Identifying region of interest of sample

Abstract

The inventive concept relates to a method (40) and apparatus (10) for identifying a region of interest in a sample (192). The method (40) comprises: capturing (S400), by an image sensor (150), a plurality of digital image datasets (300), each digital image dataset comprising pixels and relating to one of a plurality of positions of the sample; for each digital image data set: forming (S402) a set of combined pixels, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value related to a subset of pixels of the digital image data set; and forming (S404) a compressed digital representation comprising the combined set of pixels; arranging (S406) the compressed digital representations in a data structure, thereby forming a common compressed digital representation (350) of the sample (192) wherein the data structure of each compressed digital representation comprises information relating to a position of the digital image dataset associated with the compressed digital representation of the plurality of positions of the sample; and identifying (S408) a region of interest of the sample (192) based on pixel values of the co-compressed digital representation.

Description

Technical Field

[0001] The inventive concept relates to a method and apparatus for identifying a region of interest of a sample. Background Art

[0002] Scanning samples (e.g., blood or bone marrow smears) is often performed using digital microscopy. However, as magnification increases and resolution increases, the field of view of the microscope decreases, resulting in an increase in the number of images required to scan the sample. Therefore, scanning a large area with a high-power microscope objective usually takes a considerable amount of time. For example, the field of view of a 100x microscope objective is typically 0.15 × 0.2 mm 2 , which means that in order to 2 To fully image a sample of 20,000, it is necessary to image the sample at approximately 20,000 individual locations. In order to produce a detailed image of the sample, the microscope objective needs to be moved so that the sample is properly focused. Each such movement of the microscope objective takes time, and since a large number of locations usually need to be imaged, it can take quite a long time to fully image a sample.

[0003] In some cases, the resolution of a high-power microscope objective is not needed, and it is desired to scan a larger area. This may occur when the main priority is to detect objects within the sample, rather than to actually analyze the sample. In some cases, this can be solved by replacing the microscope objective with a microscope objective of relatively lower magnification, because the lower the resolution, the larger the field of view. However, some microscope systems are only equipped with high-power microscope objectives or a single, non-interchangeable high-power microscope, so the field of view of the microscope objective cannot be increased. Therefore, there is a need in the art. Summary of the invention

[0004] An object is to at least partially mitigate, alleviate or eliminate one or more of the above mentioned deficiencies in the art singly or in any combination.

[0005] According to a first aspect, a method for identifying a region of interest of a sample is provided. The method comprises: capturing a plurality of digital image data sets by an image sensor, each digital image data set comprising pixels and relating to one of a plurality of locations of the sample; for each digital image data set: forming a combined pixel set, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value relating to a subset of pixels of the digital image data set, and forming a compressed digital representation comprising the combined pixel set; arranging the compressed digital representations in a data structure to form a common compressed digital representation of the sample, wherein the data structure of each compressed digital representation comprises information relating to one of a plurality of locations of the sample, the digital image data set associated with the compressed digital representation; and identifying a region of interest of the sample based on the pixel values ​​of the common compressed digital representation.

[0006] In the context of the present disclosure, the expression "region of interest" should be interpreted as a region of a sample that is relatively more interesting than other regions of the sample. Such a region may, for example, include one or more objects within the sample that may be of interest for analysis and / or imaging, etc.

[0007] In the context of the present disclosure, the expression "digital image dataset" should be interpreted as data relating to a digital image captured using an image sensor. The digital image dataset may be used to form a digital image of a corresponding imaged portion of a sample.

[0008] In the context of the present disclosure, the expression "compressed digital representation" should be interpreted as a representation of a corresponding digital image data set. The compressed digital representation preferably comprises fewer pixels than the plurality of digital image data sets. The number of pixels in the compressed digital representation may be similar to or equal to the number of formed combined pixels used to form the compressed digital representation.

[0009] The compressed digital representation is arranged in a data structure to form a common compressed digital representation of a sample. For each compressed digital representation, the data structure includes information about a position of a digital image data set associated with the compressed digital representation in a plurality of positions of the sample. In other words, for each compressed digital representation, the data structure includes information about a position in a plurality of positions of the sample, at which position its associated digital image data set (i.e., the digital image data set forming the compressed digital representation) is captured. Therefore, it can be sorted relative to the position of the compressed digital representation originally in the sample, for example to form a graphical representation of the sample. Any type of data structure can be advantageously used. Non-limiting examples of related data structures include images, arrays, vectors, matrices, and lists.

[0010] The inventive concept allows for the identification of a region of interest using less information than that captured by the image sensor. In other words, the captured information is reduced, for example by reducing the number of pixels, and the region of interest of the sample is identified using the reduced information. This in turn reduces the amount of data that needs to be processed to identify the region of interest of the sample. This reduction in the amount of data to be processed can reduce the requirements for associated processing power and / or associated bandwidth.

[0011] A further associated advantage is that a region of interest of the sample can be identified without using the spatial details of the sample depicted in the multiple digital image data sets. Instead, the region of interest can be identified based on the pixel values ​​of the common compressed digital representation (i.e., the pixel values ​​of the combined pixel set). Therefore, since the region of interest of the sample can be identified without using the spatial details of the sample, the sample does not need to be focused when capturing the multiple digital image data sets.

[0012] In forming the combined pixel set, each pixel value in the combined pixel set may be determined based on a function of at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set.

[0013] Therefore, each pixel value of these combined pixel sets can be determined in the following manner: at least one of the intensity value and the color value related to the pixel subset of the digital image data set is input into a function, thereby obtaining a pixel value as an output. Therefore, the pixel value thus obtained will be based on a function of at least one of the intensity value and the color value. It should be understood that each pixel value of these combined pixel sets can be determined by inputting at least one of the value related to the intensity value and the value related to the color value (the intensity value and the color value are related to the pixel subset of the digital image data set) into a function. In other words, it is not necessary to input the exact intensity value and / or color value into the function to determine each pixel value. For example, a close value, a rounded value or a value otherwise related to the intensity value and / or the color value can be advantageously used.

[0014] In the context of the present disclosure, the expression "function" should be interpreted as an operation performed on input values ​​such that a specific output value is produced, wherein the relationship between the input values ​​and the output values ​​is determined by the function.

[0015] The function may include performing a single operation directly on the input value. Thus, the function may include performing an operation on at least one of intensity values ​​and color values ​​associated with a subset of pixels of the digital image data set. Examples of such operations include forming, for each pixel, an average, a weighted average, a median of at least one of intensity values ​​and color values ​​associated with a subset of pixels of the digital image data set.

[0016] The function can be a one-to-one relationship between input values ​​and output values.

[0017] The function may include performing a plurality of operations, wherein a first operation is performed directly on an input value. Thus, the function may include performing a first operation on at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set, and then performing a second operation on a result of the first operation. Non-limiting examples of such operations include forming, for each pixel, a square value, a square root value, or a logarithmic value of at least one of an intensity value and a color value for each pixel in the subset of pixels of the digital image data set, and then forming an average, a weighted average, a median of the values ​​obtained earlier, thereby obtaining, for each pixel, a pixel value associated with the subset of pixels of the digital image data set.

[0018] Further, the function may include performing a first operation on at least one of intensity values ​​and color values ​​associated with a subset of pixels of the digital image data set, then performing a second operation on a result of the first operation, and then performing a further operation on a result of the second operation. Any number of further operations may be advantageously used.

[0019] In forming the combined pixel set, each pixel value in the combined pixel set may be determined based on at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set.

[0020] Each pixel value in these combined pixel sets may be an average, a median, or a sum of the pixel subsets of the corresponding digital image data set.

[0021] An associated advantage is that each pixel value in the combined pixel set may be calculated in a simple and / or efficient manner.

[0022] Each combined pixel set may consist of one combined pixel.

[0023] An associated advantage is that the number of pixels that collectively combine the digital representation (ie, the combined pixels) may be reduced, thereby further reducing one or more of associated bandwidth requirements, memory requirements, and processing requirements.

[0024] A subset of pixels of a digital image dataset may consist of all pixels of the digital image dataset.

[0025] In other words, each pixel value of the combined pixel sets may be based on at least one of intensity values ​​and color values ​​associated with all pixels of the corresponding digital image data set.

[0026] An associated advantage is that the number of pixels that collectively combine the digital representation (ie, the combined pixels) may be reduced, thereby further reducing one or more of associated bandwidth requirements, memory requirements, and processing requirements.

[0027] The subset of pixels may be a predetermined subset of pixels.

[0028] In other words, the subset of the digital image data set may include a predetermined number of pixels.

[0029] According to a second aspect, a device for identifying a region of interest of a sample is provided. The device includes: an image sensor, and a circuit system configured to perform: a capture function configured to capture multiple digital image data sets using the image sensor, each digital image data set including pixels and associated with one of a plurality of locations of the sample; a formation function configured to: form a combined pixel set for each digital image data set, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set; and form a compressed digital representation including the combined pixel set; an arrangement function configured to arrange the compressed digital representations in a data structure to form a common compressed digital representation of the sample, wherein the data structure of each compressed digital representation includes information related to a position of the digital image data set associated with the compressed digital representation among a plurality of locations of the sample; and an identification function configured to identify a region of interest of the sample based on the pixel values ​​of the common compressed digital representation.

[0030] Each pixel value in these combined pixel sets may be an average, a median, or a sum of the pixel subsets of the corresponding digital image data set.

[0031] Each combined pixel set may consist of one combined pixel.

[0032] A subset of pixels of a digital image dataset may consist of all pixels of the digital image dataset.

[0033] The subset of pixels may be a predetermined subset of pixels.

[0034] The above features of the first aspect also apply to this second aspect where applicable. To avoid excessive repetitions, reference is made to the above.

[0035] The device may be a camera.

[0036] According to a third aspect, there is provided a non-transitory computer readable storage medium comprising program code portions which, when executed on a device comprising processing capabilities and an image sensor, perform the method according to the first aspect.

[0037] The above features of the first and second aspects also apply to this third aspect where applicable. To avoid excessive repetitions, reference is made to the above.

[0038] Further scope of applicability of the present disclosure will become apparent from the detailed description given below. However, it should be understood that although the detailed description and specific examples indicate preferred variations of the inventive concept, they are given only by way of illustration, because various changes and modifications within the scope of the inventive concept will become apparent to those skilled in the art from the detailed description.

[0039] Therefore, it should be understood that the inventive concept is not limited to the specific steps of the described method or the parts of the described system, because such methods and systems can vary. It should also be understood that the terms used herein are only for the purpose of describing specific embodiments and are not intended to be restrictive. It must be noted that, unless the context clearly stipulates otherwise, as used in this specification and the appended claims, the articles "a (a)", "a kind of", "the" and "said" are intended to mean one or more of the elements present. Therefore, for example, mentioning "unit" or "the unit" can include several devices, etc. In addition, the words "include", "comprise", "contain", "contain" and similar terms do not exclude other elements or steps. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and other aspects of the inventive concept will now be described in more detail with reference to the accompanying drawings showing variations of the inventive concept. The accompanying drawings should not be considered to limit the inventive concept to specific variations; rather, they are used to explain and understand the inventive concept. As illustrated in the accompanying drawings, the sizes of layers and regions are exaggerated for illustrative purposes, and are therefore provided to illustrate the overall structure of variations of the inventive concept. Throughout the text, like reference numerals refer to like elements.

[0041] Figure 1 A microscope system comprising a device for identifying a region of interest of a sample is illustrated.

[0042] FIG. 2A to FIG. 2C A non-limiting example of how a compressed representation of a sample may be formed is illustrated.

[0043] FIG. 3A to FIG. 3D A non-limiting example of how a common compressed digital representation of a sample may be formed is illustrated.

[0044] Figure 4 is a block diagram of a method for identifying a region of interest of a sample.

[0045] Figure 5 A non-transitory computer-readable storage medium is illustrated. DETAILED DESCRIPTION

[0046] The inventive concept will now be described more fully hereinafter with reference to the accompanying drawings, in which presently preferred variations of the inventive concept are shown. However, the inventive concept may be implemented in many different forms and should not be construed as limited to the variations set forth herein; rather, these variations are provided for thoroughness and completeness and to fully convey the scope of the inventive concept to the skilled person.

[0047] In the following, Figure 1 The apparatus 10 for identifying a region of interest of a sample 192 is described in the context of the microscope system 1 illustrated in FIG. In this context, a "region of interest" may be a region of the sample 192 that is relatively more interesting than other regions of the sample 192. Such a region may include, for example, one or more objects within the sample 192 that may be of interest for analysis and / or imaging, etc.

[0048] Figure 1 The microscope system 1 shown in FIG. 1 comprises a device 10 for identifying a region of interest of a sample 192. Figure 1 As shown, the microscope system 1 may include a microscope objective 170, a relay lens 180, and a sample holder 190. Figure 1 In the illustrated example, device 10 is a camera. Device 10 includes image sensor 150 and circuit system 100. Figure 1 As shown, the device 10 may further include one or more of a memory 110, a processing unit 120, a transceiver 130, and a data bus 140. The device 10 may include a shutter 160 that can be controlled so that light can be blocked or allowed to reach the image sensor 150. The processing unit 120 may include a central processing unit (CPU) and / or a graphics processing unit (GPU). The transceiver 130 may be configured to communicate with an external device. For example, the transceiver 130 may be configured to communicate with a server, a computer external device (e.g., an external storage device), etc. The external device may be a local device or a remote device (e.g., a cloud server). The transceiver 130 may be configured to communicate with the external device via an external network (e.g., a local area network, the Internet, etc.). The transceiver 130 may be configured for wireless and / or wired communication. Technologies suitable for wireless communication are known to technicians. Some non-limiting examples include Wi-Fi and near field communication (NFC). Technologies suitable for wired communication are known to technicians. Some non-limiting examples include USB, Ethernet, and FireWire. One or more of the memory 110, the processing unit 120, the transceiver 130, the image sensor 150, and the shutter 160 may communicate via the data bus 140. The memory 110 may be a non-transitory computer-readable storage medium. The memory 110 may be a random access memory. The memory 110 may be a non-volatile memory. Figure 1As illustrated in the example of , the memory 110 may store a program code portion corresponding to one or more functions. The program code portion may be executed by the processing unit 120, which thereby performs the function. Therefore, when it is mentioned that the circuit system 100 is configured to perform a specific function, the processing unit 120 may execute a program code portion corresponding to the specific function, which may be stored on the memory 110. However, it should be understood that one or more functions of the circuit system 100 may be hardware-implemented and / or implemented in a specific integrated circuit. For example, a field programmable gate array (FPGA) may be used to implement one or more functions. In other words, one or more functions of the circuit system 100 may be implemented in hardware or software or a combination of the two.

[0049] The sample holder 190 may include a microscope slide. Figure 1 In the example of FIG. 1 , sample 192 has been applied to a microscope slide of sample holder 190. It should be understood that sample 192 may be covered by a cover glass ( Figure 1 (not shown). Sample 192 may be a biological sample. Sample 192 may be, for example, a sample from a human or an animal (e.g., blood, bone marrow, tissue, etc.). Sample 192 may be primarily a two-dimensional sample. For example, sample 192 may be a smear sample. Sample 192 may be a three-dimensional sample. For example, sample 192 may be a tissue sample. Sample holder 190 may be configured to hold sample 192 to be analyzed. Sample holder 190 may be movable (e.g., by being coupled to a manual and / or motorized stage), thereby allowing sample 192 to be moved so that different portions of sample 192 may be imaged onto image sensor 150 by microscope objective 170. In other words, sample holder 190 may further include manual and / or motorized stages that are arranged to move sample 192 in a plane extending substantially along first axis X and second axis Y. As shown in Figure 1 As seen in the example of , the surface of the sample holder 190 (or microscope slide) may extend in a plane whose normal is parallel to the third axis Z. The first axis X, the second axis Y and the third axis Z may be perpendicular to each other.

[0050] like Figure 1 , the microscope objective 170 can be configured to image a portion of the sample 192 at position P onto the image sensor 150 via a relay lens 180. It should be understood that the relay lens 180 can be selected (e.g., focal length, material, size, etc.) based on the magnification and / or numerical aperture of the microscope objective 170. The size of the imaged portion of the sample 192 can depend on the field of view 172 of the microscope objective 170. Generally, a microscope objective with a relatively high magnification has a smaller field of view than a microscope objective with a relatively low magnification.

[0051] The microscope objective 170 can be connected to a manual and / or motorized stage ( Figure 1 The microscope objective 170 may be movable along the third axis Z (not shown). The optical axis of the microscope objective 170 may be parallel to the third axis Z. In other words, the microscope objective 170 may be movable in the focusing direction of the microscope objective 170. The microscope objective 170 may be movable so that a focused image may be captured by the image sensor 150. The focusing of the microscope objective 170 may be controlled manually and / or automatically. The position of the microscope objective 170 along the third axis Z may be controlled by the control circuit system ( Figure 1 For example, the control circuit system can be configured to perform a focusing function ( Figure 1 The focusing function is configured to adjust the position of the microscope objective 170 along the third axis Z. The focusing function can be configured to automatically adjust the position of the microscope objective 170 along the third axis Z. In other words, the focusing function can be an automatic focusing function. It should be further understood that the relay lens 180 can be moved in a direction parallel to the third axis Z so that a focused image of the sample 192 can be captured by the image sensor 150.

[0052] The circuit system 100 is configured to perform a capture function 1100, a formation function 1102, an arrangement function 1104, and an identification function 1106. The capture function 1100 is configured to capture multiple digital image data sets using the image sensor 150. In this context, a "digital image data set" can be data related to a digital image captured using the image sensor 150. The digital image data set can be a digital image. The digital image data set can be used to form a digital image of a corresponding imaging portion of the sample 192. The capture function 1100 can be further configured to control the shutter 160. Each of the multiple digital image data sets includes pixels. Each of the multiple digital image data sets is related to one of a plurality of positions of the sample 192. In other words, each digital image data set can be associated with a coordinate corresponding to the position of the corresponding imaging portion of the sample 192. The position of the imaging portion can be a position relative to the sample 192. The combined size of the imaging portion can correspond to the size of the sample 192. In other words, the multiple digital image data sets can correspond to a scan of the sample 192. Alternatively, the combined size of the imaging portion can be smaller than the size of the sample 192. In other words, the multiple digital image data sets may correspond to a partial scan of sample 192.

[0053] The forming function 1102 is configured to form a combined pixel set for each digital image data set. Each combined pixel can be associated with a position related to the digital image data set in the multiple positions of the sample 192. Each combined pixel can be associated with a position of the sample 192. Each combined pixel set can be composed of a predetermined number of pixels. The predetermined number of pixels can be less than the number of pixels of the corresponding digital image data set. Each combined pixel set can, for example, be composed of a combined pixel. Each combined pixel has a pixel value. The pixel value of each combined pixel is determined based on at least one of an intensity value and a color value related to a pixel subset of the digital image data set. For example, each pixel value in these combined pixel sets can be an average value, a median value, or a sum of the pixel values ​​of the pixel subset of the corresponding digital image data set. Therefore, each pixel value in these combined pixel sets can be an average value, a median value, or a sum of the pixel values ​​of the pixel subset of the corresponding digital image data set. The number of pixels in the combined pixel set can be one pixel to 50% of the number of pixels in the subset forming the combined pixel set. For example, in the case where the pixel subset includes 100 pixels, the number of pixels in the corresponding combined pixel set can be 1 to 50 pixels.

[0054] Now refer to FIG. 2A to FIG. 2C A non-limiting example of how to form a combined pixel set is described below. Figure 2A One digital image dataset 200A from the plurality of digital image datasets is illustrated. The digital image dataset 200A includes pixels and is associated with one of the plurality of locations of the sample 192. Figure 2A In the example of FIG. 4 , four pixel subsets 210A, 212A, 214A, 216A are illustrated. However, it should be understood that other numbers of subsets may be used instead. For example, Figure 2B and Figure 2C In an example, a single pixel subset 210B, 210C of a digital image dataset 200B, 200C may be used. Each pixel subset may be a predetermined pixel subset. Each subset of the digital image dataset may include a predetermined number of pixels. Each pixel subset may include a certain number of pixels relative to the number of pixels in the digital image dataset. For example, subset 210B may include a portion of the pixels in digital image dataset 200B, such as Figure 2B The portion may be 10% to 100%. One or more subsets of the digital image data set may be non-overlapping (e.g. Figure 2A The pixel subset of the digital image data set may include at least two pixels. Figure 2CAs illustrated in the example of , the pixel subset 210C of the digital image dataset 200C may, for example, consist of all pixels of the digital image dataset 200C. In other words, each pixel value of these combined pixel sets may be based on at least one of intensity values ​​and color values ​​associated with all pixels of the corresponding digital image dataset. Figure 2A As further illustrated, the combined pixel set 220A is formed by the pixel subsets 210A, 212A, 214A, 216A of the digital image data set 200A. In this example, the combined pixel set 220A includes four combined pixels 2200A, 2202A, 2204A, 2206A formed based on the four subsets 210A, 212A, 214A, 216A. Figure 2B and Figure 2C In the illustrated example, the combined pixel sets 220B, 220C each include a single combined pixel 2200B, 2200C formed from a subset 210B, 210C of the respective digital image data set 200B, 200C.

[0055] Back to Figure 1 , the forming function 1102 is further configured to form a compressed digital representation including a combined pixel set for each digital image data set. In this context, the compressed digital representation may be a representation of the corresponding digital image data set. The compressed digital representation may preferably include fewer pixels than the corresponding digital image data set. The number of pixels in the compressed digital representation may be similar to or equal to the number of combined pixels formed to form the compressed digital representation. For example, where the formed combined pixel set consists of only one combined pixel, the compressed digital representation may include only one pixel (i.e., the combined pixel in the formed combined pixel set). Figure 2A In the example of FIG. 2 , the compressed digital representation 230A formed includes four combined pixels 2200A, 2202A, 2204A, and 2206A. Figure 2A As further seen in the example of , each combined pixel in the compressed digital representation 230A can have a position relative to the compressed digital representation that is similar to the position of the corresponding pixel subset relative to the digital image data. For example, Figure 2A The top left corner combined pixel 2202A in the compressed digital representation 230A illustrated in FIG. 2 is formed by a combined pixel 2202A, which is in turn formed based on the pixel subset 210A at the top left corner of the digital image data set 200A. Figure 2B and Figure 2C , the compressed digital representations 230B, 230C each include a single combined pixel 2200B, 2200C because only a single combined pixel is formed in each of these examples.

[0056] Back to Figure 1, the arrangement function 1104 is configured to arrange the compressed digital representations in a data structure to form a common compressed digital representation of the sample 192. The common compressed digital representation of the sample 192 can be similar to the digital image of the sample 192. The relative position of each compressed digital representation in the common compressed digital representation can be based on the relative position in the sample 192 depicted by the corresponding digital image that formed the compressed digital representation. The position of each compressed digital representation relative to the common compressed digital representation can be the same as the position of the corresponding imaged portion relative to the sample 192.

[0057] Now refer to FIG. 3A to FIG. 3D A non-limiting example of how a common compressed digital representation 350 of sample 192 may be formed is described. Figure 3A A top view of sample 192 is shown. Figure 3A The sample 192 in FIG. 1 is present on a microscope slide 394. A plurality of imaged portions 340 of the sample 192 (ie, a plurality of portions 340 of the sample 192 imaged by the image sensor 150) are further indicated by dashed lines. Figure 3A Each imaged portion in corresponds to a location in sample 192. For example, first portion 340A of sample 192 is associated with a first location in sample 192. It should be understood that a location in sample 192 can be defined in a variety of different ways. For example, the location of a portion of sample 192 can be the location of the center of the portion. A different example is that the location of a portion of sample 192 can be the location of a corner of the portion. In this example, only a portion of sample 192 is imaged. In other words, in Figure 3A In the example of FIG. 1 , the combined area of ​​the imaging portion 340 is smaller than the area of ​​the sample 192. However, it should be understood that the entire sample 192 may be imaged. Figure 3A As seen in FIG. 1 , there are several objects 360 in the sample 192. Here, the objects 360 are of interest for analysis and / or imaging, so the imaging portion 340 in which the objects are present may be Figure 3A The region of interest of sample 192 is shown in FIG. Figure 3A For each imaging portion in the image sensor 150 , a digital image data set is captured, thereby forming a plurality of digital image data sets 300 . Figure 3B 1. A plurality of digital image data sets 300 are illustrated in FIG. Each digital image data set in the plurality of digital image data sets 300 corresponds to an imaged portion of the sample 192. For example, when a first portion 340A of the sample 192 is imaged by the microscope objective 170, a first digital image data set 300A is captured by the image sensor 150. Based on the plurality of digital image data sets 300, a combined pixel set 320 is formed, for example, in a manner similar to that of a combined pixel set 320. FIG. 2A to FIG. 2C One or more of the methods described. Figure 3CA combined pixel set 320 is illustrated in FIG. In this example, each combined pixel is formed by averaging the intensity values ​​of all pixels in the corresponding digital image data set. Figure 3C In the example of , each combined pixel set includes one combined pixel. Figure 3D As illustrated in , these combined pixel sets are arranged in a data structure to form a common compressed digital representation 350 of the sample 192. In other words, in Figure 3D In the example of FIG. 3 , each pixel of the common compressed digital representation 350 corresponds to one of the plurality of digital image data sets 300. For example, the first combined pixel 3200A is formed based on the first digital image data set 300A. Figure 3D As illustrated in the example of , the first combined pixel 3200A has a position relative to the common compressed digital representation 350 that can be the same as the position of the corresponding imaging portion (i.e., the first portion 340A) relative to the sample 192. It should be understood that Figure 3D The common compressed digital representation 350 of is only one example, and the skilled person may envision other arrangements. For example, the combined pixel set 320 may be arranged in a (one-dimensional or multi-dimensional) array, and the position of each element (i.e., combined pixel) relative to the array may correspond to a position in the sample 192.

[0058] Back to Figure 1 , the identification function 1106 is configured to identify the region of interest of the sample 192 based on the pixel values ​​of the common compressed digital representation. The identification function 1106 can be configured to identify the region of interest of the sample 192 by comparing the pixel values ​​of the pixels of the common compressed digital representation with a threshold value. The threshold value can be relative to the pixel values ​​of the pixels of the common compressed digital representation. For example, the threshold value can be based on the average or median of the pixel values ​​of the pixels of the common compressed digital representation. The threshold value can be based on the pixel value of the background level. For example, it is known that a specific pixel of the common compressed digital representation may not be associated with the imaged sample 192. This may be because the sample 192 is applied to the sample holder 190, and some parts of the sample holder 190 may not receive the sample 192. The sample holder 190 can, for example, be configured so that one or more parts of the sample holder 190 do not receive the sample 192. Pixels related to such parts of the sample holder 190 can be used to determine the background level. For example, at least one of the multiple digital images can be a digital image of a blank portion of the sample holder 190, and the digital image can be used to determine the background level. The background level may be, for example, an average or median value of such pixels. The threshold may be scaled by a numerical factor. The numerical factor may be less than 1. The numerical factor may be 0.5. Depending on the type of imaged sample 192, the region of interest may correspond to a portion of the imaged sample 192 where the pixel values ​​of the combined pixels are above or below the threshold. For example, in Figure 3DIn the example, a plurality of pixels have pixel values ​​below a threshold value (which may be scaled by a numerical factor). The digital image data set corresponding to these combined pixels in turn corresponds to relatively interesting portions of the sample 192. Therefore, these relatively interesting portions are determined to be regions of interest of the sample 192. Therefore, the region of interest can be identified using less information than the information actually captured by the image sensor 150. In the above, the recognition function 1106 is described as identifying the region of interest of the sample 192 by comparing the pixel values ​​of the common compressed digital representation with the threshold value. However, it should be understood that other methods can be used to identify the region of interest of the sample. For example, the recognition function 1106 can be configured to use machine learning to identify the region of interest of the sample 192. There are several machine learning algorithms that may be suitable for object detection, such as YOLO, SSD, etc. Therefore, the captured information is reduced by, for example, reducing the number of pixels, and the region of interest of the sample 192 is identified using the reduced information. This in turn reduces the amount of data that needs to be processed to identify the region of interest of the sample 192. This reduction in the amount of data to be processed can reduce the requirements for the associated processing power and / or the associated bandwidth. For example, the device 10 does not need to send multiple digital images to a separate device 10 to subsequently analyze the digital images in order to identify the region of interest in the sample 192. The region of interest of the sample 192 can also be identified without a high requirement for focusing the sample 192 when capturing multiple digital image data sets. This is because the pixel value of the combined pixel may be less sensitive to focus changes. In other words, the pixel value of the combined pixel formed using the digital image data set captured when the imaging portion of the sample 192 is in focus may be similar to the pixel value of the combined pixel formed using the digital image data set captured when the same imaging portion of the sample 192 is not in focus. In other words, the region of interest of the sample 192 can be determined without using the spatial details of the sample 192, and the digital image data set can be captured without focusing the sample 192. The microscope objective 170 can be positioned so that the sample 192 is in focus when the first digital image data set is captured. By assuming that the sample 192 is substantially flat, additional digital image data sets can be captured without adjusting the focus of the microscope objective 170. Therefore, the process of capturing the digital image data set may take less time. For example, the sample 192 may be moved during the capture of the digital image dataset (since spatial details of the sample do not need to be preserved in the digital image dataset), thereby further reducing the time taken to capture the digital image dataset of the sample 192. However, it should be understood that the focus of the microscope objective 170 may be adjusted during the capture of the digital image dataset, if desired. This may be the case if the area of ​​the sample 192 to be imaged is large compared to the field of view 172 of the microscope objective 170.Additionally or alternatively, this may also be affected by the manual / motorized stage used to move the sample. For example, depending on the accuracy of the stage mounting (e.g., relative alignment of two vertical stages configured to move the sample in a horizontal plane) and / or the quality of the stage (e.g., linearity, vibrations associated with movement, etc.), the focus of the sample 192 may be inadvertently moved (e.g., in a vertical direction) during movement (e.g., in a horizontal plane). The present method can allow identification of regions of interest of the sample 192 even under such non-ideal conditions.

[0059] The inventive concept will now be described with reference to specific example embodiments. It should be understood that this example is discussed for the purpose of understanding the inventive concept and is not intended to be limiting. In this embodiment, a device for identifying a region of interest of a sample includes a digital camera and a computer. When capturing a digital image data set (e.g., a digital image) of a sample, the digital camera is configured to determine the average value of the pixel intensity values ​​of the captured digital image data set. The determined average value of the pixel intensity values ​​of the captured digital image is then used as the pixel value of the combined pixel. Therefore, in this embodiment, each combined pixel set includes a single combined pixel, and the pixel value of each combined pixel is the average value of the pixel value of the corresponding captured digital image data set. Therefore, in this embodiment, each compressed digital representation includes a single combined pixel. The compressed digital representation is transferred from the digital camera to the computer. In this example, each compressed digital representation (i.e., the average value of the pixel intensity values ​​of the captured image data set) is transferred to the computer in relation to the capture of the digital image data set. In other words, once the camera captures the digital image data set, the average value is sent from the digital camera to the computer. After receiving the compressed digital representation, the computer is configured to arrange the compressed digital representation in a data structure to form a common compressed digital representation of the sample. In this embodiment, the number of pixels of the common compressed digital representation of the sample is equal to the number of digital image data sets in the plurality of digital image data sets used to form the combined pixel.Finally, the computer is configured to identify a region of interest of the sample 192 based on the common compressed digital representation.

[0060] Figure 4 is a block diagram of a method 40 for identifying a region of interest of a sample 192. The method 40 may be implemented in a circuit system of a camera, for example, Figure 1. The method 40 comprises: capturing S400 a plurality of digital image data sets by an image sensor 150, each digital image data set comprising pixels and relating to one of a plurality of locations of a sample 192; for each digital image data set: forming S402 a combined pixel set, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value relating to a pixel subset of the digital image data set, and forming S404 a compressed digital representation comprising the combined pixel set; arranging S406 the compressed digital representation in a data structure, thereby forming a common compressed digital representation of the sample 192; and identifying S408 a region of interest of the sample 192 based on the pixel values ​​of the common compressed digital representation. Each pixel value in the combined pixel sets may be an average, a median, or a sum of a pixel subset of a corresponding digital image data set. Each combined pixel set may consist of one combined pixel. A pixel subset of a digital image data set may consist of all pixels of the digital image data set. A pixel subset may be a predetermined pixel subset.

[0061] Figure 5 A non-transitory computer readable storage medium 50 is shown. The non-transitory computer readable storage medium 50 includes program code portions that, when executed on a device including processing capabilities, perform Figure 4 The method shown in the figure.

[0062] Those skilled in the art realize that the inventive concept is by no means limited to the preferred variants described above. On the contrary, many modifications and variations are possible within the scope of the appended claims.

[0063] For example, the device for identifying the region of interest of the sample can be a single device, such as a digital camera. Alternatively, the device can be more than one device. For example, the device can include a digital camera and a computing device (e.g., a computer, a server, a cloud server, a smart phone, etc.), and the function of the circuit system of the device can be distributed between the digital camera and the computing device. For example, the capture function and possibly the formation function can be performed on the digital camera, and one or more of the arrangement function and the recognition function can be performed on the computing device.

[0064] Additionally, variations to the disclosed variations can be understood and effected by the skilled artisan in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0065] Itemized List of Exemplary Embodiments

[0066] IEE 1. A method for identifying a region of interest of a sample, the method comprising:

[0067] capturing, by an image sensor, a plurality of digital image data sets, each digital image data set comprising pixels and relating to one of a plurality of locations of the sample;

[0068] For each digital image dataset:

[0069] forming a set of combined pixels, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set, and

[0070] forming a compressed digital representation comprising the combined pixel set;

[0071] arranging the compressed digital representations in a data structure to form a common compressed digital representation of the sample; and

[0072] A region of interest of the sample is identified based on the pixel values ​​of the common compressed digital representation.

[0073] IEE 2. The method according to IEE 1, wherein each pixel value in the combined pixel sets is an average, a median, or a sum of a subset of pixels in the corresponding digital image data set.

[0074] IEE 3. The method according to IEE 1 or IEE 2, wherein each combined pixel set consists of one combined pixel.

[0075] IEE 4. The method according to any one of IEE 1 to IEE 3, wherein the pixel subset of the digital image data set consists of all pixels of the digital image data set.

[0076] IEE 5. The method according to any one of IEE 1 to IEE 4, wherein the subset of pixels is a predetermined subset of pixels.

[0077] IEE 6. A device for identifying a region of interest of a sample, the device comprising:

[0078] Image sensor; and

[0079] A circuit system configured to perform:

[0080] a capture function configured to capture a plurality of digital image data sets using the image sensor, each digital image data set comprising pixels and relating to one of a plurality of locations of the sample;

[0081] a forming function configured to: form, for each digital image data set, a combined pixel set, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set; and form a compressed digital representation comprising the combined pixel set;

[0082] an arrangement function configured to arrange the compressed digital representations in a data structure to form a common compressed digital representation of the sample; and

[0083] An identification function is configured to identify a region of interest of the sample based on pixel values ​​of the common compressed digital representation.

[0084] IEE 7. The apparatus according to IEE 6, wherein each pixel value in the combined pixel sets is an average, a median, or a sum of a subset of pixels of the corresponding digital image data set.

[0085] IEE 8. The device according to IEE 6 or IEE 7, wherein each combined pixel set consists of one combined pixel.

[0086] IEE 9. The apparatus according to any one of IEE 6 to IEE 8, wherein the pixel subset of the digital image data set consists of all pixels of the digital image data set.

[0087] IEE 10. The apparatus according to any one of IEE 6 to IEE 9, wherein the subset of pixels is a predetermined subset of pixels.

[0088] IEE 11. The device according to any one of IEE 6 to IEE 10, wherein the device is a camera.

[0089] IEE 12. A non-transitory computer-readable storage medium comprising program code portions which, when executed on a device comprising processing capabilities, perform a method according to any one of IEE 1 to IEE5.

Claims

1. A method (40) for identifying a region of interest of a sample, the method (40) comprising: capturing (S400) a plurality of digital image data sets (300) by an image sensor (150), each digital image data set comprising pixels and relating to one of a plurality of locations of the sample; For each digital image dataset: forming (S402) a combined pixel set, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set, and forming (S404) a compressed digital representation comprising the combined pixel set; arranging (S406) the compressed digital representations in a data structure to form a common compressed digital representation (350) of the sample (192), wherein the data structure of each compressed digital representation includes information related to a position of a digital image data set associated with the compressed digital representation among a plurality of positions of the sample; and A region of interest of the sample (192) is identified (S408) based on the pixel values ​​of the common compressed digital representation.

2. The method (40) according to claim 1, wherein: Each pixel value in the combined pixel set is an average, a median, or a sum of a subset of pixels in a corresponding digital image data set.

3. The method (40) according to claim 1 or 2, wherein: Each combined pixel set consists of one combined pixel.

4. The method (40) according to any one of claims 1 to 3, wherein: The pixel subset of the digital image data set consists of all pixels of the digital image data set.

5. The method (40) according to any one of claims 1 to 4, wherein: The subset of pixels is a predetermined subset of pixels.

6. A device (10) for identifying a region of interest of a sample, the device comprising: Image sensor (150); as well as A circuit system (100) configured to perform: a capture function (1100) configured to capture a plurality of digital image data sets using the image sensor (150), each digital image data set comprising pixels and associated with one of a plurality of locations of the sample (192); forming a function (1102) configured to: form, for each digital image data set, a combined pixel set, each combined pixel having a pixel value, and wherein each pixel value is determined based on at least one of an intensity value and a color value associated with a subset of pixels of the digital image data set; and forming a compressed digital representation including the combined pixel set; an arrangement function (1104) configured to arrange the compressed digital representations in a data structure to form a common compressed digital representation of the sample (192), wherein the data structure of each compressed digital representation includes information related to a position of a digital image data set associated with the compressed digital representation among a plurality of positions of the sample; and An identification function (1106) configured to identify a region of interest of the sample (192) based on the pixel values ​​of the common compressed digital representation.

7. The device (10) according to claim 6, wherein: Each pixel value in the combined pixel set is an average, a median, or a sum of a subset of pixels in a corresponding digital image data set.

8. The device (10) according to claim 6 or 7, wherein: Each combined pixel set consists of one combined pixel.

9. The device (10) according to any one of claims 6 to 8, wherein: The pixel subset of the digital image data set consists of all pixels of the digital image data set.

10. The device (10) according to any one of claims 6 to 9, wherein: The subset of pixels is a predetermined subset of pixels.

11. The device (10) according to any one of claims 6 to 10, wherein: The device (10) is a camera.

12. A non-transitory computer-readable storage medium (50) comprising program code portions which, when executed on a device comprising processing capabilities and an image sensor, perform the method (40) according to any one of claims 1 to 5.

Images