• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    Device for determining a skin inflammation value (Z), comprising an opto-electronic measuring device (1), preferably a 3D scanner, for taking a three-dimensional image (B) of an inflammatory region (E) on human or animal skin (H), wherein the opto-electronic measuring device (1) area-related (A), spatial (V) and color (F) values of the three-dimensional image (B) are detectable, a calculation unit (2) for calculating the skin inflammation value (Z) from the detected by the measuring device (1) area-related (A), spatial (V) and color (F) values and a display unit (3) for displaying the calculated skin inflammation value (Z).
    公开号:AT511265A1
    申请号:T420/2011
    申请日:2011-03-24
    公开日:2012-10-15
    发明作者:
    申请人:Strohal Robert Dr；Soldatitsch Markus Mag；
    IPC主号:
    专利说明:

    1 68930 22 / hn
    The invention relates to a device and a method for determining a skin inflammation value.
    In the medical field, there are already a variety of facilities for diagnostic support for a doctor. For example, X-ray machines, computer tomographs, various 3D scanners and much more have been used for a long time.
    However, the first steps are being taken in the field of diagnostic support for skin surface inflammation. This goes, for example, from the article "Beyond flat weals. vatidation of a three-dimensional imaging technology that wants to improve skin allergy research "from the journal" Clinical and Experimental Dermatology, 33, pages 772-775 ", a description of a method how to use a 3D scanner, the topography of the skin surface can measure in the area of inflammation or skin calluses. The resulting, high-resolution three-dimensional topographical image of the callus gives the diagnosing physician additional important clues. A disadvantage of this system or in this method, however, is that only the height information and volume information can be included in the diagnosis. In the case of the skin examination carried out in accordance with this article in the form of a so-called prick test, this value usually suffices as a diagnostic aid.
    However, if other types of skin examinations are performed (e.g., a so-called epicutaneous test), the sole height or volume value will not be sufficient to provide sufficient diagnostic support to a diagnosing physician.
    The object of the invention is therefore to provide a comparison with the prior art improved diagnostic support for inflammation of the skin. In particular, in addition to the spatial values, other meaningful further expressions are also to be added. * * * * * · • · · • • • • • •,,,,,,,,, 4 4. ..........
    Values above the measured range of inflammation are included in the diagnostic support.
    For a device for determining a skin inflammation value, this is achieved by an opto-electronic measuring device, preferably a 3D scanner, for taking a three-dimensional image of an inflammatory region on human or animal skin, the surface-related, spatial and color values of the area being determined by the opto-electronic measuring device Three-dimensional image can be detected, a computing unit for calculating the skin inflammation value from the area-related, spatial and color values detected by the meter and a display unit for displaying the calculated skin inflammation value. As a result, not only are the spatial values incorporated into the skin inflammation value to be determined, but also the area-related and color values of the scanned inflammation area are taken into account. In other words, the present invention can determine a much more meaningful value that is closer to the actual severity of the inflammation. Thus, the diagnosis is substantially supported and improved and the physician no longer has to make a diagnosis solely on the basis of his subjective assessment of the roughness, the size and the redness, but can - based on stored empirical values from previous measurements and now actually measured and with values comparable to empirical values - make a more objective diagnosis.
    According to a preferred embodiment of the invention, it can be provided that the recorded three-dimensional image of the zone of ignition consists of a multiplicity of pixels arranged in grid form in a three-dimensional coordinate system, each area-related value corresponding to a single pixel unambiguous in the coordinate system. The resulting pixels in the coordinate system thus provide a virtual image of the real surface of the skin. It can preferably be provided that each spatial value corresponds to a height value of the respective pixel in the three-dimensional coordinate system.
    In order to obtain as meaningful a result as possible, it is preferably provided that each surface-related value of a three-dimensional image recorded by the optoelectronic measuring device can be assigned both a preferably single color value and a preferably single spatial value. A single pixel or a pixel may preferably have the size between 1 pm and 10 pm. Most preferably, the pixel size is exactly 3.05597 pm.
    Furthermore, it can preferably be provided that each color value corresponds to a magenta value in the CMYK color model, a gray value or a saturation value in the HSV color space. The CMYK color model is a so-called subtractive color model, where CMYK stands for Cyan, Magenta, Yellow and Key. The HSV color space is the color space of some color models, using the hue, the color saturation and the light value or the dark level.
    The present invention is primarily used for diagnostic support in dermatitis, so an inflammatory reaction of the skin, especially the dermis (dermis). The term eczema can also be used as a synonym for dermatitis. The skin inflammations to be examined may be both naturally occurring inflammations and intentionally caused by an allergy test inflammation (for example Epicutantest or prick test). However, moles or wounds can also be assessed, although the classification method must be adapted accordingly.
    Basically, it is possible to view the entire scanned area as a uniformly rated area of inflammation. Preferably, however, it is provided that by the arithmetic unit, preferably by delimiting the color values of the individual pixels or by delimiting the spatial values of the individual pixels, the area-related values of the recorded three-dimensional image in a field of inflammation and an adjacent to the hearth and this surrounding hearth ambient are distinguishable. For the demarcation between the inflammatory focus and
    Of course, a range of color values, spatial values, and / or area-related values can also be used for the focal area of the herd.
    In order to obtain meaningful detail values for the demarcated areas, which apply over the entire demarcated area, it can preferably be provided that a relative total color value of the entire inflammatory focus can be determined by comparison of the averaged color values in the focus of inflammation and the averaged color values in the focal area , Further possibilities consist of the fact that from the spatial values in the inflammation hearth an absolute total volume value of the entire inflammatory hearth can be determined and in that a relative total volume value of the inflammatory herd can be determined by comparison of averaged spatial values in the inflammation hearth to averaged spatial values in the hearth environment.
    Especially for the latter relative total volume value, it may be preferable for the relative total volume value to be a comparison value of the surface roughness in the hearth to the surface roughness in the hearth environment. The calculation method of the surface roughness can be based on the calculation of the line roughness according to the German industrial standard EN ISO 4288.
    Additional or alternative detail values that may be used to calculate the total skin inflammatory value are given below. For example, it may be provided that a surface-related value corresponds to a circumference value corresponding to the circumference of the inflammation focus and / or a surface-related value corresponds to an area value representing the surface of the inflammation focus. Furthermore, it can be provided that a surface-related value is formed as a function of the area value and the circumferential value and corresponds to the compactness value representing the ratio of the peripheral value to the area value or that a total volume value corresponds to the average height value and / or the average height of all elevations in the ignition cooker the area of the highest elevations representing the maximum height area value corresponds, with the highest elevations are those surveys whose amount is at least 70%, preferably at least 85%, the height of the highest elevation.
    Furthermore, protection is desired for a method for determining a skin inflammation value, in particular feasible with a device according to one of claims 1 to 13, with an optoelectronic measuring device, preferably a 3D scanner, a computing unit and a display unit, characterized by the steps: picking up a three-dimensional image of an area of inflammation on human or animal skin with the opto-electronic measuring device, determining area-related, color and spatial values of the three-dimensional image, calculating the skin inflammation value from the calculated area, color and spatial values and displaying the calculated skin inflammation value on the display unit. Thus, this method is not to be regarded as a diagnostic method, but rather as a method for data acquisition (color, space and area related values) or processing that can be used in a medical diagnostic procedure.
    Further preferred method steps are also mentioned in claim 15. It should be noted that the features of claim 15 further describe or define the steps of determining the three-dimensional image and calculating the skin inflammation value.
    Further details and advantages of the present invention will be explained in more detail below with reference to the description of the figures with reference to the exemplary embodiments illustrated in the drawings. Show:
    Fig. 1 is a schematic representation of a device for determining a
    Dermatitis value,
    Figures 2 to 5 are images of dermal inflammatory regions with the four different classes of dermal inflammatory values;
    6 to 8 Fig. 9 and 10 Fig. 11 Fig. 12 Fig. 13 Fig. 14 Fig. 15 to 18 Fig. 19 to 22 Fig. 23 shows the flow of smoothing a height image, shown in the three-dimensional coordinate system, the representation of Heights in a gray value image, a binary image of the average heights, an image with a height limiting contour, a picture with checking the center of gravity of the height limiting contour, a flow chart of a first method for determining a skin inflammation value, the performance of a contour calculation based on color and area-related values,
    Steps for calculating the value in a second method for determining a skin inflammation value and a flow chart of the most important steps of the second exemplary method for determining a skin inflammation value.
    1 shows the essential components of a device for determining a skin inflammation value Z. In this case, an optoelectronic measuring device 1 (3D scanner - for example the PRIMOS pico of GFM) is held over the skin H of a human or an animal or preferably directly onto the skin Skin H attached. Of course, the meter 1 should be used over a (suspected) area of ignition E. Through the individual scanning elements 5, the entire area of ignition E is recorded via two scanning areas St and S2, and a corresponding three-dimensional image B is transmitted to the arithmetic unit 2. This image B consists of a plurality of pixels P, each corresponding to a surface-related value A. Each individual surface-related value A is filled, as it were, with a color value F and a spatial value V. The entire image B is imaged in a three-dimensional coordinate system 4 (see also FIG. 6). The arithmetic unit 2 may be in the form of a computer which is connected to the measuring device 1. However, the arithmetic unit 2 can also be integrated directly into the measuring device 1.
    On the basis of the collected values A, V and F, the inflammatory region E is then subdivided into an inflammation focus C and a focal environment U in a first important calculation step. Absolute color values FW and / or absolute volume values VW and / or relative color values FW and / or relative color values VW over the entire ignition region E are subsequently determined for the source of ignition C. The relative color value FW can be calculated, for example, by subtracting or dividing the averaged magenta value of the hearth environmental range U by the average magenta value of the inflammation range C. The total volume value VW can, for example, represent the total volume of the total callous or inflammation as the absolute volume value FWV. The reference character FWR may stand for a total relative volume value in which the roughnesses of the inflammation focus C and the hearth surrounding area U are compared.
    Subsequently, each of these determined values FW, VWv and VWr can be classified into one of the inflammation classes K0, Κι, K2 or K3. The limits of these classification classes are predetermined and are based on empirical values stored in the arithmetic unit 2, collected and previously categorized. From the allocation to the individual classes K0, Ki, K2 and K3, an average, preferably rounded, skin inflammation value Z is then obtained, which is then output on the display unit 3 accordingly. Equivalent to the visual display can also be a pure acoustic output via a speaker. As a display unit 3 can also serve individual LEDs. For example, the skin inflammation value can be detected by the color of a diode. However, the number of light emitting diodes may also reflect the skin inflammatory value.
    In FIGS. 2 to 5, by way of example, images of different areas of ignition E are shown, wherein in each case a segmentation rectangle Q and a contour surrounding rectangle T are shown. The contour K forms the boundary between the inflammation focus C and the focal region U. In addition, the center Xq of the segmentation rectangle Q and the center of gravity X "of the contour K are shown on each of these FIGS. As a respective exact point, the crossing point of the letter X is to be considered. FIG. 5 shows an intense redness and swelling with large bubbles (inflammation class K3), in which the upper left X corresponds to the center of the segmentation rectangle Q and the right lower X corresponds to the center of gravity of the contour K.
    Two methods for determining a skin inflammation value are described in detail below, but it should not be ruled out that one or more calculation steps of the two methods are also carried out in a separate method with arbitrarily "mixed" calculation steps. Of course, partial process steps can be omitted in each individual process. It is essential that in each case area-related, spatial and color values A, V and F of the three-dimensional image B taken with the optoelectronic measuring device are taken into account for the calculation of the skin inflammatory value. Of course, it should not be ruled out that other unnamed alternative calculation variants can be used to determine a skin inflammation value Z.
    Accordingly, a first method with exemplary algorithms for an epicutaneous test will be described below. The analysis of the epicutaneous tests is divided into three steps: i) Detection of the wheal (callus) by means of a height segmentation method ii). Measurement of the wheal (height and color values) iii) Evaluation of the measurement results
    These three steps are described in the following text, wherein the problems of the solution used so far are presented and possibilities are shown how a suitable for the invention, new software solution can support the ordination even better and more efficiently.
    By re-implementing the software solution existing problems can already be prevented in advance and the structure of the application can be optimally adapted to the current requirements. You can also * * * * * «··· • • ♦ * * *» «fr» «« • • · · «« «* · * · * ····· 1 ψ " 9 ............
    Performing optimizations in the individual areas and thereby making the entire support process more efficient and reducing the time required for the users of the system. i) height segmentation:
    The segmentation is roughly divided into 7 steps 1. Smoothing the height image 2. Filtering the height image 3. Displaying the heights in a gray-scale image (maximum height is white, minimum height is black) 4. Determining the above-average magenta values in the CMYK image and Increase the values in the height gray value image at those points which have an above-average magenta value. 5. Calculation of the average height and creation of a binary image, 6. Find the boundary contour of the largest coherent survey. 7. Check whether the center of gravity of the height gray scale image lies within the rectangle enclosing the found boundary contour of the largest coherent elevation. 1. Smooth the height image:
    Since that area of the skin that was detected (see original height image according to FIG. 6) has a curvature in most cases, the height image is largely straightened, so that an idealized flat skin can continue to be used.
    For this purpose, the 25 extreme height values are used in each case at the edges and with their help a curved plane is calculated which corresponds to the skin curvature HK (see FIG. 7).
    The new height image is now formed as follows: those values that are smaller in the original height image than the corresponding value of the calculated plane are set to the value of the calculated plane. All other values maintain the original values. Following this, the corresponding value of the calculated plane is subtracted from each height value. In this way, the curvature of the skin, as well as any pores of the skin that create deeper valleys in the height image, are eliminated. The height 0 can now be considered as the base height of the skin. Such a smoothed height image (original height image minus the calculated skin curvature) is shown in FIG. 2. Filtering the height image:
    To eliminate minor outliers in the elevation image, this is smoothed with a median filter (currently working with the neighborhood size 3). 3. Representation of the heights in a gray value image (FIG. 9): For the further processing of the height image with the aid of image processing algorithms, a grayscale image with 256 gray levels is calculated from the height image. The highest altitude is used for the value 255 (white), the lowest altitude is used for the value 0 (black). The height values in between are converted proportionally into different gray levels. 4. Increase the values in the height gray value image at those locations which have an above-average magenta value (FIG. 10):
    In order to be able to better restrict the site which depicts an inflammation, these are increased in the height image by the degree of above-average redness. For this, the original image is converted into a CMYK image and the magenta channel is considered. A greyscale image corresponding to the magenta channel is created, but any magenta values that do not reach a certain percentage (for example, 120%) of the average magenta value are set to 0.
    Thereafter, the individual points of the elevation image are considered and compared with the corresponding pixel in the magenta image. If the value in the magenta image is higher than that in the grayscale bitd of the height image, the pixel in the grayscale image of the height image is recalculated from a fraction of the current value and a fraction of the value of the magenta image (for example, the value of the Magenta-picture 60% and the value of the height-gray-scale picture 40% to the new value). 5. Calculation of average height and creation of a binary image (Figure 11):
    From the gray value image of the height image, which has been intensified with the aid of the magenta channel of the CMYK image, a binary image is now calculated, which is needed to search out contours. Threshold is the average gray value (times a coefficient, currently 2.0).
    Before the binary image is created, the grayscale image is smoothed with a median filter (the current neighborhood size is 9). The binary image is still being eroded and widened (currently there are three iterations of eroding and one of widening). 6. Find the boundary contour of the largest contiguous elevation (Figure 12):
    Those parts of the elevation image above the average height (times a coefficient) are shown in this binary image as white spots. The algorithm now searches for the white spot in the binary image that has the largest area and provides the bounding contour K of the area, as well as a bounding rectangle T enclosing the contour K. The area enclosed by the contour K (focal point C) captures that part of the height image which represents the highest closed, inflated elevation and thus the desired skin swelling and is surrounded by the focal area U. 7 Calculation and testing of the center of gravity of the altitude gray scale image (FIG. 13): 12.
    As a control measure, the "center of gravity" of the height gray scale image is calculated (point Xq). If the "center of gravity" lies within the region of the found boundary contour K or the rectangle T enclosing this contour K, this confirms the found contour K and thus the localization of the supposed measurement surface.
    Is the center of gravity not within the rectangle T as in Fig. 13, it can be assumed that the survey found is not outstanding compared to other surveys. As a rule, these are those tests which show no or less pronounced swelling.
    In this case, not the region which encloses the contour K but the region which represents the supposed measuring surface or the square Q enclosing this region is used for the further measurement. The center Xq of the square Q represents the "center of gravity" of the height gray value image (the size of the square corresponds in each case to the real measurement surface). ii) Surveying:
    After the detection of skin swelling has been completed, it is measured. There are three parameters that are used for the evaluation: 1. The volume of swelling compared to the area of the swelling 2. The roughness of the swelling compared to the roughness of the remaining area of the skin 3. The redness of the swelling compared to the remaining skin color 1. The volume of swelling compared to the area of swelling:
    The base of the swelling is the area that is enclosed by the contour K. Now, the total volume of the swelling that is within the contour K is calculated. Here, only that part of the height which is above the average height of the skin is counted.
    This calculated total volume of swelling is divided by the area. The result is the average amount of swelling. This is used for the evaluation. 2. The roughness of the swelling compared to the roughness of the remaining skin area:
    Another significant characteristic of the swelling is the roughness. So that a possible rough normal skin does not affect the measurement results too much, the roughness inside and outside the rectangle, which encloses the boundary contour, is calculated. The roughness of the swelling (within the rectangle) minus the roughness of the remaining skin (outside the rectangle) is now used for the evaluation.
    The method implemented for calculating the surface roughness is based on the method for calculating the line roughness (DIN EN ISO 4288).
    The limiting parameters are 10% and 90%, respectively. This means that it is not the difference between the highest point (0% areal proportion) and the lowest point (100% areal proportion) that is used as the roughness value, but the difference between those cutting heights that result in an areal proportion of 10% and 90%, respectively. 3. The redness of the swelling compared to the remaining skin color:
    In addition to the two measured values, which are calculated from the height image, the degree of reddening of the measuring surface is determined from the color image. For this purpose, the magenta channel of the CMYK representation of the original color image of the measuring point is used. Similar to the calculation of the roughness and the average volume, a value within and a value outside of the range bounded by the contour is also determined here. For further evaluation, the average value within the contour minus the average value outside the contour is used. iii) Evaluation:
    The wheal, after it has been measured, is evaluated and divided into four common classes in practice. The following table gives an approximate, subjective description of the classes.
    Class Example Description 0 (Ko) Fig. 2 Doubtful reaction: Possible slight redness 1 (Ki) Fig. 3 Slight positive reaction: Red and slightly swollen skin 2 (Ka) Fig. 4 Strong positive reaction: Red and swollen skin with individual Blisters 3 (Ka) Fig. 5 Extremely positive reaction: Intense redness and swelling with large blisters
    The overall rating of the wheal consists of the individual partial scores of the characteristic values from the survey. In the current case, three partial ratings are created in four classes whose rounded average results in the class of the overall score. Since the value of redness for strongly reddened normal skin decreases from a defined limit on validity, in the course of the evaluation explicitly addresses this fact.
    If redness of the normal skin above the threshold value is detected, the erythema of the swelling is not used for evaluation.
    For a better understanding, the following exemplary calculation example is used: 15 ♦ «« «
    Example Class Limits Sample Measurements Classes of Partial Values Volume 0-5.5-11.11-16, 16-infinity 6 Ϊ Roughness 0-3.3-13.13-17.17- infinite 14 2 Erythrocyte between 0 and 1 0-4, 4-9.9-11.11 infinite 12 3
    This gives the overall rating 2 (mean of 1 + 2 + 3 is 2).
    Calculation example with severe skin reddening:
    Example Class Limits Sample Measurements Classes of Partial Values Volume 0-5.5-11.11-16. 16 infinity 19 3 roughness 0-3,3-13,13-17,17- infinity 18 3 redness between 0 and 1 0-4,4-9,9-11,11- infinity 2 1
    The classification of redness would lower the overall score to 2 (rounded average of 3 + 3 + 1 is 2). Considering skin redness above the threshold results in a classification of 3 (mean of 3 + 3 is 3).
    FIG. 14 shows a flow chart of the first method and again represents the method steps just mentioned in a logical context.
    In order to give not only general ranges for the inflammation classes K0 to K3, in the following four, different classes belonging, concrete examples of measured values including evaluation are given. These relate concretely to the different degrees or classes of inflammations shown in FIGS. 2 to 5. 16
    ♦ * · · * · ♦ * «· · φ · i) Surveying
    The following parameters were determined for these images: 1. Average height (average volume) of the inflammation 2. Roughness value minus the basic roughness (relative roughness) 3. Redness in comparison to the color of the remaining skin (relative redness)
    If the center of gravity Xq of the segmentation image does not lie in the rectangle T which encloses the contour K, then instead of the regions inside or outside the contour K and inside or outside the rectangle T enclosing the contour K, the area used, which is inside or outside the square Q, which is formed with the center of gravity Xq of the segmentation image as the center. 1. Average height (average volume) of inflammation:
    The heights of all measuring points which are located within the recognized wheal bordered by the contour K are summed up. Only that part of the height above the average height of the skin is counted. This volume is divided by the number of measurement points. The calculated average volume is used for the evaluation.
    Sample image values (The footprint of a pixel is 0.00305597 mm2):
    Total volume of wheals Total area of wheal Average volume per pixel Fig. 2 - Ko 1.6913977 mm * 190 9985264 mm2 0.0000271 mm " Fig. 3 - K-i 7,3151578 mm3 61.7780914 mm2 0.0003619 mm " Fig. 4 - K2 16.76766525 mm3 62.867547 mm1 0.0008106 mm " Fig. 5 - K3 40.2830175 mm3 93.6228937 mm2 0.0013149 mm " 2. Roughness value minus the basic roughness (relative roughness): 17 * «* 17 *« * »« • *
    The roughness of the surface is calculated for the area within the contour K and for the area between the contour K and the rectangle T. The difference between the two roughness values forms an evaluation basis.
    Values of the sample images:
    Roughness within the bounding rectangle Roughness outside the bounding rectangle Difference Fig. 2 - Ko 0,0732433 mm 0,0550084 mm 0,0182349 mm Flg. 3 - Ki 0,1658371 mm 0,0924609 mm 0,0733762 mm Fig. 4 - K2 0,3263570 mm 0,1401592 mm 0,1861978 mm Fig. 5 - K3 0,4609349 mm 0,1506546 mm 0,3102803 mm 3 , Redness compared to the color of the remaining skin (relative redness):
    From the magenta channel of the color image, the average redness of the areas inside and outside the detected wheal (contour K) is determined. The difference between the two average values is included in the valuation.
    Values of the example images: I Redness of the wheal Reddening of the environment Difference Fig. 2-Ko 65.104.384 66.6805231 -1.5761391 Fig. 3 - Ki 75.2352490 67.1557576 8.0794914 Fig. 4-K2 137.7521633 107 , 7737394 29.9784239 Fig. 5-K3 104.6286619 67.2027139 37.425948 3a. Redness of the surrounding skin is the average redness of the skin outside the wheal above a threshold, so the relative redness is not used for evaluation. * 4 »· 18
    Values of the sample images:
    Class 0: 66.6805231 Class 1: 67.1557576 Class 2: 107.7737394 Class 3: 67.2027139 ii) Evaluation:
    The evaluation is done separately for each value separately. For this purpose limits are set for each measured value. The currently used limit values for the individual measured values (but can be determined and changed individually in consultation with doctors) are as follows:
    Class 0 Class 1 Class 2 Class 3 Average volume of ignition <0.000225492 <0.000646506 <0.001029246> = 0.001029246 Roughness value less the basic roughness <0.02655275 <0.1102376 <0, 21623841> = 0.21623841 redness compared to the rest of the skin <4.68131157 <12.488887981 <32.98374644> = 32.98374644
    In addition, there is a threshold value, which determines from which redness the surrounding skin is considered to be too reddish, and determines whether the redness is used for the evaluation in comparison to the color of the remaining skin. This threshold is currently set at 109.98770675.
    The overall classification results from the (rounded) average classification of the partial assessments.
    A second variant for determining a skin inflammation value Z, which can be carried out with the device according to the invention, is provided below. • * * * * * # * * * * * * * * * * * * * * * * ♦ · ♦ ·· »· + * · ♦ ···« · «19 ......... .....
    By analyzing different color spaces and representations, it has been found that the magenta color space in the CMYK false color representation and the saturation value in the HSV color space are best suited for filtering and determining sites of inflammation on the human skin. At the beginning of the image processing, two images are generated from the original image (FIG. 15) and a conversion to a CMYK and an HSV image takes place.
    As a next step, optional pre-filtering of the image in which patches are filtered out can be carried out. For this purpose, a distinction is made for each pixel based on a fixed limit value in the magenta plane of the CMYK image as to whether the pixel corresponds to a plaster or the skin (= so-called threshold function). The starting value is assumed to be 100 for the limit value, ie, when passing through each pixel of the image, it is checked whether the magenta value is higher than 100 or not. If this is the case, the pixel value is taken from the original image; if not, the color value is set to 0 (= black). Thereafter, it is checked by means of an evaluation function whether sufficient pixels have been preserved for further processing, or whether the threshold has been set too high. In this case, the fixed limit is graded and the filtering and control is performed again. This process is repeated up to four times to ensure that there is optimal filtering of patch segments in the image without losing too much of the actual information.
    Now the image is filtered in the magenta color space. There are two variants that are used depending on the camera used. The first one calculates the magenta mean of all pixels obtained. Thereafter, it is again filtered in a loop by means of a threshold function (mulfaktor), whether a pixel of inflammation or neutral skin can be assigned. The threshold value is iteratively reduced, i. So in the first step, all pixels that are above a certain percentage of the average magenta value are taken over. In the second variant, the actual pixel value is not compared with the average magenta value * mulfactor, but an average value from the 5x5 pixel neighborhood of the pixel is compared with the threshold value. The result image in both cases is a gray value image with the filtered magenta pixin. This is followed by some image processing steps to optimize the filtering result. This includes a mean value filter (to eliminate pixel noise, ie small pixel groups are filtered out). Erode and Dilate functions are then used to close any gaps. This is followed by a conversion into a binary image (= black and white image) in which a contour finding algorithm is now performed. The found contours are then examined step by step to be able to identify a so-called region of interest ROI, as a potential segmentation area (see FIG. 16). For this purpose, if the contour corresponds to a minimum size and a defined position in the image, first the compactness of the contour (= area of the contour / circumference of the contour) is calculated. The more regular the compactness, the sooner inflammation can be assumed. If this is greater than the compactness of a preceding contour, the average radius R (resulting from the distance of each pixel of the contour to the center of gravity Xk of the contour averaged over the circumference of the contour is determined for the current contour). This results in a circle with center in the center of gravity and a radius = average radius (see FIG. 17), the surrounding square is defined as a region of interest ROI (see FIG. 18).
    In this area, the evaluation of the segmentation is now based on a determination of the average magenta value and the average saturation value. As another evaluation coefficient, the compactness value is divided by the mean radius (since the average size of the filtered region plays a significant role in the classification).
    Thus, at the end of the calculation, three classification values are created for a certain threshold. Then the threshold (mulfaktor) is reduced by 1% and the calculation is carried out again. This happens ten times in the first step. In the obtained values, the optimal region for further processing is then considered on the basis of the maximum value of these calculations. If no suitable result is obtained in the first step, a further reduction is made in 10 steps of the threshold value. The result of the first steps (prefiltering,
    Fig. 18) is a square with a defined starting point and a defined page length in pixels, and the classification values average magenta value (1st classification value from segmentation), average saturation value (2nd classification value) and compactness on radius {compact radius, 3rd classification value).
    The segmented square is then passed to the altitude processing algorithms for further processing and determination of the characteristics. The course of the height determination is shown in FIGS. 19 to 22.
    In this case, in the first step, the region of interest is created from the originai altitude map, which results from the image taken with the GFM camera (absolute image information exists for each pixel, see FIG. 19). This is done by means of a mean value filter, which is applied to the height map until a homogeneous surface results, which is a kind of center area for the entire image (see FIG. 20). With the aid of this central area, it is now possible to determine relative heights of the individual peaks in the height image. For this purpose, first a sub-rate height map is created by subtracting the central area from the original area (see FIG. 21). For all remaining pixels in the image, the relative height is now added, giving an average volume (= first height classification value. AvgVolume).
    In the next step, all peaks (starting with the highest altitude value GH) are searched for and recorded in a list. If a new peak is found as the maximum value in the remaining height map, it will search in both the positive and negative x and y directions until the pixel values rise again for the first time. So it is a kind of summit surface of the summit top G determined. The resulting surface is deleted from the map to allow the search for the next higher peak. This process is repeated until no more peaks are found, the heights are stored for all peaks found, at the end of this process the total height is then divided by the number of peaks found by a 22 ......... ..... • * • «average relative height of all peaks in the subtraction height map (= 2nd classification value, AvgHeigthl).
    To speed up further processing, all peaks whose relative height is below a defined limit (AvgHeightl 1EZThresh) are now filtered out. Then calculate the third and fourth values, the AvgArea2 (average area of the remaining peaks) and SumAreal (base area of the remaining peaks). In the last step, the maximum height value (ie the highest peak in the segmented area) is used to determine the third classification value. All remaining peaks whose relative height is lower by a certain percentage than the maximum height are also filtered out. The remaining highest peaks are then added up including their area. This results in further classification values, such as the PixelAboveThreshold (base area of the now remaining peaks), AvgHeight3 (average height of the pixels now remaining), (see FIG. 22).
    For clarity, the executed algorithms are still shown in the flowchart of FIG. 23.
    For this purpose, reference is made to the following definitions of the result or parameter or values: 1
    AvgMagenta = Average magenta value of the pixels within the contour or rectangle that encloses the contour. AvgSaturation = Average saturation value of the pixels within the contour or rectangle that encloses the contour. • compactRadius = ratio of the quotient of area and circumference Contour in relation to the average radius of the contour «AvgVolume = Average height of all points larger than the mean surface (= volume of the addition map) • AvgHeightl = Average height of the peaks of all found peaks • AvgArea2 = Average area of the peaks whose peaks ( RelHeight) above AvgHeightl 1EZThresh • * # * «« «· • ··· · ·« «» · · * * • * * * * * * φ φ »* ·» * ·· »φ # 23". ........... • SumAreal = Area (PeakArea) of those peaks whose peaks (RelHeight) are above AvgHeight1 * EZThresh • AvgHeight3 = Average height d he pixel whose height value is greater than PixeAboveThreshThreshold * (height of the highest peak) • PixelAboveThresh = number of pixels above a certain threshold (depending on the highest height occurring in the segment)
    In the end, the determined values are combined for the overall determination or for the determination of comparable classifications depending on the used camera type. Various combinations and combinations are possible, eg the product of AvgMagenta, AvgSaturation, KompaktRadius, AvgVolume, AvgHeightl and PixelAboveThreshold or the product of AvgMagenta, AvgSaturation, AvgHeight3, AvgVolume, AvgArea2 and SumAreal. Other combinations are conceivable. Instead of a multiplication, the values can also be added at least in part.
    Innsbruck, March 23, 2011
    权利要求:
    Claims (15)
    [1]
    1 B8930 22 / eh Claims --¾. 1. A device for determining a skin inflammation value (Z), comprising - an optoelectronic measuring device (1), preferably a 3D scanner, for taking a three-dimensional image (B) of an inflammatory region (E) on human or animal skin (H), wherein the optoelectronic measuring device (1) surface-related (A), spatial (V) and color (F) values (of the three-dimensional image (B) can be detected, - a computing unit (2) for calculating the skin inflammation value (Z) from the measuring device (1 ) recorded area-related (A), spatial (V) and color (F) values and - a display unit (3) for displaying the calculated skin inflammation value (Z).
    [2]
    2. Device according to claim 1, characterized in that the recorded three-dimensional image (B) of the ignition region (E) consists of a plurality of raster-shaped in a three-dimensional coordinate system (4) arranged pixels (P), wherein each surface-related value (A) a single, in the coordinate system (4) unique pixel (P) corresponds.
    [3]
    3. Device according to claim 1 or 2, characterized in that each area-related value (A) of a by the opto-electronic measuring device (1) recorded three-dimensional image (B) both one, preferably single, color value (F) and a, preferably single, spatial value (V) is assignable.
    [4]
    4. Device according to one of claims 1 to 3, characterized in that each color value (F) corresponds to a magenta value in the CMYK color model, a gray value or a saturation value in the HSV color space. • *. *. *. * * * * * * * * * * * * * * * * * * * * »» 2
    [5]
    5. Device according to claim 3 or 4, characterized in that each spatial value (V) corresponds to a height value of the respective pixel (P) in the three-dimensional coordinate system (4).
    [6]
    6. Device according to one of claims 1 to 5, characterized in that by the arithmetic unit (2), preferably by delimiting the color values (F) of the individual pixels (P) or by delimiting the spatial values (V) of the individual pixels ( P), the area-related values (A) of the recorded three-dimensional image (B) in a focus of inflammation (C) and a hearth surrounding area (U) adjacent to and surrounding the hearth (C) are distinguishable.
    [7]
    7. Device according to claim 6, characterized in that by comparing the averaged color values (F) in the focus of inflammation (C) and the averaged color values (F) in the focal area (U) a relative total color value (FW) of the inflammatory focus (C ) can be determined.
    [8]
    8. Device according to claim 6 or 7, characterized in that an absolute total volume value (VW) of the inflammation range (C) can be determined from the spatial values (V) in the area of ignition (C).
    [9]
    9. Device according to one of claims 6 to 8, characterized in that by comparing averaged spatial values (V) in the focus of inflammation (C) to averaged spatial values (V) in the hearth area (U) a relative total volume value (VW) of Inflammatory focus (C) can be determined.
    [10]
    10. The device according to claim 9, characterized in that the relative total volume value (VW) is a comparative value of the surface roughness in the focal point (C) to the surface roughness in the hearth environmental area (U). * · «·« · · · · · · * * * · · · ♦ ······ * * »* * #» ♦ * * «* ···» «· · 3
    [11]
    11. Device according to one of claims 1 to 10, characterized in that a surface-related value (A) corresponds to a circumference of the inflammation herd corresponding circumferential value and / or a surface-related value (A) corresponds to an area of the inflammatory focus (C) representing area value.
    [12]
    12. Device according to claim 11, characterized in that a surface-related value (A) is formed as a function of the area value and of the circumferential value and corresponds to a ratio of the circumferential value to the area value representing the compactness value.
    [13]
    13. Device according to one of claims 1 to 12, characterized in that a total volume value (VW) a the average height of all surveys (G) in the focal point (C) representing average height value and / or the area of the highest elevations (G ). The highest elevations (G) are those elevations (G) whose height is at least 70%, preferably at least 85%, of the height of the highest elevation (GH).
    [14]
    14. A method for determining a skin inflammation value (Z), in particular feasible with a device according to one of claims 1 to 13, with an opto-electronic measuring device (1), preferably a 3D scanner, a computing unit (2) and a display unit (3 characterized by the steps of: - acquiring a three-dimensional image (B) of an inflammatory region (E) on human or animal skin (H) with the opto-electronic measuring device (1), - determining area-related (A), color (F) and spatial (V) values of the three-dimensional image (B), - calculating the skin ignition value (Z) from the calculated area-related (A), color (F) and spatial (V) values and • · 4 · ··· ♦ 4 • v * «· · Ι · 4« «af ···» ♦ * · · * • * * # * ·· # · * 4 - Display the calculated skin inflammation value (Z) on the display unit (3).
    15. The method according to claim 14, characterized by the further steps of: - associating the ascertained color values (F) and spatial values (V) of the surface of the recorded image (B) in each case one, the area-related values (A) of the three-dimensional image ( B) representing the three-dimensional image (B) of a plurality of grid-like arranged pixels (P), - dividing the inflammation area (E) in a focus of inflammation (C) and a Herdumgebungsbereich (U), wherein the The area of the center of ignition (C) is delimited from the surface of the hearth area (U) by the color (F) and / or spatial (V) values assigned to the individual area-related values (A), - calculating either an absolute total color value (FW ), which corresponds to the averaged color value (F), preferably the averaged magenta value, of the inflammatory focus (C), or a relative total color value (FW) corresponding to the mean the color value (F) of the inflammatory focus (C) compared to the averaged color value (F) of the focal area (U), - calculating an absolute total volume value (VW) equal to the sum of the individual spatial values (V) of the inflammatory focus (C), and / or a total relative volume value (VW), preferably a roughness value, calculated by comparing the individual spatial values (V) of the inflammatory focus (C) to the individual spatial values (V) of the focal area (U) - calculating the skin inflammation value (Z) a. from at least one of the calculated total color values (FW) and at least one of the calculated total volume values (VW) or b. by allocating at least one of the calculated total color values (FW) to a defined inflammation class (Ko, Κι, K2, K3), * * * · «&lt; * »* • t 4 * * * ·· * * # β ···« 4 · · «· **« «·· ♦ # 4 · 5 Assign at least one, preferably several, of the calculated total volume values (VW) to a fixed category of inflammation (Ko, Κι, K2, K3) and averaging from the inflammation classes determined during the allocation and - output of the, preferably rounded, mean value as skin inflammation value (Z). Innsbruck, on March 13, 2011

    SUBSEQUENT

    SUBSEQUENT





    FOLLOWING £ &gt; * *









    p IG. FLASHED

    SUBSEQUENT

    REPLACED | ~ ι &. ^

    Ο o

    FLG. R



    Ρί6. 2Ϊ l *, 1 i '· 4 "ί FOLLOWED

    2. A device for determining a skin inflammation value (2), comprising - an optoelectronic measuring device (1), preferably a 3D scanner, for taking a three-dimensional image (B) of an inflammatory region ( E) on human or animal skin (H), wherein surface-related (A), spatial (V) and color (F) values of the three-dimensional image (B) can be detected by the optoelectronic measuring device (1), - a computing unit (2 ) for calculating the skin inflammation value (Z) from the area-related (A), spatial (V) and color (F) values detected by the measuring device (1), and - a display unit (3) for displaying the calculated skin inflammation value (Z), 2. device according to claim 1, characterized in that the recorded three-dimensional image (B) of the ignition region (E) consists of a plurality of raster-shaped pixels arranged in a three-dimensional coordinate system (4) (P) Each area-related value (A) corresponds to a single image point (P) which is unambiguous in the coordinate system (4). 3. Device according to claim 1 or 2, characterized in that each area-related value (A) of a by the opto-electronic measuring device (1) recorded three-dimensional image (B) both one, preferably single, color value (F) and a, preferably single, spatial value (V) is assignable. 4. Device according to one of claims 1 to 3, characterized in that each color value (F) corresponds to a magenta value in the CMYK color model, a gray value or a saturation value in the HSV color space. 5. A device according to claim 3 or 4, characterized in that each spatial value (V) corresponds to a height value of the respective pixel (P) in the three-dimensional coordinate system (4 ) corresponds. 6. Device according to one of claims 1 to 5, characterized in that by the arithmetic unit (2), preferably by delimiting the color values (F) of the individual pixels (P) or by delimiting the spatial values (V) of the individual pixels ( P), the area-related values (A) of the recorded three-dimensional image (B) in a focus of inflammation (C) and a hearth surrounding area (U) adjacent to and surrounding the hearth (C) are distinguishable. 7. Device according to claim 6, characterized in that by comparing the averaged color values (F) in the focus of inflammation (C) and the averaged color values (F) in the focal area (U) a relative total color value (FW) of the inflammatory focus (C ) can be determined. 8. Device according to claim 6 or 7, characterized in that from the spatial values (V) in the focal point of inflammation (C) an absolute total volume value (VWv) of the inflammatory hearth (C) can be determined. 9. Device according to one of claims 6 to 8, characterized in that by comparing averaged spatial values (V) in the focus of inflammation (C) to averaged spatial values (V) in the hearth area (U) a relative total volume value (VWR) of Inflammatory focus (C) can be determined. 10. A device according to claim 9, characterized in that the relative total volume value (VWr) is a comparative value of the surface roughness in the focal point (C) to the surface roughness in the hearth area (U). 11. Device according to one of Claims 1 to 10, characterized in that a surface-related value (A) corresponds to a circumferential value corresponding to the circumference of the inflammatory focus and / or a surface-related value (A) corresponds to an area value representing the surface of the inflammatory focal point (C) equivalent. 12. Device according to claim 11, characterized in that a surface-related value (A) is formed as a function of the area value and of the circumferential value and corresponds to a ratio of the circumferential value to the area value representing the compactness value. 13. Device according to one of claims 1 to 12, characterized in that a relative total volume value (VWr) a the average height of all surveys (G) in the focal point (C) representing the average height value and / or the area of the highest elevations ( G), wherein the highest elevations (G) are those elevations (G) whose height is at least 70%, preferably at least 85%, of the height of the highest elevation (GH). 14. A method for evaluating three-dimensional images, in particular feasible with a device according to one of claims 1 to 13, with an opto-electronic measuring device (1), preferably a 3D scanner, a computing unit (2) and a display unit (3), characterized by the steps of: - acquiring a three-dimensional image (B) of an area of inflammation (E) on human or animal skin (H) with the opto-electronic measuring device (1), - determining area-related (A), color (F) and spatial (A) V) Values of the three-dimensional image (B), - Calculation of the skin inflammation value (Z) from the calculated area-related (A), color (F) and spatial (V) values and POSSIBLE REPLACEMENT * · I «· Μ I« · · · »· ···················································································································································································································· calculated skin inflammation value (Z) on the display unit (3).
    [15]
    15. The method according to claim 14, characterized by the further steps of: - associating the ascertained color values (F) and spatial values (V) of the surface of the recorded image (B) in each case one, the area-related values (A) of the three-dimensional image ( B) representing the three-dimensional image (B) of a plurality of grid-like arranged pixels (P), - dividing the inflammation area (E) in a focus of inflammation (C) and a Herdumgebungsbereich (U), wherein the Area of the focal point (C) is delimited from the area of the focal area (U) by the color (F) and / or spatial (V) values assigned to the individual area values (A), - calculating either an absolute total color value (FW) which corresponds to the averaged color value (F), preferably the mean magenta value, of the inflammatory focus (C), or a relative total color value (FW) corresponding to the mean corresponds to the color value (F) of the inflammatory focus (C) compared to the mean color value (F) of the focal area (U), - calculating an absolute total volume value (VWv) equal to the sum of the individual spatial values (V) of the inflammatory focus (C), and / or a total relative volume value (VWR), preferably a roughness value, calculated by comparing the individual spatial values (V) of the inflammatory focus (C) to the individual spatial values (V) of the focal area (U) - calculating the skin inflammation value (Z) a. from at least one of the calculated total color values (FW) and at least one of the calculated total volume values (VWv, VWr) or b. by allocating at least one of the calculated total color values (FW) to a defined inflammation class (K0, Κι, K2, K3), | SUBSEQUENTLY allocate at least one, preferably more, of the calculated total volume values {VWv, VWR) to a defined inflammation class (Ko, Κι, K2, K3) and form an average of the inflammation classes determined during the allocation and output of, preferably rounded, Mean value as skin inflammation value (Z). Innsbruck, on December 22, 2011 | SUBSEQUENT
    类似技术:
    公开号 | 公开日 | 专利标题
    AT511265B1|2013-12-15|DEVICE FOR DETERMINING A CHARACTERIZATION VALUE AND METHOD FOR EVALUATING THREE-DIMENSIONAL IMAGES
    DE102009025856A1|2009-12-17|Processing and visualization technology of medical data
    DE14153444T1|2014-11-20|Detection by means of integrated attenuation of optical neuropathy in three-dimensional optical coherence tomography
    DE102006043347A1|2007-04-26|Airway visualization system and method for evaluation
    EP3073924B1|2021-10-06|Evaluation of an x-ray image of a breast produced during a mammography
    DE112014005372T5|2016-08-04|Device for supporting the diagnosis of osteoporosis
    EP3332710B1|2020-09-16|Characterisation of plaque
    EP3287914A1|2018-02-28|Determination of outcome data based on medical test data from different measurements
    DE102011081541A1|2012-03-01|PICTURE PROCESSING DEVICE, PICTURE PROCESSING METHOD AND PROGRAM MEMORY CARRIER
    DE112012004847B4|2020-03-12|Method and system for detecting lines in an image and lane detection system for analyzing street images
    DE102007014413B4|2016-02-04|Method for evaluating fluorescent image sets and apparatus for carrying it out
    DE102015206630A1|2016-10-20|Multispectral CT imaging
    CN101390129A|2009-03-18|Method and apparatus for analyzing clusters of objects
    DE10255527B4|2008-08-21|Generation of vascular-associated pulmonary nodule candidates
    DE10229880A1|2004-01-29|Image analysis method and device for image evaluation for in vivo small animal imaging
    DE112011100032T5|2013-05-29|Methodology and apparatus for objective, noninvasive and in vivo assessment and assessment of the scaliness of psoriasis wounds using digital imaging
    DE112019004112T5|2021-06-17|SYSTEM AND PROCEDURE FOR ANALYSIS OF MICROSCOPIC IMAGE DATA AND FOR GENERATING A NOTIFIED DATA SET FOR TRAINING THE CLASSIFICATORS
    DE112009005102T5|2013-04-25|Splitting of multipart objects
    DE102018104616A1|2019-08-29|A method of dividing one or more images of a sample into color-separated image data, computer program product, computer-readable medium on which the computer program product is stored, and a system for splitting one or more images of a sample into color-separated image data
    DE102005022156A1|2005-12-08|Method and device for ranking pixels in medical imaging
    DE102014108357B4|2019-06-19|Whole body imaging and image processing system and method of operation
    DE112016006913T5|2019-02-14|Image processing apparatus, operating method of the image processing apparatus, and operation program of the image processing apparatus
    DE102010018147A1|2011-10-27|Method for analysis of pathological objects in computer diagnostics for visualization or automatic detection of structural features, involves focusing mathematical approaches toward structure and form of identification during analysis
    DE102020113313A1|2021-11-18|METHOD, COMPUTER PROGRAM AND MICROSCOPE SYSTEM FOR PROCESSING MICROSCOPE IMAGES
    Mustafa2015|Assessing, monitoring and mapping forest resources in the Blue Nile Region of Sudan using an object-based image analysis approach
    同族专利:
    公开号 | 公开日
    EP2688465A1|2014-01-29|
    EA201391383A1|2014-11-28|
    AU2012231802B2|2016-05-19|
    EA026318B1|2017-03-31|
    AR085916A1|2013-11-06|
    US20140010423A1|2014-01-09|
    CA2828785C|2017-12-12|
    CA2828785A1|2012-09-27|
    TW201302154A|2013-01-16|
    TWI544898B|2016-08-11|
    US9330453B2|2016-05-03|
    AT511265B1|2013-12-15|
    HK1194270A1|2014-10-17|
    JP5921665B2|2016-05-24|
    JP2014512900A|2014-05-29|
    ES2540953T3|2015-07-15|
    AU2012231802A1|2013-09-19|
    CN103619238A|2014-03-05|
    EP2688465B1|2015-05-13|
    WO2012126027A1|2012-09-27|
    CN103619238B|2015-08-19|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    DE10021431A1|2000-05-03|2001-11-22|Inst Neurosimulation Und Bildt|Method and device for classifying optically observable skin or mucosal changes|
    DE10065146A1|2000-12-22|2002-07-11|Karsten Koenig|Method for non-invasive 3D optical examination of skin and for the therapy of pathological changes ascertained treats melanomas with laser applications|
    US20080304736A1|2007-02-20|2008-12-11|Masahiro Nakagawa|Method of estimating a visual evaluation value of skin beauty|
    WO2009024904A2|2007-08-22|2009-02-26|Koninklijke Philips Electronics N.V.|Method and apparatus for the optical characterization of surfaces|
    US5588428A|1993-04-28|1996-12-31|The University Of Akron|Method and apparatus for non-invasive volume and texture analysis|
    US5957837A|1996-10-17|1999-09-28|Faro Technologies, Inc.|Method and apparatus for wound management|
    US6081612A|1997-02-28|2000-06-27|Electro Optical Sciences Inc.|Systems and methods for the multispectral imaging and characterization of skin tissue|
    JPH11216120A|1998-02-02|1999-08-10|Pola Chem Ind Inc|Method for differentiating inflammation|
    US6381026B1|1999-03-15|2002-04-30|Lifecell Corp.|Method of measuring the contour of a biological surface|
    JP2003524490A|2000-01-29|2003-08-19|イー． トムソン，ポール|Apparatus and method for detecting and quantifying inflammation of joints and tissues|
    US6757413B1|2000-02-23|2004-06-29|American Telecare, Inc.|Low-cost medical image transfer and control system and method|
    US6594388B1|2000-05-25|2003-07-15|Eastman Kodak Company|Color image reproduction of scenes with preferential color mapping and scene-dependent tone scaling|
    JP3938534B2|2002-09-19|2007-06-27|株式会社リコー|Image processing apparatus and method, image forming apparatus, and program|
    AU2002952748A0|2002-11-19|2002-12-05|Polartechnics Limited|A method for monitoring wounds|
    JP3919722B2|2003-09-11|2007-05-30|花王株式会社|Skin shape measuring method and skin shape measuring apparatus|
    JP2009511163A|2005-10-14|2009-03-19|アプライドリサーチアソシエイツエヌゼットリミテッド|Method and apparatus for observing surface features|
    US7495208B2|2006-06-01|2009-02-24|Czarnek And Orkin Laboratories, Inc.|Portable optical wound scanner|
    US8849380B2|2007-11-26|2014-09-30|Canfield Scientific Inc.|Multi-spectral tissue imaging|
    US20100121201A1|2008-10-13|2010-05-13|George Yiorgos Papaioannou|Non-invasive wound prevention, detection, and analysis|
    JP2010200971A|2009-03-03|2010-09-16|Hoyu Co Ltd|Method for predicting/estimating abnormal hair loss, precaution/prevention method for abnormal hair loss, and method for evaluating abnormal hair loss preventive agent|
    US20100234737A1|2009-03-12|2010-09-16|Miranda Aref Farage|Method for assessing skin irritation using infrared light|
    US8150501B2|2009-03-26|2012-04-03|Johnson & Johnson Consumer Companies, Inc.|Method for measuring skin erythema|
    FR2944898B1|2009-04-23|2018-03-16|Lvmh Recherche|METHOD AND APPARATUS FOR CHARACTERIZING SKIN IMPERFECTIONS AND METHOD OF ASSESSING THE ANTI-AGING EFFECT OF A COSMETIC PRODUCT|
    CN101894212B|2010-07-05|2012-02-15|上海交通大学医学院|Skin wound comprehensive detection method|
    JP5165732B2|2010-07-16|2013-03-21|オリンパス株式会社|Multispectral image processing method, image processing apparatus, and image processing system|US5169986A|1986-05-21|1992-12-08|Toray Industries, Inc.|Organic nonlinear optical material|
    JP2009511163A|2005-10-14|2009-03-19|アプライドリサーチアソシエイツエヌゼットリミテッド|Method and apparatus for observing surface features|
    US9179844B2|2011-11-28|2015-11-10|Aranz Healthcare Limited|Handheld skin measuring or monitoring device|
    US9854970B2|2012-02-21|2018-01-02|Massachusetts Eye & Ear Infirmary|Calculating conjunctival redness|
    ES2774307T3|2013-03-13|2020-07-20|Innoprick S L|Hives measurement and allergy detection|
    CA2947295A1|2014-05-02|2015-11-05|Massachusetts Eye And Ear Infirmary|Grading corneal fluorescein staining|
    JP6504914B2|2015-05-20|2019-04-24|花王株式会社|Method of observing skin capillaries|
    US10007971B2|2016-03-14|2018-06-26|Sensors Unlimited, Inc.|Systems and methods for user machine interaction for image-based metrology|
    US9928592B2|2016-03-14|2018-03-27|Sensors Unlimited, Inc.|Image-based signal detection for object metrology|
    US10013527B2|2016-05-02|2018-07-03|Aranz Healthcare Limited|Automatically assessing an anatomical surface feature and securely managing information related to the same|
    CN106023269B|2016-05-16|2019-03-22|北京大学第一医院|A kind of method and device for estimating wound area|
    JP6793325B2|2016-05-25|2020-12-02|パナソニックＩｐマネジメント株式会社|Skin diagnostic device and skin diagnostic method|
    CN106361288A|2016-09-28|2017-02-01|湖南老码信息科技有限责任公司|Summer dermatitis prediction method and system based on incremental neural network model|
    US11116407B2|2016-11-17|2021-09-14|Aranz Healthcare Limited|Anatomical surface assessment methods, devices and systems|
    CN109493310A|2017-09-08|2019-03-19|丽宝大数据股份有限公司|Biological information analytical equipment and its hand skin analysis method|
    CN109330566A|2018-11-21|2019-02-15|佛山市第人民医院（中山大学附属佛山医院）|A kind of wound monitoring method and device|
    法律状态:
    2020-11-15| MM01| Lapse because of not paying annual fees|Effective date: 20200324 |
    优先权:
    申请号 | 申请日 | 专利标题
    ATA420/2011A|AT511265B1|2011-03-24|2011-03-24|DEVICE FOR DETERMINING A CHARACTERIZATION VALUE AND METHOD FOR EVALUATING THREE-DIMENSIONAL IMAGES|ATA420/2011A| AT511265B1|2011-03-24|2011-03-24|DEVICE FOR DETERMINING A CHARACTERIZATION VALUE AND METHOD FOR EVALUATING THREE-DIMENSIONAL IMAGES|
    TW101108586A| TWI544898B|2011-03-24|2012-03-14|Device and method for determining a skin inflammation score|
    JP2014500201A| JP5921665B2|2011-03-24|2012-03-20|Apparatus and method for determining skin inflammation value|
    CA2828785A| CA2828785C|2011-03-24|2012-03-20|Device and method for determining a skin inflammation value|
    AU2012231802A| AU2012231802B2|2011-03-24|2012-03-20|Apparatus and method for determining a skin inflammation value|
    US14/006,173| US9330453B2|2011-03-24|2012-03-20|Apparatus and method for determining a skin inflammation value|
    PCT/AT2012/000069| WO2012126027A1|2011-03-24|2012-03-20|Apparatus and method for determining a skin inflammation value|
    EP12719241.7A| EP2688465B1|2011-03-24|2012-03-20|Apparatus and method for determining a skin inflammation value|
    CN201280015027.7A| CN103619238B|2011-03-24|2012-03-20|For determining the apparatus and method of skin inflammation value|
    EA201391383A| EA026318B1|2011-03-24|2012-03-20|Apparatus and method for determining a skin inflammation value|
    ES12719241.7T| ES2540953T3|2011-03-24|2012-03-20|Device and method to determine a skin inflammation score|
    ARP120100979A| AR085916A1|2011-03-24|2012-03-23|DEVICE AND METHOD FOR DETERMINING A CUTANEOUS INFLAMMATION SCORE|
    HK14107580.5A| HK1194270A1|2011-03-24|2014-07-25|Apparatus and method for determining a skin inflammation value|
    [返回顶部]