terminal adaptive rendering method for remote medical images, characterized in that: Includes the following steps: Acquire the medical image data to be transmitted and obtain the rendering configuration parameters of the target display terminal; The medical image data is divided into multiple transmission rendering units, and the pixel feature indicators of each transmission rendering unit are extracted in combination with the rendering configuration parameters. Based on the rendering configuration parameters and pixel feature indicators, the potential distortion type of each transmission rendering unit is identified; Develop a transport rendering strategy based on the potential distortion type of each transport rendering unit; The remote transmission and rendering display of the medical image data are controlled and executed based on the transmission and rendering strategy.

2. The cross-terminal adaptive rendering method for remote medical images as described in claim 1, characterized in that: The transmission rendering unit is a local image block obtained by dividing medical image data according to pixel coordinates. Each transmission rendering unit is labeled with the pixel coordinates and pixel signal values ​​of the pixels it contains. Any transmission rendering unit corresponds to a continuous display area in the display window of the target display terminal.

3. The cross-terminal adaptive rendering method for remote medical images as described in claim 2, characterized in that: The rendering configuration parameters include the display window width and display window level of the target display terminal; The pixel feature index includes the pixel value span; the method for extracting the pixel value span of any transmission rendering unit includes: The pixel signal value of each pixel in the transmission rendering unit is truncated based on the display window width and display window level of the target display terminal. Sort the pixel signal values ​​of all pixels in the transmission rendering unit from smallest to largest, and extract the first pixel value and the second pixel value respectively, where the first pixel value is greater than the second pixel value; The difference between the first pixel value and the second pixel value is calculated and used as the pixel value span of the transmission rendering unit.

4. The cross-terminal adaptive rendering method for remote medical images as described in claim 3, characterized in that: The pixel feature index also includes local detail density; the method for extracting the local detail density of any transmission rendering unit includes: Calculate the pixel gradient magnitude of each pixel in the transmission rendering unit based on the pixel signal value; calculate the average pixel gradient magnitude of all pixels in the transmission rendering unit, and denot it as the reference pixel gradient. A pixel gradient threshold is set based on the reference pixel gradient; if the pixel gradient magnitude of any pixel is greater than the pixel gradient threshold, then the pixel is marked as a detail pixel. The ratio of the total number of detail pixels within a transport rendering unit to the total number of pixels within the transport rendering unit is calculated and used as the local detail density of the transport rendering unit.

5. The cross-terminal adaptive rendering method for remote medical images as described in claim 4, characterized in that: The rendering configuration parameters also include the display window size of the target display terminal and the number of available gray levels; The potential distortion types are divided into grayscale merging distortion and structural detail weakening; Methods for identifying the potential distortion type of any transport rendering unit include: Set a pixel span threshold; if the pixel value span of any transmission rendering unit is greater than the pixel span threshold, then mark the transmission rendering unit as a higher-level unit. For any high-level unit, the pixel signal value of each pixel is mapped to the gray level of the target display terminal; Extract the first reference pixel value, the second reference pixel value, and the third reference pixel value from the higher-level unit; wherein the first reference pixel value is greater than the second reference pixel value, and the second reference pixel value is greater than the third reference pixel value; If any two of the first reference pixel value, the second reference pixel value, and the third reference pixel value are mapped to the same gray level of the target display terminal, then the potential distortion type of the higher-level unit includes gray level merging distortion.

6. The cross-terminal adaptive rendering method for remote medical images as described in claim 5, characterized in that: The method for mapping the pixel signal value of any pixel in a high-level unit to a gray level of a target display terminal includes: after the truncation process, calculating the difference between the pixel signal value of any pixel and the lower limit of the display, as the pixel offset of the pixel; and mapping the pixel signal value of the pixel to a gray level between 0 and L-1 based on the pixel offset, where L is the number of available gray levels of the target display terminal.

7. The cross-terminal adaptive rendering method for remote medical images as described in claim 6, characterized in that: Methods for identifying the potential distortion type of any transport rendering unit include: Set a detail density threshold; if the local detail density of any transfer rendering unit is greater than the detail density threshold, then mark the transfer rendering unit as a high detail unit; For any high detail unit, each pixel is projected onto the display window of the target display terminal according to the display window size, and the projection coordinates of each pixel are recorded; If any two detail pixels in a high detail unit have the same projected coordinates, then the two corresponding detail pixels are marked as coincident detail pixels. The ratio of the number of overlapping detail pixels within a high detail unit to the total number of detail pixels within the high detail unit is calculated as the detail overlap ratio of the high detail unit. If the detail overlap ratio is greater than a preset overlap ratio threshold, the potential distortion type of the high detail unit includes structural detail weakening.

8. The cross-terminal adaptive rendering method for remote medical images as described in claim 7, characterized in that: The transmission rendering strategy includes assigning a processing priority to each transmission rendering unit; the processing priority includes a first priority, a second priority, and a third priority; If any transmission rendering unit has a potential distortion type that includes structural detail reduction, then its processing priority is the first priority. If the potential distortion type of any transmission rendering unit does not include structural detail weakening but includes grayscale merging distortion, then its processing priority is the second priority. If the potential distortion type of any transmission rendering unit does not include structural detail weakening and grayscale merging distortion, then its processing priority is the third priority.

9. The cross-terminal adaptive rendering method for remote medical images as described in claim 8, characterized in that: The transmission rendering strategy further includes: if the processing priority of any transmission rendering unit is the first priority, then a reconstruction error threshold is set for that transmission rendering unit; before compressing the transmission rendering unit and sending it to the target display terminal, the encoding fidelity of the compression is controlled so that the reconstruction error of the transmission rendering unit is less than the reconstruction error threshold.

10. The cross-terminal adaptive rendering method for remote medical images as described in claim 9, characterized in that: The transmission rendering strategy further includes: if the processing priority of any transmission rendering unit is the second priority, then when mapping the gray level of the transmission rendering unit, a local display window width narrowing process is performed; the local display window width narrowing process includes increasing the lower limit of the display and decreasing the upper limit of the display.

Images