Image processing method for biliopancreatic duct simulator

Abstract

The invention discloses an image processing method for a biliopancreatic duct simulator. The image processing method comprises the following steps: a processing unit receives an image to be processed and a reference image; the processing unit performs differentiation operation on the image to be processed and the reference image to obtain a differentiated image, and the processing unit finds out a starting point in the differentiated image; the processing unit performs binarization processing on the differentiated image to obtain a binarized image; the processing unit performs morphological closed operation on the binarized image to obtain a de-noised image; the processing unit takes a point farthest from the starting point in the de-noised image as an instrument position at the tail end of an instrument, and marks the instrument position in the to-be-processed image to form an output image; and the processing unit transmits the output image to an output unit for outputting. Therefore, a physician can more clearly position the instrument and know the operation condition in the practice without additionally arranging any thing on the instrument.

Description

Technical Field

[0001] The invention relates to an image processing method, and in particular to an image processing method specifically used for a bile and pancreas duct simulator. Background Art

[0002] The training mold for abdominal surgery, for example, is the laparoscopic liver suturing training simulator provided by Chinese Patent Publication No. CN117831374A.

[0003] The above-mentioned laparoscopic liver suturing training simulator includes an openable shell model, a simulated gallbladder, a three-dimensional mechanical sensor and an electromagnetic tracking device. The openable shell model includes an imitation human abdominal upper shell fixed on a bottom plate; the three-dimensional mechanical sensor and the liver model are fixed in the openable shell model, and the liver model is provided with a simulated gallbladder, a simulated bile duct, and simulated liver blood vessels and their branches. A neural network is used to automatically segment the liver position and the liver blood vessels and their branches from CT images, and a three-dimensional model is constructed and then made by 3D printing; simulated bile ducts, liver blood vessels and their branches are perfused with simulated liquid; the measurement range of the electromagnetic tracking device covers the working space of the end of the suturing surgical instrument, and is used to track the movement trajectory of the end of the suturing surgical instrument.

[0004] In the aforementioned patent case, an electromagnetic tracking device is used to track the movement trajectory of the end of the suture surgical instrument. However, in the aforementioned patent case, the measuring head of the electromagnetic tracking device must be fixed to the end of the surgical instrument used before tracking can be performed, which is inconvenient in implementation. Summary of the invention

[0005] Therefore, an object of the present invention is to provide an image processing method for a bile and pancreas duct simulator.

[0006] The present invention provides an image processing method for a bile and pancreas duct simulator, comprising: a processing unit receives an image to be processed and a reference image, wherein the image to be processed includes an image of a bile and pancreas duct simulator and an image of an instrument, and the reference image includes the image of the bile and pancreas duct simulator; the processing unit performs a differentiation operation on the image to be processed and the reference image to obtain a differentiated image, and the processing unit finds a starting point in the differentiated image; the processing unit performs a binarization operation on the differentiated image to obtain a binarized image; the processing unit performs a morphological closing operation on the binarized image to obtain a denoised image; the processing unit uses the point farthest from the starting point in the denoised image as an instrument position at the end of the instrument, and marks the instrument position on the image to be processed to form an output image; and the processing unit transmits the output image to an output unit for output.

[0007] Furthermore, after receiving the image to be processed and the reference image, the processing unit first performs a grayscale processing on the image to be processed and the reference image, and then performs the difference operation on the image to be processed and the reference image after the grayscale processing.

[0008] Furthermore, after obtaining the differential image, the processing unit first performs a Gaussian filter process on the differential image, and then performs the binarization process on the differential image after the Gaussian filter process.

[0009] Furthermore, after the processing unit obtains the denoised image, the processing unit uses the point farthest from the starting point in the denoised image as the device position, and the processing unit performs an erosion process on the denoised image to obtain an eroded image. The processing unit uses the point farthest from the starting point in the eroded image as another device position, and the processing unit marks the device position and the other device position on the image to be processed to form the output image.

[0010] Furthermore, when the processing unit marks the position of the device, it takes the position of the device as a center in the image to be processed and draws a circle with a diameter of a plurality of pixels from the center to form the output image.

[0011] The processing unit receives two images in a time sequence, and uses the first image in the time sequence as the reference image and the second image as the image to be processed.

[0012] According to the above technical features, the following effects can be preferably achieved:

[0013] 1. Through the image processing of the present invention, the physician can locate the instrument more clearly and understand the operation status during practice without adding anything to the instrument.

[0014] 2. Use reference images to ensure the accuracy of subsequent image processing, and use differential operations to effectively detect the changes between the image to be processed and the reference image.

[0015] 3. Grayscale processing can reduce the dimension of image data, thereby reducing computational complexity and increasing processing speed, while retaining sufficient structural information for subsequent image analysis.

[0016] 4. Gaussian filtering and binarization processing can enhance the contour of the target object, making the subsequent morphological closing operation more accurate.

[0017] 5. The morphological closing operation can connect broken contours, further remove noise, and ensure the integrity of the object contour.

[0018] 6. Erosion treatment can effectively separate the first instrument from the second instrument, facilitating accurate detection of the instrument position of the second instrument. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a system block diagram of an embodiment of the present invention.

[0020] Figure 2 It is a flow chart of an embodiment of the present invention.

[0021] Figure 3 Schematic diagram of an embodiment of the present invention Figure 1 , indicating the image to be processed after grayscale processing.

[0022] Figure 4 Schematic diagram of an embodiment of the present invention Figure 2 , indicating the reference image after grayscale processing.

[0023] Figure 5 Schematic diagram of an embodiment of the present invention Figure 3 , indicating the differentiated image.

[0024] Figure 6 Schematic diagram of an embodiment of the present invention Figure 4 , indicating the first denoised image.

[0025] Figure 7 Schematic diagram of an embodiment of the present invention Figure 5 , indicating the binary image.

[0026] Figure 8 Schematic diagram of an embodiment of the present invention Figure 6 , indicating the second denoised image.

[0027] Fig. 9 Schematic diagram of an embodiment of the present invention Figure 7 , indicating the erosion image.

[0028] Fig.10 Schematic diagram of an embodiment of the present invention Figure 8 , indicating the output image.

[0029] Explanation of the reference numerals: 1-processing unit; 2-output unit. DETAILED DESCRIPTION

[0030] In view of the above technical features, the main effects of the image processing method for the bile and pancreas duct simulator of the present invention can be clearly presented in the following embodiments.

[0031] See also Figure 1 and Figure 2 , which discloses an image processing method for a bile and pancreas duct simulator according to an embodiment of the present invention, comprising:

[0032] A processing unit 1 receives an image to be processed and a reference image. The image to be processed includes an image of a biliopancreatic duct simulator and images of two instruments. The reference image includes the image of the biliopancreatic duct simulator. The instruments described below are named a first instrument and a second instrument for easy distinction.

[0033] Preferably, the processing unit 1 receives two images in time sequence and performs a grayscale processing on the images. The grayscale processing can reduce the dimension of the image data, thereby reducing the computational complexity and increasing the processing speed, while retaining sufficient structural information for subsequent image analysis.

[0034] Next, the processing unit 1 uses the first image in the time sequence as the reference image, such as Figure 4 As shown, the second image is used as the image to be processed, such as Figure 3 shown.

[0035] For example, the image taken at 0 seconds when the first instrument and the second instrument have not yet been inserted into the bile-pancreatic duct simulator can be used as the reference image, and the image taken at 5 seconds after the first instrument and the second instrument have been inserted into the bile-pancreatic duct simulator can be used as the image to be processed.

[0036] The processing unit 1 is, for example, a processor of a computer, and may have an image capture unit signal connected to the processing unit 1. After the image capture unit captures the image, the image capture unit transmits the image to the processing unit 1. Alternatively, the image capture unit may be further connected to the processing unit 1 via a storage unit signal, and the storage unit may be, for example, a cloud hard drive, a physical hard drive, a flash drive, a memory card, etc., and then equipped with an appropriate adapter port, etc., so as to transmit the image to the processing unit 1.

[0037] The processing unit 1 performs a difference operation on the image to be processed and the reference image to obtain a difference image, such as Figure 5 shown.

[0038] The processing unit 1 finds a starting point in the differential image. Figure 5 For example, the bottom of the object in the differential image may be used as the starting point.

[0039] The reference image is used to ensure the accuracy of subsequent image processing, and the difference operation is used to effectively detect the changed part between the image to be processed and the reference image.

[0040] The processing unit 1 performs a Gaussian filter process on the difference image to obtain a first denoised image, such as Figure 6 shown.

[0041] The processing unit 1 performs a binarization process on the first denoised image to obtain a binarized image. Figure 7 shown.

[0042] The Gaussian filtering process helps to remove random noise in the image, and the binarization process makes the edge of the object clearer. Both can enhance the contour of the target object (ie, the instrument) and make the subsequent morphological closing operation more accurate.

[0043] The processing unit 1 performs the morphological closing operation on the binary image to obtain a denoised image, that is, a second denoised image. Figure 8 This morphological closing operation helps to connect the broken object contours, further remove small noise in the image, and ensure the integrity of the object contour.

[0044] The processing unit 1 uses the point farthest from the starting point in the second denoised image as an instrument position of the first instrument end, ie, a first instrument position.

[0045] The processing unit 1 performs an erosion process on the second denoised image to obtain an eroded image, such as Fig. 9 shown.

[0046] The processing unit 1 uses the point farthest from the starting point in the eroded image as another tool position of the second tool end, ie, a second tool position.

[0047] The erosion process can effectively separate the first instrument from the second instrument, facilitating accurate detection of the second instrument position of the second instrument.

[0048] The processing unit 1 marks the first device position and the second device position on the image to be processed to form an output image, such as Fig.10 shown.

[0049] More specifically, the processing unit 1 takes the first device position and the second device position as the center of the circle in the image to be processed, and draws circles with a diameter of a plurality of pixels from the center of the circle to form the output image.

[0050] At Fig.10 The first device position is marked in a text box (such as P first ), the second device position (such as P second ) and the starting point (such as P start ), however, the aforementioned marked positions are for illustration only, and each figure of the present invention does not necessarily use the same processed image. In actual implementation, there does not necessarily have to be a text box, and the text box does not necessarily have to be marked with English text.

[0051] Finally, the processing unit 1 transmits the output image to an output unit 2 connected to the processing unit 1 for output. The output unit 2 is, for example, a screen.

[0052] It should be particularly noted that the preferred embodiment of the present invention takes two groups of the above-mentioned instruments as an example. In actual implementation, if there is only a single group of the above-mentioned instruments, the etching treatment step can be omitted and the invention can also be implemented.

[0053] Through the image processing of the present invention, the physician can more clearly locate the instrument and understand the operation status during practice without adding anything to the instrument.

[0054] Based on the description of the above embodiments, the operation, use and effects of the present invention can be fully understood. However, the above embodiments are only preferred embodiments of the present invention and should not be used to limit the scope of the present invention. That is, simple equivalent changes and modifications made according to the claims and the description of the present invention are all within the scope of the present invention.

Claims

1. An image processing method for a bile and pancreas duct simulator, It is characterized in that Include: A processing unit receives an image to be processed and a reference image, wherein the image to be processed includes an image of a bile-pancreatic duct simulator and an image of an instrument, and the reference image includes the image of the bile-pancreatic duct simulator; The processing unit performs a difference operation on the image to be processed and the reference image to obtain a difference image, and the processing unit finds a starting point in the difference image; The processing unit performs a binarization process on the differential image to obtain a binarized image; The processing unit performs a morphological closing operation on the binary image to obtain a denoised image; The processing unit uses the point farthest from the starting point in the denoised image as an instrument position of the end of the instrument, and marks the instrument position on the image to be processed to form an output image; and The processing unit transmits the output image to an output unit for output.

2. The image processing method for the bile and pancreas duct simulator according to claim 1, It is characterized in that After receiving the image to be processed and the reference image, the processing unit first performs a grayscale processing on the image to be processed and the reference image, and then performs the difference operation on the image to be processed and the reference image after the grayscale processing.

3. The image processing method for the bile and pancreas duct simulator according to claim 1, It is characterized in that After obtaining the differential image, the processing unit first performs a Gaussian filter process on the differential image, and then performs the binarization process on the differential image after the Gaussian filter process.

4. The image processing method for the bile and pancreas duct simulator according to claim 1, It is characterized in that After the processing unit obtains the denoised image, the processing unit uses the point farthest from the starting point in the denoised image as the device position, and the processing unit performs an erosion process on the denoised image to obtain an eroded image. The processing unit uses the point farthest from the starting point in the eroded image as another device position, and the processing unit marks the device position and the other device position on the image to be processed to form the output image.

5. The image processing method for the bile and pancreas duct simulator according to claim 1, It is characterized in that When the processing unit marks the position of the device, it takes the position of the device as a center in the image to be processed and draws a circle with a diameter of a plurality of pixels from the center to form the output image.

6. The image processing method for the bile and pancreas duct simulator according to claim 1, It is characterized in that The processing unit receives two images in a time sequence, and uses the first image in the time sequence as the reference image and the second image as the image to be processed.

Images