CN114239678A - Pathological section image labeling method and system and readable storage medium - Google Patents

Abstract

The embodiment of the application provides a pathological section image labeling method, a pathological section image labeling system and a readable storage medium, wherein the method comprises the steps of obtaining a pathological section image and receiving a labeling and dotting operation instruction; when responding to an annotation dotting operation instruction, performing annotation dotting processing on the pathological section image to obtain a corresponding annotation image block; marking cell image blocks belonging to different cell types in the marked image blocks by adopting different colors; and when the received image display operation instruction is received, displaying the marked image block through a front-end display interface. The method can improve the identification degree of the marked points.

Description

Pathological section image labeling method and system and readable storage medium

Technical Field

The application relates to the technical field of image processing, in particular to a pathological section image labeling method, a pathological section image labeling system and a readable storage medium.

Background

The pathological section images formed by the sections are often tens of thousands of cells, and a pathologist needs to analyze and label the digital sections in detail when observing the pathological images. In recent years, with the rapid development of deep learning techniques and digital scanners. Some auxiliary marking tools are also increasing. The auxiliary marking tool used in the market at present mainly obtains displayed digital slices through computer software, manually dots the digital slices, and manually inputs character identifiers to perform classification. However, the method only solves the problem that the on-line operation of converting the off-line annotation into the digital slice lacks some convenience and readability, and the problem that the annotation point identification is poor.

Disclosure of Invention

The embodiment of the application aims to provide a pathological section image annotation method, a pathological section image annotation system and a readable storage medium, which can improve the identification degree of an annotation point.

The embodiment of the application also provides a pathological section image labeling method, which comprises the following steps:

acquiring a pathological section image and receiving an annotation dotting operation instruction;

when the annotation dotting operation instruction is responded, performing annotation dotting processing on the pathological section image to obtain a corresponding annotation image block; wherein, the cell image blocks belonging to different cell types in the labeled image block are dotted and labeled by adopting different colors;

and when the received image display operation instruction is received, displaying the marked image block through a front-end display interface.

In a second aspect, an embodiment of the present application further provides a pathological section image annotation system, where the system includes an image acquisition module, an image annotation module, and an image display module, where:

the image acquisition module is used for acquiring pathological section images and receiving marking and dotting operation instructions;

the image annotation module is used for performing annotation dotting processing on the pathological section image to obtain a corresponding annotated image block when responding to the annotation dotting operation instruction; wherein, the cell image blocks belonging to different cell types in the labeled image block are dotted and labeled by adopting different colors;

and the image display module is used for displaying the marked image blocks through a front-end display interface when the received image display operation instruction is received.

In a third aspect, an embodiment of the present application further provides a readable storage medium, where the readable storage medium includes a program of a pathological section image annotation method, and when the program of the pathological section image annotation method is executed by a processor, the method implements the steps of the pathological section image annotation method described in any one of the above.

As can be seen from the above, according to the pathological section image labeling method, system and readable storage medium provided in the embodiments of the present application, on one hand, cell image blocks belonging to different cell types in the labeled image block are dotted and labeled with different colors, so that the problem that cell classification cannot be well distinguished due to single labeling color of the image is avoided, and the identification degree of the labeling point is improved. On the other hand, the labeling image blocks are displayed through the front end, so that the labeling result can be further displayed in front of the user, the user can conveniently and quickly observe and position the labeling and classifying results of the pathological section images based on the front end display result, and good visual experience is brought.

Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

Fig. 1 is a flowchart of a method for labeling a pathological section image according to an embodiment of the present disclosure.

Fig. 2 is a diagram of the display effect of the front-end display interface.

Fig. 3 is a schematic structural diagram of a pathological section image annotation system according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

In one or more embodiments of the present invention, as shown in fig. 1, a pathological section image annotation method is provided, which is described by taking as an example that the method is applied to a computer device (the computer device may specifically be a terminal, where the terminal may specifically be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices), and includes the following steps:

and S101, acquiring a pathological section image and receiving an annotation dotting operation instruction.

Specifically, the pathological section image may be uploaded to the computer device in advance by the operating user or the administrator, and stored in the database, and when the computer device needs to acquire the pathological section image, the pathological section image is determined by requesting the database and based on data fed back from the database.

In one embodiment, the user can select a pathological section image which the user wants to view in a browsing interface provided by the computer device, and select an image area of interest in the pathological section image to view. When the user selects the interested image area, the user can click a drawing tool provided in the browsing interface, for example, a drawing tool such as a rectangle or free drawing, to draw the area, and mark and dot in the drawn area. In the current embodiment, when a user clicks a drawing tool to draw a region, a marking and dotting operation instruction is synchronously generated; subsequently, the computer equipment synchronously displays the drawing result in the browsing interface based on the received marking and dotting operation instruction and in combination with the operation condition of the user on the drawing tool.

Step S102, when responding to an annotation dotting operation instruction, performing annotation dotting processing on the pathological section image to obtain a corresponding annotation image block; and marking the cell image blocks belonging to different cell types in the marked image blocks by adopting different colors.

Based on the above embodiment, the computer device provides a way of prompting the user to manually draw the region to be labeled by operating the mouse, and after it is determined that the drawing by the user is completed, provides a way of manually dotting, labels the cells contained in the image, and displays the labeled result in the browsing interface.

In one embodiment, the computer device performs edge detection on the relative size of the annotation point mapped in the image and the drawn annotation area to ensure that the annotation point is accurately drawn in the range included in the annotation area, and synchronously performs drawing colors and recording of mapping coordinate points of the annotation points on different types of annotation points respectively. Like this, follow-up user when observing the mark result, through the mark colour that shows, can discern the categorised condition of mark cell fast, from this, brings the good experience in the vision, improves the degree of distinguishing of mark point.

And step S103, displaying the marked image blocks through the front-end display interface when the received image display operation instruction is received.

Specifically, each of the labeled image blocks generated in step S102 is synchronously stored in the database, when the computer device receives an image display operation instruction, it is determined that a target labeled image block to be displayed needs to be displayed at present on the front-end display interface, the computer device requests the database for data retrieval, and at present, the database retrieves a corresponding target labeled image block from each of the stored labeled image blocks based on the received data retrieval request, and further feeds the target labeled image block as a retrieval result back to the computer device for displaying by the computer device through the front-end display interface.

In one embodiment, before performing data retrieval, the computer device generates a retrieval request instruction based on the unique image characteristics of the target annotation image block, and sends the retrieval request instruction to the database, and the database performs data retrieval based on the determined image characteristics, so as to improve the retrieval efficiency of the target annotation image block.

It should be noted that, of course, each annotation image block generated in step S102 is not limited to be stored in a database, and may also be stored in a cloud, or a server cluster connected to a computer device, and the like, which is not limited in this embodiment of the present application. For example, before the computer device stores the annotated image block in the database, the annotated image block is numbered, and then the annotated image block and the corresponding assignment number are bound and stored, so that after the assignment number of the target annotated image block is determined, the computer device can generate the retrieval request instruction based on the assignment number, which is not limited in the embodiment of the present application.

Therefore, according to the pathological section image labeling method provided by the embodiment of the application, on one hand, cell image blocks belonging to different cell types in the labeled image blocks are dotted and labeled by adopting different colors, so that the problem that cell classification cannot be well distinguished due to single labeling color of the image is solved, and the identification degree of the labeling points is improved. On the other hand, the labeling image blocks are displayed through the front end, so that the labeling result can be further displayed in front of the user, the user can conveniently and quickly observe and position the labeling and classifying results of the pathological section images based on the front end display result, and good visual experience is brought.

In one embodiment, in step S102, the labeling and dotting process is performed on the pathological section image, and includes:

in step S1021, an annotatable target region is determined in the pathological section image.

Specifically, the computer device determines the target region that can be labeled according to the distribution dispersion degree of the cell image blocks in the pathological section image, that is, the target region can maximally cover the multiple cell image blocks that are distributed tightly (in a specific implementation, refer to fig. 2, a region outlined by a rectangular frame in fig. 2 is the target region, and each "dot" existing in the region is each labeled cell image block, in the present embodiment, based on the "dot" distribution, the cell distribution in the region can be further determined).

In step S1022, the coordinate mapping points and the cell types to which the coordinate mapping points belong are determined for each cell image block in the target region to which the cell image belongs.

Specifically, the computer device may identify, for each cell image block of the target area, a coordinate mapping point of each cell image block from the target area based on an edge detection method. And further determining the cell type to which each cell image block is distributed based on the image detail characteristics of each cell image block through past processing experience or from a database in which 'image detail characteristics-cell type' association binding data is stored.

The purpose of the edge detection method is to: points in the digital image where the brightness change is significant are identified. Wherein significant changes in image attributes typically reflect significant events and changes in the attributes. These include (1) discontinuities in depth, (2) surface orientation discontinuities, (3) material property changes, and (4) scene lighting changes. In specific implementation, the data size is greatly reduced by image edge detection, irrelevant information is removed, and important structural attributes of the image are reserved.

And S1023, marking and dotting the pathological section image based on the determined coordinate mapping points and the cell types, so as to respectively mark and mark cell image blocks of each type by adopting different colors in the target area.

Specifically, the computer device determines a marking point position based on the determined coordinate mapping point. And then marking the cells by manually dotting according to the cell shape outline at the position. In addition, the computer device can also perform pre-definition of drawing colors for cell classes. When the corresponding cell image blocks are marked, respectively assigning corresponding drawing colors to the cell image blocks of different categories based on the predefined drawing colors; the drawing color of each cell type is unique, so that when a user observes the labeling result in a corresponding browsing interface, the labeled cell types can be seen at a glance through different colors, and good visual experience is brought.

In the present embodiment, of course, the method is not limited to a manual dotting manner, for example, in the case of more mature technology, the computer device can also automatically generate a shape contour of a cell in a corresponding target region after the corresponding target region is selected by a frame on a pathological section image based on a written automatic labeling script, so as to achieve the purpose of automatic labeling of the cell contour. In addition, the computer device is not limited to distinguish different types of cells by colors, and may also distinguish different types of cells by assigning special marks or images to the different types of cells, and the like.

In one embodiment, in step S103, displaying the annotation image block through the front-end display interface includes: counting the number of cells and the cell proportion of each cell image block labeled in the labeled image block to obtain a corresponding statistical result; and when the marked image blocks are displayed through the front-end display interface, performing correlation display on the statistical results.

Specifically, the computer device determines the total number of cells contained in the target region by traversing each image block of cells. And in the process of traversing, determining the number of cells corresponding to each classified cell based on the classification result of the cells. After the traversal is finished, the cell proportion corresponding to each classified cell can be further calculated by combining the determined total number of the cells and the cell number corresponding to each classified cell. For example, referring to fig. 2, from the current display interface, it can be further determined that the cell categories included in the currently framed target region are: the total number of cells of the weak incomplete membrane-positive tumor cells and the weak-medium complete cell membrane-positive tumor cells is 2, and the proportion of the cells is 11.76% based on the display area at the lower right corner of the display interface; the total number of "weak-intermediate intact cell membrane positive tumor cells" was 7, which was 41.18%.

In one embodiment, the calculated statistical result may be displayed in the right area of the display interface (as shown in fig. 2) to visually display the statistical data in the user field of view. In one embodiment, a checkbox may be set in the display interface, and a user may click the checkbox to link to the corresponding display area and display the specific statistics of the cell image blocks in the display area. In one embodiment, the specific statistics can be summarized in a table, and data presentation is performed through the table, which can also help a user to quickly locate the most abundant cell types.

In the current embodiment, the marked image blocks and the corresponding associated statistical results are displayed in various display modes, so that a user can clearly view the marked results, and the user can concentrate on the marked slices.

In one embodiment, when displaying the annotation image block through the front-end display interface, performing the associated display of the statistical result includes: correlating the statistical results to corresponding target cell image blocks; and acquiring the marked color of the target cell image block, and adjusting the font color of the statistical result to be the marked color when the statistical result is displayed in an associated manner so as to keep the statistical result and the corresponding associated cell image block unified in the displayed color.

Specifically, in order to ensure visual appearance consistency, the computer device adjusts the font color of the statistical result that is associated with and required to be displayed by the corresponding target cell image block to the corresponding required labeling color. Therefore, when the correlation display of the statistical result is carried out, based on the color consistency, the user can quickly locate the corresponding correlation statistical information, and the phenomenon that the working efficiency of the user is influenced by paying attention to the wrong statistical result under the condition of displaying more information is avoided.

In one embodiment, the computer device may also display the target cell image block and the corresponding statistical information to be associated in an associated manner through a guide symbol such as a guide arrow drawn in real time without changing a font color of the associated statistical information. Therefore, the user can further position the corresponding associated statistical information along the corresponding guiding direction through the guiding symbol displayed in the display interface.

In the current embodiment, based on the modes of displaying the unification of colors or guiding symbols and the like, the cell image blocks and the corresponding statistical information are displayed in an associated manner, so that a user is helped to quickly locate the correct associated statistical information, and the operation experience of the user is improved.

In one embodiment, the cell type of each cell image block is determined by: inputting the cell image blocks into a trained classification network, and processing the cell image blocks through the classification network to obtain cell class classification results; based on the manual classification labeling result, when the cell classification result is determined to be correct, determining the corresponding cell classification based on the cell classification result; upon determining that the cell class classification result is erroneous, the classification network is retrained based on the re-determined correct labeling result.

In one embodiment, before the step of inputting the cell image block into the trained classification network, the method further comprises: acquiring original sample data and countermeasure sample data, wherein the original sample data comprises a cell image sample added with an artificial classification labeling result, and the countermeasure sample data comprises a cell image sample applying interference factors on the basis of the original sample data; inputting original sample data and challenge sample data into a classification network, performing virtual challenge training on the classification network, and processing the extracted image features based on a preset support vector machine in the training process to obtain a corresponding cell classification result.

In one embodiment, the method further comprises: aiming at each cell image block which is labeled, when the cell type of the corresponding cell image block belongs to is changed, the target labeling color required by the corresponding changed cell type is determined; and synchronously changing the current labeling color of the corresponding cell image block into the target labeling color, so that the synchronous change of the labeling colors is kept when the cell type to which the cell image block belongs is changed.

Specifically, the computer device may record and store target labeling colors required for each cell type in advance, further determine a labeling color corresponding to a required adjustment based on each item of stored information stored in advance when it is determined that the cell type needs to be changed currently, and simultaneously change the labeling color and the counted information (for example, total cell data and cell proportion) while adjusting the cell type. For example, when the modification result is synchronously displayed, prompt information such as "the cell type of a certain cell a has been modified from the type B to the type C, and the statistical information has been synchronously modified" is displayed in a certain specified area in the display interface.

Referring to fig. 3, an embodiment of the present application further provides a pathological section image annotation system 300, where the system 300 includes an image acquisition module 301, an image annotation module 302, and an image display module 303, where:

the image obtaining module 301 is configured to obtain a pathological section image and receive an annotation dotting operation instruction.

The image annotation module 302 is configured to perform annotation dotting processing on the pathological section image to obtain a corresponding annotation image block when responding to an annotation dotting operation instruction; and marking the cell image blocks belonging to different cell types in the marked image blocks by adopting different colors.

The image display module 303 is configured to display the annotation image block through a front-end display interface when the received image display operation instruction is received.

In one embodiment, the image annotation module 302 is further configured to determine an annotatable target region in the pathological section image; determining coordinate mapping points and cell types of the cell image blocks aiming at the cell image blocks of the target area; and marking and dotting the pathological section images based on the determined coordinate mapping points and the cell types so as to respectively mark and label the cell image blocks of each type by adopting different colors in the target area.

In one embodiment, the image displaying module 303 is further configured to count the number of cells and the ratio of the cells for each cell image block labeled in the labeled image block to obtain a corresponding statistical result; and when the marked image blocks are displayed through the front-end display interface, performing correlation display on the statistical results.

In one embodiment, the image display module 303 is further configured to associate the statistical result with the corresponding target cell image block; and acquiring the marked color of the target cell image block, and adjusting the font color of the statistical result to be the marked color when the statistical result is displayed in an associated manner so as to keep the statistical result and the corresponding associated cell image block unified in the displayed color.

In one embodiment, the image labeling module 302 is further configured to input the cell image block into a trained classification network, and process the cell image block through the classification network to obtain a cell class classification result; based on the manual classification labeling result, when the cell classification result is determined to be correct, determining the corresponding cell classification based on the cell classification result; upon determining that the cell class classification result is erroneous, the classification network is retrained based on the re-determined correct labeling result.

In one embodiment, the image annotation module 302 is further configured to obtain original sample data and countermeasure sample data, where the original sample data includes a cell image sample to which the manual classification annotation result has been added, and the countermeasure sample data includes a cell image sample to which an interference factor is applied on the basis of the original sample data; inputting original sample data and challenge sample data into a classification network, performing virtual challenge training on the classification network, and processing the extracted image features based on a preset support vector machine in the training process to obtain a corresponding cell classification result.

In one embodiment, the image displaying module 303 is further configured to, for each cell image block that has been labeled, when the cell type to which the corresponding cell image block belongs is changed, determine a target labeling color required by the corresponding changed cell type; and synchronously changing the current labeling color of the corresponding cell image block into the target labeling color, so that the synchronous change of the labeling colors is kept when the cell type to which the cell image block belongs is changed.

Therefore, the pathological section image labeling system provided by the embodiment of the application, on one hand, the cell image blocks belonging to different cell categories in the labeled image blocks are dotted and labeled by adopting different colors, so that the problem that cell classification cannot be well distinguished due to single labeling color of the image is avoided, and the identification degree of the labeling points is improved. On the other hand, the labeling image blocks are displayed through the front end, so that the labeling result can be further displayed in front of the user, the user can conveniently and quickly observe and position the labeling and classifying results of the pathological section images based on the front end display result, and good visual experience is brought.

The embodiment of the present application provides a storage medium, and when being executed by a processor, the computer program performs the method in any optional implementation manner of the above embodiment. The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (10)

1. A pathological section image labeling method is characterized by comprising the following steps:

acquiring a pathological section image and receiving an annotation dotting operation instruction;

when the annotation dotting operation instruction is responded, performing annotation dotting processing on the pathological section image to obtain a corresponding annotation image block; wherein, the cell image blocks belonging to different cell types in the labeled image block are dotted and labeled by adopting different colors;

and when the received image display operation instruction is received, displaying the marked image block through a front-end display interface.

2. The method of claim 1, wherein said labeling and dotting said pathological section image comprises:

determining an annotatable target area in the pathological section image;

determining coordinate mapping points and cell types of the cell image blocks aiming at the cell image blocks of the target area;

and marking and dotting the pathological section image based on the determined coordinate mapping points and the cell types so as to respectively mark and mark the cell image blocks of each type by adopting different colors in the target area.

3. The method of claim 1, wherein said displaying the annotation image block via a front-end display interface comprises:

counting the number of cells and the cell ratio of each cell image block labeled in the labeled image block to obtain a corresponding statistical result;

and when the marked image blocks are displayed through a front-end display interface, performing correlation display of statistical results.

4. The method according to claim 3, wherein the performing associated display of the statistical result while displaying the labeled image block through the front-end display interface comprises:

correlating the statistical results to corresponding target cell image blocks;

and acquiring the marked color of the target cell image block, and adjusting the font color of the statistical result to the marked color when the statistical result is displayed in a correlated manner so as to keep the statistical result and the corresponding correlated cell image block uniform in the displayed color.

5. The method according to claim 1, wherein the cell type of each cell image block is determined by the following steps:

inputting the cell image blocks into a trained classification network, and processing the cell image blocks through the classification network to obtain cell class classification results;

based on the manual classification labeling result, when the cell classification result is determined to be correct, determining a corresponding cell classification based on the cell classification result;

upon determining that the cell class classification result is erroneous, the classification network is retrained based on the re-determined correct labeling result.

6. The method of claim 5, wherein prior to the step of inputting the patch of cells into the trained classification network, the method further comprises:

obtaining original sample data and countermeasure sample data, wherein the original sample data comprises a cell image sample added with an artificial classification labeling result, and the countermeasure sample data comprises a cell image sample applying interference factors on the basis of the original sample data;

and inputting the original sample data and the countermeasure sample data into a classification network, performing virtual countermeasure training on the classification network, and processing the extracted image characteristics based on a preset support vector machine in the training process to obtain a corresponding cell classification result.

7. The method according to any one of claims 1-6, further comprising:

aiming at each cell image block which is labeled, when the cell type of the corresponding cell image block belongs to is changed, the target labeling color required by the corresponding changed cell type is determined;

and synchronously changing the current labeling color of the corresponding cell image block into the target labeling color, so that the labeling colors are kept to be synchronously changed when the cell type to which the cell image block belongs is changed.

8. The pathological section image labeling system is characterized by comprising an image acquisition module, an image labeling module and an image display module, wherein:

the image acquisition module is used for acquiring pathological section images and receiving marking and dotting operation instructions;

the image annotation module is used for performing annotation dotting processing on the pathological section image to obtain a corresponding annotated image block when responding to the annotation dotting operation instruction; wherein, the cell image blocks belonging to different cell types in the labeled image block are dotted and labeled by adopting different colors;

and the image display module is used for displaying the marked image blocks through a front-end display interface when the received image display operation instruction is received.

9. The system of claim 8, wherein the image labeling module is further configured to determine an annotatable target region in the pathology slice image; determining coordinate mapping points and cell types of the cell image blocks aiming at the cell image blocks of the target area; and marking and dotting the pathological section image based on the determined coordinate mapping points and the cell types so as to respectively mark and mark the cell image blocks of each type by adopting different colors in the target area.

10. A readable storage medium, characterized in that the readable storage medium includes a pathological section image labeling method program, which when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images