Methods, apparatuses, and systems for normalizing pixel intensity of an image

Abstract

The present disclosure relates to normalizing pixel intensity values of images. Qualitative images that must be compared need to have actual pixel intensity values that are within a suitable range. Typically, the qualitative images to be compared are rendered to appear visually similar by adjusting display settings. A first image and a second image are received that have different actual pixel intensity values but appear visually identical. One or more normalization parameters are determined and used with one or more contrast and illumination parameters associated with the first and second images. Thereafter, normalized pixel intensity values are determined and a normalized image is generated using the one or more normalization parameters. The pixel intensity values of the normalized image can be compared to the actual pixel intensity values of the first image or the second image.

Description

[0001] The following specification specifically describes the invention and how it is to be performed. Technical Field

[0002] This disclosure generally relates to the field of image processing technology. More specifically, but not specifically, this disclosure relates to methods, apparatus, and systems for normalizing pixel intensity of an image. Background Technology

[0003] Image processing technology is widely used in various applications for image analysis. Image processing techniques are performed based on the properties of an image (pixel intensity, color, saturation, contrast, hue, brightness, and various other parameters). Different images can be compared as long as the relevant parameters are within a comparable range. For example, images of the same object captured using different imaging devices may have different pixel intensity values ​​due to the settings of each imaging device. Similarly, various other parameters representing the same object can differ in two images, even though the two images may appear similar when viewed on a display unit such as a monitor. Often, the display unit applies settings to the image according to the viewer's needs. For example, the image contrast can be changed in the display unit, the image brightness can be changed, and so on. Advanced computing systems can be used to process and analyze images according to applications.

[0004] In medical imaging, different imaging devices are used to acquire images, such as cameras, computed tomography (CT) machines, magnetic resonance imaging (MRI) machines, and ultrasound machines. Laboratory technicians may need to compare images captured at different times using different modalities (CT, MRI) to analyze them. Two images may appear visually identical (i.e., qualitatively similar), but their pixel intensity values ​​can differ (i.e., quantitatively different). Display settings (e.g., windowing) are used to adjust the two images to appear visually identical to the user. However, computational systems can compare image properties (e.g., pixel intensity) themselves and typically do not use display properties to compare images.

[0005] Existing systems normalize one of two images relative to the other so that computational systems can meaningfully compare them. Several existing systems perform calibration to quantitatively represent two images in a similar manner, but do not consider display settings used to make the two images appear visually similar. The solutions provided by such systems are not general and are highly subjective regarding image parameters or image content, as discussed below.

[0006] Several existing systems perform intensity normalization techniques on qualitative images. Typically, histogram-based methods are followed to normalize intensity values. Intensity normalization factors can be measured based on the entire image or a portion of it. When considering the entire image by this method, noise levels in the image play a significant role and affect normalization, thus only high SNR images are good candidates for such methods. When considering a portion of the image by normalization methods, it can be severely biased because the normalization is entirely driven by pixel values ​​within that region, and it can 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 section is intended only to enhance the understanding of the general background of the invention and should not be construed as an admission that the information constitutes prior art known to those skilled in the art or any form of implication. Summary of the Invention

[0008] In one embodiment, a method for normalizing the pixel intensity of an image is disclosed. The method receives actual pixel intensity values ​​of a first image and a second image generated by an image processing device, one or more contrast parameters, and one or more illumination parameters. In this embodiment, the first and second images are visually similar to the human eye, even though different pixel intensities in the first and second images represent the same area. Furthermore, one or more normalization parameters are determined using one or more contrast and illumination parameters of the first and second images. The 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 apparatus for normalizing pixel intensity of an image is disclosed. The image processing apparatus includes a memory and a processor. The processor is configured to receive actual pixel intensity values, one or more contrast and illumination parameters generated by the image processing apparatus for a first image and a second image. Although different pixel intensities in the first and second images represent the same region, the first and second images appear visually similar to the human eye. The processor uses one or more contrast and illumination parameters of the first and second images to determine one or more normalization parameters. Furthermore, the processor determines normalized pixel intensity values ​​of the second image based on the one or more normalization parameters, and generates a normalized image by transforming the second image relative to the first image using the normalized pixel intensity values.

[0010] In one embodiment, a system including an imaging device, a display unit, and an image processing apparatus is disclosed. The imaging device is configured to capture a first image and a second image. The display unit is configured to apply a first window horizontal value and a first window width to the first image and to apply a second window horizontal value and a second window width to the second image, such that the first image and the second image appear visually similar on the display unit. The image processing apparatus is configured to determine a normalized slope value based on the window width values ​​of the first image and the second image. Furthermore, the image processing apparatus determines a normalized intercept value based on the window horizontal values ​​of the first and second images, the window width values ​​of the first and second images, and the highest displayed pixel intensity value. Subsequently, the image processing apparatus determines a normalized pixel intensity value of the second image based on the normalized slope and the normalized intercept value, and also 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 overview is illustrative only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, other aspects, embodiments, and features will become apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0012] The novel features and characteristics of this disclosure are set forth in the appended claims. However, the disclosure itself, its preferred modes of use, further objectives, and advantages will be best understood by referring to the following detailed description of illustrative 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 accompanying drawings, wherein similar reference numerals denote similar elements, and wherein:

[0013] Figure 1 This is an illustration of a block diagram for normalizing the pixel intensity of an image according to some embodiments of the present disclosure;

[0014] Figure 2 This is an exemplary illustration of the internal structure of an image processing apparatus configured to normalize the pixel intensity of an image according to some embodiments of the present disclosure;

[0015] Figure 3 This is a flowchart illustrating exemplary method steps for normalizing the pixel intensity of an image according to some embodiments of the present disclosure;

[0016] Figure 4 This is a flowchart illustrating detailed method steps for normalizing the pixel intensity of an image according to some embodiments of the present disclosure;

[0017] Figure 5 Exemplary images are shown, representing the same region in visually similar images, according to some embodiments of this disclosure;

[0018] Figure 6 This is a flowchart illustrating exemplary method steps for determining normalized intercept values ​​according to some embodiments of the present disclosure; and

[0019] Figure 7 A general-purpose computer system for normalizing the pixel intensity of an image is shown according to some embodiments of the present disclosure.

[0020] Those skilled in the art will recognize that any block diagram herein represents a conceptual view of an illustrative system embodying the principles of the subject matter. Similarly, it will be appreciated that any flowchart, flow diagram, state transition diagram, pseudocode, etc., represents various processes that can be substantially represented in a computer-readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.

[0021] Figure label:

[0022]

[0023] Detailed Implementation

[0024] In this document, the term "exemplary" is used 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 superior to other embodiments.

[0025] While this disclosure is readily adaptable to various modifications and alternatives, specific embodiments thereof have been illustrated by way of example in the accompanying drawings and will be described in detail below. However, it should be understood that this disclosure is not intended to limit it to the particular forms disclosed, but rather to cover all modifications, equivalents, and alternatives falling within the scope of this disclosure.

[0026] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an arrangement, apparatus, or method that includes a list of components or steps includes not only those components or steps but may also include other components or steps not expressly listed or inherent to such arrangement, apparatus, or method. In other words, one or more elements in a system or apparatus followed by “comprising…” do not exclude the presence of other elements or additional elements in the system or apparatus, unless further constraints are imposed.

[0027] Embodiments of this disclosure relate to normalizing the pixel intensity values ​​of images. Qualitative images to be compared need to have actual pixel intensity values ​​within a suitable range. The “actual” pixel intensity values ​​of an image can be considered as intensity values ​​generated and / or stored in the image data of the image. For example, 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. Typically, qualitative images to be compared are presented as visually similar by adjusting display settings. Therefore, the images are presented as visually similar because the displayed pixel intensities are the same or similar. Using the relationship between the display settings of the qualitative images, this disclosure normalizes the pixel intensity values ​​of qualitative images to enable comparison of images by any image processing device.

[0028] Figure 1 This is an illustration of a block diagram of a system (100) for normalizing the pixel intensity of an image according to some embodiments of the present disclosure. Figure 1 As shown, the system (100) includes: an imaging unit (102) and two images, namely, a first image (I) input to the image processing device (101). a (105) and the second image (I) b (106), object (103), and display unit (104). In embodiments, the imaging unit (102) may be a camera, magnetic resonance imaging (MRI) device, computed tomography (CT) device, or any other device capable of imaging the patient (104). For simplicity, the first and second images are not yet partly designated. However, it should be apparent to those skilled in the art that... Figure 1 The part numbers (105 and 106) refer to the first image and the second image, respectively. In one embodiment, the first image (I) is presented to the radiologist / laboratory technician as visually similar. a ) and the second image (I b (I) can be captured by the same imaging unit. In one embodiment, different imaging units can be used to capture a first image (I) that appears visually similar to a radiologist / laboratory technician. a ) and the second image (I b In another embodiment, the first image (I) a ) and the second image (I b (I) can be captured by different imaging units of similar / identical modalities. For example, a first image (I) can be captured using a first MRI scanner. a And a second image can be captured using a second MRI scanner (I) b In another embodiment, the first image (I) a) and the second image (I b (I) can be captured by different imaging units of different modalities. For example, the first image (I) can be captured using an MRI scanner. a And a second image can be captured using a CT scanner (I b In this case, the parameters of the MRI scanner can be adjusted so that the first image captured by the MRI scanner (I) a ) and the second image captured by the CT scanner (I b The images are presented as visually similar / identical. In one embodiment, the first image (I) a ) and the second image (I b The images are captured at different times. In one embodiment, when the imaging unit (102) is a camera, the first image (I) is captured at different times. a ) and the second image (I b ) can represent, for example, the skin of the object (103), the eyes of the object (103), and the like. In one embodiment, when the imaging unit (102) is an MRI device, the first image (I a ) and the second image (I b ) can represent, for example, an organ of object (103), tissue of object (103), and bone of object (103). In one embodiment, when the imaging unit (102) is a CT device, the first image (I a ) and the second image (I b ) can represent, for example, the organs of object (103), the tissues of object (103), the bones of object (103), and the blood vessels of object (103).

[0029] In the embodiment, the first image (I) a ) and the second image (I b () can represent the same region / point of an object. In the embodiment, the first image (I) a ) and the second image (I b () can represent a region of an object, such as the object's tissue or organ. In an embodiment, the first image (I) a The actual pixel intensity value (X) a ) and the second image (I b The actual pixel intensity value (X) b The images (I) can be different, while the first image (I) a ) and the second image (I b The images are presented visually similar on the display unit (104). In this embodiment, the actual pixel intensity and the first image (I) are considered similar. a ) and the second image (I bThe result of a combination of one or more contrast and lighting parameters of the object in the image, for viewing the first image (I) on the display unit (104). a ) and the second image (I b For users / laboratory technicians, the images may appear similar. In an embodiment, the first image (I) a The display pixel intensity value (Y) a ) equals the second image (I) b The display pixel intensity value (Y) b In another embodiment, the pixel intensity value (Y) is displayed. a ) and (Y b The image is received from the display unit (104) by the image processing device.

[0030] In the embodiment, the first image (I) a The display pixel intensity value (Y) a ) and the second image (I b The display pixel intensity value (Y) b With the corresponding actual pixel intensity value (X) a and X b The actual pixel intensity value (X) varies. In some examples, the displayed pixel intensity values ​​of the first and / or second images include the pixel intensity values ​​displayed on the display unit. As used herein, the actual pixel intensity value (X) a and X b ) refers to the pixel intensity value generated and / or stored by the image processing device (101). As used herein, the display pixel intensity value (Y) a and Y b ) refers to the pixel intensity value displayed on the display unit (104). For example, the display pixel intensity may include the intensity of the pixels displayed by the image viewer on the display unit (e.g., a monitor), and this may depend on the range of intensities that the image viewer is able to display (e.g., 256 colors, ranging from 0: black to 255: white).

[0031] In the embodiment, the first image (I) a ) and the second image (I bOne or more contrast and illumination parameters may include, but are not limited to, hue, saturation, contrast, luminance, gamma, and combinations thereof. In some embodiments, one or more illumination parameters may include illuminance (e.g., based on HSI (hue, saturation, intensity), HSL (hue, saturation, luminance), and HSV (hue, saturation, value) or HSB (hue, saturation, luminance)). In other embodiments, one or more contrast and illumination parameters may include parameters other than those mentioned herein. Generally, one or more contrast and illumination parameters may include any suitable contrast and illumination parameters that can be normalized and used to determine normalized pixel intensity values ​​for an image.

[0032] In this embodiment, the imaging unit (102) can communicate with the image processing device (101) via a communication network (not shown). The imaging unit (102) can be configured to communicate with the communication network via a network interface (not shown). The network interface can employ connection protocols, including but not limited to direct connection, Ethernet (e.g., twisted pair 10 / 100 / 1000Base T), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 802.11a / b / g / n / x, etc. The communication network can include, 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, Wi-Fi, etc.

[0033] In an embodiment, the image processing device (101) generates a value for the actual pixel intensity (X). a or X b Normalization is performed on the first and second images (I) to achieve normalization. a and I b Meaningful comparisons between normalized pixel intensity values. Normalized pixel intensity values ​​can inherently form a normalized image (I). a 'or I b (107). An alternative interpretation is provided without reference to part number (107). However, it should be obvious to those skilled in the art that part number (107) refers to the normalized image (I). a 'or I b ').

[0034] Figure 2This is an exemplary illustration of the internal structure of an image processing apparatus (101) configured to normalize the pixel intensity of an image according to some embodiments of the present disclosure. The image processing apparatus (101) may include at least one central processing unit (“CPU” or “processor”) (203) and a memory (202) storing instructions executable by the at least one processor (203). The processor (203) may include at least one data processor for executing program components for fulfilling user- or system-generated requests. The memory (202) is communicatively coupled to the processor (203). The image processing apparatus (101) also includes an input / output (I / O) interface (201). The I / O interface (201) is coupled to the processor (203) through which input signals and / or output signals are transmitted.

[0035] In this embodiment, the data (204) may be stored in the memory (202). The data (204) may include, for example, contrast and lighting parameters (205), display pixel intensity values ​​(206), and other data (207).

[0036] In the embodiments, the contrast and illumination parameters (205) may include, but are not limited to, hue, saturation, contrast, brightness, gamma, or combinations thereof.

[0037] In an embodiment, the highest display pixel intensity value (206) (hereinafter referred to as G) may be the highest pixel intensity value displayed on the display unit (104). In an embodiment, the highest display pixel intensity (G) may vary depending on the display unit (104). In an embodiment, the highest display pixel intensity (G) may be determined using a specification table of the display unit (104). In an embodiment, other data (207) may include parameters related to the imaging unit (102) and parameters related to the first image (I). a ) and the second image (I b The associated timestamp.

[0038] In this 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), electronic circuit, field-programmable gate array (FPGA), etc. Programmable System-on-Chip (PSoC), combinational logic circuitry, and / or other suitable components that provide the described functionality. When configured with the functionality defined in this disclosure, module (208) produces novel hardware.

[0039] In one implementation, module (208) may include, for example, a communication module (209), a normalized slope 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 a module (209) may be represented as a single module or a combination of different modules.

[0040] In one embodiment, the communication module (209) may be configured to receive a first image (I) from the imaging unit (102) via a communication network. a ) and the second image (I b In an embodiment, the communication module (209) can be configured to preprocess the first image (I). a ) and the second image (I b In this embodiment, preprocessing may include, but is not limited to, image enhancement, noise reduction, and image compression. The communication module (209) may also receive the first image (I). a ) and the second image (I b The actual pixel intensity value (X) a X b ), highest display pixel intensity value (G), window horizontal value (L) a L b ) and window width value (W a W b ).

[0041] In the embodiment, the pixel intensity value (Y) is displayed. a Y b ) can be adjusted according to the corresponding actual pixel intensity value (X) a X b It changes linearly.

[0042] In an embodiment, the normalized slope determination module (210) can be configured to determine the slope based on a first image (I). a ) and the second image (I b The window width value (W) a W b To determine the normalization slope (M) f ).

[0043] In an embodiment, the normalized intercept determination module (211) can be configured to determine the intercept based on a first image (I). a ) window level value (L) a ), second image (I) b ) window level value (L) b ), first image (I) a The window width value (W) a ), second image (I) bThe window width value (W) b The normalized intercept value (C) is determined by the highest displayed pixel intensity value (G) and the highest displayed pixel intensity value (G). f ).

[0044] In the embodiments, the normalized slope value (M) can be determined. f ) and normalized intercept (C f ), to analyze the corresponding images (I a I b The display pixel intensity value (Y) a Y b ) and actual pixel intensity value (X) a X b The relationship between ).

[0045] In this embodiment, the functions of the normalized slope determination module (210) and the normalized intercept determination module (211) can be combined, and a single module can perform the functions of the normalized slope determination module (210) and the normalized intercept determination module (211). The normalized slope (M... f ) and normalized intercept (C f These can be represented together as one or more normalization parameters. In some embodiments, one or more normalization parameters may include one or more of the following: the first image (I a ) and / or the second image (I b The highest display pixel intensity value (G) and window horizontal value (L) a L b ) and window width value (W a W b ).

[0046] In this embodiment, the normalized pixel intensity determination module (212) is configured to determine the pixel intensity based on the normalized slope (M). f ) and normalized intercept (C f Determine the second image (I) b Normalized pixel intensity value (X) b In the embodiment, the normalized pixel intensity value (X) is... b ') can be represented in relation to the first image (I) a The actual pixel intensity value (X) a The second image within the comparable range (I) b The actual pixel intensity value (X) b In this embodiment, the actual pixel intensity value (X) is used. b ) relative to the actual pixel intensity value (X) a The transformation is performed to obtain the normalized pixel intensity value (X). bIn this embodiment, the normalized pixel intensity determination module (212) can use one or more normalization parameters to determine the normalized pixel intensity value (X). b In the embodiment, the normalized pixel intensity value (X) is... b ') Forming a normalized image (I b Normalized image (I) b ') can be used with the first image (I a Make meaningful comparisons.

[0047] In an embodiment, other modules (213) may include a classification module, a labeling module, and a segmentation module.

[0048] In this embodiment, the classification module can classify the first image (I a ) and the second image (I b The classification module can be used to classify the first image (I) into one or more predefined categories. For example, the classification module can be used to classify the first image (I) into one or more predefined categories. a ) and the second image (I b The classification module can categorize the first image (I) as including tumor cells. Similarly, the classification module can classify the first image (I) as including tumor cells. a ) and the second image (I b They are classified into different categories.

[0049] In an embodiment, the segmentation module can be configured to be based on a second image (I b ) and the first image (I a The comparison is used to segment the first image (I). a ) and the second image (I b For example, the segmentation module can segment images of blood smears based on blood concentration.

[0050] In an embodiment, the labeling module can be configured to label the first image (I) based on comparison. a ) and the second image (I b For example, the labeling module can label image patches as including red blood cells (RBCs).

[0051] Figure 3 This is a flowchart illustrating exemplary method steps for normalizing the pixel intensity of an image according to some embodiments of the present disclosure.

[0052] like Figure 3 As illustrated, according to some embodiments of this disclosure, the method (300) may include one or more steps for normalizing the pixel intensity of an image. The method (300) may be described in the general context of computer-executable instructions. Typically, computer-executable instructions may include routines, programs, objects, components, data structures, processes, modules, and functions that perform a particular function or implement a particular abstract data type.

[0053] The order in which the method (300) is described is not intended to be construed as limiting, and any number of described method blocks can be combined in any order to implement the method. Furthermore, individual blocks can be removed from the method without departing from the scope of the subject matter described herein. Moreover, the method can be implemented in any suitable hardware, software, firmware, or a combination thereof.

[0054] At step 301, the communication module (209) receives the first image (I) from the imaging unit (102). a ) and the second image (I b As described herein, a first image (I) can be received via a communication network. a ) and the second image (I b In an embodiment, the first image (I) a ) and the second image (I b The presentation is similar. In the embodiments, such as the window width (W) a W b ) and window level (L a L b The window settings are applied to the corresponding image so that the first image (I) a ) and the second image (I b The presentation is similar. In one embodiment, window settings are applied by the display unit (104).

[0055] At step 302, the first image (I) is determined by a single module (a combination of the normalized slope determination module (210) and the normalized intercept determination module (211)). a ) and the second image (I b One or more normalized parameters of the window parameter. Those skilled in the art will recognize that, although not explicitly mentioned, any parameter other than the window parameter can be covered within the scope of this invention.

[0056] At step 303, the normalized pixel intensity determination module (212) determines the second image (I) based on one or more normalized parameters. b Normalized pixel intensity value (X) b In the embodiment, the normalized pixel intensity value (X) is... b ') Forming a normalized image (I b Normalized image (I) b ') may have the same characteristics as the first image (I) a The actual pixel intensity value (X) a Pixel intensity values ​​(X) within the comparable range b ').

[0057] The steps for method 300 are described in detail below. Now refer to... Figure 4 .

[0058] At step 401, the communication module (209) receives the first and second images (I a I b The actual pixel intensity value (X) a X b ), Maximum display pixel intensity (G), Window horizontal value (L) a L b ) and window width value (W a W b In one embodiment, the first and second images (I) a I b Different modalities can be used to capture images, for example, the first image (I a The first image was captured using the first settings in the MRI equipment, while the second image (I) was captured using the first settings in the MRI equipment. a The first and second images (I) are captured using a second setting in the MRI equipment. In another embodiment, the first and second images (I) are... a I b Images can be of the same area of ​​the object / patient but captured at different times. Therefore, the first and second images (I) a I b There may be variations in the first and second images (I). a I b Window settings (window width and window level) are applied to the display unit (104) to make the images appear visually similar. Radiologists / laboratory technicians can view these visually similar images for comparison. In this embodiment, the window width value (W...) a W b It can indicate the contrast setting and the window level value (L). a L b It can indicate the brightness setting.

[0059] For image I, windowing (window horizontal (L) and window width (W)) is a linear contrast stretching, which can be expressed as a linear equation, as shown in Equation 1:

[0060] y = mx + c (1)

[0061] in:

[0062] y = Display / interpretation pixel intensity of the image displayed under window settings W and L;

[0063] x = the actual pixel intensity of the image;

[0064] m = the slope of the linear equation; and

[0065] c = intercept;

[0066] Therefore, for the first image (I) a ) and the second image (I b ), Y a and Y b It can be expressed in the form of a linear equation as shown below:

[0067] Y a = M a X a + C a (2)

[0068] Y b = M b X b + C b (3)

[0069] At step 402, the normalized slope determination module (210) determines the slope based on the first and second images (I). a I b ) window width (W a W b Determine the normalized slope (M) f Generally, the slope of the linearly varying display pixel intensity value (y) relative to the actual pixel intensity value (x) expressed in Equation 1 can be determined as follows:

[0070] m = G / W (4)

[0071] and

[0072] c = -m [W + L / 2] (5)

[0073] Now consider equations 2 and 3, Y a =Y b Because image I a and I b They are presented as visually similar. In an embodiment, the second image (I) can be transformed. b ) with the first image (I a ) for comparison. Alternatively, the first image (I) can be transformed. a ) with the second image (I b Let's compare them. To illustrate, let's consider the second image (I). b X is transformed. Therefore, X b It can be relative to X a This is represented as follows:

[0074] M aX a + C a = Mb X b + C b (6)

[0075] Substituting m and c as shown in equations 4 and 5, and after further solving equation 6, the normalized slope (M) is determined using the following equation. f ):

[0076] M f = W a / W b (7)

[0077] Those skilled in the art should realize that when (I a According to (I) f During transformation, W can be used. b / W a Determine M f .

[0078] While in some embodiments, transforming a second image relative to a first image may include performing a linear contrast stretching transformation, in other embodiments, the second image may be transformed relative to the first image in the geometric representation domain, pixel intensity distribution domain, Fourier domain, or any other domain (e.g., using a geometric transformation).

[0079] Now for reference Figure 5 This illustrates exemplary images of the same regions presented in visually similar images according to some embodiments of the present disclosure. As can be seen, the first image (I a ) and the second image (I b The same is presented on the display unit (104). Furthermore, from... Figure 5 It can be noted that the first image (I) a ) and L a =401 and W a =697 is associated with the window settings, while the second image (I) b ) and L b =1219 and W b =2119 is associated with window settings. Therefore, window settings are applied to the first and second images (I a I b This allows the two images to appear visually similar / identical on the display unit (104). Furthermore, radiologists / laboratory technicians can consider the first and second images (I...) a I b The regions in the circle (shown by circular selection) are used for comparison.

[0080] Tables 1a and 1b show images (I) of some embodiments according to this disclosure. a I b Exemplary pixel intensity values ​​for regions in the first and second images (I). In an embodiment, for the first and second images (I a I b The same region in ) has the same actual pixel intensity value (X) a X b The actual pixel intensity values ​​(X) are shown in Tables 1a and 1b, respectively. As can be seen, the actual pixel intensity values ​​(X) are... a X b The values ​​are different and not within the common range used for comparison. Actual pixel intensity value (X) a X b Differences can occur due to the various reasons described above in this disclosure.

[0081]

[0082] Table 1a

[0083] Table 1b

[0084] At step 403, the normalized intercept determination module (211) determines the intercept based on the first and second images (I). a I b ) window level value (L) a L b ), window width value (W) a W b The normalized intercept value (C) is determined by the highest displayed pixel intensity value (G) and the highest displayed pixel intensity value (G). f (Now for reference) Figure 6 , Figure 6 This is a flowchart illustrating exemplary method steps for determining a normalized intercept value according to some embodiments of the present disclosure.

[0085] At step 601, the normalized intercept determination module (211) determines the first image (I). a ) window level value (L) a ) and window width value (W a The first ratio. The first ratio can refer to:

[0086] R1 = L a / W a (8)

[0087] At step 602, the normalized intercept determination module (211) determines the second image (I). b ) window level value (L) b ) and window width value (W bThe second ratio. The first ratio can refer to:

[0088] R2 = L b / W b (9)

[0089] At step 603, the difference between the first ratio (R1) and the second ratio (R2) is determined by the normalized intercept determination module (211), as shown:

[0090] R1 – R2 = (L a / W a – L b / W b (10)

[0091] At step 604, the normalized intercept determination module (211) determines the normalized intercept (C) by determining the product of equation 10 and the highest display pixel intensity value (G). f Normalized intercept (C) f ) can refer to:

[0092] C f = G(L a / W a – L b / W b (11)

[0093] Return to reference Figure 4 At step 404, the normalized pixel intensity value determination module (212) determines the pixel intensity value based on the normalized slope value (M). f ) and normalized intercept (C f ) to determine the normalized pixel intensity value (X) b The normalized pixel intensity value determination module (212) can use equations 7 and 11 to determine (X). b ) transform into (X b '), as shown below:

[0094] X b ' = M f X b + C f (12)

[0095] Table 2 shows exemplary 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 value (X... b ') may be in the actual pixel intensity value (X a Within the range of ). Therefore, X a Can be with X b 'To compare.'

[0096] Table 2

[0097] In the embodiment, the generated normalized pixel intensity value (X) b ') can represent a normalized image (I b In the embodiment, a normalized pixel intensity value (X) is generated. b ') can inherently mean generating a normalized image (I b In another embodiment, the actual pixel intensity value (X) b ') can be similar to the first image (I) a The actual pixel intensity value (X) a Therefore, this disclosure provides a solution that enables meaningful comparisons of images (I) with different actual pixel intensity values ​​by normalizing the actual pixel intensity values ​​(X). For example, if images must be classified or labeled, it may be necessary to compare the image with a reference image. The image to be classified or labeled may have pixel intensity values ​​that differ from those of the reference image. For the image, normalized pixel intensity values ​​can be generated, and the pixel intensity values ​​of the image can be within the range of the reference image, making it possible to perform meaningful comparisons to successfully classify / label the image.

[0098] In this embodiment, normalization of the actual pixel intensity value (X) provides meaningful comparisons. Effective classification, labeling, segmentation, and / or multi-label classification can be performed through meaningful comparisons between images. Therefore, the normalized image (I... b ') and the first image (I a The comparison can be performed on at least one of image labeling, image classification, image segmentation, and multi-label classification. Multi-label classification will be understood as a classification type in which an image can be classified into more than one category or has more than one label.

[0099] Computer System

[0100] Figure 7 A block diagram of an exemplary computer system (700) for implementing embodiments consistent with this disclosure is illustrated. The computer system (700) may include a central processing unit (“CPU” or “processor”) (702). The processor (702) may include at least one data processor for executing program components for dynamic resource allocation during runtime. The processor (702) may include dedicated processing units, such as an integrated system (bus) controller, a memory management control unit, a floating-point unit, a graphics processing unit, a digital signal processing unit, etc.

[0101] The processor (702) can be configured to communicate with one or more input / output (I / O) devices (not shown) via an I / O interface (701). The I / O interface (701) can employ communication protocols / methods such as, but not limited to, audio, analog, digital, mono, RCA, stereo, IEEE-1394, serial bus, Universal Serial Bus (USB), infrared, PS / 2, BNC, coaxial, component, composite, digital video 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.).

[0102] Using the I / O interface (701), the computer system (700) can communicate with one or more I / O devices. For example, input devices (710) can be antennas, keyboards, mice, joysticks, (infrared) remote controls, cameras, card readers, fax machines, dongles, biometric readers, microphones, touchscreens, touchpads, trackballs, styluses, scanners, storage devices, transceivers, video devices / sources, etc. Output devices (711) can be printers, fax machines, video displays (e.g., cathode ray tube (CRT), liquid crystal displays (LCD), light-emitting diodes (LEDs), plasma displays, plasma display panels (PDP), organic light-emitting diode displays (OLEDs), etc.), audio speakers, etc.

[0103] In some embodiments, the computer system (700) is connected to a service provider via a communication network (709). The processor (702) may be configured to communicate with the communication network (709) via a network interface (703). The network interface (703) may communicate with the communication network (709). The network interface (703) may employ connection protocols, including but not limited to direct connection, Ethernet (e.g., twisted pair 10 / 100 / 1000Base T), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 802.11a / b / g / n / x, etc. The communication network (709) may include, but is not limited to, direct interconnect, e-commerce networks, peer-to-peer (P2P) networks, local area networks (LANs), wide area networks (WANs), wireless networks (e.g., using Wireless Application Protocol), the Internet, Wi-Fi, etc. Using the network interface (703) and the communication network (709), the computer system (700) may communicate with one or more service providers.

[0104] In some embodiments, the processor (702) may be configured to connect to the memory (705) via a storage interface (704) (e.g., Figure 7(RAM, ROM, etc., not shown) communicate. The storage interface (704) can be connected to the memory (705), including but not limited to memory drives, removable disk drives, etc., using 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. The storage drive may also include magnetic drums, disk drives, magneto-optical drives, optical drives, redundant arrays of independent disks (RAID), solid-state storage devices, solid-state drives, etc.

[0105] The memory (705) may store a collection of program or database components, including but not limited to a user interface (706), an operating system (707), a network server (708), etc. In some embodiments, the computer system (700) may store user / application data (706), such as data, variables, records, etc., as described in this disclosure. Such a database may be implemented as a fault-tolerant, relational, scalable, and secure database, such as Oracle or Sybase.

[0106] An operating system (707) facilitates resource management and operation of a 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 Suite (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.

[0107] In some embodiments, the computer system (700) may implement program components stored in a web browser (708). The web browser (708) may be an hypertext viewing application, such as Microsoft Internet Explorer, Google Chrome, Mozilla Firefox, Apple Safari, etc. Secure web browsing may be provided using protocols such as Secure Hypertext Transfer Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), etc. The web browser (708) may utilize facilities such as AJAX, DHTML, Adobe Flash, JavaScript, Java, Application Programming Interface (API), etc. In some embodiments, the computer system (700) may implement program components stored in a mail server. The mail server may be an Internet mail server such as Microsoft Exchange. The mail server may utilize facilities such as ASP, ActiveX, ANSI C++ / C#, Microsoft .NET, CGI scripts, Java, JavaScript, PERL, PHP, Python, WebObjects, etc. The mail server may utilize communication protocols 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) may implement a program component stored in the mail client. The mail client may be a mail viewing application, such as Apple Mail, Microsoft Entourage, Microsoft Outlook, Mozilla Thunderbird, etc.

[0108] In an embodiment, the imaging unit (712) can be configured to capture first and second images (I a and I b And the first and second images (I) are transmitted via the communication network (709). a and I b The data is provided to the computer system (700) for normalizing the actual pixel intensity values. In an embodiment, the display unit (713) can display the first and second images (I... a and I b ).

[0109] Unless otherwise expressly stated, the terms “an embodiment,” “an embodiment,” “each embodiment,” “the embodiment,” “the respective embodiments,” “one or more embodiments,” “some embodiments,” and “an embodiment” refer to “one or more (but not all) embodiments of the invention.”

[0110] Unless otherwise expressly stated, the terms “including,” “comprise,” “have,” and variations thereof mean “including but not limited to.”

[0111] Unless otherwise expressly stated, the list of items does not imply that any or all items are mutually exclusive. Unless otherwise expressly stated, the terms “a,” “an,” and “the” mean “one or more.”

[0112] The description of an embodiment having several components that communicate with each other does not imply that all of these components are necessary. Rather, a variety of optional components are described to illustrate a variety of possible embodiments of the invention.

[0113] When this document describes a single device or article, it will be readily apparent that more than one device / article may be used instead of a single device / article (whether or not they cooperate). Similarly, when this document describes more than one device or article (whether or not they cooperate), it will be readily apparent that a single device / article may be used instead of more than one device or article, or a different number of devices / articles may be used instead of the number of devices or programs shown. The functionality and / or features of a device may alternatively be embodied by one or more other devices not explicitly described as having such functionality / features. Therefore, other embodiments of the invention do not necessarily need to include the device itself.

[0114] Figure 3 , Figure 4 and Figure 7 The illustrated operations demonstrate specific events occurring in a particular order. In alternative embodiments, some operations may be performed, modified, or deleted in a different order. Furthermore, steps can be added to the logic described above while still conforming to the described embodiments. Additionally, the operations described herein may occur sequentially, or some operations may be processed in parallel. Furthermore, operations may be performed by a single processing unit or by distributed processing units.

[0115] Finally, the language used in this specification has been chosen primarily for readability and guidance purposes, and may not have been chosen for the purpose of describing or limiting the subject matter of the invention. Therefore, the scope of the invention is intended not to be limited by this detailed description, but rather by any claims published on the application based herein. Thus, the disclosure of embodiments of the invention is intended to illustrate, and not limit, the scope of the invention as set forth in the appended claims.

[0116] While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for illustrative purposes and are not intended to be limiting; the true scope is indicated by the appended claims.

Claims

1. A method for normalizing pixel intensity of an image, comprising: The first image (I) is received by the image processing device. a ) and the second image (I b One or more contrast parameters, one or more illumination parameters, and the actual pixel intensity value (X) generated by the image processing device. a X b ); The image processing device is based on the first image (I) a ) and the second image (I b The one or more contrast ratios and the one or more illumination parameters are used to determine one or more normalization parameters; The image processing device determines the second image (I) based on the one or more normalization parameters. b Normalized pixel intensity value (X) b ');and The image processing device uses the normalized pixel intensity value (X) b ') relative to the first image (I a ) for the second image (I b Transformation is performed to generate a normalized image (I) b '), Although different pixel intensities represent the same areas in the first image and the second image, the first image and the second image are presented as visually similar on the display unit (104).

2. The method according to claim 1, wherein, The first image (I) a ) and the second image (I b The display pixel intensity value (Y) a Y b With the corresponding actual pixel intensity value (X) a X b The display pixel intensity value varies, wherein the display pixel intensity value includes the pixel intensity value displayed on the display unit.

3. The method according to claim 1, wherein, The one or more contrast ratios and the one or more lighting parameters include hue, saturation, contrast ratio, brightness, gamma, or combinations thereof.

4. The method according to claim 1, comprising: Receive the first image (I) a ) and the second image (I b The actual pixel intensity value (X) a X b ), highest display pixel intensity value (G), window horizontal value (L) a L b ) and window width value (W a W b ), wherein the first image (I) a ) and the second image (I b The display pixel intensity value (Y) a Y b With the corresponding actual pixel intensity value (X) a X b It changes linearly; Based on the first image (I) a ) and the second image (I b The window width value (W) a W b To determine the normalized slope value (M) f ); Based on the first image (I) a The window level value (L) a ), the second image (I) b The window level value (L) b ), the first image (I) a The window width value (W) a ), the second image (I) b The window width value (W) b The normalized intercept value (C) is determined using the highest displayed pixel intensity value (G) and the highest displayed pixel intensity value (G). f ); Based on the normalized slope value (M) f ) and the normalized intercept value (C f ) to determine the second image (I b The normalized pixel intensity value (X) b ');and By using the second image (I) b The normalized pixel intensity value (X) b ') will the second image (I b ) relative to the first image (I a The normalized image (I) is generated by performing a transformation. b ').

5. The method according to claim 4, wherein, The first image (I) a ) and the second image (I b ( ) are images of the same object, which appear visually identical despite having different actual pixel intensities.

6. The method according to claim 4, wherein, Determine the normalized slope value (M) f This includes determining the window width value (W) of the first image. a ) and the window width value (W) of the second image b The ratio of ).

7. The method according to claim 4, wherein, Determine the normalized intercept value (C) f )include: Determine the first image (I) a The window level value (L) a ) and the window width value (W) a The first ratio; Determine the second image (I) b The window level value (L) b ) and the window width value (W) b The second ratio; Determine the difference between the first ratio and the second ratio; and The normalized intercept value (C) is determined by multiplying the difference by the highest displayed pixel intensity value (G). f ).

8. The method according to claim 4, wherein, Determine the normalized pixel intensity value (X) b ')include: Determine the normalized slope value (M) f ) and the second image (I b The actual pixel intensity value (X) b The product of ) and Determine the determined product and normalized intercept value (C). f ) and .

9. The method according to claim 8, wherein, Using the normalized pixel intensity value (X) b ') will the second image (I b Transformed into the normalized image (I) b '), where, for the first image (I) a ) and the normalized image (I b One or more regions in the normalized image (I) b ') and the first image (I a They have the same actual pixel intensity value.

10. The method according to claim 4, wherein, The window width value (W) a W b ) respectively indicate the first image (I a ) and the second image (I b The contrast of the window and the window level value (L) a L b ) respectively indicate the first image (I a ) and the second image (I b (brightness).

11. The method according to claim 4, wherein, The normalized image (I) b ') and the first image (I a The comparison is performed on at least one of the following: image labeling, image classification, image segmentation, and multi-label classification.

12. An image processing apparatus for normalizing pixel intensity of an image, comprising: processor; as well as A memory, communicatively coupled to the processor, stores processor-executable instructions that, when executed, cause the processor to: Receive the first image (I a ) and the second image (I b One or more contrast parameters, one or more illumination parameters, and the actual pixel intensity value (X) generated by the image processing device. a X b ); Based on the first image (I) a ) and the second image (I b The one or more contrast ratios and the one or more illumination parameters are used to determine one or more normalization parameters; The second image (I) is determined based on the one or more normalized parameters. b Normalized pixel intensity value (X) b ');and By using the normalized pixel intensity value (X) b ') relative to the first image (I a ) for the second image (I b Transformation is performed to generate a normalized image (I) b '), Although different pixel intensities represent the same areas in the first image and the second image, the first image and the second image are visually similar on the display unit.

13. The image processing apparatus according to claim 12, wherein, The processor is configured to: Receive the first image (I) a ) and the second image (I b The actual pixel intensity value (X) a X b ), highest display pixel intensity value (G), window horizontal value (L) a L b ) and window width value (W a W b ), wherein the first image (I) a ) and the second image (I b The display pixel intensity value (Y) a Y b With the corresponding actual pixel intensity value (X) a X b It changes linearly; Based on the first image (I) a ) and the second image (I b The window width value (W) a W b To determine the normalized slope value (M) f ); Based on the first image (I) a The window level value (L) a ), the second image (I) b The window level value (L) b ), the first image (I) a The window width value (W) a ), the second image (I) b The window width value (W) b The normalized intercept value (C) is determined using the highest displayed pixel intensity value (G) and the highest displayed pixel intensity value (G). f ); Based on the normalized slope value (M) f ) and the normalized intercept value (C f ) to determine the second image (I b The normalized pixel intensity value (X) b ');and By using the second image (I) b The normalized pixel intensity value (X) b ') relative to the first image (I a ) for the second image (I b The normalized image (I) is generated by performing a transformation. b ').

14. The image processing apparatus according to claim 13, wherein, The processor receives a first image (I) of the same object. a ) and the second image (I b The first image and the second image appear to be visually identical despite having different actual pixel intensities.

15. The image processing apparatus according to claim 13, wherein, The processor determines the window width value (W) of the first image. a ) and the window width value (W) of the second image b The normalized slope value (M) is determined by the ratio of ) to ). f ).

16. The image processing apparatus according to claim 13, wherein, The processor determines the normalized intercept value (C). f The processor is configured to: Determine the first image (I) a The window level value (L) a ) and the window width value (W) a The first ratio; Determine the second image (I) b The window level value (L) b ) and the window width value (W) b The second ratio; Determine the difference between the first ratio and the second ratio; and The normalized intercept value (C) is determined by multiplying the difference by the highest displayed pixel intensity value (G). f ).

17. The image processing apparatus according to claim 13, wherein, The processor determines the normalized pixel intensity value (X). b '), wherein the processor is configured as: Determine the product of the normalized slope value (Mf) and the actual pixel intensity value (Xb) of the second image (Ib); and Determine the determined product and normalized intercept value (C). f ) and .

18. The image processing apparatus according to claim 17, wherein, The processor uses the normalized pixel intensity value (X). b ') will the second image (I b Transformed into the normalized image (I) b '), where, for the first image (I) a ) and the normalized image (I b One or more regions in the normalized image (I) b ') and the first image (I a They have the same actual pixel intensity value.

19. The image processing apparatus according to claim 13, wherein, The processor is configured to process the normalized image (I) b ') and the first image (I a The comparison is performed on at least one of the following: image labeling, image classification, image segmentation, and multi-label classification.

20. A system comprising: Imaging equipment; Display unit; as well as The image processing apparatus according to claim 12; The imaging device is configured to capture a first image (I) of the object. a ) and the second image (I b ), where the first window horizontal value (L) a ) and the first window width value (W) a ) is applied to the first image (I) a ), and the second window level value (L b ) and the second window width value (W b ) is applied to the second image (I) b ), to display the first image (I) on the display unit. a ) and the second image (I b ); The image processing device is configured as follows: Based on the first image (I) a ) and the second image (I b The window width value (W) a W b To determine the normalized slope value (M) f ); Based on the first image (I) a The window level value (L) a ), the second image (I) b The window level value (L) b ), the first image (I) a The window width value (W) a ), the second image (I) b The window width value (W) b The normalized intercept value (C) is determined by the highest displayed pixel intensity value (G) and the highest displayed pixel intensity value (G). f ); Based on the normalized slope value (M) f ) and the normalized intercept value (C f ) to determine the second image (I b Normalized pixel intensity value (X) b ');and By using the second image (I) b The normalized pixel intensity value (X) b ') relative to the first image (I a ) for the second image (I b The normalized image (I) is generated by performing a transformation. b ').

Images