Method of measuring fluorescence signal, determining peak frequency map and providing risk prediction value and image capturing and processing device

Abstract

To provide an improved method of measuring a fluorescence signal, an improved image capturing and processing device, and an improved endoscope or laparoscope.SOLUTION: An image capturing device 10 measures a fluorescence signal in a tissue of a body part 4 and images a surface of the body part. The image capturing device comprises a fluorescence imaging unit configured to capture a fluorescence image and a visible light imaging unit configured to capture a visible light image. The fluorescence imaging unit is further configured to capture a time sequence of fluorescence images. In a processing device 12, a peak frequency map unit is configured to determine a peak frequency map for an area of interest in the fluorescence images by analyzing the time sequence of fluorescence images. An output unit is configured to output the peak frequency map together with the visible light image and / or the fluorescence image.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention measures the fluorescent signal in tissue of a body part to which a fluorescent agent has been added, and images the surface of the body part. measurement The present invention further relates to a method for measuring a fluorescent signal in tissue of a body part to which a fluorescent agent has been added, the method being configured to image a surface of the body part. Measuring Equipment Further, the present invention relates to Measuring Equipment The present invention relates to an endoscope or laparoscope including

[0002] The present invention also relates to methods for diagnosing lymphatic dysfunction, particularly lymphedema, and methods for the long-term treatment of lymphatic dysfunction, particularly lymphedema.

[0003] Books measurement Method and Measuring Equipment It particularly relates to the imaging and measurement of lymphatic dysfunction, particularly lymphatic function, with further regard to the diagnosis, treatment and / or prevention of lymphatic dysfunction, particularly lymphedema.

[0004] The present invention also provides risk prediction values ​​based on measuring the fluorescent signal in tissue of a body part to which a fluorescent agent has been added. Providing risk prediction values The present invention further relates to a computer-based clinical decision support system (CDSS) for providing risk prediction values ​​based on measurements of fluorescent signals in tissue of a body part to which a fluorescent agent has been added. [Background technology]

[0005] Lymphedema is a lymphatic dysfunction that results in the accumulation of lymph fluid in the tissues of the body. Oxygenated blood is pumped from the heart to the tissues through the arteries, while deoxygenated blood returns to the heart through the veins. The pressure level on the arterial side is much higher than on the venous side, so the colorless, fluid portion of the blood is forced into the spaces between the cells. Typically, more fluid is pushed out than is reabsorbed on the venous side. The excess fluid is transported by lymphatic capillaries. In addition, the fluid carries away localized foreign bodies such as larger proteins and cellular debris. Once in the lymphatic system, this fluid, containing the transported materials, is called lymph or lymphatic fluid.

[0006] The lymphatic system contains lymphatic vessels that have one-way valves similar to those in veins to transport lymph fluid to the next lymph node, which removes certain substances and cleanses the fluid before it is returned to the bloodstream.

[0007] When the lymphatic system is obstructed in that lymph flow is blocked or does not occur at the desired level, lymph fluid accumulates in the interstitial spaces between tissue cells. This accumulation, caused by impaired lymphatic transport, is called lymphedema. The accumulation of lymph fluid can cause an inflammatory response that damages the cells surrounding the affected area. It can further cause fibrosis, which can turn into hardening of the affected tissue.

[0008] Because lymphedema is a lifelong condition for which there is no cure or drug therapy, early diagnosis and appropriate early countermeasures to improve drainage and reduce fluid load are crucial to the patient's health and recovery. Possible treatments, such as lymphatic massage and compression bandaging up to surgery, depend on the level of severity, which is a four-stage system defined by the World Health Organization (WHO) as follows: Stage 1: Normal flow in the lymphatic system. No signs or symptoms. Stage 2: Fluid accumulation with swelling. Stage 3: Persistent swelling that does not resolve with elevation of the affected limb or body part. Stage 4: Elephantiasis (severely deformed limbs), thickened skin with "warty" growths, and extensive scarring.

[0009] In the diagnosis of lymphatic system function, a commonly used technique is manual examination of the affected limb or body part by a physician. A known imaging technique is lymphoscintigraphy, in which a radioactive tracer is injected into the tissues of the affected body part, followed by MRI (magnetic resonance imaging), CT (computed tomography), PET-CT scan (positron emission tomography) or ultrasound imaging.

[0010] A relatively new imaging technique is infrared fluorescence imaging, which uses a fluorescent dye, for example, ICG (indocyanine green). ICG is a green medical dye used for over 40 years. The dye fluoresces when excited with near-infrared light having a wavelength of 600 nm to 800 nm. This excitation causes ICG to emit fluorescence at 750 nm to 950 nm. The fluorescence of the ICG dye can be detected using a CCD or CMOS sensor or camera. The fluorescent dye is administered to the tissues of the affected limb or body part, and lymphatic concentration and flow can be tracked based on the detected fluorescence.

[0011] Lymphatic dysfunction is caused by insufficient circulation of lymphatic fluid in the tissues of the body. Tissue perfusion is generally an important biomarker in many clinical conditions. For example, it is an indicator of successful recovery after surgery, for example in gastrointestinal surgery.

[0012] Fluorescence imaging provides useful information for the assessment of tissue perfusion. Data analysis is typically performed by analyzing the time-intensity curves of the fluorescence intensity. The time-intensity curves can be extracted from the time-dependent recording of the fluorescence images. The time-intensity data can be extracted, for example, pixel-by-pixel or averaged over a specific region. The time-intensity curves can be analyzed by fitting a model, the coefficients of which give specific information about physiological parameters. However, the coefficients of the model describe the shape of the time-intensity curve more or less accurately and are not directly linked to the underlying biological processes. Thus, the interpretation of the derived coefficients can be challenging. Summary of the Invention [Problem to be solved by the invention]

[0013] A first object of the present invention is to provide an improved method for measuring fluorescent signals. measurement Methods, improved Measuring Equipment and an improved endoscope or laparoscope, in particular where improved fluorescent imaging output can be provided. It is a further object of the present invention to provide improved methods of diagnosing lymphedema and improved methods of long-term therapy of lymphedema.

[0014] A second object of the present invention is to provide an improved method for providing risk prediction value based on fluorescent signals. Providing risk prediction values The present invention provides a method for determining whether a patient is at increased risk of developing a disease and an improved computer-based clinical decision support system (CDSS) for providing risk prediction values. [Means for solving the problem]

[0015] The first objective is to measure the fluorescent signal in the tissue of a body part to which a fluorescent agent has been added and to image the surface of the body part. measurement direction By law This has been resolved, measurement How to do it 、 firefly Excitation of fluorescent agents to provide optical images InitiationIlluminating the tissue with excitation light having a wavelength suitable for producing photoemitted light. death, capturing at least one fluorescence image within the examination area by spatially resolved measurement of the emitted light; 、 Inspection capturing at least one visible light image of a surface of the body part within the scan area. P and firefly repeating the step of capturing a fluorescence image to capture a plurality of fluorescence images over time to provide a time series of light images; To provide a time series of visible light images , possible repeating the step of capturing a visible light image to capture a plurality of visible light images over time; 、 firefly Determining a peak frequency map of a region of interest in a fluorescent image by analyzing a time series of optical images. P and Outputting a peak frequency map together with the visible light image and / or the fluorescent image. and the viewing directions and / or viewpoints of the fluorescent image and the visible light image are linked via a known relationship; The step of determining a peak frequency map comprises: determining a time-dependent intensity curve of at least one pixel within the region of interest; identifying peaks in the time dependent intensity curve and determining a frequency of the identified peaks and / or a maximum height of the identified peaks; generating a graphical representation of the determined frequency and / or maximum height for at least one pixel and including the graphical representation in said peak frequency map.

[0016] An important piece of information for diagnosing lymphedema is the rate of lymphatic transport into the lymphatic system. Rapid transport of lymph indicates that the lymphatic veins are intact and there is no lymphedema, whereas slow transport of lymph strongly indicates that the patient has developed lymphedema at a stage where he or she should undergo therapeutic treatment. Lymphatic transport can be seen in fluorescent images because a fluorescent agent, for example ICG (indocyanine green), has been administered to the tissues of the body part that will show insufficient lymphatic function. By observing the fluorescent images over time, the uptake of lymphatic fluid in the lymphatic system can be observed. In a healthy lymphatic system, the fluorescent agent is rapidly taken up by the lymphatic system along with the lymph. The lymphatic veins rapidly transport lymph in a straight path. These lymphatic vessels contain one-way valves to prevent the backflow of fluid.

[0017] In a healthy lymphatic system, there is a rhythmic transport of lymphatic fluid in lymphatic vessels. This process can be observed in time-resolved fluorescence images. The rhythmic transport of lymphatic fluid results in intensity oscillations in certain regions of the fluorescence image. These regions correspond to the location of lymphatic vessels.

[0018] In lymphedema, when lymph flow is obstructed, pressure in the lymphatic vessels increases, which causes lymph to leak into the subcutaneous tissue. For the prevention of lymphedema, early diagnosis and treatment of the disease are of utmost importance. In the lymphatic system of patients with lymphedema, a significant decrease in lymphatic transport can be observed. Again, this phenomenon can be detected by analyzing a series of time-resolved fluorescent images. Therefore, the analysis of multiple fluorescent images taken over time is an important task for a reliable and early diagnosis of lymphedema.

[0019] After administration of the fluorescent agent, where this step occurs before the method of measuring a fluorescent signal according to aspects of the present invention begins, the fluorescent signal can be tracked and analyzed based on a series of captured fluorescent images, which are time-resolved fluorescent images representing a time series of fluorescent images.

[0020] Fluorescent agents are, for example, ICG (indocyanine green) or methylene blue. Within the context of this specification, the term "fluorescent dye" or "dye" (also called "fluorochrome" or "fluorophore") refers to a moiety of a molecule that makes the molecule fluorescent. A moiety is a functional group in a molecule that absorbs energy at a specific wavelength and re-emits the energy at a different specific wavelength. In various embodiments, the fluorescent agent includes a fluorescent dye, an analog thereof, a derivative thereof, or a combination thereof. Suitable fluorescent dyes include, but are not limited to, indocyanine green (ICG), fluorescein, methylene blue, isosulfan blue, patent blue, cyanine 5 (Cy5), cyanine 5.5 (Cy5.5), cyanine 7 (Cy7), cyanine 7.5 (Cy7.5), cypate, silicon rhodamine, 5-ALA, IRDye 700, IRDye 800CW, IRDye 800RS, IRDye 800BK, porphyrin derivatives, Illuminare-1, ALM-488, GCP-002, GCP-003, LUM-015, EMI-137, SGM-101, ASP-1929, AVB-620, OTL-38, VGT-309, BLZ-100, ONM-100, BEVA800.

[0021] However, the analysis of lymphatic flow performed by aspects of the invention goes beyond the mere observation of a time-resolved series of fluorescent images. The time series of fluorescent images is analyzed by first defining a region of interest in the fluorescent images. This region of interest can range from a single pixel in the fluorescent image to a full-scale fluorescent image, i.e. the complete fluorescent image. Often the region of interest is somewhat intermediate. For example, a selection rectangle can be defined on the screen using a suitable tool that can be manipulated by the input hardware, for example with a mouse or a trackball. In this region of interest, the fluorescent images are analyzed over time. This can be the entire time of the examination during which the time series of fluorescent images was captured, or a predefined or selected period of time.

[0022] For ease of explanation, reference will be made to the analysis of a single pixel in the fluorescent image. In other words, the region of interest is, for simplicity's sake, a single pixel. A similar approach applies when multiple pixels are analyzed.

[0023] As a first step, the intensity of the pixel under examination in a time series of fluorescent images is analyzed and a time-dependent intensity curve of said pixel is determined. If the pixel being analyzed is located in an area of ​​the fluorescent image where lymphatic transport takes place, the time-dependent intensity curve typically shows various peaks. This transport is indicated by a changing intensity of the fluorescent signal. For example, the intensity of the fluorescent signal follows the oscillations of lymphatic fluid in the lymphatic vessels.

[0024] After determining the time-dependent intensity curve, the curve is analyzed and intensity peaks are identified. The maximum height of the peaks and the location of the peaks can be determined. For example, this can be performed by gradient analysis or with any other suitable approach. Based on the information on the location of the peaks, the frequency of the identified peaks can be calculated. The units of this frequency are, for example, peaks per second, peaks per frame, or peaks per 100 frames. Information on the frequency of the peaks is output together with a visible image of the surface of the patient's body part. Based on this information, the operator is provided with information on the lymphatic transport in the region of interest. A high frequency indicates a typical pulsatile transport of lymphatic fluid, thereby clearly indicating a high transport volume. The frequency values ​​can be output as numbers, on a color scale, or with any other suitable information.

[0025] As further or alternative information, the maximum height of the peaks can be analyzed: the higher the peak of the fluorescent signal, the higher the concentration of lymphatic fluid in the analyzed pixel within the region of interest (or the region of interest when considered in its entirety). The maximum height of the identified peaks is determined. This information can also be very informative, especially in combination with information about the frequency of the peaks. The maximum gives information about the concentration of lymphatic fluid, whereas the frequency gives information about the transport of lymphatic fluid.

[0026] If the above-mentioned approach is performed for all pixels in the region of interest, a map of the frequency of the maximum values, a so-called frequency map, can be generated. The map can be displayed on a color scale. Similarly, a map of the maximum values ​​of the detected peaks can be generated. This map can also be displayed on a color scale. The map can be shown side-by-side with the fluorescence image and in combination with the visible light image. In particular, the combination with the visible light image allows the user to identify the location on the patient's body part where a particular diagnostic finding was made. This allows, for example, a doctor to provide the patient with a tailored therapy for the detected lymphedema.

[0027] The output of the peak frequency map can include additional information, e.g. regarding the frequency state or percentage. This can be expressed in the form of a scoring probability, e.g. indicated with a good or bad color indication. The detection of maxima in the time-dependent intensity curve can be performed, e.g. by a slope analysis of the intensity curve. The detection of peaks can also be based on a threshold analysis, meaning that all parts of the curve that exceed a certain threshold are considered as peaks. The output of the peak frequency map can be a color indication, a graph, a value or pseudocolor showing the amount of a value, or a simple table. An easy to understand graphical representation is an intensity plot.

[0028] According to an advantageous embodiment, the measurement The method is to use a graphic representation Include in peak frequency map It is further improved in that the step includes generating an intensity plot indicative of the determined frequency and / or maximum height of the identified peaks at the location of at least one pixel within the region of interest.

[0029] The intensity plot may be a pseudocolor representation of the frequency of the identified peaks and / or the maximum height of the identified peaks. It may also be a plot showing contour lines in a pseudocolor representation, in particular contour lines with colors taken from the intensity plot.

[0030] To further simplify the interpretation of the measurement results, a registration of the peak frequency map with the fluorescence and / or visible light images may be performed.

[0031] According to an advantageous embodiment, the measurement The method is: A step of overlaying the peak frequency map and the fluorescence image to provide a peak / fluorescence overlay image. , and outputting the peak / fluorescence overlay image together with the fluorescence image as an output of the peak frequency map; 、 P The peak frequency map and the visible light image are overlaid to provide a peak / visible overlay image. , and outputting the peak / visible overlay image as an output of the peak frequency map together with the visible light image; At least one of Further includes:

[0032] The overlay of the peak frequency map with the fluorescence image simplifies interpretation of the fluorescence image. The overlay of the peak frequency map with the visible light image allows a user to identify specific areas where a specific treatment is desired, for example for lymphedema.

[0033] Further, according to another embodiment measurement A method, wherein the steps of capturing a fluorescence image and capturing a visible light image are performed simultaneously, particularly when there is no time switching between the signals of the fluorescence image and the visible light image. measurement There is a way.

[0034] Advantageously, the fluorescence image and the visible light image can be captured simultaneously. As a result, there is a perfect correspondence between the measurement of the fluorescence signal, which means the fluorescence image, and the visible light image, which shows the surface of the body part under examination. Based on this information, a coordinated and spatially accurate precision treatment of, for example, lymphatic dysfunction can be performed. The same applies to the diagnostic possibilities.

[0035] According to yet another advantageous embodiment of the invention, the method for measuring comprises the steps of: Repeating the steps of capturing a fluorescent image and capturing a visible light image to provide a series of fluorescent images and a series of visible light images. Toto , To generate large visible light images A set of stitching parameters is determined and applied. Algorithm A series of visible light images To apply Toto , Applying a stitching algorithm to a series of fluorescent images to generate a large fluorescent image Toto , further comprising a series of fluorescent images and a series of visible light images showing different overlapping regions of an examination of a body part; The stitching algorithm applied to the series of fluorescence images uses a set of stitching parameters determined when generating the large visible light image. Peak frequency map The output step is Outputting a large visible light image along with a large fluorescence image and peak frequency map Includes.

[0036] Stitching By applying the algorithm, larger areas of the body part can be examined. Advantageously, Stitching The algorithm is Stitching It was previously determined when running Stitching Reconstruction of a series of fluorescence images based on a set of parameters Stitching Execute. Stitching Sometimes it is particularly possible to use only one image from the time series of fluorescent images and the time series of visible light images. Stitching The application of the parameters is performed when the fluorescence image is typically Stitching This is advantageous because it provides rare special features that are well suited for carrying out the process. The visible light image and the fluorescent image are linked by a known fixed relationship with respect to the viewing direction and / or viewpoint, so that the visible light image is used Stitching The parameters of the algorithm are Stitching This can also be applied to Stitching The process and the outcomes that can be achieved are significantly improved.

[0037] According to another advantageous embodiment of the invention, the measurement of the fluorescent signal is carried out on tissue to which at least a first and a second fluorescent agent have been added, The step of capturing a fluorescent image includes: First excitation of the first fluorescent agent Initiation capturing a first fluorescence image in a first wavelength range produced by illuminating the tissue with a first excitation light having a first wavelength suitable for producing light emitted by the tissue; The second excitation of the second fluorescent agent Initiation capturing a second fluorescence image in a second wavelength range produced by illuminating the tissue with a second excitation light having a second wavelength suitable for producing light emitted by the tissue; Multiple over time Fluorescent image Statue determining a peak frequency map; Bipi The step of outputting a frequency map is performed on the first and second fluorescent images.

[0038] Since various fluorescent dyes open up the field of differential diagnosis, fluorescent imaging based on two fluorescent agents may be desirable. The first fluorescent agent may be, for example, ICG and the second fluorescent agent may be methylene blue. The first fluorescent image may be captured in a wavelength range of 700 nm to 800 nm when methylene blue is used as the first fluorescent agent or dye. The second fluorescent image may be captured in a wavelength range of 800 nm to 900 nm when ICG is used as the second fluorescent agent or dye. According to an embodiment of the present invention measurement The method can be performed with a variety of fluorescers and dyes. Essentially any combination of suitable dyes and suitable or compatible excitation light sources can be applied.

[0039] In many cases, lymphatic function is affected in the extremities of the body. However, measuring the fluorescent signal measurement The method is not limited to testing the extremities. measurementThe method generally refers to the examination of a body part, which may be a patient's extremities, but also the torso, head, neck, back or any other part of the body. It is also possible that the body part is an organ, in particular an internal organ. Measuring the fluorescent signal measurement The method is an indication of lymphatic flow and can also be performed during open surgery. The same applies to situations where the surgery is a minimally invasive procedure performed using an endoscope or laparoscope.

[0040] Within the context of this specification, a "visible light image" is an image of a real-world situation. It reproduces an image impression similar to what the human eye can see. Unlike the human eye, the visible light image can be a color image, a grayscale image, or even a pseudocolor scale plot. The visible light image shows the surface of the body part, including the tissue to which the fluorescent agent has been administered. If the tissue is located on the surface of the body part, for example when an internal organ is examined, the imaging of the surface of the body part includes the imaging of the surface of the tissue.

[0041] Further, according to another embodiment measurement The method includes capturing a first fluorescent image. And Capture a second fluorescent image And are performed simultaneously, especially if there is no time switching between the signals of the first and second fluorescent images.

[0042] The simultaneous capture of the first and second fluorescent images results in a measurement in which the information derived from the first fluorescent image and the information derivable from the second fluorescent image truly refer to the same point in time. Thus, the features or information that can be obtained from the comparison of the two images are not corrupted by changes over time in the body part, for example rapid fluctuations in lymphatic fluid. This improves the quality of the measurement.

[0043] According to another advantageous embodiment, the viewing direction and viewpoint of the fluorescent image and the visible light image are identical, in particular the fluorescent image and the visible light image are in particular captured through one and the same objective lens. Capturing both images through one single objective lens provides an almost perfect alignment of the viewing direction and the viewpoint of the images.

[0044] In particular, the fluorescent and visible light images are captured in the absence of time switching. This can be done by an image capture device that includes a prism assembly and multiple image sensors. The fluorescent and visible light enter the prism assembly as a common light beam through the same entrance face of the prism assembly. The prism assembly or structure can also include a filter to separate the visible wavelength range from the infrared wavelength range in which the excited emission of the fluorescent agent typically occurs. The different wavelength ranges are directed to different sensors. These sensors can be operated independently and no time switching of the sensor's signals is required. This is advantageous because the infrared stills, which are the fluorescent stills, and the visible light stills are captured exactly at the same time using separate image sensors. Thus, the images can be captured at high frame repetition rates, for example 60 frames per second or more. Higher frame rates typically cannot be achieved when performing time switching. Furthermore, when the fluorescent and visible light images are captured on individual sensors, both of these sensors can be positioned in focus with precision. Furthermore, the sensor settings can be individually adjusted taking into account the requirements for image capture of the visible light and fluorescent images. This concerns, for example, adjustment of sensor gain, noise reduction or exposure time.

[0045] The first object is also to measure the fluorescent signal in the tissue of the body part to which the fluorescent agent has been added and to image the surface of the body part. Measuring Equipment is solved by Measuring Equipment teeth, Excitation of fluorescent agents Initiation an illumination unit configured to illuminate the tissue with excitation light having a wavelength suitable for generating light emitted by the tissue; To provide a fluorescence image, excitation of the fluorescent agent is performed. Initiation Illuminating the tissue with excitation light having a wavelength suitable for producing photoemitted light. death, a fluorescence imaging unit configured to capture a fluorescence image in the examination area by spatially resolved measurement of the emitted light; a visible light imaging unit configured to capture a visible light image of a surface of the body part within the examination area; To , an image capture device including the viewing directions and / or viewpoints of the fluorescent image and the visible light image are linked via a known relationship; the fluorescence imaging unit is further configured to capture a plurality of fluorescence images over time to provide a time series of fluorescence images; In particular, the visible light imaging unit is configured to capture a plurality of visible light images over time to provide a time series of visible light images; Measuring Equipment teeth, a peak frequency map unit configured to determine a peak frequency map of a region of interest in the fluorescent images by analyzing a time series of the fluorescent images; To , an output unit configured to output a peak frequency map together with the visible light image and / or the fluorescent image; The present invention further includes a processing device including fruit, The peak frequency map unit is determining a time-dependent intensity curve of at least one pixel within the region of interest; identifying peaks in the time dependent intensity curve and determining a frequency of the identified peaks and / or a maximum height of the identified peaks; generating a graphical representation of the determined frequency and / or maximum height for at least one pixel and including the graphical representation in a peak frequency map; configured to perform an analysis including .

[0046] Measure the fluorescent signal measurement The same or similar advantages mentioned in relation to the method are applicable to the same or similar methods. Measuring Equipment applies to and is therefore not repeated.

[0047] According to an advantageous embodiment of the invention, Measuring Equipment is the peak frequency map unit , Seki generating an intensity plot showing the determined frequency and / or maximum height of the identified peaks at at least one pixel location within the cardiac region; And It will be further improved in that respect.

[0048] Furthermore, the processing device particularly includes a superposition unit, The stacking unit is A configuration capable of executing at least one of a first overlay process and a second overlay process, The output unit is A configuration capable of executing at least one of a first output process and a second output process, The first registration process is a process of registering the peak frequency map and the fluorescence image to provide a peak / fluorescence overlay image; The first output process is a process of outputting the peak / fluorescence overlay image together with the fluorescence image as an output of the peak frequency map; Second Overlay Processing overlays the peak frequency map with the visible light image to provide a peak / visible overlay image It is a process , Second output process outputs a peak / visible overlay image as a peak frequency map output along with the visible light image It is a process .

[0049] According to yet another advantageous embodiment of the present invention, Measuring Equipment The present invention relates to an image capture device, in particular a fluorescent imaging unit and a visible light imaging unit, To provide a series of fluorescence images and a series of visible light images, of Captivity Capture and visible light images of Captivity Capture Repeat death , A series of fluorescence image and a series of visible light images indicates various overlapping areas of body part examination. death , The processing device To generate large visible light images A set of stitching parameters is determined and applied. Algorithm A series of visible light images Configured to apply Stitching Unit To Further including, Stitching The unit captures a series of fluorescent images. Stitching and further configured to apply an algorithm to generate a large fluorescent image. The output unit is further configured to output the large visible light image together with the large fluorescent image and the peak frequency map. R, A stitching algorithm is applied to the series of fluorescence images to generate a large visible light image with a set of stitching parameters determined. It will be further improved in that respect.

[0050] Furthermore, according to an advantageous embodiment, Measuring Equipment teeth, A fluorescent imaging unit and a visible light imaging unit are arranged to provide a series of fluorescent images and a series of visible light images. of Captivity Capture and visible light images of Captivity Capture Repeat death , A series of fluorescence image and a series of visible light images indicates various overlapping areas of body part examination. death, Processing The management device To generate large visible light images A set of stitching parameters is determined and applied. Algorithm A series of visible light images Configured to apply Stitching Unit To Further including, Stitching The unit captures a series of fluorescent images. Stitching and further configured to apply an algorithm to generate a large fluorescent image. An output unit is configured to output the large visible light image together with the large fluorescent image and the peak frequency map. R, The stitching algorithm applied to the series of fluorescence images uses a set of stitching parameters determined when generating the large visible light image. It will be further improved in that respect.

[0051] Books Measuring Equipment The fluorescent imaging unit and the visible light imaging unit are configured so that the viewing direction and viewpoint of the fluorescent image and the visible light image are the same. So that Consists of, among other things ,firefly Optical and visible light images are captured through one and the same objective lens like It can be further improved in terms of its structure.

[0052] According to yet another advantageous embodiment of the present invention, Measuring Equipmentis further improved in that the fluorescence imaging unit and the visible light imaging unit are configured to capture fluorescence images and visible light images simultaneously, particularly where there is no time switching between the fluorescence image signals and the visible light image signals.

[0053] According to yet another advantageous embodiment of the invention, the image capture device comprises: a dichroic prism assembly configured to receive, through an input surface, fluorescent light forming a fluorescent image and visible light forming a visible light image; Further equipped , The dichroic prism assembly is a first prism, a second prism, a first compensator prism located between the first prism and the second prism, a further dichroic prism assembly for splitting the visible light into three light components, and a second compensator prism located between the second prism and the further dichroic prism assembly. Including fruit, The first prism and the second prism each have a cross section with at least five corners, each corner having an inside angle of at least 90 degrees. ,So Each of the light sources has an entrance surface and an exit surface, and the direction of the entrance surface is parallel to the normal of the entrance surface. To The incident beam entering the incidence plane is 1. prism and each of the second prisms is reflected twice inside the To Through the exit surface 1. prism and each of the second prisms Each is designed to come out of 1. prism and each of the second prisms The normal to the incident surface and the normal to the exit surface are perpendicular to each other, When light enters the first prism through the input surface, the light is partially reflected toward the output surface of the first prism. , No. the light travels a first path length from the input face of the first prism to the output face of the first prism, the light partially enters the second prism through the first compensator prism, is partially reflected towards the output face of the second prism, and travels a second path length from the input face of the first prism to the output face of the second prism; The first prism has a first path length and a second path length that are equal to each other. Become so it is larger than the second prism.

[0054] Advantageously, the five prism assemblies described above allow for the simultaneous capture of two fluorescent images at two wavelengths and three colors for visible light imaging. The colors of the visible light image can be, for example, red, blue, and green. The five prism assemblies are advantageous in that the optical path lengths of the light traveling from the entrance face to each one of the sensors have the same length. All the sensors can be positioned in focus, and furthermore, there are no timing gaps between the signals of the sensors. Advantageously, the present invention Measuring Equipment does not require time switching of the received signal. The prism assembly is more compact and does not make the capture device unnecessarily large.

[0055] According to yet another aspect, the image capture device defines first, second, and third optical paths for directing the fluorescent light and the visible light to the first, second, and third sensors, respectively, and the image capture device further includes a dichroic prism assembly configured to receive the fluorescent light and the visible light through the entrance surface, the dichroic prism assembly including a first prism, a second prism, and a third prism, each prism having a respective first, second, and third exit surface, the first exit surface being provided with a first sensor, the second exit surface being provided with a second sensor, and the third exit surface being provided with a third sensor, in particular, the first optical path being provided with a first filter, the second optical path being provided with a second filter, and the third optical path being provided with a third filter; The first filter, the second filter, and the third filter, in any order, are green filters, infrared filters, and red / blue patterned filters including red and blue filters in an alternating pattern such that half of the light received by the red / blue patterned filter passes through the blue filter and half of the light received by the red / blue patterned filter passes through the red filter.

[0056] Furthermore, according to another aspect, the first, second, and third filters are, in any order, a red / green / blue patterned filter (RGB filter), a first infrared filter, and a second infrared filter, and in particular, the first and second infrared filters have different transmission wavelengths.

[0057] In other words, the first and second infrared filters are for filtering IR light of different IR wavelength intervals, for example a first IR band in which a typical fluorescent dye emits a first fluorescence peak, and a second IR band in which a typical fluorescent dye emits a second fluorescence peak. Typically, the second IR band is located at a higher wavelength compared to the first IR band. The first and second infrared filters can also be tuned to the emission bands of different fluorescent agents. Thus, for example, the emission of a first fluorescent agent can pass through the first filter (particularly blocked by the second filter) and be detected on a corresponding first sensor, and the emission of a second fluorescent agent can pass through the second filter (particularly blocked by the first filter) and be detected on a corresponding second sensor. For example, the first filter can be configured to measure the fluorescence emission of methylene blue, and the second filter can be configured to measure the fluorescence emission of ICG.

[0058] Measuring Equipment For the embodiment of the present invention, the fluorescent signal is also measured. measurement The same or similar advantages and advantageous aspects as mentioned for the method apply.

[0059] The first object is further solved by an endoscope or laparoscope, the endoscope or laparoscope being adapted to provide a method for treating a vascular endoscopic lesion according to one or more of the preceding embodiments. Measuring Equipment Advantageously, the imaging device is configured to function as an image capture device within the Measuring Equipment can be used in open surgery as well as during endoscopic or laparoscopic surgery. measurement Method and / or Measuring Equipment The same or similar advantages mentioned with respect to apply to endoscopes or laparoscopes in the same or similar manner.

[0060] The first object is a method for diagnosing lymphatic dysfunction, in particular lymphedema, comprising: administering a fluorescent agent to a body part; - measuring a fluorescent signal in tissue of the body part to which a fluorescent agent has been administered and imaging a surface of the body part, the tissue to which the fluorescent agent has been administered forming part of the body part; capturing a fluorescence image by illuminating the tissue with excitation light having a wavelength suitable to produce light emitted by excited emission of the fluorescent agent to provide a fluorescence image, and by spatially resolved measurement of the emitted light; capturing a visible light image of a surface of the body part within an examination area, the viewing directions and / or viewpoints of the fluorescent image and the visible light image being linked via a known relationship; repeating the step of capturing a fluorescence image to capture a plurality of fluorescence images over time to provide a time series of fluorescence images; In particular, repeating the step of capturing a visible light image to capture a plurality of visible light images over time to provide a time series of visible light images; - determining a peak frequency map of a region of interest in the fluorescent images by analyzing a time series of fluorescent images, the analysis comprising: determining a time-dependent intensity curve of at least one pixel within the region of interest; identifying a peak in the time dependent intensity curve; and determining the frequency of the identified peaks and / or the maximum height of the identified peaks; generating a graphical representation of the determined frequency and / or maximum height for at least one pixel and including the graphical representation in a peak frequency map; determining, - outputting a peak frequency map together with the visible light image and / or the fluorescent image; - deriving a diagnostic result regarding lymphatic dysfunction, in particular lymphoedema, in particular regarding the severity or level of lymphatic dysfunction, in particular lymphoedema, by analyzing the fluorescence images and the peak frequency map; The problem is further solved by a method comprising:

[0061] Advantageously, the method of diagnosing lymphedema can be performed with higher accuracy and reliability, thus providing improved diagnostic results. The entirely new approach can advantageously replace the classical method of diagnosing lymphedema. The conventional method of diagnosing lymphedema is to perform a manual examination of the affected body part by a physician. However, this method is inevitably influenced by the physician's personal experience and qualifications. The method of diagnosing lymphedema according to an aspect of the present invention overcomes this influence. Thus, the results are more reproducible and reliable.

[0062] The method can be further improved in that the steps of capturing a fluorescence image and capturing a visible light image are performed simultaneously, particularly if there is no time switching between the fluorescence image signal and the visible light image signal.

[0063] The method is advantageously improved in that the fluorescent agent is administered to the patient's arm or leg by injecting the agent into the interphalangeal tissue of the patient's foot or hand.

[0064] The first object is to provide a method for the long-term treatment of lymphatic dysfunction, in particular lymphedema, comprising: - performing a diagnosis of lymphatic dysfunction, in particular lymphoedema, in a patient by carrying out the steps of the method for diagnosing lymphatic dysfunction, in particular lymphoedema, as described above; administering a therapy to the patient, the therapy being adjusted depending on the diagnosis regarding lymphatic dysfunction, in particular lymphedema; - repeating the steps of diagnosing lymphatic insufficiency, in particular lymphoedema, and administering a therapy to the patient, where in each iteration the therapy is adjusted according to the diagnosis of lymphatic insufficiency, in particular lymphoedema, and further in particular the severity or level of the lymphatic insufficiency, in particular lymphoedema; The problem is also solved by a method comprising:

[0065] The method of long-term therapy according to the aspects of the present invention is particularly useful because the diagnosis of lymphatic dysfunction, particularly lymphedema, provides an objective result regarding the severity of the disease, in contrast to conventional methods. The success of the long-term treatment therapy can be analyzed from an objective perspective. This greatly improves the therapy and the success of the therapy.

[0066] The second objective is to provide risk prediction values ​​based on the measurement of fluorescent signals in tissues of body parts to which fluorescent agents have been added. Providing risk prediction values This method is used to solve the problem. Providing risk prediction values How to do it 、 firefly Excitation of fluorescent agents to provide optical images Initiation Illuminating the tissue with excitation light having a wavelength suitable for producing photoemitted light. death, capturing at least one fluorescence image within the examination area by spatially resolved measurement of the emitted light; 、 firefly repeating the step of capturing a fluorescence image to capture a plurality of fluorescence images over time to provide a time series of light images; Multiple Fluorescence images Few defining at least one calculation region in at least one fluorescence image; 、 total calculating a time-intensity curve from the signal intensities in the calculation region; 、 Small approximating the time-intensity curve with a model having at least one coefficient and determining at least one coefficient associated with the approximation of the model to at least a portion of the time-intensity curve; With an input interface, an artificial intelligence model, and an output interface To the processor input interface At least one coefficient Steps to be taken and, P The processor applies at least one coefficient to the AI ​​model. death, From the output of the AI ​​model, a risk prediction value indicating tissue perfusion within the computational domain is generated as output data in the output interface. Recommended Execute logical operation Rus Tep and 、 Yu communicating the risk prediction via a user interface; Includes.

[0067] Advantageously, the artificial intelligence model improves the analysis of the coefficients of the model applied to approximate the time-intensity curve. For example, the model is fitted to the time-intensity curve. The coefficients of the model thus describe the best fit of the model to the shape of the time-intensity curve. Because the coefficients of the model are not directly linked to the underlying biological processes, it is often difficult for medical staff to interpret these coefficients to give meaning in terms of medical indicators such as treatment success or future therapeutic measures. The artificial intelligence model can be trained to output risk prediction values ​​that are easy to interpret for medical staff.

[0068] For this purpose, an artificial intelligence model, for example a neural network, can be trained using training data for which the clinical outcome is known. The training data can be derived from patient records. The neural network is trained in supervised learning, and both types of supervised learning, classification and regression, can be applied. Regression is typically used to predict a continuous output value, and classification is used to predict a particular class of output. The continuous value and the class are linked to the clinical outcome of the patient data used to train the AI ​​model.

[0069] According to an advantageous embodiment, the present Providing risk prediction values How to do it 、 total Defining a computational domain; 、 time calculating the interfacial strength curve; 、 M approximating a time-intensity curve by a model and determining at least one coefficient; 、 Small providing at least one coefficient to an input interface of a processor; 、 A The step of executing an inference operation based on the I-model and generating and outputting a risk prediction value is It is performed for multiple calculation regions, in particular for each pixel or voxel of the fluorescence image, Books Providing risk prediction values How to do it 、 Multiple converting the risk predictions over a number of computational domains into a risk prediction derivation image map; 、 Yu outputting the risk prediction value derived image map via a user interface; Further includes:

[0070] The possibility to define a specific computational region, which may be a region of interest where tissue perfusion is to be analyzed, is advantageous, since, for example, during surgery or after a surgical procedure, a specific critical region of the surgical field may be analyzed. A complete analysis of the fluorescence image, which means an analysis on a pixel basis, gives the maximum possible information, but may be demanding in terms of computational power. The conversion of the risk prediction value, for example, into a color scale, facilitates the interpretation of the image, which is the risk prediction value derivation image map. This can be output or displayed in combination with a visible light image showing the surgical field.

[0071] Therefore, this Providing risk prediction values How to do it 、 Inspection capturing at least one visible light image of a surface of the body part within the scan area. P and , outputting the risk prediction value and the visible light image via a user interface; Further including fruit, The viewing direction and / or viewpoint of the fluorescent and visible light images are linked via a known relationship. This can be further improved.

[0072] In yet another advantageous aspect, the present invention Providing risk prediction values How to do it 、 Inspection capturing at least one visible light image of a surface of the body part within the scan area. P and Yu outputting the risk prediction value derivation image map as an overlay image together with the visible light image via a user interface; Further including fruit, The viewing direction and / or viewpoint of the fluorescent and visible light images are linked via a known relationship. .

[0073] Advantageously, a direct link between the visible light image and the risk prediction value and the risk prediction value derived image map, respectively, can be provided, which makes it easy to assign a particular finding, e.g., a particular risk prediction value, to a particular point or region within the surgical field.

[0074] According to yet another advantageous aspect, the steps of capturing the fluorescent image and the visible light image are performed simultaneously. In particular, the images are acquired without time switching between the signals of the fluorescent image and the visible light image. The simultaneous capture of images provides a direct link between the fluorescent and visible light imaging and values ​​derived from the fluorescent image, in particular risk prediction values. As the images are captured at the same time, also highly dynamic areas of the examination can be analyzed.

[0075] According to yet another advantageous embodiment, the model applied to approximate the time-intensity curve is a single tissue compartment model, in particular the Adiabatic Approximation to Tissue Homogeneity (AATH) model.

[0076] The AATH model was found to best explain the time-intensity curves, and is therefore a very suitable model for predicting clinical outcomes.

[0077] Furthermore, according to another advantageous embodiment of the present invention, the artificial intelligence (AI) model is a pre-trained neural network, in particular a supervised training based on clinical patient data. In A pre-trained neural network.

[0078] Training the neural network on clinical patient data results in an AI model with high quality in terms of the confidence level of the risk prediction value. In other words, the training of the AI ​​model is important in terms of the confidence level of the risk prediction value.

[0079] The objective of this study is to develop a computer-based clinical decision support system (CDSS) to provide risk prediction values ​​based on the measurement of fluorescent signals in tissues of body parts to which a fluorescent agent has been added. ) This is further resolved and the CDSS is 、 firefly Photochemical stimulation Initiation an illumination unit configured to illuminate the tissue with excitation light having a wavelength suitable for generating light emitted by the tissue; 、 firefly Excitation of fluorescent agents to provide optical images Initiation Illuminating the tissue with excitation light having a wavelength suitable for producing photoemitted light. death, configured to capture at least one fluorescence image within the examination region by spatially resolved measurement of the emitted light. 、 a fluorescence imaging unit further configured to capture a plurality of fluorescence images over time to provide a time series of fluorescence images; a processor having an input interface, an artificial intelligence model, and an output interface; Processing Device and , a user interface; The processing device Multiple Fluorescence images Fewdefining at least one calculation region within at least one of the fluorescent images; 、 total Calculating the time-intensity curve from the signal intensity in the calculation area 、 Small approximating the time-intensity curve with a model having at least one coefficient and determining at least one coefficient associated with the approximation of the model to at least a portion of the time-intensity curve; 、 Small At least one coefficient is provided to the input interface of the processor. Toto , configured to 、 P The processor applies at least one coefficient to the AI ​​model. death, A risk prediction value indicating tissue perfusion within the computational domain is generated from the output of the AI ​​model as output data in the output interface. Recommended and configured to perform logic operations and communicate the risk prediction value to a user interface. R, User Interface is configured to display the risk prediction value. R .

[0080] For CDSS, provide a predicted value Providing risk prediction values The advantages mentioned above with respect to the method apply in the same or similar manner and, with this in mind, they will not be repeated.

[0081] CDSS is a processing device 、 total Defining the computational domain 、 time Calculate the interfacial strength curve 、 M and approximating the time-intensity curve by the model and determining at least one coefficient. 、 Small providing at least one coefficient to an input interface of a processor; 、 recommendation Execute logical actions based on AI models 、 For multiple computational regions, in particular for each pixel or voxel of a fluorescence image, Risk prediction value Generate and output 、 Multiple Transforming the risk prediction values ​​over a number of computational domains into a risk prediction value derivation image map; 、 R Communicating the image map derived from the predicted image to a user interface. Toto , To do In Made R, The user interface displays a risk prediction value derivation image map. This can be further improved.

[0082] Furthermore, according to another advantageous embodiment, the CDSS comprises 、 Inspection and a visible light imaging unit configured to capture at least one visible light image of a surface of the body part within the examination area. The viewing direction and / or viewpoint of the fluorescent and visible light images are linked via a known relationship. 、 Processing The processing device is further configured to output the risk prediction value and the visible light image to a user interface. 、 Yu A user interface is configured to display the risk prediction value and the visible light image. do.

[0083] CDSS is a system 、 Inspection and a visible light imaging unit configured to capture at least one visible light image of a surface of the body part within the examination area. The viewing direction and / or viewpoint of the fluorescent and visible light images are linked via a known relationship. 、 ProcessingThe processing device is further configured to output the risk prediction value derived image map and the visible light image to a user interface. 、 Yu The user interface is configured to display the risk prediction value derived image map as an overlay image with the visible light image. ,and It can be further improved in that respect.

[0084] Furthermore, the fluorescence imaging unit and the visible light imaging unit may be configured to capture the fluorescence image and the visible light image simultaneously, particularly where there is no time switching between the fluorescence image signal and the visible light image signal.

[0085] According to yet another advantageous aspect, the fluorescence imaging unit and the visible light imaging unit are configured to simultaneously capture a fluorescence image and a visible light image, in particular, said units being configured to capture the respective images in the absence of time switching between the signals of the fluorescence image and the signals of the visible light image.

[0086] According to yet another advantageous aspect of the invention, the processing device comprises a model applied to approximate the time-intensity curve, which is a single tissue compartment model, in particular the adiabatic approximation to tissue homogeneity (AATH) model.

[0087] In addition, CDSSs allow the processing device to use pre-trained neural networks, specifically supervised training based on clinical patient data. In It can be improved in that it includes an artificial intelligence (AI) model that is a pre-trained neural network.

[0088] The first and second objectives are to develop a combined method, Measuring Equipment , as well as by computer-based clinical decision support systems (CDSSs).

[0089] According to yet another aspect of the present invention, a fluorescent signal is measured. measurementMethod and providing risk prediction value based on measurement of fluorescent signal Providing risk prediction values The combined method has a common step of measuring a fluorescent signal in tissue of the body part to which a fluorescent agent has been added and imaging a surface of the body part; P The method includes the common step of: - Excitation of fluorescent agents to provide fluorescent images Initiation capturing at least one fluorescence image in the examination region by illuminating the tissue with excitation light having a wavelength suitable for generating light emitted by the tissue and by spatially resolved measurement of the emitted light; - capturing at least one visible light image of a surface of a body part within an examination area, the viewing directions and / or viewpoints of the fluorescence image and the visible light image being linked via a known relationship; - repeating the step of capturing a fluorescence image to capture a plurality of fluorescence images over time to provide a time series of fluorescence images; - repeating the step of capturing visible light images to capture a plurality of visible light images over time, in particular to provide a time series of visible light images; Further comprising: Further, the combined method comprises a first group of the following steps for determining a peak frequency map: - determining a peak frequency map of a region of interest in the fluorescent images by analysing a time series of fluorescent images, determining a time-dependent intensity curve of at least one pixel within the region of interest; identifying peaks in the time dependent intensity curve and determining a frequency of the identified peaks and / or a maximum height of the identified peaks; generating a graphical representation of the determined frequency and / or maximum height for at least one pixel and including the graphical representation in a peak frequency map; determining by performing - outputting a peak frequency map together with the visible light image and / or the fluorescent image; Including, Additionally, the combined method may include a second group of the following steps for providing a risk prediction value: - defining at least one calculation region in at least one fluorescence image of the sequence of fluorescence images; - calculating a time-intensity curve from the signal intensities in a calculation area; - approximating the time-intensity curve by a model having at least one coefficient and determining at least one coefficient associated with the approximation of the model to at least a portion of the time-intensity curve; - providing at least one coefficient to an input interface of a processor, the processor including an input interface, an artificial intelligence (AI) model, and an output interface; - executing an inference operation by applying at least one coefficient to an AI model and generating, from an output of the AI ​​model, a risk prediction value indicative of tissue perfusion in the computational domain as output data at an output interface; - communicating the risk prediction value via a user interface; Includes.

[0090] According to a further aspect of the invention, the first group of steps may further comprise the method steps described as embodiments for solving the first object, and the second group of steps may further comprise the method steps described as embodiments for solving the second object.

[0091] In another aspect of the invention, a combination Measuring Equipment as well as computer-based clinical decision support systems (CDSSs). Measuring Equipment is configured to measure a fluorescent signal in tissue of the body part to which a fluorescent agent has been added and to image a surface of the body part, the tissue to which the fluorescent agent has been added forming part of the body part; Measuring Equipment teeth, -Excitation of fluorescent agents Initiation an illumination unit configured to illuminate the tissue with excitation light having a wavelength suitable for generating light emitted by the tissue; - Excitation of fluorescent agents to provide fluorescent images Initiation a fluorescence imaging unit configured to capture a fluorescence image in the examination region by illuminating the tissue with excitation light having a wavelength suitable for generating light emitted by the tissue and by spatially resolved measurement of the emitted light; - a visible light imaging unit configured to capture a visible light image of a surface of the body part within the examination area, the viewing directions and / or viewpoints of the fluorescence image and the visible light image being linked via a known relationship; an image capture device including the fluorescence imaging unit is further configured to capture a plurality of fluorescence images over time to provide a time series of fluorescence images; In particular, the visible light imaging unit is configured to capture a plurality of visible light images over time to provide a time series of visible light images; - Measuring Equipment teeth, a peak frequency map unit configured to determine a peak frequency map of a region of interest in the fluorescence images by analysing a time series of fluorescence images, the peak frequency map unit comprising: determining a time-dependent intensity curve of at least one pixel within the region of interest; identifying peaks in the time dependent intensity curve and determining a frequency of said identified peaks and / or a maximum height of the identified peaks; generating a graphical representation of the determined frequency and / or maximum height for at least one pixel and including the graphical representation in a peak frequency map; a peak frequency map unit configured to perform an analysis including: an output unit configured to output a peak frequency map together with the visible light image and / or the fluorescence image;

[0023] The present invention further includes a processing device, 1. A computer-based clinical decision support system (CDSS) for providing a risk prediction value based on measurements of fluorescent signals in tissue of a fluorescently-doped body part, the fluorescently-doped tissue forming part of the body part, the CDSS comprising: -Excitation of fluorescent agents Initiation an illumination unit configured to illuminate the tissue with excitation light having a wavelength suitable for generating light emitted by the tissue; - Excitation of fluorescent agents to provide fluorescent images Initiation a fluorescence imaging unit configured to capture at least one fluorescence image in an examination region by illuminating the tissue with excitation light having a wavelength suitable for generating light emitted by the tissue and by spatially resolved measurement of the emitted light, a fluorescence imaging unit, the fluorescence imaging unit being further configured to capture a plurality of fluorescence images over time to provide a time series of fluorescence images; 1. A processing device, comprising: - defining at least one calculation region within at least one fluorescence image of the sequence of fluorescence images; - calculating a time-intensity curve from the signal intensities in a calculation area; - approximating the time-intensity curve with a model having at least one coefficient and determining at least one coefficient associated with the approximation of the model to at least a portion of the time-intensity curve; providing at least one coefficient to an input interface of a processor, the processing device including a processor further including an input interface, an artificial intelligence (AI) model, and an output interface; a processing device, the processor configured to perform an inference operation by applying at least one coefficient to an AI model and by generating a risk prediction value indicative of tissue perfusion in a computational domain from an output of the AI ​​model as output data at an output interface, and to communicate the risk prediction value to a user interface; - the CDSS further comprises a user interface configured to display the risk prediction value.

[0092] In the combined system, Measuring Equipment And the CDSS may share hardware of similar or identical units, for example, an illumination unit, a fluorescence imaging unit, a visible light unit, and a processing device.

[0093] According to a further aspect of the present invention, Measuring Equipment The CDSS may further include the features described as embodiments for solving the first object. The CDSS may further include the features described as embodiments for solving the second object.

[0094] The solutions to the first and second objectives are linked in that both provide improved solutions for perfusion analysis in tissues of a body part. In particular, improved perfusion analysis of lymphatic fluid can be provided.

[0095] Further features of the invention will become apparent from the description of embodiments according to the invention in conjunction with the claims and the accompanying drawings, which can embody individual characteristics or a combination of several characteristics.

[0096] The present invention is described below on the basis of exemplary embodiments, without limiting the general spirit of the invention, and explicit reference is made to the drawings for the disclosure of all details according to the invention that are not described in more detail herein. [Brief description of the drawings]

[0097] [Figure 1] Schematic diagram of the measurement device. [Diagram 2] 1 is a schematic diagram of an image capture device and a processing unit. [Diagram 3] Time-dependent intensity curve. [Figure 4] Overlay image of visible light image and frequency map. [Diagram 5]Frequency map in pseudocolor plot. [Figure 6] Overlay image of visible light image and maximum value map. [Figure 7] Maximum map in pseudocolor plot. [Figure 8] An example of a visible light image and a corresponding fluorescence image. [Figure 9] A large overlay image generated in part from the visible light and fluorescent images shown in Figure 8. [Figure 10] Schematic diagram showing the internal prism assembly of the image capture device. [Figure 11] 1 is a schematic diagram of an endoscope or laparoscope including an image capture device. [Figure 12] 1 is a flowchart of the stitching algorithm. [Figure 13] 1 is a schematic diagram showing another internal prism assembly of an image capture device. [Figure 14] Time-intensity curve of the fluorescent signal. [Figure 15] Schematic of an inspection area with a defined computational domain. [Figure 16] Schematic diagram of a computer-based clinical decision support system (CDSS) for providing risk prediction values ​​based on the measurement of fluorescent signals. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0098] In the drawings, elements of the same or similar type or respective corresponding parts are provided with the same reference numbers, in order not to have to reintroduce the items.

[0099] FIG. 1 illustrates a fluorescent light source configured to measure fluorescent signals in tissue of a body part 4 of a patient 6. Measuring Equipment2 is shown. Purely by way of example, the examined body part 4 of the patient 6 is the arm. The measurement of the fluorescent signal can also be performed on other body parts 4 of the patient 6, for example the leg, parts of the head, the neck, the back or any other part of the body. This measurement can also be performed during an open surgery. In this application scenario, the body part 4 can for example be an internal organ of the patient 6. The measurement of the fluorescent signal can also be performed during a minimally invasive surgery. In this application scenario, Measuring Equipment 2 is at least partially integrated into, for example, an endoscope or laparoscope, which includes image capture device 10. Details of endoscopes are described further below.

[0100] Before starting a measurement for the first time, a fluorescent agent 8 is administered or injected into the tissue of the patient's body part 4 . Measuring Equipment 2, which will also be described with reference to FIG. 2, measurement The method excludes the step of administering a fluorescent agent 8.

[0101] The fluorescent agent 8 is, for example, ICG. ICG (indocyanine green) is a green medical dye that has been used for over 40 years. ICG emits fluorescence when excited with near-infrared light having a wavelength of 600 nm to 800 nm. The emitted fluorescence is 750 nm to 950 nm. Another suitable fluorescent agent 8 is methylene blue. The fluorescent agent 8 may also include two different medical dyes. For example, the fluorescent agent 8 may be a mixture of methylene blue and ICG.

[0102] Following administration of the fluorescent agent 8, the patient's body part 4 is Measuring Equipment 2. The inspection is carried out using an image capture device 10 which forms part of the optical fiber 10.

[0103] The image capture device 10 is configured to image a surface 11 of the body part 4 and to detect a fluorescent signal resulting from illumination of the fluorescent agent 8 by the excitation light. When the image capture device 10 is applied in surgery, the surface 11 of the body part 4 is, for example, a surface of an internal organ. In this case, the surface 11 of the body part 4 is identical to the surface of the tissue to which the fluorescent agent 8 has been administered. For the emission of light having a suitable excitation wavelength, the image capture device 10 comprises an illumination unit 16 (not shown in FIG. 1 ).

[0104] The captured image is Measuring Equipment 2. The results of the analysis are output, for example displayed on a display 14 of the processing device 12. The image capture device 10 can be handled by a physician 3.

[0105] Figure 2 shows Measuring Equipment 1 is a schematic diagram showing the image capture device 10 and the processing unit 12 of FIG. 2 in more detail. The image capture device 10 includes an illumination unit 16 configured to illuminate the tissue with excitation light having a wavelength suitable for exciting the emission of the fluorescent agent 8, thereby generating fluorescence. The illumination unit 16 is provided with, for example, a number of LEDs.

[0106] The image capture device 10 further includes an objective lens 18 through which the visible light and the fluorescent light are captured. The light is directed through the objective lens 18 to a prism assembly 20. The prism assembly 20 is configured to separate the fluorescent light, particularly in the wavelength range of 750 nm to 950 nm, from the visible light resulting in a visible light image. The fluorescent light is directed to a fluorescence imaging unit 22, which may be, for example, a CCD or CMOS sensor, optionally with additional wavelength filters and electronics. The fluorescent light imaging unit 22 is configured to capture the fluorescent image by spatially resolved measurement of the emitted light, i.e., the excited emission of the fluorescent agent 8, to provide a fluorescent image. In addition, there is a visible light imaging unit 24, which may be another CCD or CMOS sensor, optionally with additional different wavelength filters and electronics. The prism assembly 20 is configured to direct the visible light to the visible light imaging unit, so as to enable the visible light imaging unit 24 to capture a visible light image of a portion of the surface 11 of the patient's body part 4. Similarly, the prism assembly 20 is configured to direct the fluorescent light to the fluorescence imaging unit 22. Prism assembly 20, fluorescence imaging unit 22 and visible light imaging unit 24 are described in further detail below. Image data is communicated from image capture device 10 to processing device 12 via a suitable data link 26, which may be a wireless data link or a wired data link, such as a data cable.

[0107] The image capture device 10 is configured in that it operates the fluorescent imaging unit 22 and the visible light imaging unit 24 to capture visible light images and fluorescent images simultaneously. In particular, the image capture device 10 does not perform time switching between the signals of the fluorescent image and the visible light image. In other words, the sensors of the fluorescent imaging unit 22 and the visible light imaging unit 24 are dedicated to capture images in the respective wavelength ranges, which means that the sensors of the imaging units 22, 24 are used to capture fluorescent images in the IR spectrum or to capture visible light images in the visible spectrum. The sensors 22, 24 are not used to capture images in both wavelength ranges. This brings about significant advantages. For example, the sensors can be precisely positioned in focus, which is not possible when an image sensor is used for both purposes, i.e. to capture visible and infrared light, since the focus for these different wavelengths is typically differently positioned. Furthermore, the sensor parameters can be individually adjusted, for example with respect to the required exposure time or sensor gain. Since the IR signal is typically lower than the visible light signal, an individual setting is advantageous.

[0108] The fluorescent imaging unit 22 and the visible light imaging unit 24 have a fixed spatial relationship to each other because they are located in one single mounting structure or frame of the image capture device 10. Furthermore, the fluorescent imaging unit 22 and the visible light imaging unit 24 use the same objective lens 18 and prism assembly 20 for capturing the fluorescent and visible light images, respectively. With these measures, the fluorescent imaging unit 22 and the visible light imaging unit 24 are configured in that the viewing directions and viewpoints of the fluorescent and visible light images are linked via a known, fixed relationship. In a given embodiment, the viewing directions of the two images are identical because both units 22, 24 capture through the same objective lens 18.

[0109] The fluorescence imaging unit 22 is further configured to capture a plurality of fluorescence images over time. In other words, a time series of fluorescence images is captured. This time series of fluorescence images is subsequently analyzed by a peak frequency map unit 60. The peak frequency map unit 60 is part of the processing device 12. The peak frequency map unit 60 is configured to determine a peak frequency map by analyzing the time-dependent variations in intensity of pixels within a region of interest in the time series of fluorescence images. The analysis includes the following steps:

[0110] First, a region of interest 62 is defined in the fluorescence image. This region of interest can range from a single pixel to the full image of the fluorescence image. As an example, the region of interest is halfway between these two extremes. of( In b) there is a fluorescence image 7 in which a rectangular region of interest 62 is shown.

[0111] The peak frequency map unit 60 analyzes the intensity of the fluorescent signal in the region of interest 62. The intensity of every pixel in the region of interest 62 can be calculated. Based on this information, the peak frequency map unit 60 determines a time-dependent intensity curve that reflects the change in intensity of every pixel in the region of interest 62 over time.

[0112] FIG. 3 shows the time-dependent intensity curve for one arbitrary pixel in the region of interest 62. The signal intensity in arbitrary units is plotted against the frame number which is equal to time. By way of example only, the time-dependent intensity curve shows four main peaks located approximately at frame number 100, frame number 450, frame number 1000 and frame number 2000. The peaks can be identified by a gradient analysis. It is also possible to consider as peaks all intensity values ​​above a certain threshold, for example all values ​​above an intensity threshold equal to 50. The exact position of the peaks can again be determined by a gradient analysis. The peaks are identified by their position, in this case with respect to the frame number at which they are found, and by their maximum height, i.e. maximum signal intensity.

[0113] The peak frequency map unit 60 is further configured to determine a frequency of the identified peaks, which is a value of the number of peaks per unit time. The frequency of the peaks may be, for example, a value of peaks per 100 frames, peaks per 1000 frames, peaks per second, or any other suitable unit. Based on this information, the frequency of the identified peaks may be plotted in a graphical representation.

[0114] Figure 5 shows an illustration of a frequency map in a pseudocolor plot. In this case, the region of interest is the entire fluorescent image, and the peak analysis described above was performed for each pixel of the fluorescent image. The frequency of the identified peaks, meaning the number of peaks per unit time, is coded by the color of the pixel. The frequency values ​​can be binned into several classes or bins to reduce the number of colors and increase the clarity of the plot. Pixels of the same or similar value are classified into one bin, and the continuous area occupied by pixels in one bin can be surrounded by a margin line with the respective color. This is shown in Figure 5. It is clearly visible that in the center of the depicted image a high frequency of identified peaks can be found.

[0115] In a healthy lymphatic system, there is a rhythmic transport of lymph in the lymphatic vessels. This process leads to intensity oscillations in the fluorescence image. If the rhythmic contraction of the blood vessels is fast, this results in a high frequency of peaks. However, this intensity oscillation can only be found in certain areas of the fluorescence image, as can be seen in Figure 5. These areas often correspond to the location of the lymphatic vessels.

[0116] A graphical representation of the determined frequencies, i.e. a representation of the found frequencies as a pseudo-colour plot (see Fig. 5), is generated by a peak frequency map unit 60. The peak frequency map is output via an output unit 64 and displayed, for example, on the display 14. The peak frequency map is then added to the visible light image 5 (Fig. 8). (a) ) and / or fluorescent images 7 (Figure 8 (b)4. The peak / visible overlay image may also be output by the output unit 64 onto the display 14. The peak frequency map (see FIG. 5) and the fluorescent image (see FIG. 8) may also be output by the output unit 64. The peak frequency map (see FIG. 6) and the fluorescent image (see FIG. 9) may also be output by the output unit 64. The peak frequency map (see FIG. 7) and the fluorescent image (see FIG. 10) may also be output by the output unit 64. The peak frequency map (see FIG. 8) and the fluorescent image (see FIG. 11) may also be output by the output unit 64. The peak frequency map (see FIG. 9) and the fluorescent image (see FIG. 12) may also be output by the output unit 64. The peak frequency map (see FIG. 13) and the fluorescent image (see FIG. 14) may also be output by the output unit 64. The peak frequency map (see FIG. 14) and the fluorescent image (see FIG. 15) may also be output by the output unit 64. (b) The method may be further configured to calculate an overlay image that is a combination of the two images (see references).

[0117] In the embodiment described with reference to Figures 3, 4 and 5, the peak frequency map is a frequency map. According to a further embodiment described with reference to Figures 3, 6 and 7, the peak frequency map is a maximum value map.

[0118] For the determination of the maximum map, the time-dependent intensity curve shown in FIG. 3 is analyzed with respect to the maximum height or value of the identified peaks. In other words, for all pixels in the region of interest 62, the maximum value of the signal intensity is determined. This information regarding the maximum height of the peaks is contained in a maximum map, which in this case represents a peak frequency map. The maximum map is shown in a pseudocolor plot in FIG. 7. The maximum value of the peaks is calculated for each one of the pixels in the fluorescence image, which means that the region of interest 62 contains the complete image. The maximum map is calculated by a peak frequency map unit 60. It can be output by an output unit 64 together with the visible light image 5 or the fluorescence image 7. The maximum map, like the frequency map, can also be superimposed on the visible light image by a superimposition unit 66. This is shown in FIG. 6. According to another embodiment, the maximum map can be superimposed on the fluorescence image.

[0119] The image capture device 10 is further configured to operate the fluorescence imaging unit 22 and the visible light imaging unit 24 to repeat the capture of the fluorescence images and the visible light images to provide a series of fluorescence images and a series of visible light images. This operation can be performed by the processing device 12 operating the image sensor of the fluorescence imaging unit 22 and the image sensor of the visible light imaging unit 24. The series of images is typically captured while an operator or physician 3 (see FIG. 1 ) moves the image capture device 10 along the longitudinal direction L of the body part 4 of the patient 6. This movement can be performed in that subsequent images in the series of images include overlapping portions. In other words, details shown in a first image in the series of images are also shown in a subsequent second image in the series of images. This allows for a smooth transition of the images in the series of images. Stitching It is important for the process. To ensure that the corresponding features can be found in subsequent images, the frequency of image acquisition can be set to a sufficiently high value. The capture of images can be initiated manually, for example by the physician 3, or the capture of images can be controlled by the image capture device 10 in that the described requirements are met.

[0120] The image capture device 10 is configured to capture a time series of fluorescent images, which is not to be confused with the above-mentioned series of images showing different parts of the limb 4.

[0121] Once two series of images (i.e. a first series of visible light images and a second series of fluorescent images showing different parts of the limb 4) or a series of image pairs (each image pair including a fluorescent image and a visible light image) have been captured by the capture device 10 and received by the processing device 12, the series of visible light images may be Stitching It is processed by unit 28 (see FIG. 2). Stitching The unit 28 processes the sequence of visible light images to generate a large visible light image of the body part 4. Stitching The large image is "larger" in that it shows a larger portion of the body part 4 of the patient 6 being analyzed with the image capture device 10 than a single image.

[0122] Stitching The algorithm is Stitching Start from. Stitching The algorithm is: Stitching When you perform an operation Stitching Generate and apply a set of parameters. Stitching The detailed operation of unit 28 is described further below. Stitching Unit 28 is used to generate a series of visible light images as well as a series of fluorescent images to produce a large fluorescent image. Stitching The algorithm is adapted to apply the fluorescence image sequence to the fluorescence images. In the fluorescence images, a time series of fluorescence images is available. Furthermore, there is a series of fluorescence images comprising images captured at different parts of the limb 4. Stitching In the , you can select only one fluorescence image or the average fluorescence image from the time series and use this image for subsequent Stitching This may be a suitable technique to use in the process.

[0123] Fluorescence images Stitching applies to Stitching The algorithm is Stitching In addition, the same algorithm is used for the fluorescence image. Stitching is the visible light image Stitching It was determined when running Stitching This is possible because there is a fixed relationship between the viewing direction and viewpoint of the visible light and fluorescent images. Of course, if the viewing direction and viewpoint of the visible light and fluorescent images are not identical, a fixed offset or Stitching A shift in parameters must be applied, which takes into account the known and fixed spatial relationship between the IR and Vis image sensors and the corresponding optics.

[0124] StitchingFollowing this, a large visible light image and a large fluorescence image are output. This output is complemented with the output of a peak frequency map. For example, the images and the peak frequency map are displayed side by side on the display 14. Unlike conventional examination systems, the display 14 shows the mutually corresponding visible light image and fluorescence image as well as the peak frequency map. In other words, details that are visible on the fluorescence image or the peak frequency map, for example high fluorescence intensity or frequency indicating lymphatic fluid accumulation or high lymphatic fluid transport, can be found in the visible light image. This allows the physician 3 to precisely locate, for example, areas where lymphatic fluid accumulation is present. This is highly useful information for a tailored specific therapy of the patient 6, for example.

[0125] The visible light image and the fluorescent image, in particular the large visible light image and the large fluorescent image, can also be superimposed to provide an overlay image, in particular a large overlay image, of the body part 4. This is also performed by a superimposition unit 30 of the processing device 12. The overlay image can also be output via the display 14.

[0126] Figure 8 of( a) shows an example of a visible light image 5 in which a portion of the surface 11 of a body part 4 of a patient 6 is visible. By way of example only, a portion of the patient's leg is shown. of( b) shows the corresponding fluorescence image 7 determined by measuring the fluorescence signal of a fluorescent agent 8 applied to the tissue of the patient's leg. High intensity spots or areas of the fluorescence signal are visible, which strongly indicate lymphatic accumulation due to slow lymphatic transport and possible lymphedema in the patient's leg. Advantageously, the physician 3 can localize the areas where slow lymphatic transport occurs by comparing the fluorescence image 7 with the visible light image 5. of( In b), a region of interest 62 is indicated by a rectangle. The analysis of the time-dependent fluorescence intensity in this region 62 is explained with reference to figures 3 to 7.

[0127] In FIG. 9, there is an overlay image 9 of a visible light image 5 and a fluorescent image 7. of( a) and Figure 8 of( In addition to the image shown in b), visible light image 5 and fluorescent image 7 are Stitching has been performed. Exemplary single visible light image 5 and fluorescence image 7 can also be seen in Figure 9, each projected between the straight dashed lines shown in a larger overlay image 9. By stitching together the visible light image 5 and the fluorescence image 7, a large overlay image 9 can be provided that shows substantially the entire body part 4 of the patient 6. The fluorescence signal can be shown in pseudocolor to clearly distinguish it from features in the visible light image 5.

[0128] In FIG. 10, there is an embodiment of the prism assembly 20 of the image capture device 10. The first prism P1 is a pentaprism. The incident light beam A, which is visible light and fluorescent light, enters the first prism P1 through the incident surface S1 and is partially reflected at the surface S2, which is one of the two surfaces not adjacent to the incident surface S1. The reflected beam B is then reflected against the first surface of the surfaces adjacent to the incident surface S1. The reflection angle may be less than the critical angle, so the reflection is not internal (the adjacent surface may be coated to avoid light leakage and reflect the required wavelengths of interest). The reflected beam C then intersects with the incident light beam A and exits the first prism P1 through the second surface of the surfaces adjacent to the incident surface S1 toward the sensor D1. A portion of the beam A passes through the surface S2 and enters the compensation prism P2. Two non-internal reflections can be used to direct the incident beam A to the sensor D1 via beams B and C. Additionally, there may be no air gap between prisms P1 and P2, no air gap between prisms P3 and P4, and no air gap between prisms P2 and P3. Prism P2 is a compensator prism for adjusting the individual lengths of the optical paths from input face S1 to sensors D1-D5.

[0129] prismFrom P2, beam D enters the second pentaprism P3. As with prism P1, internal reflections are used to make the beam cross itself. For brevity, the description of the beams will not be repeated except to state that in prism P3, beam portions E, F and G correspond to beam portions A, B and C, respectively, in prism P1. Prism P3 also cannot use internal reflections to reflect the incident beam towards sensor D2. Two non-internal reflections can be used to direct incident beam E towards sensor D2 via beams F and G.

[0130] After prism P3 there is another compensation prism P4. Finally, beam H enters a dichroic prism assembly including prisms P5, P6 and P7 with sensors D3, D4 and D5 respectively. The dichroic prism assembly is for splitting the red, green and blue components of visible light towards the respective sensors D3, D4 and D5. The light enters the prism assembly through beam I. An optical coating C1 is placed between prisms P5 and P6, and another optical coating C2 is placed between prisms P6 and P7. Each optical coating C1 and C2 has a different reflectivity and wavelength sensitivity. Optical Coatings At C1, the incident beam I is partially reflected (beam J) back to the same face of the prism from which it entered. At that same face, a beam now labeled K is reflected once again towards sensor D3. beam From J beam The reflection to K is an internal reflection. Thus, sensor D3 receives light reflected by coating C1, similarly sensor D4 receives light from beam L (beams M and N) reflected by coating C2, and sensor D5 receives light from beam O that traversed the prism unimpeded.

[0131] There is an air gap between prisms P4 and P5. In prism assembly 20, the following total path lengths can be defined for each endpoint channel (defined with respect to the sensor at the end of the channel): Sensor D1 (e.g., first near-infrared) path: A+B+C Sensor D2 (e.g., second near-infrared) path: A+D+E+F+G Sensor D3 (e.g., red) path: A+D+E+H+I+J+K Sensor D4 (e.g., blue) Path: A+D+E+H+I+ L+M+N Sensor D5 (e.g., green) Path: A+D+E+H+I+ L+O

[0132] The path length is A+B+C=A+D+E+F+G=A+D+E+H+l+J+K=A+D+E+H+l+ L+M+N =A+D+E+H+I+ L+O The equation is adjusted so that

[0133] Matching the path lengths can include adjusting the focal plane focus position difference of the wavelengths detected at the sensors D1-D5. That is, for example, the path length to a sensor for blue (B) light may not be exactly the same as the path length to a sensor for red (R) light, because the ideal distance to produce a sharply focused image depends to some extent on the wavelength of the light. The prisms can be configured to allow for these dependencies. The length of D+H can be adjusted by lateral displacement of the compensator prisms P2, P4, which can act as wavelength shift focus compensators.

[0134] The larger air gap in path I can be used for additional filters or can be filled with glass compensators for focus shift and compensation. Due to internal reflections in the path from beam J to beam K, an air gap needs to exist at that particular bottom surface of the red prism. Space can be reserved between the prism output surface and each of the sensors D1-D5 to provide additional filters or should be filled with glass compensators accordingly.

[0135] Sensors D1 and D2 are IR sensors configured for capturing the fluorescence image 7. As an example, sensors D1 and D2 plus suitable electronics are part of the fluorescence imaging unit 22. Sensors D3, D4 and D5 are for capturing the three components of the visible light image 5. As an example, sensors D3, D4 and D5 plus suitable electronics are part of the visible light imaging unit 24. It is also possible to consider corresponding prisms that direct light beams to the sensors that are part of the respective units, i.e., the fluorescence imaging unit 22 and the visible light imaging unit 24.

[0136] 11 shows a schematic diagram of an endoscope 50 or laparoscope according to an embodiment of the present invention. In view of the aspects of the present invention, the difference between a laparoscope and an endoscope is relatively small. Thus, where the description refers to an endoscope, a laparoscopic configuration is generally also possible. By way of example only, in the following, reference will be made to the endoscope 50.

[0137] Endoscope 50 includes image capture device 10, described in more detail above. Image capture device 10 includes objective lens 18 through which fluorescence image 7 and visible light image 5 are captured. Objective lens 18 focuses light incident on entrance face S1 of prism assembly 20 onto sensors D1-D5. Objective lens 18 may also be integrated into the last portion of the endoscope section to match the back focal length of the prisms.

[0138] The endoscope 50 includes an optical fiber 52 connected to a light source 54 that couples light into the endoscope 50. The light source 54 can provide white light for illumination of the surface 11 of the body part 4 and capture of the visible light image 5. Furthermore, the light source 54 can be configured to emit excitation light suitable for exciting a fluorescent dye applied as a fluorescent agent to emit fluorescence. In other words, the light source 54 can be configured to emit both visible light and light in the IR spectrum.

[0139] Inside the shaft 56 of the endoscope 50, the optical fiber 52 splits into several fibers 51. The endoscope 50 can have a flexible shaft 56 or a rigid shaft 56. In the rigid shaft 56, a lens system consisting of lens elements and / or relay rod lenses can be used to guide the light through the shaft 56. If the endoscope 50 has a flexible shaft 56, the fiber 51 can be used to guide the light of the light source 54 to the tip of the endoscope shaft 56. A fiber bundle 58 is arranged in the shaft 56 of the endoscope 50 to guide the light coming from the examination area from the distal tip of the endoscope shaft 56 (not shown in FIG. 6 ) to the image capture device 10 at the proximal end of the shaft 56. In another embodiment not shown in the figures, the entire image capture device 10 can be miniaturized and placed at the distal tip or end of the endoscope shaft 56.

[0140] Figure 12 can be used to stitch visible light and fluorescent images. Stitching The algorithm flowchart is shown. The flowchart is more or less self-explanatory and very simply explained. First, a series of acquired images (S1) is processed by the processing device 12. Stitching The frame preselection is then performed (step S2). In this preselection step: Stitching The frame suitable for S3 is selected. Stitching The images represent the selected images to be processed, which then undergo pre-processing (step S4). On the pre-processed images (S5), feature extraction is performed (step S6). Once image features have been extracted (S7), image matching (step S8) is performed using the known images from S3 and the features extracted from step S7. Based on the selected images (S9), the transformation of the image is estimated (step S10). StitchingAn estimate of this image transformation (S11), also called parameters, is applied (step S12). Application of the transformation results in a transformed image (S13). Further image corrections, e.g. exposure correction (step S14), can be performed. The transformed and corrected images (S15) are stitched together by locating the seams (step S16), i.e. the lines where the images are stitched together. Data indicating the location of the seams (S17) are used together with the transformed and corrected images (S12) to create a composite of the images (step S18). In the given embodiment, this is done by: Stitching The result (S19) is a large visible light image or a large fluorescent image.

[0141] Furthermore, the image capture device 10 applied to capture the visible light image 5 and the fluorescence image 7 may further comprise a distance sensor 33 in communication with a measurement unit 32 located in the processing device 12. The distance sensor 33 is configured to measure a distance d (see FIG. 1 ) between the surface 11 of the patient's body part 4 captured in the visible light image 5 and the image capture device 10. The distance sensor 33 in communication with the measurement unit 32 is, for example, an ultrasonic sensor, a laser distance sensor, or any other suitable distance measuring device. Furthermore, the image capture device 10 is configured to output a signal indicative of the measured distance d. For example, the image capture device 10 outputs an optical or acoustic signal that gives the operator of the device 10 information about the best distance d for performing the measurement. Performing the measurement at a constant distance d significantly improves the measurement result, especially since there is a uniform illumination.

[0142] 13 is another embodiment of the prism assembly 20 of the image capture device 10. The prism assembly 20 includes prisms P5, P6, and P7, which are configured to split the light into red, green, and blue components, for example, toward the respective sensors D3, D4, and D5. According to a further embodiment, the prism assembly 20 is configured to split the incident light into a green, red / blue, and infrared component and direct them to the respective sensors D3, D4, and D5. According to yet another embodiment, the prism assembly 20 is configured to split the incident light into a visible light component that is directed to a red / green / blue sensor (RGB sensor), a first infrared component of a first wavelength or wavelength interval, and a second infrared component of a second wavelength or wavelength interval and direct them to the respective sensors D3, D4, and D5.

[0143] Light enters the prism assembly 20 through the arrows shown. prism An optical coating C1 is disposed between prisms P5 and P6, and an optical coating C2 is disposed between prisms P6 and P7, with each optical coating C1 and C2 having a different reflectance and wavelength sensitivity. Optical Coatings At C1, the incident beam I is partially reflected (beam J) onto the same face of prism P5 from which it entered. At that same face, a beam now labeled K is reflected once again towards filter F3 and sensor D3. beam From J beam The reflection to K is an internal reflection. Thus, filter F3 and sensor D3 receive light reflected by coating C1, and similarly, filter F4 and sensor D4 receive light from beam L (beams M and N) reflected by coating C2. Filter F5 and sensor D5 receive light from beam O that passes through the prism unimpeded.

[0144] When referring to an embodiment in which the incident light is split into red, green and blue components, the coatings and filters are selected accordingly.

[0145] In an embodiment where the incident light is separated into green, red / blue and infrared components, filter F3 can be a patterned filter (red / blue). In particular, there is an array of red and blue filters in an alternating pattern. The pattern can consist of a group of 2x2 pixels that are filtered for one particular color. Filter F4 can be a green filter, meaning that the filter only contains green filters. There is a single pixel grid, and the light received at each pixel is filtered with a green filter. Filter F5 can be an IR filter. Each pixel is filtered with an IR filter.

[0146] In general, coatings C1, C2 need to be matched to filters F3, F4, F5. For example, the first coating C1 can transmit visible light while reflecting IR light, so the IR light is directed towards IR filter F3. The second coating C2 can be transparent to green light while reflecting red and blue light, so filter F4 needs to be a red / blue patterned filter, filter F5 should be a green filter 23.

[0147] According to a further embodiment in which the incident light is split into a visible light component (RGB), a first infrared component and a second infrared component, the coatings C1, C2 and the filters F3, F4, F5 are configured in such a way that, for example, the sensor D4 is a color sensor (RGB sensor) for detecting all three color visible light images. Furthermore, the sensor D3 can be configured for detecting fluorescence of a first wavelength and the sensor D5 is configured for detecting fluorescence of a second wavelength.

[0148] Similarly, referring to the prism assembly 20 of FIG. 10, the faces S1, S2, S3, S4, coatings C1 and C2, and filters F1, F2, F3, F4, and F5 disposed in front of each one of the sensors D1, D2, D3, D4, and D5 can be configured in that they can detect up to four fluorescence wavelengths. For example, the sensor D4 is a color sensor for detecting visible light images of all three colors. The sensor D3 is for detecting fluorescence of a first wavelength or wavelength interval, the sensor D5 is for detecting fluorescence of a second wavelength or wavelength interval, the sensor D1 is for detecting fluorescence of a third wavelength or wavelength interval, and the sensor D2 is for detecting fluorescence of a fourth wavelength or wavelength interval.

[0149] As discussed above in relation to Figs. 1 and 2 Measuring Equipment 2 can also be applied to measure a fluorescent signal from which a time-intensity curve can be derived or calculated.

[0150] In the following a method for providing a risk prediction value based on measuring a fluorescent signal is described, the fluorescent signal being detected in tissue of a body part 4 to which a fluorescent agent 8 has been added, the tissue to which the fluorescent agent 8 has been added forming part of the body part 4.

[0151] At least one fluorescence image 7 is captured. The fluorescence image 7 is captured in the examination region by illuminating the tissue with excitation light having a wavelength suitable to generate light emitted by excited emission of the fluorescent agent 8. A spatially resolved measurement of the emitted light is performed to provide the fluorescence image 7. The step of capturing the fluorescence image 7 is repeated to capture a plurality of fluorescence images 7 over time and to provide a time series of the fluorescence images 7. At least one calculation region 80 is defined in at least one fluorescence image 7 of the sequence of the fluorescence images 7. In this calculation region 80, a time-intensity curve is calculated from the signal intensity in the calculation region 80.

[0152] FIG. 14 shows a time-intensity curve of the signal intensity in a calculation area 80. FIG. 15 shows a schematic diagram of the examination area, in which specific calculation areas 80 are shown, only some of which are given reference numbers. In the examination area there is an exemplary organ 82, in which a surgical procedure has been performed. For the risk assessment of the surgical procedure, a specific calculation area 80 is defined, in which a perfusion measurement is to be performed. In other words, at least one time-intensity curve, which is shown in principle in FIG. 14, can be calculated from each one of the calculation areas 80.

[0153] The time-intensity curve is approximated by a model having at least one coefficient. The model applied to the approximation of the time-intensity curve is, for example, a single tissue compartment model. In particular, the adiabatic approximation to tissue homogeneity (AATH) model has been found to be particularly suitable for approximating the time-intensity curve. The result of modeling the time-intensity curve is a best fit of the model to the shape of the time-intensity curve at least in a particular region or segment. From this best fit, at least one coefficient of the model can be determined.

[0154] At least one coefficient of the model is provided to an input interface of a processor 84 which forms part of a processing device 92. The processing device 92 may for example be a computer, a medical device or even be implemented in a computing cloud and is part of a computer-based clinical decision support system (CDSS), which is shown diagrammatically in FIG.

[0155] The CDSS 86 includes an image capture device 10, which is illustrated in detail in FIG. 2. The relevant input feature is at least one coefficient of a model to be fitted to the time-intensity curve. The coefficients are communicated to an input interface of a processor 84, and the 1st to Nth input features are coefficients 1 to N of the model used to fit the time-intensity curve. The processor 84 holds an AI model, e.g., a neural network. The processor 84 performs an inference operation by applying the at least one coefficient as an input feature to the AI ​​model. The output of the AI ​​model, meaning the predicted output from the AI ​​model inference operation, is a risk prediction value. The risk prediction value can be communicated to a user interface 88 together with a confidence score.

[0156] The user interface 88 may display risk prediction values ​​for a particular computation region 80. Additionally, a visible light image 5 may be displayed, for example, showing the organ 82, computation region 80, and associated risk values. Additionally, a risk prediction value may be calculated for each pixel of the fluorescence image 7. The plurality of risk prediction values ​​may be converted into a prediction value derivation image map. The image map may also be communicated via the user interface 88, for example, as an overlay image to the visible light image.

[0157] In particular, the fluorescent image 7 and the visible light image 5 may be captured simultaneously using an image capture device including a prism arrangement such as those shown in FIG. 10, FIG. 11 or FIG.

[0158] The AI ​​model is in particular a pre-trained neural network. This neural network can be trained using data of patient records 90 retrieved from a database. The patient records 90 include, for example, clinical outcomes of a particular operation. By this criterion, the time-intensity curve and the risk predictor are linked to a particular clinical outcome. These patient records can be used for supervised training of the neural network, which can be implemented as an AI model in the processor 84. In particular, the processing device 92 can further include the image capture device 10 and a user interface 88. It can also optionally include a database including the patient records 90.

[0159] 16 is a schematic diagram of an exemplary computer-based clinical decision support system (CDSS) configured to provide a risk prediction value based on at least one coefficient of a model applied to an approximation of the time-intensity curve provided at inference. In various embodiments, the CDSS 86 includes an input interface in which the at least one coefficient specific to the patient is provided as an input feature to an artificial intelligence (AI) model, a processor 84 that performs an inference operation in which the at least one coefficient is applied to the AI ​​model to generate a risk prediction value, and a user interface (UI) 88 in which the risk prediction value is communicated to a user, e.g., a clinician.

[0160] In some embodiments, the input interface may be a direct data link between the CDSS 86 and one or more medical devices, e.g., the image capture device 10, that generate at least some of the input features. For example, the input interface may transmit the input features directly to the CDSS 86 during a therapeutic and / or diagnostic medical procedure. Additionally or alternatively, the input interface may be a classic user interface that facilitates an interaction between a user and the CDSS 86. For example, the input interface 88 may facilitate a user interface through which a user may manually input at least one coefficient. Additionally or alternatively, the input interface may provide the CDSS 86 with access to an electronic patient record from which one or more input features may be extracted. In any of these cases, the input interface is configured to collect one or more of the following input features associated with a particular patient at or before the time the CDSS 86 is used to evaluate the coefficients of the model:

[0161] Time intensity curves can be extracted from the fluorescent image recording by calculating the average image intensity within each computational region 80 for each frame in the recording. Time intensity curves can be characterized by the following parameters: Time to Max(s): the time it takes for the signal to reach its maximum intensity starting from the beginning of the entry phase, Ingress(i / s): the average slope of the signal curve in the entry phase, Max Ingress(i / s): the value in the entry phase with the maximum slope, Time to Max Ingress(s): the timestamp from the beginning of the entry phase to the time with the maximum entry slope, Average(i): the average signal intensity, AUC(i·s): the area under the curve (AUC) of the signal curve, AUC10(i·s): the AUC between the beginning of the entry phase and 10 seconds thereafter, AUC Ingress(i·s): the AUC of the signal curve in the entry phase.

[0162] For example, the time-intensity curve shown in Figure 14 can be fitted by a single tissue compartment model, in particular by the adiabatic approximation to tissue homogeneity (AATH) model, described in principle in Lawrence & Lee, 1998, Elliot et al., 2020. Other fitting models could be Kang's model (Kang et al., 2009) or a biexponential model (Gurfinkel et al. 2000, Shinohara et al. 1996).

[0163] Each model contains several coefficients that may predict clinical outcome. An additional coefficient required for all models is the arrival time of the tracer, also called delay. This coefficient is fitted because the moment of fluorescent dye injection during the acquisition is not known. The coefficients fitted to the single tissue compartment model are: K1( / min), k2( / min) (additional parameter: delay (s)). The coefficients fitted to the AATH model are: F(ml / min / 100g), k ep ( / min), t c (s);E(additional parameter: delay(s)).

[0164] The goodness of fit of each model is measured using the adjusted R-squared (R 2adj ) The R2 statistic (also called the coefficient of determination) of a model is a value that indicates the proportion of variance in the data that is explained by the model.

[0165] The above coefficients can be applied to the AI ​​model as the 1st to Nth input features.

[0166] Based on one or more of the above input features, the processor 84 performs an inference operation using the AI ​​model to generate an output, i.e., a risk prediction value.

[0167] For example, an input interface can deliver one or more of the relevant input features to an input layer of an AI model, which propagates these input features through the AI ​​model to an output layer. AI models can provide computer systems with the ability to perform tasks without being explicitly programmed by making inferences based on patterns found in the analysis of data. AI models explore the research and construction of algorithms (e.g., machine learning algorithms) that can learn from existing data and make predictions on new data. Such algorithms operate by building AI models from example training data to make data-driven predictions or decisions, which are represented as outputs or evaluations.

[0168] There are two common modes of machine learning (ML): supervised ML and unsupervised ML. Supervised ML uses prior knowledge (e.g., examples correlating inputs to outputs or outcomes) to learn the relationships between inputs and outputs. The goal of supervised ML is to learn a function that best approximates the relationships between training inputs and outputs given some training data, so that an ML model can implement the same relationships given an input to produce a corresponding output. Unsupervised ML is the training of an ML algorithm using information that is not classified or labeled, allowing the algorithm to act on that information without guidance. Unsupervised ML is useful for exploratory analysis because it can automatically identify structures in the data.

[0169] Common tasks in supervised ML are classification and regression problems. Classification problems, also called categorization problems, aim to classify an item into one of several categorical values ​​(e.g., is this object an apple or an orange?). Regression algorithms aim to quantify some items (e.g., by providing a score for the value of some input). Some examples of commonly used supervised ML algorithms are logistic regression (LR), naive Bayes, random forest (RF), neural networks (NN), deep neural networks (DNN), matrix factorization, and support vector machines (SVM).

[0170] Some common tasks for unsupervised ML include clustering, representation learning, and density estimation. Some examples of commonly used unsupervised ML algorithms are K-means clustering, principal component analysis, and autoencoders.

[0171] Another type of ML is federated learning (also known as collaborative learning), which trains algorithms across multiple distributed devices that hold local data without exchanging data. This approach contrasts with traditional centralized machine learning techniques, where all local datasets are uploaded to one server, as well as more classical distributed approaches that often assume that local data samples are identically distributed. Federated learning allows multiple actors to build a common, robust machine learning model without sharing data, thus addressing critical issues such as data privacy, data security, data access rights, and access to heterogeneous data.

[0172] In a given embodiment, the AI ​​is trained in supervised learning.

[0173] In some examples, the AI ​​model may be trained continuously or periodically prior to execution of an inference operation by processor 84. Then, during the inference operation, patient-specific input features provided to the AI ​​model may be propagated from an input layer, through one or more hidden layers, and ultimately to an output layer that corresponds to a risk prediction value.

[0174] All named features, including those obtained only from the drawings, and individual features disclosed in combination with other features, are considered to be essential to the invention both alone and in combination. The embodiments according to the invention can be realized by individual features or by combinations of several features. Features combined with the words "in particular" or "especially" are treated as preferred embodiments. [Explanation of symbols]

[0175] 2 Measuring Equipment 3. Doctor 4 body parts 5 Visible light images 6 patients 7. Fluorescence Images 8 Fluorescent Agents 9. Overlay Images 10 Image capture devices 11 Surface 12 Processing Device 14 Display 16 Lighting Unit 18 Objective Lens 20 Prism Assembly 22 Fluorescence imaging unit 24 Visible light imaging unit 26 Data Links 28 Stitch Unit 30 Stacking Unit 32 Measurement Units 33 Distance Sensor 50 Endoscopy 52 Optical Fiber 51 Fiber 54 Light source 56 Shaft 58 Fiber Bundle 60 peak frequency map units 62 Areas of Interest 64 output units 66 Stacking Unit 80 Computational domain 82 Organs 84 processors 86 CDSS 88 User Interface 90 Patient Records 92 Processing Device P1 First pentaprism P2,P4 compensation prism P3 Second Pentaprism P5, P6, P7 Dichroic Prism Assembly A Incident light beam B ~ O Light beam S1 entrance plane D1 ~ D5 Sensor C1, C2 Coating L Longitudinal d Distance

Claims

1. 1. A method for measuring a fluorescent signal in tissue of a body part to which a fluorescent agent has been added and imaging a surface of the body part, comprising: - illuminating the tissue with excitation light having a wavelength suitable for generating emitted light by excitation emission of the fluorescent agent to provide a fluorescence image, and capturing at least one of the fluorescence images within an examination region by spatially resolved measurement of the emitted light; capturing at least one visible light image of a surface of the body part within the examination area; repeating the step of capturing a fluorescence image to capture a plurality of the fluorescence images over time to provide a time series of the fluorescence images; repeating the step of capturing a visible light image to capture a plurality of the visible light images over time to provide a time series of the visible light images; determining a peak frequency map of a region of interest within the fluorescent images by analyzing the time series of fluorescent images; and outputting the peak frequency map together with the visible light image and / or the fluorescent image; the viewing directions and / or viewpoints of the fluorescent image and the visible light image are linked via a known relationship; The step of determining the peak frequency map comprises: determining a time-dependent intensity curve of at least one pixel within said region of interest; identifying peaks in the time-dependent intensity curve and determining a frequency of the identified peaks and / or a maximum height of the identified peaks; generating a graphical representation of the determined frequency and / or maximum height for the at least one pixel and including the graphical representation in the peak frequency map.

2. The measurement method of claim 1, wherein the step of including the graphical representation in the peak frequency map includes generating an intensity plot showing the determined frequency and / or the maximum height of the identified peak at the location of the at least one pixel within the region of interest.

3. A method of detecting a peak frequency map and a fluorescence image, comprising the steps of: overlaying the peak frequency map and the fluorescence image to provide a peak / fluorescence overlay image; and outputting the peak / fluorescence overlay image together with the fluorescence image as an output of the peak frequency map; overlaying said peak frequency map and said visible light image to provide a peak / visible overlay image, and outputting said peak / visible overlay image together with said visible light image as an output of said peak frequency map; The method according to claim 2 , further comprising at least one of the following:

4. The measurement method of claim 1 , wherein the steps of capturing the fluorescent image and capturing the visible light image are performed simultaneously, with no time switching between the fluorescent image signal and the visible light image signal. repeating the steps of capturing fluorescence images and capturing visible light images to provide a series of fluorescence images and a series of visible light images; applying a stitching algorithm to the set of visible light images, wherein a set of stitching parameters is determined and applied to generate a larger visible light image; applying the stitching algorithm to the series of fluorescent images to generate a large fluorescent image; the series of fluorescent images and the series of visible light images depicting different overlapping regions of an examination of the body part; the stitching algorithm applied to the series of fluorescence images applies the set of stitching parameters determined when generating the large visible light image; The step of outputting the peak frequency map comprises: The method of claim 1 , further comprising outputting the large visible light image together with the large fluorescent image and the peak frequency map.

6. The measurement of the fluorescent signal is performed on tissue to which at least a first and a second fluorescent agent have been added; The step of capturing the fluorescence image includes: capturing a first fluorescence image in a first wavelength range produced by illuminating the tissue with a first excitation light having a first wavelength suitable for producing light emitted by a first excitation emission of the first fluorescent agent; capturing a second fluorescence image in a second wavelength range produced by illuminating the tissue with a second excitation light having a second wavelength suitable for producing light emitted by a second excitation emission of the second fluorescent agent; Including, 2. The measurement method of claim 1, wherein the steps of capturing a plurality of the fluorescent images over time, determining the peak frequency map, and outputting the peak frequency map are performed on the first and second fluorescent images.

7. 7. The measurement method of claim 6, wherein capturing the first fluorescent image and capturing the second fluorescent image are performed simultaneously when there is no time switching between the signal of the first fluorescent image and the signal of the second fluorescent image.

8. 1. A measurement device configured to measure a fluorescent signal in tissue of a body part to which a fluorescent agent has been added and to image a surface of said body part, comprising: an illumination unit configured to illuminate the tissue with excitation light having a wavelength suitable to generate light emitted by excitation emission of the fluorescent agent; a fluorescence imaging unit configured to illuminate the tissue with excitation light having a wavelength suitable for generating emitted light by excitation emission of the fluorescent agent to provide a fluorescence image, and to capture the fluorescence image within an examination area by spatially resolved measurement of the emitted light; a visible light imaging unit configured to capture a visible light image of a surface of the body part within the examination area; an image capture device comprising: the viewing directions and / or viewpoints of the fluorescent image and the visible light image are linked via a known relationship; the fluorescence imaging unit is further configured to capture a plurality of the fluorescence images over time to provide a time series of the fluorescence images; the visible light imaging unit is configured to capture a plurality of the visible light images over time to provide a time series of the visible light images; The measuring device is a peak frequency map unit configured to determine a peak frequency map of a region of interest within the fluorescence images by analysing the time series of fluorescence images; an output unit configured to output said peak frequency map together with said visible light image and / or said fluorescent image; a processing device comprising: The peak frequency map unit comprises: determining a time-dependent intensity curve of at least one pixel within said region of interest; identifying peaks in the time-dependent intensity curve and determining a frequency of the identified peaks and / or a maximum height of the identified peaks; generating a graphical representation of the determined frequency and / or maximum height for the at least one pixel and including the graphical representation in the peak frequency map.

9. The measurement apparatus of claim 8 , wherein the peak frequency map unit generates an intensity plot indicative of the determined frequency and / or the maximum height of the identified peaks at the location of the at least one pixel within the region of interest.

10. The processing device further comprises a superposition unit; the superposition unit is configured to be capable of executing at least one of a first superposition process and a second superposition process; the output unit is configured to be capable of executing at least one of a first output process and a second output process; the first registration process is a process of registering the peak frequency map and the fluorescence image to provide a peak / fluorescence overlay image; the first output process being a process of outputting the peak / fluorescence overlay image together with the fluorescence image as an output of the peak frequency map; the second registration process is a process of registering the peak frequency map and the visible light image to provide a peak / visible overlay image; the second output process being a process of outputting the peak / visible overlay image together with the visible light image as an output of the peak frequency map; 10. The measuring device according to claim 9.

11. The image capture device includes: repeating the capturing of the fluorescent images and the capturing of the visible light images to provide a series of fluorescent images and a series of visible light images; the series of fluorescent images and the series of visible light images depicting different overlapping regions of an examination of the body part; The processing device comprises: a stitching unit configured to apply a stitching algorithm to the sequence of visible light images, wherein a set of stitching parameters is determined and applied to generate a large visible light image; the stitching unit is further configured to apply the stitching algorithm to the series of fluorescence images to generate a large fluorescence image; the output unit is further configured to output the large visible light image together with the large fluorescent image and the peak frequency map; The measurement apparatus of claim 8 , wherein the stitching algorithm applied to the series of fluorescent images applies the set of stitching parameters determined when generating the large visible light image.

12. The fluorescence imaging unit and the visible light imaging unit repeat capturing the fluorescence images and capturing the visible light images to provide a series of fluorescence images and a series of visible light images. the series of fluorescent images and the series of visible light images depicting different overlapping regions of an examination of the body part; The processing device comprises: a stitching unit configured to apply a stitching algorithm to the sequence of visible light images, wherein a set of stitching parameters is determined and applied to generate a large visible light image; the stitching unit is further configured to apply the stitching algorithm to the series of fluorescence images to generate a large fluorescence image; the output unit is configured to output the large visible light image together with the large fluorescent image and the peak frequency map; The measurement apparatus of claim 8 , wherein the stitching algorithm applied to the series of fluorescent images applies the set of stitching parameters determined when generating the large visible light image.

13. 9. The measurement device of claim 8, wherein the fluorescence imaging unit and the visible light imaging unit are configured such that the viewing direction and viewpoint of the fluorescence image and the visible light image are the same, and the fluorescence image and the visible light image are captured through one and the same objective lens.

14. 9. The measurement device of claim 8, wherein the fluorescence imaging unit and the visible light imaging unit are configured to capture the fluorescence image and the visible light image simultaneously in the absence of time switching between the fluorescence image signal and the visible light image signal.

15. the image capture device further comprising a dichroic prism assembly configured to receive, through an input face, fluorescent light forming the fluorescent image and visible light forming the visible light image; the dichroic prism assembly comprises a first prism, a second prism, a first compensator prism located between the first prism and the second prism, a further dichroic prism assembly for splitting the visible light into three light components, and a second compensator prism located between the second prism and the further dichroic prism assembly; the first prism and the second prism each have a cross section with at least five corners, each corner having an inside angle of at least 90 degrees, a respective entrance face and a respective exit face, each designed such that an incident beam entering the entrance face in a direction parallel to a normal to the entrance face is reflected twice within each of the first prism and the second prism, and exits each of the first prism and the second prism through the exit face parallel to the normal to the exit face; a normal to the entrance surface of each of the first prism and the second prism and a normal to the exit surface of each of the first prism and the second prism are perpendicular to each other; When light enters the first prism through the entrance surface, the light is partially reflected toward the exit surface of the first prism and travels a first path length from the entrance surface of the first prism to the exit surface of the first prism, the light partially enters the second prism through the first compensator prism and is partially reflected toward the exit surface of the second prism and travels a second path length from the entrance surface of the first prism to the exit surface of the second prism, the first prism is larger than the second prism such that the first path length and the second path length are the same; 9. The measuring device according to claim 8.

16. An endoscope configured as the image capture device in the measurement apparatus of claim 8.

17. A laparoscope configured as the image capture device in the measurement apparatus described in claim 8.

18. 1. A method for providing a risk prediction value based on measuring a fluorescent signal in tissue of a body part to which a fluorescent agent has been added, comprising: - illuminating the tissue with excitation light having a wavelength suitable for generating emitted light by excitation emission of the fluorescent agent to provide a fluorescence image, and capturing at least one of the fluorescence images within an examination region by spatially resolved measurement of the emitted light; repeating the step of capturing a fluorescence image to capture a plurality of the fluorescence images over time to provide a time series of the fluorescence images; defining at least one calculation region in the at least one fluorescence image of the plurality of fluorescence images; calculating a time-intensity curve from the signal intensities within the calculation region; approximating the time-intensity curve with a model having at least one coefficient and determining the at least one coefficient associated with an approximation of the model to at least a portion of the time-intensity curve; providing the at least one coefficient to an input interface of a processor having an input interface, an artificial intelligence model, and an output interface; performing an inference operation by the processor applying the at least one coefficient to the artificial intelligence model and generating from an output of the artificial intelligence model a risk prediction value indicative of tissue perfusion within the computational domain as output data at the output interface; communicating said risk prediction via a user interface; A method for providing a risk prediction value, comprising:

19. The method of claim 18, further comprising: defining the computational domain; calculating said time-intensity curve; approximating the time-intensity curve with the model to determine the at least one coefficient; providing said at least one coefficient to said input interface of said processor; The step of executing the inference operation based on the artificial intelligence model and generating and outputting the risk prediction value includes: for each pixel or voxel of the fluorescence image for a plurality of said computation regions; The method for providing a risk prediction value comprises: converting the risk predictions across the plurality of computational domains into a risk prediction derivation image map; outputting said risk prediction value derivation image map via said user interface; The method for providing a risk prediction value according to claim 18, further comprising:

20. Capturing at least one visible light image of a surface of the body part within the examination area; outputting the risk prediction value and the visible light image via the user interface; Further comprising:

20. A method for providing a risk prediction value as claimed in claim 18, wherein the viewing directions and / or viewpoints of the fluorescent images and the visible light images are linked via a known relationship.

21. Capturing at least one visible light image of a surface of the body part within the examination area; outputting the risk prediction value derivation image map as an overlay image together with the visible light image via the user interface; Further comprising:

20. A method for providing a risk prediction value as claimed in claim 19, wherein the viewing directions and / or viewpoints of the fluorescent images and the visible light images are linked via a known relationship.

22. 20. The method of claim 18, wherein the model applied to approximate the time-intensity curve is a single tissue compartment model, the Adiabatic Approximation for Tissue Homogeneity (AATH) model.

23. 20. The method of claim 18, wherein the artificial intelligence model is a neural network pre-trained with supervised training based on clinical patient data.

24. 1. A computer-based clinical decision support system for providing a risk prediction value based on measurements of fluorescent signals in tissue of a body part to which a fluorescent agent has been added, comprising: an illumination unit configured to illuminate the tissue with excitation light having a wavelength suitable to generate light emitted by excitation emission of the fluorescent agent; a fluorescence imaging unit configured to illuminate the tissue with excitation light having a wavelength suitable to generate emitted light by excitation emission of the fluorescent agent to provide a fluorescence image, and to capture at least one fluorescence image within an examination area by spatially resolved measurement of the emitted light, and further configured to capture a plurality of the fluorescence images over time to provide a time series of the fluorescence images; a processing device including a processor having an input interface, an artificial intelligence model, and an output interface; a user interface; The processing device comprises: defining at least one calculation region within the at least one fluorescent image of the plurality of fluorescent images; calculating a time-intensity curve from signal intensities within said calculation region; approximating the time-intensity curve with a model having at least one coefficient and determining the at least one coefficient associated with an approximation of the model to at least a portion of the time-intensity curve; providing the at least one coefficient to the input interface of the processor; the processor is configured to perform an inference operation to apply the at least one coefficient to the artificial intelligence model and generate from an output of the artificial intelligence model a risk prediction value indicative of tissue perfusion within the computational domain as output data at the output interface, and communicate the risk prediction value to the user interface; The user interface is configured to display the risk prediction value.

25. The processing device comprises: Defining the computational domain; calculating said time-intensity curve; approximating the time-intensity curve with the model to determine the at least one coefficient; providing said at least one coefficient to said input interface of said processor; performing the inference operation to generate and output the risk prediction value for each pixel or voxel of the fluorescence image for a plurality of the computational regions based on the artificial intelligence model; converting the risk predictions across the plurality of computational domains into a risk prediction derivation image map; communicating the risk prediction value derived image map to the user interface; configured to:

25. The clinical decision support system of claim 24, wherein the user interface displays the risk prediction value derivation image map.

26. The method of claim 20, further comprising: providing a visible light imaging unit configured to capture at least one visible light image of a surface of the body part within the examination area; the viewing directions and / or viewpoints of the fluorescent image and the visible light image are linked via a known relationship; the processing device is further configured to output the risk prediction value and the visible light image to the user interface; 25. The clinical decision support system of claim 24, wherein the user interface is configured to display the risk prediction value and the visible light image.

27. The method of claim 20, further comprising: providing a visible light imaging unit configured to capture at least one visible light image of a surface of the body part within the examination area; the viewing directions and / or viewpoints of the fluorescent image and the visible light image are linked via a known relationship; the processing device is further configured to output the risk prediction value derivation image map and the visible light image to the user interface; 26. The clinical decision support system of claim 25, wherein the user interface is configured to display the risk prediction value derivation image map as an overlay image along with the visible light image.

28. the processing device includes the model that is applied to approximate the time-intensity curve; 25. The clinical decision support system of claim 24, wherein the model is a single tissue compartment model, the Adiabatic Approximation for Tissue Homogeneity (AATH) model.

29. 25. The clinical decision support system of claim 24, wherein the processing device includes the artificial intelligence model, which is a neural network pre-trained with supervised training based on clinical patient data.

Images