An intelligent slicing method, device and system for tissue slicer

Abstract

The present application discloses a tissue slicer slicing method, device and system. The tissue slicer slicing method comprises: obtaining the relative position relationship between the slicer's knife holder and the tissue block to be sliced; moving the slicer's knife holder to the target position according to the relative position relationship; setting initial cutting thickness information; cutting the tissue block to be sliced ​​at least twice according to the initial cutting thickness information, wherein the position of the slicing separation needle is obtained by image recognition after each cutting of the tissue block to be sliced; judging whether the position of the slicing separation needle needs to be adjusted according to the position of the slicing separation needle and the position of the uncut surface of the tissue block to be sliced. The tissue slicer slicing method of the present application performs automated cutting processing by image recognition and by presetting the cutting thickness, thereby improving the drawbacks of the existing slicing technology of the purely manual operation of the slicer and realizing intelligent cutting of the slicer.

Description

Technical Field

[0001] The present application relates to the technical field of slicers, and in particular to an intelligent slicing method for a tissue slicer, an intelligent slicing device for a tissue slicer, and an intelligent slicing system for a tissue slicer. Background Art

[0002] At present, the process of slicing human or animal tissue paraffin specimens is to use a traditional semi-automatic rotary slicer. In the first step, the left hand needs to manually shake the left handwheel of the slicer to adjust the contact between the tissue block to be cut at the chuck of the tissue block on the slicer and the blade on the knife holder; in the second step, the left hand continues to shake the handwheel while the right hand shakes the right handwheel to move the tissue block up and down. The two coordinate operations so that the blade cuts out the excess wax scraps on the tissue block. After the tissue in the tissue block is fully exposed, the left hand stops shaking, and the right hand continues to shake the handwheel to make the blade continue to flatten the tissue surface. The right hand finally rotates the handwheel until a 4-5 micron wax slice is cut out, and the slicing operation is completed. In addition, the so-called "fully automatic slicer" is not truly "fully automatic". It just adds a small motor to drive the left hand handwheel to rotate, and the right hand still repeats the above operation. This manual slicing method of repeatedly slicing a tissue block has the following defects:

[0003] First, it greatly consumes the arm function of personnel, causing labor loss; second, due to the influence of human factors, it will lead to poor slicing repeatability and lack of standardized quality control, affecting the quality of the final slices; third, the cost of personnel training is too high, and it takes three years or more than 200,000 slices to train a skilled slicer technician to be competent; fourth, the slicer needs manual operation to work, lacks intelligence, and has low efficiency. In order to reduce labor loss and reduce personnel training costs, improve slicing efficiency and ensure slicing quality, it is necessary to design an intelligent slicing method, device and system for tissue slicers to improve the shortcomings of the existing manual slicing technology of the slicer and realize intelligent slicing.

[0004] Therefore, it is hoped that a technical solution can be provided to solve or at least alleviate the above-mentioned deficiencies of the prior art. Summary of the invention

[0005] The object of the present invention is to provide an intelligent positioning and slicing method for a tissue slicer to at least solve one of the above-mentioned technical problems.

[0006] The present invention provides the following scheme:

[0007] According to one aspect of the present invention, there is provided an intelligent slicing method for a tissue slicer, the intelligent slicing method for a tissue slicer comprising:

[0008] Obtaining the relative position relationship between the knife holder of the slicer and the tissue block to be sliced;

[0009] Sending a control signal to the slicer according to the relative position relationship, so that the knife holder of the slicer moves to a target position according to the relative position relationship;

[0010] Set the initial cutting thickness information;

[0011] The tissue block to be sliced ​​is cut at least twice according to the initial cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, the position of the slicing separation needle is obtained by image recognition; according to the position of the slicing separation needle and the position of the uncut surface of the tissue block to be sliced, it is determined whether the position of the slicing separation needle needs to be adjusted, and if so, the slicing separation needle is adjusted to the position that fits the uncut surface of the tissue block to be sliced ​​before the next cutting.

[0012] Optionally, the intelligent slicing method for a tissue slicer further comprises:

[0013] Obtain cutting thickness change signal;

[0014] After obtaining the cutting thickness change signal, setting new cutting thickness information;

[0015] Cutting the tissue block to be sliced ​​according to the new cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the new cutting thickness information each time, acquiring an image of an uncut surface of the tissue block to be sliced;

[0016] By means of image recognition, it is determined whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions. If so,

[0017] Generates prompt information.

[0018] Optionally, the intelligent slicing method for a tissue slicer further comprises:

[0019] By means of image recognition, it is determined whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions. If not,

[0020] The tissue block to be sliced ​​is cut next time according to the new cutting thickness information.

[0021] Optionally, the step of obtaining the relative position relationship between the blade holder of the slicer and the tissue block to be sliced ​​comprises:

[0022] Generate a unified coordinate system;

[0023] Acquire an image of the tissue block to be sliced, which is taken by a camera device located at a known position in the unified coordinate system, wherein a reference object of known size is included in the image;

[0024] Obtaining the position of the tool holder of the slicer in the unified coordinate system;

[0025] The relative positional relationship between the tool holder and the tissue block to be sliced ​​is acquired according to the position of the tool holder in the unified coordinate system and the image having the tissue block to be sliced.

[0026] Optionally, after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, obtaining the position of the slicing separation needle by image recognition includes:

[0027] Get the cutting completion signal;

[0028] After receiving the cutting completion signal, a shooting signal is sent to the camera device;

[0029] Acquiring a connected tissue slice image acquired by a camera device according to the shooting signal;

[0030] The position of the connected tissue relative to the slice separation needle is obtained according to the connected tissue slice image.

[0031] Optionally, acquiring the position of the connected tissue relative to the slice separation needle according to the connected tissue slice image includes:

[0032] Obtaining location information of a camera device;

[0033] The relative position relationship is acquired according to the connected tissue slice images and preset camera position information.

[0034] Optionally, acquiring the relative position relationship according to the connected tissue slice images and preset camera position information includes:

[0035] Gray-scale processing is performed on the connected tissue slice image to obtain gray-scale image information;

[0036] Resizing the grayscale image information to obtain resized image information;

[0037] Get the trained object detection model;

[0038] extracting image features of the resized image information;

[0039] Inputting the image features into a trained object detection model to obtain identified connected tissue slice image portions;

[0040] The relative position relationship is obtained according to the identified connected tissue slice image parts and the preset camera position information.

[0041] Optionally, acquiring the relative position relationship according to the identified connected tissue slice image parts and preset camera position information includes:

[0042] Get the coordinate transformation matrix;

[0043] After identifying the pixel coordinates of the connected tissue slice image parts, based on the coordinate conversion matrix, the pixel coordinates of the connected tissue slice image parts are converted into the spatial coordinates of the tissue slice image parts, wherein the centroid coordinates of the two slices of the two connected tissue slice images are (x1, y1, z1) and (x2, y2, z2) respectively;

[0044] The position of the connected tissue relative to the sectioning needle is obtained through matrix transformation.

[0045] The present application also provides an intelligent slicing device for a tissue slicer, the intelligent slicing device for a tissue slicer comprising:

[0046] A relative position relationship acquisition module, which is used to acquire the relative position relationship between the knife holder of the slicer and the tissue block to be sliced;

[0047] a control signal sending module, the control signal sending module being used to send a control signal to the slicer according to the relative position relationship, so that the knife holder of the slicer moves to a target position according to the relative position relationship;

[0048] An initial cutting thickness information setting module, wherein the initial cutting thickness information setting module is used to set initial cutting thickness information;

[0049] An initial cutting module, the initial cutting module is used to cut the tissue block to be sliced ​​at least twice according to the initial cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, the position of the slicing separation needle is obtained by image recognition; according to the position of the slicing separation needle and the position of the uncut surface of the tissue block to be sliced, it is judged whether the position of the slicing separation needle needs to be adjusted, and if so, the slicing separation needle is adjusted to the position that fits the uncut surface of the tissue block to be sliced ​​before the next cutting.

[0050] The present application also provides an intelligent slicing system for a tissue slicer, which includes a slicer, the intelligent slicing device for the tissue slicer as described above, and a camera device; wherein the slicer, the intelligent slicing device for the tissue slicer, and the camera device cooperate to implement the intelligent slicing method for the tissue slicer as described above.

[0051] The intelligent slicing method for a tissue slicer of the present application performs intelligent slicing processing through image recognition and preset cutting thickness, thereby improving the drawbacks of the existing slicer's purely manual slicing technology, and utilizing AI technology to assist the slicer in slicing to achieve intelligent slicing. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of an intelligent slicing method for a tissue slicer in one embodiment of the present application.

[0053] Figure 2 It is a schematic diagram of the structure of an electronic device in one embodiment of the present application.

[0054] Figure 3 It is a schematic diagram of the structure of a slicer in one embodiment of the present application.

[0055] 1- Camera device; 2- Knife holder; 3- Tissue block chuck. DETAILED DESCRIPTION

[0056] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Figure 1 It is a flow chart of an intelligent slicing method for a tissue slicer in one embodiment of the present application.

[0058] like Figure 1 The intelligent positioning and slicing method for a tissue slicer shown includes:

[0059] Step 1: Obtain the relative position relationship between the knife holder of the slicer and the tissue block to be sliced;

[0060] Step 2: sending a control signal to the slicer according to the relative position relationship, so that the knife holder of the slicer moves to the target position according to the relative position relationship;

[0061] Step 3: Set the initial cutting thickness information;

[0062] Step 4: cutting the tissue block to be sliced ​​at least twice according to the initial cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, obtaining the position of the slicing separation needle by means of image recognition; judging whether the position of the slicing separation needle needs to be adjusted according to the position of the slicing separation needle and the position of the uncut surface of the tissue block to be sliced, and if so, adjusting the slicing separation needle to the position that fits the uncut surface of the tissue block to be sliced ​​before performing the next cutting.

[0063] The intelligent slicing method for a tissue slicer of the present application performs automated cutting processing by means of image recognition and a preset cutting thickness, thereby freeing up manpower and realizing automated cutting of the slicer.

[0064] In this embodiment, the intelligent slicing method for a tissue slicer further comprises:

[0065] Step 5: Obtain cutting thickness change signal;

[0066] Step 6: After obtaining the cutting thickness change signal, set new cutting thickness information;

[0067] Step 7: cutting the tissue block to be sliced ​​according to the new cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the new cutting thickness information each time, an image of the uncut surface of the tissue block to be sliced ​​is acquired;

[0068] Step 8: Use image recognition to determine whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions. If so,

[0069] Step 9: Generate prompt information.

[0070] In this embodiment, the cutting thickness change signal is provided manually by the operator. For example, during the automatic cutting process, when the operator believes that the cutting thickness can be changed, the signal is provided through a button or human-computer interaction.

[0071] In this embodiment, the reason why the signal is transformed is that most areas of a tissue block to be sliced ​​are not needed when cutting. For example, a tissue block to be sliced ​​is assumed to have a diameter of 10 cm, and the part containing tissue or relatively complete tissue may be 2 or 3 cm thick. Assume that these 2 or 3 cm are located in the middle area of ​​the entire tissue block to be sliced, that is, there may be 3 or 4 cm in the front that are not cut, and no fine cutting is required, only rough cutting (that is, cutting with a larger thickness) is required. In this way, when the part that needs fine cutting is not cut, a relatively large cutting thickness can be set, and when fine cutting is required, the cutting thickness needs to be adjusted.

[0072] It is understandable that the new cutting thickness information can be set manually. For example, the initial cutting thickness may be 2 mm each time, while the new cutting thickness information may be 1 mm each time.

[0073] In this embodiment, since automatic cutting is performed, it is necessary to ensure that the slicing separation needle is attached to the uncut surface of the tissue block to be sliced ​​each time cutting is performed, so as to ensure that the set cutting thickness is the same as the actual cutting thickness. That is, if the cutting thickness is set to 2 mm, if the slicing separation needle is far away from the uncut surface of the tissue block to be sliced ​​during slicing (assuming a distance of 1 mm), the actual cut of the tissue block to be sliced ​​is only 1 mm, which cannot meet the requirement. Therefore, the position of the slicing separation needle needs to be identified each time cutting is performed.

[0074] In this embodiment, judging whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions by image recognition specifically refers to:

[0075] After the first image of the uncut surface of the tissue block to be sliced ​​is obtained after cutting using the new cutting thickness information, image recognition is performed simultaneously on each image of the uncut surface of the tissue block to be sliced ​​and the image of the uncut surface of the previous tissue block to be sliced ​​(the image obtained after the first cutting using the new cutting thickness information does not need to be subjected to the above method, because there is no image of the uncut surface of the previous tissue block to be sliced ​​at this time, and starts from the next image), and it is determined whether, in the two adjacent images of the uncut surfaces of the tissue blocks to be sliced, the area occupied by the tissue recognized in the image of the uncut surface of the tissue block to be sliced ​​taken later in time in the image of the uncut surface of the tissue block to be sliced ​​is smaller than the area occupied by the tissue recognized in the image of the uncut surface of the previous tissue block to be sliced; if so, it is determined to meet the preset conditions.

[0076] In this embodiment, the area occupied by the tissue in the image of the uncut surface of the tissue block to be sliced ​​can be obtained by image recognition, that is, extracting image features of the image and inputting them into a trained classifier, thereby realizing the recognition of the area of ​​the tissue.

[0077] In this embodiment, the intelligent slicing method for a tissue slicer further comprises:

[0078] By means of image recognition, it is determined whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions. If not,

[0079] The tissue block to be sliced ​​is cut next time according to the new cutting thickness information.

[0080] In this embodiment, obtaining the relative position relationship between the blade holder of the slicer and the tissue block to be sliced ​​includes:

[0081] Generate a unified coordinate system;

[0082] Acquire an image of the tissue block to be sliced, which is taken by a camera device located at a known position in the unified coordinate system, wherein a reference object of known size is included in the image;

[0083] Obtaining the position of the tool holder of the slicer in the unified coordinate system;

[0084] The relative positional relationship between the tool holder and the tissue block to be sliced ​​is acquired according to the position of the tool holder in the unified coordinate system and the image having the tissue block to be sliced.

[0085] In this embodiment, after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, obtaining the position of the slicing separation needle by image recognition includes:

[0086] Get the cutting completion signal;

[0087] After receiving the cutting completion signal, a shooting signal is sent to the camera device;

[0088] Acquiring a connected tissue slice image acquired by a camera device according to the shooting signal;

[0089] The position of the connected tissue relative to the slice separation needle is obtained according to the connected tissue slice image.

[0090] In this embodiment, obtaining the position of the connected tissue relative to the slice separation needle according to the connected tissue slice image includes:

[0091] Obtaining location information of a camera device;

[0092] The relative position relationship is acquired according to the connected tissue slice images and preset camera position information.

[0093] In this embodiment, the acquiring the relative position relationship according to the connected tissue slice images and the preset camera position information includes:

[0094] Gray-scale processing is performed on the connected tissue slice image to obtain gray-scale image information;

[0095] Resizing the grayscale image information to obtain resized image information;

[0096] Get the trained object detection model;

[0097] extracting image features of the resized image information;

[0098] Inputting the image features into a trained object detection model to obtain identified connected tissue slice image portions;

[0099] The relative position relationship is obtained according to the identified connected tissue slice image parts and the preset camera position information.

[0100] In this embodiment, the step of acquiring the relative position relationship according to the identified connected tissue slice image parts and the preset camera position information includes:

[0101] Get the coordinate transformation matrix;

[0102] After identifying the pixel coordinates of the connected tissue slice image parts, based on the coordinate conversion matrix, the pixel coordinates of the connected tissue slice image parts are converted into the spatial coordinates of the tissue slice image parts, wherein the centroid coordinates of the two slices of the two connected tissue slice images are (x1, y1, z1) and (x2, y2, z2) respectively;

[0103] The position of the connected tissue relative to the sectioning needle is obtained through matrix transformation.

[0104] In this embodiment, grayscale processing is performed on the connected tissue slice image to obtain grayscale image information as follows:

[0105] The preprocessed image is grayed out, and the conversion formula is:

[0106] Gray=(R*30+G*59+B*11) / 100

[0107] Where R, G, and B are the pixel values ​​of the three channels of RGB in the color image, and Gray is the pixel value of the grayscale image obtained after grayscale processing.

[0108] In this embodiment, the grayscale image information is resized to obtain the resized image information as follows:

[0109] Adjust the captured image to the size required by the model. YOLOv5 usually requires 640x640 pixels. Normalize the image so that the pixel value is within the range used when training the target detection model. In this embodiment, when training the target detection model, the data set of the target detection model is divided into a training set, a validation set, and a test set, usually in a ratio of 70%:15%:15%, to ensure the generalization ability of the model on different data.

[0110] When training the target detection model, increase the diversity of training data through random rotation, flipping, scaling, cropping and other operations to improve the generalization ability of the model; train the model on the training set, regularly evaluate the performance on the validation set, and adjust the hyperparameters based on the evaluation results; use the early stopping strategy to prevent overfitting, and use callback functions such as model saving and learning rate adjustment to optimize the training process.

[0111] In this embodiment, the trained model is converted into a format suitable for deployment, such as TensorRT, ONNX, etc., to optimize the inference speed.

[0112] In this embodiment, obtaining the relative position relationship according to the identified connected tissue slice image parts and the preset camera position information includes:

[0113] Obtaining a coordinate transformation matrix; specifically, obtaining the coordinate transformation matrix through camera calibration after identifying the connected tissue slice images.

[0114] After identifying the pixel coordinates of the connected tissue slice image portion, based on the coordinate conversion matrix, the pixel coordinates of the connected tissue slice image portion are converted into the spatial coordinates of the tissue slice image portion, wherein the centroid coordinates of the two slices of the two connected tissue slice images are (x1, y1, z1) and (x2, y2, z2) respectively. Specifically as follows: After identifying the pixel coordinates of the two connected tissue slice images, based on the coordinate conversion matrix, the pixel coordinates are converted into spatial coordinates, wherein the centroid coordinates of the two connected tissue slice images are (x1, y1, z1) and (x2, y2, z2) respectively, and the position of the connected tissue relative to the slice separation needle is obtained through matrix conversion, and the slice separation needle is positioned to the middle position of the centroid of the two connected tissues and the slices are separated by moving in the Z direction.

[0115] In this embodiment, when determining the position of the position-connected tissue relative to the slicing separation needle, the shape information of the sample to be sliced ​​must first be obtained. Specifically, the pixel size of the preprocessed image is calculated based on the feature points of each reference object in the preprocessed image and the actual size of the reference object; the contour of the sample to be sliced ​​is identified in the preprocessed image based on the pixel size of the preprocessed image to obtain the contour coordinates of the sample to be sliced; the shape information of the sample to be sliced ​​is calculated based on the contour coordinates of the sample to be sliced. In order to effectively detect stable key points in the scale space, Gaussian difference kernels of different scales are used to generate image convolution.

[0116] In this embodiment, the position of the feature point of each reference object in the preprocessed image can be obtained by the following formula:

[0117]

[0118] Where w(x, y) is the window function, (I(x+u, y+v)-I(x, y)] 2 is the gradient value of the image grayscale. w(x, y) can be a rectangular window or a Gaussian window.

[0119] In this embodiment, D(x,y,σ)=(G(x,y,kσ)-G(x,y,σ))*I(x,y)=L(x,y,kσ)-L(x,y,σ)

[0120] where * is the convolution operator between x and y,

[0121]

[0122] (x, y) is the spatial coordinate and σ is the scale coordinate.

[0123] In this embodiment, in actual work, first the slicer needs to be in the initial position, that is, the positions of the various components of the slicer in the unified coordinate system are known positions. Therefore, if at the beginning, the position of the slicer is not in the initial position (for example, the knife holder is not in the preset position), it only needs to be adjusted to the preset position.

[0124] In this embodiment, the “positioning information” refers to the spatial position information of the tissue block to be sliced ​​in a unified coordinate system, such as the coordinates of the center point of the tissue block to be sliced.

[0125] In this embodiment, the “relative position information” mentioned here refers to the position information of the tissue block to be sliced ​​relative to the microtome, such as the distance between the center coordinates of the tissue block to be sliced ​​and the tool holder of the microtome.

[0126] In this embodiment, at least one reference object of known size is found in the image of the tissue block to be sliced, and the corresponding coordinates of each reference object in the preprocessed image are obtained;

[0127] Calculating the pixel size of the preprocessed image according to the corresponding coordinates of each reference object in the image of the tissue block to be sliced ​​and the actual size of the reference object;

[0128] According to the pixel size of the preprocessed image, identifying the contour of the tissue block to be sliced ​​in the image of the tissue block to be sliced, and obtaining the contour coordinates of the tissue block to be sliced;

[0129] According to the contour coordinates of the tissue block to be sliced, the positioning information of the tissue block to be sliced ​​is calculated.

[0130] Specifically, a reference object of known size can be placed on the surface of the tissue block to be sliced, so that the pixel size of the pre-processed image can be inferred from the coordinates of the reference object in the image of the tissue block to be sliced ​​and the actual size of the reference object. Once the pixel size of the pre-processed image is known, the contour of the tissue block to be sliced ​​can be identified in the pre-processed image, and the contour coordinates of the tissue block to be sliced ​​can be obtained. In this way, the relative position relationship between the knife holder of the slicer and the tissue block to be sliced ​​can be calculated.

[0131] The present application also provides an intelligent slicing device for a tissue slicer, the intelligent slicing device for a tissue slicer comprises a relative position relationship acquisition module, a control signal sending module, an initial cutting thickness information setting module and an initial cutting module, wherein:

[0132] The relative position relationship acquisition module is used to acquire the relative position relationship between the knife holder of the slicer and the tissue block to be sliced;

[0133] The control signal sending module is used to send a control signal to the slicer according to the relative position relationship, so that the knife holder of the slicer moves to the target position according to the relative position relationship;

[0134] The initial cutting thickness information setting module is used to set the initial cutting thickness information;

[0135] The initial cutting module is used to cut the tissue block to be sliced ​​at least twice according to the initial cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, the position of the slicing separation needle is obtained by image recognition; according to the position of the slicing separation needle and the position of the uncut surface of the tissue block to be sliced, it is judged whether the position of the slicing separation needle needs to be adjusted, and if so, the slicing separation needle is adjusted to the position that fits the uncut surface of the tissue block to be sliced ​​before the next cutting.

[0136] The present application also provides an intelligent slicing system for a tissue slicer, which includes a slicer, the intelligent slicing device for the tissue slicer as described above, and a camera device; wherein the slicer, the intelligent slicing device for the tissue slicer, and the camera device cooperate to implement the intelligent slicing method for the tissue slicer as described above.

[0137] See also Figure 3 The tissue slicer used in this application can be Figure 3 As shown, the tissue block to be cut is set on the tissue block chuck 3, and a blade is set on the knife holder 2 and the blade needs to be close to the tissue to be cut. The camera device 1 of the present application can be placed Figure 3 upper position of the slicer.

[0138] In this embodiment, the camera device can be a CCD camera, or a CMOS camera, etc., which can be selected according to actual needs. In addition, a light, such as an LED light, can be set on the camera device to make the surface image of the tissue block to be sliced ​​collected by the camera device clearer.

[0139] Figure 2 It is a structural block diagram of an electronic device provided by one or more embodiments of the present invention.

[0140] like Figure 2 As shown, the present application also discloses an electronic device, including: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the tissue slicer slicing method.

[0141] The present application also provides a computer-readable storage medium storing a computer program executable by an electronic device. When the computer program is run on the electronic device, the steps of the intelligent slicing method for a tissue slicer can be implemented.

[0142] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0143] The electronic device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and a memory. The operating system can be any one or more computer operating systems that implement electronic device control through a process, such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a Windows operating system. In addition, in an embodiment of the present invention, the electronic device can be a handheld device such as a smart phone or a tablet computer, or can be an electronic device such as a desktop computer or a portable computer, which is not particularly limited in the embodiment of the present invention.

[0144] The execution subject of the electronic device control in the embodiment of the present invention may be an electronic device, or a functional module in the electronic device that can call and execute a program. The electronic device may obtain the firmware corresponding to the storage medium. The firmware corresponding to the storage medium is provided by the supplier. The firmware corresponding to different storage media may be the same or different, which is not limited here. After the electronic device obtains the firmware corresponding to the storage medium, the firmware corresponding to the storage medium may be written into the storage medium, specifically, the firmware corresponding to the storage medium may be burned into the storage medium. The process of burning the firmware into the storage medium may be implemented using existing technology, which will not be described in detail in the embodiment of the present invention.

[0145] The electronic device may also obtain a reset command corresponding to the storage medium. The reset command corresponding to the storage medium is provided by the supplier. The reset commands corresponding to different storage media may be the same or different, and are not limited here.

[0146] At this time, the storage medium of the electronic device is a storage medium in which the corresponding firmware is written, and the electronic device can respond to the reset command corresponding to the storage medium in the storage medium in which the corresponding firmware is written, so that the electronic device resets the storage medium in which the corresponding firmware is written according to the reset command corresponding to the storage medium. The process of resetting the storage medium according to the reset command can be implemented by the existing technology and will not be described in detail in the embodiments of the present invention.

[0147] For the convenience of description, the above devices are described in terms of functions and are divided into various units and modules. Of course, when implementing the present application, the functions of each unit and module can be implemented in the same or multiple software and / or hardware.

[0148] Those skilled in the art will appreciate that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined.

[0149] For the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0150] It can be known from the description of the above implementation modes that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute the methods described in the various implementation modes of the present application or certain parts of the implementation modes.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent slicing method for a tissue slicer, characterized in that: The intelligent slicing method for a tissue slicer comprises: Obtaining the relative position relationship between the knife holder of the slicer and the tissue block to be sliced; Sending a control signal to the slicer according to the relative position relationship, so that the knife holder of the slicer moves to a target position according to the relative position relationship; Set the initial cutting thickness information; The tissue block to be sliced ​​is cut at least twice according to the initial cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, the position of the slicing separation needle is obtained by image recognition; according to the position of the slicing separation needle and the position of the uncut surface of the tissue block to be sliced, it is determined whether the position of the slicing separation needle needs to be adjusted, and if so, the slicing separation needle is adjusted to the position that fits the uncut surface of the tissue block to be sliced ​​before the next cutting; The intelligent slicing method for a tissue slicer further comprises: Obtain cutting thickness change signal; After obtaining the cutting thickness change signal, setting new cutting thickness information; Cutting the tissue block to be sliced ​​according to the new cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the new cutting thickness information each time, acquiring an image of an uncut surface of the tissue block to be sliced; By means of image recognition, it is determined whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions. If so, Generates prompt information.

2. The intelligent slicing method for a tissue slicer according to claim 1, characterized in that: The intelligent slicing method for a tissue slicer further comprises: By means of image recognition, it is determined whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions. If not, The tissue block to be sliced ​​is cut next time according to the new cutting thickness information.

3. The intelligent slicing method for a tissue slicer according to claim 2, characterized in that: The step of obtaining the relative position relationship between the blade holder of the slicer and the tissue block to be sliced ​​comprises: Generate a unified coordinate system; Acquire an image of the tissue block to be sliced, which is taken by a camera device located at a known position in the unified coordinate system, wherein a reference object of known size is included in the image; Obtaining the position of the tool holder of the slicer in the unified coordinate system; The relative positional relationship between the tool holder and the tissue block to be sliced ​​is acquired according to the position of the tool holder in the unified coordinate system and the image having the tissue block to be sliced.

4. The intelligent slicing method for a tissue slicer according to claim 2, characterized in that: After the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, obtaining the position of the slicing separation needle by image recognition includes: Get the cutting completion signal; After receiving the cutting completion signal, a shooting signal is sent to the camera device; Acquiring a connected tissue slice image acquired by a camera device according to the shooting signal; The position of the connected tissue relative to the slice separation needle is obtained according to the connected tissue slice image.

5. The intelligent slicing method for a tissue slicer according to claim 4, characterized in that: The step of obtaining the position of the connected tissue relative to the slice separation needle according to the connected tissue slice image comprises: Obtaining location information of a camera device; The relative position relationship is acquired according to the connected tissue slice images and preset camera position information.

6. The intelligent slicing method for a tissue slicer according to claim 5, characterized in that: The acquiring of the relative position relationship according to the connected tissue slice images and the preset camera position information comprises: Gray-scale processing is performed on the connected tissue slice image to obtain gray-scale image information; Resizing the grayscale image information to obtain resized image information; Get the trained object detection model; extracting image features of the resized image information; Inputting the image features into a trained object detection model to obtain identified connected tissue slice image portions; The relative position relationship is obtained according to the identified connected tissue slice image parts and the preset camera position information.

7. The intelligent slicing method for a tissue slicer according to claim 6, characterized in that: The step of obtaining the relative position relationship according to the identified connected tissue slice image parts and the preset camera position information includes: Get the coordinate transformation matrix; After identifying the pixel coordinates of the connected tissue slice image parts, based on the coordinate conversion matrix, the pixel coordinates of the connected tissue slice image parts are converted into the spatial coordinates of the tissue slice image parts, wherein the centroid coordinates of the two slices of the two connected tissue slice images are (x1, y1, z1) and (x2, y2, z2) respectively; The position of the connected tissue relative to the sectioning needle is obtained through matrix transformation.

8. An intelligent slicing device for a tissue slicer, characterized in that: The intelligent slicing device for a tissue slicer comprises: A relative position relationship acquisition module, which is used to acquire the relative position relationship between the knife holder of the slicer and the tissue block to be sliced; a control signal sending module, the control signal sending module being used to send a control signal to the slicer according to the relative position relationship, so that the knife holder of the slicer moves to a target position according to the relative position relationship; An initial cutting thickness information setting module, wherein the initial cutting thickness information setting module is used to set initial cutting thickness information; an initial cutting module, the initial cutting module is used to cut the tissue block to be sliced ​​at least twice according to the initial cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the initial cutting thickness information each time, the position of the slicing separation needle is obtained by image recognition; according to the position of the slicing separation needle and the position of the uncut surface of the tissue block to be sliced, it is judged whether the position of the slicing separation needle needs to be adjusted, and if so, the slicing separation needle is adjusted to the position of the uncut surface of the tissue block to be sliced ​​before the next cutting; The slicing method of the intelligent slicing device for a tissue slicer includes: Obtain cutting thickness change signal; After obtaining the cutting thickness change signal, setting new cutting thickness information; Cutting the tissue block to be sliced ​​according to the new cutting thickness information, wherein after the tissue block to be sliced ​​is cut according to the new cutting thickness information each time, acquiring an image of an uncut surface of the tissue block to be sliced; By means of image recognition, it is determined whether the uncut surface of the tissue block to be sliced ​​meets the preset conditions. If so, Generates prompt information.

9. An intelligent slicing system for a tissue slicer, characterized in that: The intelligent slicing system for a tissue slicer comprises a slicer, an intelligent slicing device for a tissue slicer as claimed in claim 8, and a camera device; wherein the slicer, the intelligent positioning slicing device for a tissue slicer, and the camera device cooperate to implement the intelligent slicing method for a tissue slicer as claimed in any one of claims 1 to 7.

Images