Method, apparatus and system for normalizing pixel intensities of an image - Patents.com

Abstract

The present disclosure relates to normalizing pixel intensity values ​​of images. Qualitative images that need to be compared need to have actual pixel intensity values ​​in an appropriate range. Typically, the qualitative images to be compared are made visually similar by adjusting display settings. First and second images that have different actual pixel intensity values ​​but visually appear similar are received. One or more normalization parameters are determined using one or more contrast and lighting parameters associated with the first and second images. Normalized pixel intensity values ​​are then determined using the one or more normalization parameters to generate a normalized image. The pixel intensity values ​​of the normalized image can be compared to the actual pixel intensity values ​​of the first or second image.

Description

[Technical field]

[0001] The following specification describes, inter alia, the invention and the manner in which it may be practiced.

[0002] The present disclosure relates generally to the field of image processing techniques. In particular, but specifically, the present disclosure relates to a method, apparatus, and system for normalizing pixel intensities of an image. [Background technology]

[0003] Image processing techniques are widely used in various applications to analyze images. Image processing techniques are performed based on image characteristics (pixel intensity, color, saturation, contrast, hue, brightness, and various other parameters). Different images can be compared if the relevant parameters are within comparable ranges. For example, images of the same object captured with different imaging devices will have different pixel intensity values ​​due to the settings of each imaging device. Similarly, various other parameters of two images depicting the same object may vary, but the two images will appear the same when displayed on a display unit such as a monitor. Often, the display unit applies settings to the image as required by the viewer. For example, the contrast of the image may be changed by the display unit, the brightness of the image may be changed by the display unit, etc. Advanced computing systems can be used to process the images and analyze the images depending on the application. Summary of the Invention [Problem to be solved by the invention]

[0004] In medical imaging, images are acquired using different imaging devices, such as cameras, computed tomography (CT) devices, magnetic resonance imaging (MRI) devices, ultrasound devices, etc. To analyze the images, a medical technician needs to compare images captured at different times from different modalities (CT, MRI). Although two images appear visually the same (i.e., qualitatively the same), the pixel intensity values ​​of the two images may differ (i.e., quantitatively different). The two images are adjusted to appear visually the same to a user using display settings (e.g., windowing). However, computing systems may compare image properties (e.g., pixel intensities) themselves and typically do not use display properties to compare images.

[0005] Existing systems normalize one of two images to the other so that a computing system can meaningfully compare the images. Some existing systems perform a calibration to quantitatively represent two images in a similar manner, but do not take into account the display settings used to make the two images appear visually the same. The solutions such systems provide are not general and are highly subjective to image parameters or image content, as discussed below.

[0006] Some existing systems perform intensity normalization techniques on qualitative images. Generally, they follow a histogram approach to normalize intensity values. The intensity normalization factor can be measured from the whole image or a part of the image. When the whole image is considered in this way, only high SNR images are suitable as good candidates for such a method, since the noise content in the image plays a significant role and may affect the normalization. When a part of an image is considered in the normalization method, the normalization is entirely done by the pixel values ​​in that region, which may fail to normalize other parts of the image. Therefore, none of the existing systems effectively normalize qualitative images.

[0007] The information disclosed in this Background of the Disclosure section is intended solely to enhance understanding of the general background of the present invention and should not be construed as an acknowledgment or any form of suggestion that this information forms prior art already known to those skilled in the art. [Means for solving the problem]

[0008] In an embodiment, a method for normalizing pixel intensities of an image is disclosed. Actual pixel intensity values, one or more contrast parameters, and one or more lighting parameters of a first image and a second image generated by an image processing device are received. In an embodiment, the first and second images appear visually the same to the human eye, even though different pixel intensities represent the same regions in the first and second images. Furthermore, one or more normalization parameters are determined using the one or more contrast parameters and lighting parameters of the first and second images. Normalized pixel intensity values ​​of the second image are determined based on the one or more normalization parameters, and a normalized image is generated by transforming the second image relative to the first image using the normalized pixel intensity values.

[0009] An image processing device for normalizing pixel intensities of an image is disclosed. The image processing device comprises a memory and a processor. The processor is configured to receive actual pixel intensity values, one or more contrast parameters and lighting parameters of a first image and a second image generated by the image processing device. The first and second images appear visually the same to the human eye, even though different pixel intensities represent the same regions in the first and second images. The processor determines one or more normalization parameters using the one or more contrast parameters and lighting parameters of the first and second images. Furthermore, the processor determines normalized pixel intensity values ​​of the second image based on the one or more normalization parameters, and the normalized image is generated by transforming the second image relative to the first image using the normalized pixel intensity values.

[0010] In an embodiment, a system is disclosed that includes an imaging device, a display unit, and an image processing device. The imaging device is configured to capture a first image and a second image. The display unit is configured to apply a first window level value and a first window width value to the first image, and apply a second window level value and a second window width value to the second image, such that the first image and the second image appear visually the same on the display unit. The image processing device is configured to determine a normalized gradient value based on the window width values ​​of the first and second images. Furthermore, the image processing device determines a normalized intercept value based on the window level values ​​of the first and second images, the window width values ​​of the first and second images, and the highest pixel intensity value displayed. Then, the image processing device determines a normalized pixel intensity value of the second image based on the normalized gradient and the normalized intercept value, and further generates a normalized image by transforming the second image relative to the first image using the normalized pixel intensity value of the second image.

[0011] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the exemplary aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

[0012] The novel features and characteristics of the present disclosure are set forth in the appended claims. However, the disclosure itself, as well as the preferred mode of use, further objects and advantages thereof, will be best understood by reference to the following detailed description of exemplary embodiments, when read in conjunction with the accompanying drawings. One or more embodiments will now be described, by way of example only, with reference to the following accompanying drawings, in which like reference numerals represent like elements, and in which: [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is an illustration of a block diagram for normalizing pixel intensities of an image according to some embodiments of the present disclosure. [Diagram 2] FIG. 2 is an exemplary illustration of the internal structure of an image processing device configured to normalize pixel intensities of an image, according to some embodiments of the present disclosure. [Diagram 3] FIG. 3 is a flowchart illustrating example method steps for normalizing pixel intensities of an image, according to some embodiments of the present disclosure. [Figure 4] FIG. 4 is a flowchart illustrating detailed method steps for normalizing pixel intensities of an image according to some embodiments of the present disclosure. [Diagram 5] FIG. 5 is an example image of the same region in a visually identical looking image, according to some embodiments of the present disclosure. [Figure 6] FIG. 6 is a flowchart illustrating example method steps for determining a normalized intercept value according to some embodiments of the present disclosure. [Figure 7] FIG. 7 illustrates a general-purpose computer system for normalizing pixel intensities of an image, according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Those skilled in the art should appreciate that any block diagrams herein represent conceptual views of exemplary systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudocode, or the like may be substantially represented on a computer-readable medium and represent various processes performed by a computer or processor, whether or not such a computer or processor is explicitly shown.

[0015] The word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0016] While the present disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and are described in detail below. It is to be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is intended to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure.

[0017] The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method comprising a list of components or steps does not include only those components or steps, but may include other components or steps not expressly listed or inherent to such setup, or device, or method. In other words, one or more elements in a system or apparatus denoted by "comprising" does not, without further constraints, preclude the presence of other or additional elements in the system or apparatus.

[0018] An embodiment of the present disclosure relates to normalizing pixel intensity values ​​of images. Qualitative images that need to be compared need to have actual pixel intensity values ​​in an appropriate range. The "actual" pixel intensity values ​​of an image can be considered to be the intensity values ​​that are generated and / or stored in the image data of the image. For example, the actual pixel intensity values ​​may form part of or be stored in digital image data, such as DICOM (Digital Imaging and Communications in Medicine) image data. Generally, the qualitative images to be compared are made to look visually the same by adjusting display settings. Thus, the images look visually the same because the displayed pixel intensities are identical or the same. The present disclosure uses the relationship between the display settings of the qualitative images to normalize pixel intensity values ​​of the qualitative images to enable comparison of the images by any image processing device.

[0019] FIG. 1 is an illustration of a block diagram of a system (100) for normalizing pixel intensities of an image, according to some embodiments of the present disclosure. As shown in FIG. 1, the system (100) includes an imaging unit (102) and a processor (103) for processing two images: a first image (I a ) (105) and the second image (I b 1 includes a first image (I) (106), a subject (103), and a display unit (104). In an embodiment, the imaging unit (102) is a camera, a magnetic resonance imaging (MRI) device, a computed tomography (CT) device, or any other device (104) capable of imaging a patient. For simplicity, the first and second images are further shown without part numbers. However, it should be clear to one skilled in the art that the part numbers (105 and 106) in FIG. 1 refer to the first and second images, respectively. In one embodiment, the first image (I) and the second image (F) are displayed in a single image (F) that appear visually the same to the radiologist / technologist. a ) and the second image (I b ) are captured by the same imaging unit. In one embodiment, the first image (I a ) and the second image (I b ) are captured using different imaging units. In a further embodiment, the first image (I a ) and the second image (I b ) are captured by different imaging units of the same / same modality. For example, the first image (I a ) is captured using a first MRI scanner, and a second image (I b ) is captured using a second MRI scanner. In another embodiment, the first image (I a ) and the second image (I b ) are captured by different imaging units of different modalities. For example, the first image (I a ) is captured using an MRI scanner, and a second image (I b) is captured using a CT scanner. In such a case, the parameters of the MRI scanner are set to 1 for the first image (I a ) is captured by the CT scanner in a second image (I b ) can be adjusted to look visually the same / identical to the first image (I a ) and the second image (I b ) are captured at different times. In one embodiment, if the imaging unit (102) is a camera, the first image (I a ) and the second image (I b ) may represent, for example, the skin of the subject (103), the eye of the subject (103), etc. In one embodiment, when the imaging unit (102) is an MRI device, the first image (I a ) and the second image (I b ) may represent, for example, an organ of the subject (103), a tissue of the subject (103), and a bone of the subject (103). In one embodiment, when the imaging unit (102) is a CT device, the first image (I a ) and the second image (I b ) represent, for example, the organs of the subject (103), the tissues of the subject (103), the bones of the subject (103), and the blood vessels of the subject (103).

[0020] In an embodiment, the first image (I a ) and the second image (I b ) represent the same area / point of the object. In an embodiment, the first image (I a ) and the second image (I b ) represents a region of the subject, such as a tissue of the subject, an organ of the subject, etc. In an embodiment, the first image (I a ) pixel intensity value (X a ) and the second image (I b ) pixel intensity value (X b ) may be different, and the first image (I a ) and the second image (I b ) appear visually the same on the display unit (104). In an embodiment, the images are the first image (I a) and the second image (I b ) in combination with one or more contrast and lighting parameters of the object, a first image (I a ) and the second image (I b ) may appear the same to a user / technologist viewing the first image (I a ) displayed pixel intensity value (Y a ) is the second image (I b ) displayed pixel intensity value (Y b In a further embodiment, the displayed pixel intensity value (Y a ) and (Y b ) is received from the display unit (104) by the image processor.

[0021] In an embodiment, the first image (I a ) displayed pixel intensity value (Y a ) and the second image (I b ) displayed pixel intensity value (Y b ) is the actual pixel intensity value (X a and X b ) varies depending on the pixel intensity values ​​of the first image and / or the second image. In some examples, the displayed pixel intensity values ​​of the first image and / or the second image comprise pixel intensity values ​​displayed on a display unit. As used herein, actual pixel intensity values ​​(X a and Xb) refer to pixel intensity values ​​generated and / or stored by the image processor (101). As used herein, displayed pixel intensity values ​​(Y a and Y b ) refers to a pixel intensity value displayed on a display unit (104). For example, the displayed pixel intensity comprises the intensity of the pixel that the image viewer displays on the display unit (e.g., a monitor), which depends on the range of intensities that the image viewer can display (e.g., a range of 256 colors from 0: black to 255: white).

[0022] In an embodiment, the first image (I a) and the second image (I b The one or more contrast and lighting parameters of the image may include, but are not limited to, hue, saturation, contrast, brightness, gamma, and combinations thereof. In some embodiments, the one or more lighting parameters comprise illuminance (e.g., illuminance measured in terms of HSI (hue, saturation, intensity), HSL (hue, saturation, brightness), and HSV (hue, saturation, value) or HSB (hue, saturation, value)). In other embodiments, the one or more contrast and lighting parameters comprise parameters other than those mentioned herein. In general, the one or more contrast and lighting parameters comprise any suitable contrast and lighting parameters that are normalized and used to determine normalized pixel intensity values ​​of the image.

[0023] In an embodiment, the imaging unit (102) communicates with the image processing device (101) via a communication network (not shown). The imaging unit (102) is arranged to communicate with the communication network via a network interface (not shown). The network interface employs a connection protocol including, but not limited to, direct connection, Ethernet (e.g., twisted pair 10 / 100 / 1000 base-T), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 802.11a / b / g / n / x, etc. The communication network includes, but is not limited to, direct interconnection, wired connection, e-commerce network, peer-to-peer (P2P) network, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol (WAP)), Internet, Wireless Fidelity (Wi-Fi), etc.

[0024] In the embodiment, the image processing device (101) processes a first image and a second image (I a and I b ) to allow for a meaningful comparison between the actual pixel intensity values ​​(X a Or X b) is normalized. The normalized pixel intensity values ​​are essentially the normalized image (I a ' or I b The following description will be given without reference to part number (107). However, part number (107) forms a normalized image (I a ' or I b It should be clear to one skilled in the art that this refers to

[0025] 2 is an exemplary illustration of the internal structure of an image processing device (101) configured to normalize pixel intensities of an image, according to some embodiments of the present disclosure. The image processing device (101) includes at least one central processing unit ("CPU" or "processor") (203) and a memory (202) that stores instructions executable by the at least one processor (203). The processor (203) comprises at least one data processor for executing program components for executing requests generated by a user or the system. The memory (202) is communicatively coupled to the processor (203). The image processing device (101) further comprises an input / output (I / O) interface (201). The I / O interface (201) is coupled to the processor (203) to which input and / or output signals are communicated.

[0026] In an embodiment, data (204) is stored in memory (202). The data (204) includes, for example, contrast and lighting parameters (205), pixel intensity values ​​to be displayed (206), and other data (207).

[0027] In an embodiment, the contrast and lighting parameters (205) include, but are not limited to, hue, saturation, contrast, brightness, gamma, or combinations thereof.

[0028] In an embodiment, the maximum pixel intensity value displayed (206), here shown as G, is the maximum pixel intensity value displayed on the display unit (104). In an embodiment, the maximum pixel intensity displayed (G) varies depending on the display unit (104). In an embodiment, the maximum pixel intensity displayed (G) is determined using the specifications of the display unit (104). In an embodiment, the other data (207) includes parameters related to the imaging unit (102) and the first image (I a ) and the second image (I b ) and a timestamp associated with the

[0029] In an embodiment, the data (204) in the memory (202) is processed by a module (208) of the image processing device (101). As used herein, the term module refers to an application specific integrated circuit (ASIC), an electronic circuit, a field programmable gate array (FPGA), a programmable system on a chip (PSoC), a combinatorial logic circuit, and / or other suitable components that provide the described functionality. A module (208), when configured with the functionality defined in this disclosure, results in new hardware.

[0030] In an embodiment, the modules (208) include, for example, a communications module (209), a normalized gradient determination module (210), a normalized intercept determination module (211), a normalized pixel intensity determination module (212), and other modules (213). It will be appreciated that such aforementioned modules (209) may be represented as a single module or a combination of different modules.

[0031] In an embodiment, the communication module (209) transmits the first image (I) from the imaging unit (102) over a communication network. a ) and the second image (I b In an embodiment, the communication module (209) is configured to receive a first image (I a ) and the second image (I b) is configured to pre-process the first image (I ). In an embodiment, the pre-processing may include, but is not limited to, image enhancement, noise reduction, image compression, etc. The communication module (209) is further configured to a ) and the second image (I b ) of the actual pixel intensity value (X a , X b ), the highest pixel intensity value displayed (G), the window level value (L a , L b ), and the window width value (W a , W b )

[0032] In an embodiment, the displayed pixel intensity value (Y a , Y b ) is the actual pixel intensity value (X a , X b ) varies linearly with

[0033] In an embodiment, the normalized gradient determination module (210) determines the gradient of the first image (I a ) and the second image (I b ) window width value (W a , W b ) based on the normalized gradient (M f ) is configured to determine

[0034] In an embodiment, the normalized intercept determination module (211) determines the first image (I a ) window level value (L a ), the second image (I b ) window level value (L b ), the first image (I a ) window width value (W a ), the second image (I b ) window width value (W b ), and the normalized intercept value (C) based on the highest pixel intensity value displayed (G). f ) is configured to determine

[0035] In an embodiment, the normalized gradient value (M f) and the normalized intercept value (C f ) for each image (I a , I b ) displayed pixel intensity value (Y a , Y b ) and the actual pixel intensity value (X a , X b ) is determined to analyze the relationship between

[0036] In an embodiment, the functionality of the normalized slope determination module (210) and the normalized intercept determination module (211) may be combined, with a single module performing the functionality of the normalized slope determination module (210) and the normalized intercept determination module (211). f ) and the normalized intercept (C f ) are expressed together as one or more regularization parameters. In some embodiments, the one or more regularization parameters are a ) and / or a second image (I b ) the highest displayed pixel intensity value (G), the window level value (L a , L b ), and the window width value (W a , W b )

[0037] In an embodiment, the normalized pixel intensity determination module (212) determines the normalized gradient (M f ) and the normalized intercept (C f ) based on the second image (I b ) normalized pixel intensity value (X b In an embodiment, the method is configured to determine a normalized pixel intensity value (X b ') is the first image (I a ) the actual pixel intensity value (X a ) in the same range as the second image (I b ) the actual pixel intensity value (X b ) In an embodiment, the normalized pixel intensity value (X b ') is the actual pixel intensity value (X a ) to the actual pixel intensity value (Xb In an embodiment, the normalized pixel intensity determination module (212) uses one or more normalization parameters to determine the normalized pixel intensity values ​​(X b In an embodiment, a normalized pixel intensity value (X b ') is the normalized image (I b The normalized image (I b ') is the first image (I a ) for meaningful comparison.

[0038] In an embodiment, the other modules (213) include a classification module, a labeling module, and a segmentation module.

[0039] In an embodiment, the classification module is a ) and the second image (I b ) into one or more predefined categories. For example, a classification module may be used to classify a first image (I a ) and the second image (I b ) as comprising tumor cells. Similarly, the classification module can classify the first image (I a ) and the second image (I b ) can be classified into different categories.

[0040] In an embodiment, the segmentation module b ) and the first image (I a ) based on a comparison with the first image (I a ) and the second image (I b For example, the segmentation module may segment an image of a blood smear based on blood concentration.

[0041] In an embodiment, the labeling module may further include: a ) and the second image (I b), For example, the labeling module may label patches of an image as comprising red blood cells (RBCs).

[0042] FIG. 3 is a flowchart illustrating example method steps for normalizing pixel intensities of an image, according to some embodiments of the present disclosure.

[0043] As shown in Figure 3, a method (300) comprises one or more steps for normalizing pixel intensities of an image, according to some embodiments of the present disclosure. The method (300) is described in the general context of computer-executable instructions. Generally, computer-executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions that perform particular functions or implement particular abstract data types.

[0044] The order in which the method (300) is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to perform the method. Additionally, individual blocks can be deleted from the method without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0045] In step 301, a first image (I) is received from the imaging unit (102) by the communication module (209). a ) and the second image (I b ) as described herein. a ) and the second image (I b ) is received via a communication network. In an embodiment, the first image (I a ) and the second image (I b ) look the same. In an embodiment, the window width (W a , W b ) and window level (L a , L b) to each image, and then the first image (I a ) and the second image (I b ) appear the same. In an embodiment, the window settings are applied by the display unit (104).

[0046] In step 302, a first image (I a ) and the second image (I b ) one or more normalization parameters. Those skilled in the art should understand that any parameters other than the window parameters are covered within the scope of the present disclosure, even though not explicitly mentioned.

[0047] In step 303, a normalized pixel intensity determination module (212) determines a second image (I b ) normalized pixel intensity value (X b In an embodiment, a normalized pixel intensity value (X b ') is the normalized image (I b The normalized image (I b ') is the first image (I a ) the actual pixel intensity value (X a ) and pixel intensity values ​​(X b ').

[0048] The following description provides a detailed explanation of the method steps of 400. Reference is now made to FIG.

[0049] In step 401, the communication module (209) receives a first and a second image (I a , I b ) of the actual pixel intensity value (X a , X b ), the maximum pixel intensity displayed (G), the window level value (L a , L b ), and the window width value (W a, W b In an embodiment, the first and second images (I a , I b ) are captured using different modalities, e.g., the first image (I a ) is captured using a first setting on the MRI device, and a second image (I a ) is captured using a second setting on the MRI device. In another embodiment, the first and second images (I a , I b ) are images of the same region of the subject / patient captured at different times. Thus, the first and second images (I a , I b ) There are variations in the window settings (window width and window level) for the first and second images (I a , I b ) to make the images appear visually the same on the display unit (104). Such visually the same looking images are viewed by a radiologist / technologist to compare the images. In an embodiment, a window width value (W a , W b ) indicates the contrast setting, and the window level value (L a , L b ) indicates the brightness setting.

[0050] For image I, the windowing (window level (L) and window width (W)) is a linear contrast stretch and can be expressed as a linear equation, as shown in Equation 1. y=mx+c (1) Where: y = displayed / interpreted pixel intensity of the image displayed with window settings W and L, x = actual pixel intensity of the image, m = the gradient of the linear equation, and c=intercept It is.

[0051] Therefore, the first image (I a ) and the second image (Ib ), then Y a and Y b can be expressed in the form of a linear equation as shown below: Y a =M a X a +C a (2) Y b =M b X b +C b (3)

[0052] In step 402, the normalized gradient determination module (210) determines the first and second images (I a , I b ) window width (W a , W b ) based on the normalized gradient (M f In general, the gradient can be determined for a linearly varying displayed pixel intensity value (y) with respect to the actual pixel intensity value (x) as expressed in Equation 1 as follows: m=G / W (4) and c=-m[W+L / 2] (5)

[0053] Now, considering Equations 2 and 3, image I a and I b Since they look visually the same, Y a =Y b In the embodiment, the second image (I b ) is the first image (I a ) for comparison with the first image (I a ) is the second image (I b ) for comparison. b ) is considered to have been transformed. Therefore, X b X a can be expressed as shown below. M a X a +C a =M b X b +Cb (6)

[0054] As shown in Equation 4 and Equation 5, by substituting m and c and then solving Equation 6, the normalized gradient (M f ) is determined using the following formula: M f =W a / W b (7)

[0055] Those skilled in the art will appreciate that a ) is (I b ), M f But, W b / W a It should be understood that the metric is determined using the

[0056] In some embodiments, transforming the second image relative to the first image comprises performing a linear contrast stretch transform, while in some embodiments the second image is transformed relative to the first image in a geometric representation domain (e.g., using a geometric transformation), a pixel intensity distribution domain, a Fourier domain, or any other domain.

[0057] Reference is now made to FIG. 5, which illustrates example images of the same region in visually identical looking images, according to some embodiments of the present disclosure. As can be seen, the first image (I a ) and the second image (I b ) appear the same on the display unit (104). Furthermore, from FIG. a ) is L a =401 and W a = 697 window setting, while the second image (I b ) is L b =1219 and W b = 2119. Thus, the window setting is a , I b) so that the two images appear visually the same / identical on the display unit (104). a , I b ) (indicated by the circular selection) is considered by the radiologist / technologist for comparison.

[0058] Tables 1a and 1b show the results of the image (I a , I b ) shows exemplary pixel intensity values ​​of a region in the first and second images (I a , I b ) for the same region, the actual pixel intensity values ​​(X a , X b ) are shown in Tables 1a and 1b, respectively. As can be seen, the actual pixel intensity values ​​(X a , X b ) varies and is not within a typical range for comparison. The actual pixel intensity values ​​(X a , X b ) may occur for a variety of reasons, as discussed earlier in this disclosure.

[0059] [Table 1a]

[0060] [Table 1b]

[0061] In step 403, the normalized intercept determination module (211) determines the first and second images (I a , I b ) window level value (L a , L b ), window width value (W a , W b ), and the normalized intercept value (C) based on the highest pixel intensity value displayed (G). fReference is now made to FIG. 6, which is a flowchart illustrating exemplary method steps for determining a normalized intercept value, according to some embodiments of the present disclosure.

[0062] In step 601, a first image (I a ) window width value (W a ) for the window level value (L a ) The first ratio may be expressed as: R1=L a / W a (8)

[0063] In step 602, the normalized intercept determination module (211) determines the second image (I b ) window width value (W b ) for the window level value (L b ) The first ratio can be expressed as: R2=L b / W b (9)

[0064] In step 603, the normalized intercept determination module (211) determines the difference between the first ratio (R1) and the second ratio (R2) as follows: R1-R2=(L a / W a -L b / W b ) (10)

[0065] In step 604, the normalized intercept determination module (211) determines the normalized intercept (C) by determining the product of the highest pixel intensity value (G) displayed and Equation 10. f The normalized intercept (Cf) can be expressed as: C f =G(L a / W a -L b / W b ) (11)

[0066] Referring back to FIG. 4, in step 404, the normalized pixel intensity determination module (212) determines the normalized gradient value (M f ) and the normalized intercept value (C f ) based on the normalized pixel intensity value (X b The normalized pixel intensity determination module (212) determines (X b ) to (X b '). X b '=M f X b +C f (12)

[0067] Table 2 shows example normalized pixel intensity values ​​of regions in a second image relative to a first image, according to some embodiments of the present disclosure. As shown, the normalized pixel intensity values ​​(X b ') is the actual pixel intensity value (X a ) range. Therefore, X a X b ' can be compared to '.

[0068] [Table 2]

[0069] In an embodiment, the generated normalized pixel intensity values ​​(X b ') is the normalized image (I b In an embodiment, the normalized pixel intensity value (X b Generating a normalized image (I b In a further embodiment, the actual pixel intensity values ​​(X b ') is the first image (I a ) the actual pixel intensity value (X a) is the same as . Thus, the present disclosure provides a solution that allows for meaningful comparison of images (I) with different actual pixel intensity values ​​by normalizing the actual pixel intensity values ​​(X). For example, when an image needs to be classified or labeled, it needs to be compared to a reference image. The image to be classified or labeled has pixel intensity values ​​that are different from the pixel intensity values ​​of the reference image. For an image, a normalized pixel intensity value can be generated, where the pixel intensity values ​​of the image are within the range of the reference image such that a meaningful comparison can be performed to successfully classify / label the image.

[0070] In an embodiment, normalization of the actual pixel intensity values ​​(X) provides a meaningful comparison. Efficient classification, labeling, segmentation, and / or multi-label classification can be performed with meaningful comparisons between images. Thus, the normalized image (I b ') is the first image (I a ) and the comparison is used for at least one of image labeling, image classification, image segmentation, and multi-label classification. Multi-label classification is understood to refer to a type of classification in which an image is classified into multiple classes or as having multiple labels.

[0071] Computer Systems 7 illustrates a block diagram of an exemplary computer system (700) for implementing embodiments consistent with the present disclosure. The computer system (700) includes a central processing unit ("CPU" or "processor") (702). The processor (702) includes at least one data processor for executing program components for dynamic resource allocation at run-time. The processor (702) includes specialized processing units such as an integrated system (bus) controller, memory management control unit, floating point unit, graphics processing unit, digital signal processing unit, etc.

[0072] A processor (702) is disposed in communication with one or more input / output (I / O) devices (not shown) via an I / O interface (701). The I / O interface (701) may employ communication protocols / methods such as, but not limited to, audio, analog, digital, monoaural, RCA, stereo, IEEE-1394, serial bus, Universal Serial Bus (USB), infrared, PS / 2, BNC, coaxial, component, composite, Digital Visual Interface (DVI), High Definition Multimedia Interface (HDMI), RF antenna, S-Video, VGA, IEEE 802.n / b / g / n / x, Bluetooth, cellular (e.g., Code Division Multiple Access (CDMA), High Speed ​​Packet Access (HSPA+), Global System for Mobile Communications (GSM), Long Term Evolution (LTE), WiMax, etc.).

[0073] Using the I / O interface (701), the computer system (700) communicates with one or more I / O devices. For example, the input devices (710) can be an antenna, keyboard, mouse, joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touch pad, track ball, stylus, scanner, storage device, transceiver, video device / source, etc. The output devices (711) can be printers, fax machines, video displays (e.g., cathode ray tubes (CRT), liquid crystal displays (LDC), light emitting diodes (LED), plasma, plasma display panels (PDP), organic light emitting diode displays (OLED), etc.), audio speakers, etc.

[0074] In some embodiments, the computer system (700) is connected to a service operator via a communication network (709). A processor (702) is disposed in communication with the communication network (709) via a network interface (703). The network interface (703) communicates with the communication network (709). The network interface (703) applies a connection protocol, including but not limited to a direct connection, Ethernet (e.g., twisted pair 10 / 10 / 1000 base T), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 808.11a / b / g / n / x, etc. The communication network (709) includes but is not limited to a direct interconnect, an e-commerce network, a peer-to-peer (P2P) network, a local area network (LAN), a wide area network (WAN), a wireless network (e.g., using a wireless application protocol), the Internet, Wi-Fi, etc. Using the network interface (703) and the communication network (709), the computer system (700) communicates with one or more service operators.

[0075] In some embodiments, the processor (702) is arranged to communicate with memory (705) (e.g., RAM, ROM, etc., not shown in FIG. 7) via a storage interface (704). The storage interface (704) connects to the memory (705), including, but not limited to, memory drives, removable disk drives, etc., employing connection protocols such as Serial Advanced Technology Attachment (SATA), Integrated Drive Electronics (IDE), IEEE-1394, Universal Serial Bus (USB), Fibre Channel, Small Computer System Interface (SCSI), etc. Memory drives further include drum, magnetic disk drives, magneto-optical drives, optical drives, redundant array of independent disks (RAID), solid state memory devices, solid state drives, etc.

[0076] The memory (705) stores a collection of program or database components, including, but not limited to, a user interface (706), an operating system (707), a web server (708), etc. In some embodiments, the computer system (700) stores user / application data (706), such as data, variables, records, etc., as described in this disclosure. Such databases are implemented as fault-tolerant, relational, scalable, secure databases, such as Oracle or Sybase.

[0077] The operating system (707) facilitates resource management and operation of the computer system (700). Examples of operating systems include, but are not limited to, Apple Macintosh OS X, Unix, Unix-like system distributions (e.g., Berkeley Software Distribution (BSD), FreeBSD, NetBSD, OpenBSD, etc.), Linux distributions (e.g., Red Hat, Ubuntu, Kubuntu, etc.), IBM OS / 2, Microsoft Windows (XP, Vista / 7 / 8, 10, etc.), Apple iOS, Google Android, Blackberry OS, etc.

[0078] In some embodiments, the computer system (700) implements program components stored in a web browser (708). The web browser (708) is a hypertext browsing application such as Microsoft Internet Explorer, Google Chrome, Mozilla Firefox, Apple Safari, etc. Secure web browsing is provided using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), etc. The web browser (708) utilizes functionality such as AJAX, DHTML, Adobe Flash, JavaScript, Java, application programming interfaces (APIs), etc. In some embodiments, the computer system (700) implements program components stored in a mail server. The mail server is an Internet mail server such as Microsoft Exchange. The mail server utilizes functionality such as ASP, ActiveX, ANSI C++ / C#, Microsoft.NET, CGI scripts, Java, JavaScript, PERL, PHP, Python, WebObjects, etc. A mail server utilizes a communication protocol such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), Microsoft Exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), etc. In some embodiments, the computer system (700) implements program components stored in a mail client, which is a mail viewing application such as Apple Mail, Microsoft Entourage, Microsoft Outlook, Mozilla Thunderbird, etc.

[0079] In an embodiment, the imaging unit (712) captures a first and a second image (I a and Ib ) and transmits the first and second images (I) to a computer system (700) via a communication network (709) for normalizing the actual pixel intensity values. a and I b In an embodiment, the display unit (713) is configured to provide the first and second images (I a and I b ) to display the

[0080] The terms "an embodiment," "embodiment," "embodiments," "the embodiment," "the embodiments," "one or more embodiments," "some embodiments," and "one embodiment" mean "one or more, but not all, embodiments of the invention," unless specifically stated otherwise.

[0081] The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless expressly stated otherwise.

[0082] An enumerated list of items does not imply that some or all of the items are mutually exclusive unless expressly stated otherwise. The singular terms "a," "an," and "the" mean "one or more" unless expressly stated otherwise.

[0083] A description of an embodiment having several components in communication with each other does not imply that all such components are required, rather, a variety of optional components are described to illustrate the wide variety of possible embodiments of the present invention.

[0084] Where a single device or article is described herein, it will be readily apparent that multiple devices / articles (whether they cooperate or not) can be used in place of the single device / article. Similarly, where multiple devices or articles are described herein, it will be readily apparent that a single device / article can be used in place of the multiple devices or articles (whether they cooperate or not), or that a different number of devices / articles can be used in place of the number of devices or programs shown. The functionality and / or features of a device are alternatively embodied by one or more other devices not explicitly described as having such functionality / features. Thus, other embodiments of the invention need not include the device itself.

[0085] The illustrated operations in Figures 3, 4, and 7 show certain events occurring in a particular order. In alternative embodiments, certain operations are performed in a different order, modified, or removed. Furthermore, steps may be added to the logic above and still be in accordance with the described embodiments. Furthermore, operations described herein may occur sequentially or certain operations may be processed in parallel. Furthermore, operations may be performed by a single processing unit or by distributed processing units.

[0086] Finally, the language used herein has been selected primarily for ease of reading and instructional purposes, and not to delineate or limit the subject matter of the present invention. Accordingly, it is intended that the scope of the invention be limited not by this detailed description, but by the claims that issue on an application based hereon. Accordingly, the disclosure of embodiments of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

[0087] While various aspects and embodiments are disclosed herein, other aspects and embodiments will be apparent to those of skill in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope being indicated by the following claims. [Explanation of symbols]

[0088] 100 Systems 101 Image processing device 102 Imaging Unit 103 subjects 104 Display unit 201 I / O Interface 202 Memory 203 Processor 204 Data 205 Contrast and Lighting Parameters 206 Displayed pixel intensity values 207 Other Data 208 Modules 209 Communication Module 210 Normalized Gradient Determination Module 211 Normalized Intercept Determination Module 212 Normalized Pixel Intensity Determination Module 213 Other Modules 700 Computer Systems 701 I / O Interface 702 Processor 703 Network Interface 704 Storage Interface 705 Memory 706 User Interface 707 Operating Systems 708 Web Services 709 Communication Network 710 Input Devices 711 Output Device 712 Imaging Unit 713 Display Unit

Claims

1. A method for normalizing pixel intensity values ​​of a second image relative to a first image to generate a normalized image, the first image and the second image being images representing the same region of an object, the method comprising: receiving, by an image processor, actual pixel intensity values ​​generated by the image processor, one or more contrast parameters, one or more lighting parameters, and a maximum pixel intensity value to be displayed of a first image and a second image, wherein the one or more contrast parameters comprise a window width value for each of the first and second images, and the one or more lighting parameters comprise a window level value for each of the first and second images; determining, by the image processor, one or more normalization parameters for use in the normalization of pixel intensity values ​​of the second image based on the one or more contrast and lighting parameters of the first image and the second image and the maximum pixel intensity value; normalizing, by the image processor, pixel intensity values ​​of the second image using the one or more normalization parameters to determine normalized pixel intensity values ​​of the second image; and generating, by the image processor, a normalized image using the normalized pixel intensity values.

2. 2. The method of claim 1, wherein the displayed pixel intensity values ​​of the first image and the second image vary according to their respective actual pixel intensity values, and the displayed pixel intensity values ​​comprise pixel intensity values ​​displayed on a display unit.

3. The method of claim 1 , wherein the one or more contrast and lighting parameters comprise hue, saturation, contrast, brightness, gamma, or a combination thereof. determining a normalized gradient value based on the window width values ​​of the first image and the second image; determining a normalized intercept value based on the window level value of the first image, the window level value of the second image, the window width value of the first image, the window width value of the second image, and the maximum pixel intensity value to be displayed; and normalizing pixel intensity values ​​of the second image using the normalized gradient value and the normalized intercept value to determine the normalized pixel intensity values ​​of the second image. The method of claim 1 , wherein the displayed pixel intensity values ​​of the first and second images vary linearly with their respective actual pixel intensity values.

5. 5. The method of claim 4, wherein the first image and the second image are images of a same object having different actual pixel intensities but whose displayed pixel intensity values ​​are made equal by applying the one or more contrast and lighting parameters.

6. The method of claim 4 , wherein determining the normalized gradient value comprises determining a ratio of the window width value of the first image to a window width value of the second image.

7. The step of determining a normalized intercept value comprises: determining a first ratio of the window level value to the window width value of the first image; determining a second ratio of the window level value to the window width value for the second image; determining a difference between the first ratio and the second ratio; and determining the normalized intercept value by determining the product of the difference and the highest pixel intensity value displayed.

8. The step of determining a normalized pixel intensity value comprises: determining the product of the normalized gradient value and the actual pixel intensity value of the second image; and determining a sum of the determined product and a normalized intercept value.

9. The method of claim 8, wherein the normalized image and the first image have the same actual pixel intensity values ​​for one or more regions in the first image and the normalized image.

10. The method of claim 4 , wherein the window width value indicates a contrast of the first image and the second image, respectively, and the window level value indicates a brightness of the first image and the second image, respectively.

11. The method of claim 4 , wherein the normalized image is compared to the first image, and the comparison is used for at least one of image labeling, image classification, image segmentation, and multi-label classification.

12. An image processing device for normalizing pixel intensity values ​​of a second image relative to a first image to generate a normalized image, the first image and the second image being images representing the same region of an object, the image processing device comprising: A processor; a processor that is communicatively coupled to the processor and that, upon execution, causes the processor to receiving actual pixel intensity values ​​generated by the image processor for a first image and a second image, one or more contrast parameters including a window width value for each of the first and second images, one or more lighting parameters including a window level value for each of the first and second images, and a maximum pixel intensity value to be displayed; determining one or more normalization parameters for use in the normalization of pixel intensity values ​​of the second image based on the one or more contrast and lighting parameters of the first image and the second image and the maximum pixel intensity value; normalizing pixel intensity values ​​of the second image using the one or more normalization parameters to determine normalized pixel intensity values ​​of the second image; and a memory storing processor-executable instructions for causing a normalized image to be generated using the normalized pixel intensity values.

13. The processor, determining a normalized gradient value based on the window width values ​​of the first image and the second image; determining a normalized intercept value based on the window level value of the first image, the window level value of the second image, the window width value of the first image, the window width value of the second image, and the maximum pixel intensity value displayed; normalizing pixel intensity values ​​of the second image using the normalized gradient value and the normalized intercept value to determine the normalized pixel intensity values ​​of the second image; 13. The image processing apparatus of claim 12, wherein the displayed pixel intensity values ​​of the first and second images vary linearly with their respective actual pixel intensity values.

14. 14. The image processing device of claim 13, wherein the processor receives the first image and the second image of a same object having different actual pixel intensities, but whereby the applied one or more contrast and lighting parameters cause displayed pixel intensity values ​​to be equal.

15. The image processing apparatus of claim 13 , wherein the processor determines the normalized gradient value by determining a ratio of a window width value of the first image to a window width value of the second image.

16. The processor determines the normalized intercept value, the processor further comprising: determining a first ratio of the window level value to the window width value of the first image; determining a second ratio of the window level value to the window width value for the second image; determining a difference between the first ratio and the second ratio; 14. An image processing apparatus as claimed in claim 13, further comprising: determining the normalised intercept value by determining the product of the difference and the highest pixel intensity value displayed.

17. The processor determines the normalized pixel intensity value, the processor further comprising: determining the product of the normalized gradient value and the actual pixel intensity value of the second image; The image processing apparatus of claim 13 , further comprising: determining a sum of the determined product and a normalized intercept value.

18. The image processing apparatus of claim 17 , wherein the processor is configured to cause the normalized image and the first image to have the same actual pixel intensity values ​​for one or more regions in the first image and the normalized image.

19. The image processing device of claim 13 , wherein the processor compares the normalized image to the first image, and the comparison is used for at least one of image labeling, image classification, image segmentation, and multi-label classification.

20. An imaging device; A display unit; and the image processing device according to claim 12, the imaging device captures a first image and a second image of an object, and a first window level value and a first window width value are applied to the first image and a second window level value and a second window width value are applied to the second image to display the first image and the second image on the display unit; The image processing device includes: determining a normalized gradient value based on the window width values ​​of the first image and the second image; determining a normalized intercept value based on the window level value of the first image, the window level value of the second image, the window width value of the first image, the window width value of the second image, and a maximum pixel intensity value displayed; normalizing pixel intensity values ​​of the second image using the normalized gradient value and the normalized intercept value to determine normalized pixel intensity values ​​of the second image; The system uses the normalized pixel intensity values ​​of the second image to generate the normalized image.

Images