Systems and methods for determining target characteristics during laser treatment - Patents.com

Abstract

To provide systems and methods for determining target characteristics during a laser procedure.SOLUTION: A method comprises: a step (i) of obtaining a relationship between (i) the number of pixels associated with a light beam reflected from a target or an object located in proximity to the target on an endoscopic image obtained from a video sensor coupled to an endoscope and (ii) a distance to the target from a tip of the endoscope; a step (ii) of measuring the number of pixels associated with the light beam reflected from the target or the object located in proximity to the target during a procedure; and a step (iii) of, based at least in part on the relationship obtained in the step (i) and the measured number of pixels in the step (ii), determining at least one of a size of the target or a distance to the target from the tip of the endoscope.SELECTED DRAWING: Figure 1A

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 262,290, filed October 8, 2021, and U.S. Provisional Patent Application No. 63 / 365,886, filed June 6, 2022, the contents of which are incorporated herein in their entireties.

[0002] The present disclosure relates to determining characteristics of a target during laser treatment. [Background technology]

[0003] During a surgical laser procedure, such as laser lithotripsy, a physician may need to interact with targets of various sizes, such as tumors, stones, tissue fragments, etc., inside a patient's body. The target may be placed in a medium (e.g., a liquid medium such as water or saline), and the physician may use a scope, such as an endoscope, to perform a surgical procedure on the target. The scope may include a laser fiber tip, an endoscope image sensor, etc., attached or connected to the end of the scope. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] U.S. Patent Publication No. 2021 / 0038064 [Patent Document 2] U.S. Patent Publication No. 2021 / 0038311 [Patent Document 3] U.S. Patent Publication No. 2021 / 0038062 Summary of the Invention [Problem to be solved by the invention]

[0005] Endoscopes and other similar surgical scopes or catheters may be used in a variety of surgical procedures, for example, in ear, nose and throat (ENT) procedures such as tonsillectomy, sinus surgery, or other similar procedures, procedures in the digestive system, or procedures within the abdomen. Many endoscopic procedures, such as lithotripsy or other similar procedures (e.g., tumor removal, tissue ablation procedures, or kidney stone ablation / removal), may utilize laser light in combination with an imaging sensor, such as a camera, mounted on the end of the scope.

[0006] It is important for physicians to know the dimensions of a target, such as a tumor or stone, when performing either a diagnostic or therapeutic procedure. For example, a physician attempting to visualize a cancerous tumor needs to determine the tumor's dimensions (e.g., height and width) to determine whether the tumor can be surgically removed, to determine a baseline measurement for the tumor to monitor changes in the size of the tumor after cancer treatment has begun, etc. Similarly, a physician performing an endoscopic procedure, such as ablation or removal of stones or tissue, may need to determine the size of the stone or tissue fragment to be removed to determine whether the target is small enough to be removed using a scope, such as removal through a ureter or access sheath having a particular inner diameter, or whether the target must be further reduced before removal. Additionally, during a laser procedure, such as laser lithotripsy, a physician may need to know the distance between the tip of the scope and the target. The distance between the tip of the scope and the target is important, for example, to determine the amount / intensity of laser light / radiation to deliver to the target and / or to monitor the condition of the medium. [Means for solving the problem]

[0007] A calibration process performed prior to or at the very beginning of a medical procedure may be used to obtain a relationship between (i) pixel measurements (e.g., total pixel count) of beam dimensions (e.g., laser beam diameter footprint, cross-sectional area of ​​the laser beam, radius of the laser beam, or arc length of the footprint of the laser beam) and / or (ii) object dimensions on the endoscopic image (e.g., diameter, cross-sectional area, perimeter, radius or arc length of the laser fiber tip) and the distance from the tip of the endoscope to the target. In one example, the relationship may be between measurements in pixel count in 1) a video image of light reflection from the target, or 2) a video image of an object such as a laser fiber in close proximity (e.g., within 1 μm, 10 μm, 100 μm, or 1 mm) to the target or directly in contact with the target, and 1) the size of that light image, or the size of a fiber in close proximity (e.g., within 1 μm, 10 μm, 100 μm, or 1 mm) to the surface of the target or directly in contact with the target, and / or 2) the distance from the tip of the endoscope to the target. Then, based on the determined relationship, a calibration curve can be obtained that can allow the distance from the tip of the endoscope to any target or the size of the target to be determined. As used herein, the term "close proximity" or "close" refers to a situation where an object (e.g., a laser fiber) is almost touching the target or is at most a distance of X mm from the target, where X is based on the desired measurement accuracy. For example, if the desired measurement accuracy is ±1%, the object (e.g., a laser fiber) can be within 1% of the distance from the tip of the endoscope to the target. In one example, assuming that the distance between the tip of the endoscope and the target is 10 mm and the desired measurement accuracy is at least 1%, the object (e.g., a fiber tip) can be 0.1 mm or less from the target when performing the calibration process. In general, a closer distance can provide a higher measurement accuracy.

[0008] In one implementation, the calibration process takes advantage of the fact that when the laser fiber tip is close to a target surface in a medium, the diameter of the laser aiming beam footprint is equal to the diameter of the glass of the laser fiber, which is a known diameter, and the fact that the refractive index of the medium proximate to the target or anatomical feature corresponds to a change in the number of pixels of the aiming beam footprint diameter on the video image when the endoscope and / or the tip of the fiber are moved relative to the target. As a result, a relationship can be determined between the pixel measurement of the laser beam diameter (or other parameters such as the cross-sectional area of ​​the laser beam, the laser beam radius, the arc length of the footprint of the laser beam, etc.) on the endoscope image and the distance from the tip of the endoscope to the target. Based on this relationship, touching the tip of the fiber to any target can provide a scale for the video system to measure its size and distance from the video sensor (or the tip of the endoscope). In one example, touching the tip of the fiber to the target may not be necessary for calibration. In such an example, as long as the tip of the fiber is visible within the field of view of the video sensor attached to the endoscope, the system can complete the calibration process.

[0009] The calibration process may involve operations or steps such as detecting the laser aiming beam circle / footprint or fiber tip at a first location / distance proximate to the target, measuring the diameter, cross-sectional area, or other relevant parameter (e.g., circumference, radius, or arc length) of the laser aiming beam footprint or fiber tip at a pixel on the video image at the first location / distance, measuring a first distance or a first amount of the laser fiber extending from the scope / video sensor, moving at least a portion of the endoscope to a second location / distance relative to the first location / distance with respect to the target, measuring a second diameter, cross-sectional area, or other relevant parameter (e.g., circumference, radius, or arc length) of the laser aiming beam footprint or fiber tip at a pixel on the video image at the second location, and measuring a second distance or a second amount of the laser fiber extending from the scope / video sensor at the second location / distance. A relationship may then be established between the pixel measurements and the distance from the tip of the endoscope to the target. Before and / or during laser treatment, the distance between the target and the tip of the endoscope can be determined based at least in part on the established relationship and pixel measurements of the laser beam diameter (or other parameter such as the cross-sectional area of ​​the laser beam, the laser beam radius, or the arc length of the footprint of the laser beam) obtained during treatment by contacting the tip of the laser fiber with the target (or by approaching the target without contacting the tip of the laser fiber with the target).

[0010] Optionally, the method may include determining the refractive index of a medium (e.g., water or saline) proximate the target or anatomical feature. The refractive index may be determined based on a ratio of an initial pixel count of the aiming beam footprint diameter (or cross-sectional area of ​​the laser beam, the laser beam radius, or the arc length of the laser beam footprint) to a change in the laser aiming beam footprint diameter (or cross-sectional area of ​​the laser beam, the laser beam radius, or the arc length of the laser beam footprint) between a first position and a second position. Or stated differently, the change in the aiming beam footprint diameter (or cross-sectional area of ​​the laser beam, the laser beam radius, or the arc length of the laser beam footprint) as the endoscope is moved relative to the target and / or fiber tip.

[0011] In addition, the method may further include measuring a number of pixels corresponding to a beam dimension, such as a target area covered by a user beam dimension footprint, a cross-sectional area of ​​the laser beam, a laser beam radius, or an arc length of the footprint of the laser beam on the endoscopic image, and determining at least one dimension (e.g., height or width) or other characteristic of the target based thereon. For example, the pixel size may be calculated by dividing the diameter of the laser aiming beam by its corresponding total number of pixels on the endoscopic image, and the height / width of the target may be estimated based on the calculated pixel size and the total number of pixels corresponding to the height / width of the target on the endoscopic image.

[0012] As described above, the relationship between pixel measurements on the endoscopic image and the distance from the tip of the endoscope to the target can be determined using object dimensions such as the diameter, cross-sectional area, circumference, radius, or arc length of the laser fiber tip. In this implementation, the calibration process can include measuring a dimension of the fiber tip (e.g., the diameter, cross-sectional area, circumference, radius, or arc length of the laser fiber tip) in pixels on the video image at a first location proximate to the target (a first number of pixels) and measuring a first amount of the laser fiber extending from the scope at the first location (e.g., using markings on the insulating jacket of the laser fiber that can be seen by the endoscopic camera). The calibration process can then include moving at least a portion of the scope to a second location relative to the target, measuring a dimension of the fiber tip in pixels on the video image at the second location (a second number of pixels), and measuring a second amount of the laser fiber extending from the scope at the second location.

[0013] Additionally or alternatively, the calibration curve may be theoretically calculated based on known parameters such as the dimensions of the aiming beam, the number of vertical pixels of the endoscope sensor (e.g., camera), and the vertical field of view in the medium. For example, for each distance or position, a height corresponding to a half angle of the field of view in the medium may first be determined based on the field of view in the medium. From there, the number of pixels per millimeter on the endoscope image and the number of pixels corresponding to a particular size of laser fiber may be calculated. These steps may be performed iteratively to obtain the number of pixels corresponding to a particular size of laser at different distances or positions, thereby establishing the calibration curve. It should be noted that the parameters used in the calibration process may differ depending on whether the curve is determined empirically or theoretically. For example, it may not be necessary when empirically obtaining a calibration curve having a relationship between (i) pixel measurements of the laser beam dimensions and / or object dimensions on the video image and (ii) the distance from the tip of the endoscope to the target.

[0014] In the drawings, which are not necessarily drawn to scale, like numerals may represent like components in different figures. Like numerals with different letter prefixes may represent different instances of the like components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document. [Brief description of the drawings]

[0015] [Figure 1A] FIG. 1 shows an example of a fiber tip located close to a target and a corresponding endoscopic image. [Figure 1B] FIG. 1 shows an example of a fiber tip located close to a target and a corresponding endoscopic image. [Figure 1C] FIG. 1C shows an example of a calibration curve empirically obtained by the process described in FIGS. 1A and 1B. [Diagram 2] FIG. 1 shows an example of a theoretically obtained calibration curve. [Diagram 3] FIG. 1 is a block diagram illustrating an example of a machine in which one or more embodiments may be implemented. [Figure 4] FIG. 1 is an exemplary flow diagram of a method for empirically obtaining a calibration curve. [Diagram 5] FIG. 1 is an exemplary flow diagram of a method for theoretically obtaining a calibration curve. [Figure 6] FIG. 1 is a schematic diagram of an exemplary computer-based clinical decision support system (CDSS). [Figure 7] FIG. 1 illustrates an exemplary method of using a calibration curve to determine a target characteristic. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Disclosed herein are systems and methods for determining target characteristics during laser procedures. The system can include a scope, such as an endoscope, a video sensor (e.g., a camera or other endoscopic imaging sensor) used at the end (e.g., distal end) of the scope, and a laser fiber inserted or attached to the scope. In one example, the laser fiber can be a surgical fiber connected to a probe laser, an ablation laser, or any similar laser or combination of lasers used during laser procedures. For example, the ablation laser can emit infrared radiation, and the probe laser can emit visible light to indicate where the tip of the scope is (and thus where the ablation energy from the ablation laser is directed) or can be used to illuminate the target. Exemplary laser fibers and systems are provided, for example, in U.S. Patent Nos. 5,233,633, 5,233,633, and 5,379,492, the entire contents of which are incorporated herein by reference. The target can be a piece of tissue, a piece of debris, or an object such as a tumor or a kidney stone. The fiber tip can have a known dimension, such as a diameter (e.g., 200 micrometers (μm)), which can be used to calibrate the pixel count of the video sensor. In addition, if the laser fiber extends beyond the end of the scope to perform a laser procedure, the distance the laser fiber extends from the video sensor (and thereby the end of the scope) can be obtained using, for example, a marking on the insulating jacket of the laser fiber that can be seen by the video sensor. Because the laser fiber is placed in close proximity to (or, in some embodiments, in contact with) the target during the procedure, the distance the laser fiber extends from the end of the scope is approximately the same as the distance from the tip of the endoscope to the target.A calibration curve may be obtained based on an estimated distance from the tip of the endoscope to the target and parameters such as the number of pixels related to the beam dimensions (e.g., laser beam diameter footprint, cross-sectional area of ​​the laser beam, laser beam radius, or arc length of the footprint of the laser beam, hereafter "beam dimensions" or "laser beam dimensions") or the object dimensions on the image acquired by the endoscope (e.g., diameter, cross-sectional area, circumference, radius, or arc length of the laser fiber tip, hereafter "object dimensions" or "laser fiber dimensions"). The calibration curve may be specific to the particular type of medium (e.g., air, water, etc.) in which the target is placed. Thus, once calibrated, the system may not need to be calibrated again. This calibration curve may be empirically determined, such as by the process discussed with respect to Figures 1A and 1B below, or may be theoretically determined as discussed with respect to Figure 2 below. It should be noted that the parameters used in the calibration process may vary depending on whether the curve is empirically or theoretically determined. For example, this may not be necessary if a calibration curve having a relationship between (i) pixel measurements of the laser beam dimensions and / or object dimensions on the video image and (ii) the distance from the tip of the endoscope to the target is obtained empirically.

[0017] 1A and 1B show an example of a laser fiber tip placed close to a target and a corresponding endoscopic image of the laser aiming beam footprint. In the example shown in FIG. 1A, an endoscope 100 is shown with a quantity of laser fiber 102 extending 10 mm from the tip / end of the scope 100 (e.g., from a video sensor used at the distal end of the endoscope 100). The distance from the tip of the endoscope to the tip of the laser fiber 102 can be measured using one or more markings on the laser fiber 102 (e.g., marks on the insulating jacket of the fiberscope that can be seen by the endoscope video sensor, such as a number of graduations 108). When the tip of the laser fiber 102 is placed on or near the surface of the target 104, a pixel measurement (e.g., X1 pixel) corresponding to the dimension of the laser fiber 102 (e.g., 200 μm fiber) can be observed on the corresponding endoscopic image 106A (based on light reflection from the target). The X1 pixel can correspond to the dimensions of the laser beam footprint emitted from the laser fiber 102 and / or the dimensions of the glass at the tip of the laser fiber 102 (e.g., the diameter of the glass tip, etc.). The dimensions of the laser beam footprint can be equal to the dimensions of the glass at the tip of the laser fiber 102 when the tip of the laser fiber 102 is close to or in contact with the surface of the target 104.

[0018] As the endoscope 100 is brought closer to the target 104 (e.g., by shortening the length of the tip of the laser fiber 102 extending from the tip of the endoscope 100 or from a video sensor used at the tip of the endoscope 100 to, e.g., 5 mm) while keeping the tip of the laser fiber 102 on or near the surface of the target 104, the same 200 μm diameter fiber will correspond to more pixels (e.g., X2 pixels) on the endoscopic image 106B. That is, as the tip of the endoscope 100 gets closer to the tip of the laser fiber 102 and therefore to the surface of the target 104, the corresponding endoscopic image will appear larger, as shown in endoscopic images 106A and 106B. Additionally, as shown in FIGS. 1A and 1B, depending on how far the laser fiber 102 extends, different numbers of multiple tick marks 108 may be visible, which can provide an indication of the distance from the tip of the endoscope 100 to the tip of the laser fiber 102 at each position relative to the target 104.

[0019] FIG. 1C shows an example of a calibration curve empirically obtained by the process described in FIG. 1A and FIG. 1B. As a result of the process described above for FIG. 1A and FIG. 1B, a relationship between pixel measurements of the dimensions of the laser beam footprint on the endoscopic image 106A, 106B and the distance from the tip of the endoscope 100 to the target can be determined. When the values ​​of the pixel measurements and the distance values ​​are plotted as shown in FIG. 1C, a calibration curve 108 can be obtained. Based on the calibration curve 108, subsequently contacting the tip of the laser fiber 102 with any target (or placing the target within the field of view of the video sensor) can provide a scale for the video system to use the pixel measurements of the dimensions of the laser beam footprint on the endoscopic image to measure its distance from the video sensor (or the tip of the endoscope 100). Additionally, a pixel size may be calculated based on the dimensions of the laser aiming beam footprint and its corresponding number of pixels on the endoscopic images 106A, 106B, and based on this calculation and the number of pixels corresponding to the target 104 on the endoscopic images 106A, 106B, the dimensions of the target 104 may be estimated. It should be noted that although FIGS. 1A-1C illustrate the use of a laser fiber to establish the calibration curve 108, any suitable object having known dimensions and located in close proximity (e.g., 1 μm, 10 μm, 100 μm, or 1 mm) to the surface of the target may be utilized to establish a calibration curve in a medium based on the techniques described above, and thus is within the scope of the present invention.

[0020] In an alternative example, calibration can occur as long as the tip of the laser fiber 102 (or any suitable object) is within the field of view of the video sensor used at the tip of the endoscope 100, regardless of whether the tip of the laser fiber 102 (or object) touches the target 104. This can be determined because the medium is known and therefore the cone of field of view within the medium is known as well as the dimensions of the laser fiber 102 (or object). Thus, calibration can be performed based on those known parameters and the design of the endoscope 100 and the laser fiber 102. For example, if the laser fiber 102 appears just at the edge of the field of view, it can be determined that the laser fiber 102 extends at a distance of 3-4 mm from the tip of the endoscope 100. This is a calibration based on the design of the endoscope 100 and known dimensions such as the diameter of the laser fiber 102 (e.g., 200 microns, 365 microns, etc.). Similarly, if the tip of the laser fiber 102 is near the center of the field of view, it may be determined that the laser fiber 102 extends a distance of 8-10 mm from the tip of the endoscope 100. The exact distance that the tip of the laser fiber 102 extends from the tip of the endoscope 100 may be determined from the markings on the laser fiber 102, as discussed above.

[0021] In various embodiments, calibration curves for different types of media (e.g., water, saline, or air) may be established using the techniques described above. The endoscope 100 is operated in one of the media (e.g., water, saline, or air) during the laser procedure. The type of media may be input by a user in a control system, user interface, etc. coupled / connected to the endoscope 100 before and / or during the laser procedure. Additionally or alternatively, the type of media may be determined based on divergence. For example, water and air have different refractive indices such that an object appears larger in water than in air. Thus, by comparing how large an object appears in a medium to its actual size, the type of media may be determined and the calibration curve corresponding to that medium may be used.

[0022] The medium may vary depending on the medical procedure being performed. For example, for gastrointestinal (GI) and gynecological procedures, the medium is air. Thus, in one embodiment, the system can automatically select / select the appropriate medium and its corresponding calibration curve based on the procedure selected by the user or input into the system. For example, the surgeon can identify a GI procedure and the system can automatically select air and a calibration curve established in air. Conversely, if the procedure is to treat gallstones, the system can select saline as the medium and obtain a corresponding calibration curve. The size of any targets (e.g., lesions, stones, etc.) found during the procedure can then be estimated using the calibration curve corresponding to the selected medium.

[0023] During a medical procedure, the media may change. For example, during a GI procedure, once the endoscope is in the bile duct, the surgeon may apply irrigation with saline. In such a situation, the system may provide both options (e.g., air or saline) for the surgeon to select. In another example, the system may automatically select a new media type depending on which media is more air or saline. For example, if saline is applied and there is more saline than air in the bile duct, the system may determine that a new type of media is present. The system may then recalibrate the number of pixels of the video sensor based at least in part on the change in media using the configuration techniques described above. Then, based on the recalibration, adjust the determined size of the target (e.g., height or width of the target) and / or the distance from the tip of the scope to the target. Alternatively, upon detecting a new type of medium (e.g., upon receiving a signal indicating that a pump for applying saline to the patient's body has been activated) and / or upon receiving input from the surgeon indicating the presence of a new type of medium, the system may automatically obtain a calibration curve corresponding to the new type of medium established before or during the procedure and, based on the obtained calibration curve, estimate the size of the target and / or the distance from the tip of the scope to the target.

[0024] In some situations, the surgeon may irrigate to clear the front of the scope or to clear the target, but the medium does not actually change. Thus, before adjusting the medium type and changing the calibration curve, the surgeon or the system can check to determine whether the medium has actually changed. For example, if a laser is being used, a short low energy pulse can be emitted. If vapor bubbles are present, the medium is determined to be water or saline. If no vapor bubbles are present, the medium is air. In one example, such a medium check can be performed at any time during the procedure, and if there is an error in the selection of the medium, the medium type can be automatically corrected by the system and / or manually corrected by the surgeon. From there, the system can use the correct calibration curve (corresponding to the medium present in the patient's body) and correct the estimated size and / or distance for the target using the correct calibration curve.

[0025] In one example, the system can make treatment recommendations based on the size of the target (e.g., lesion or polyp) and display the recommendations to the user for approval or selection. For example, depending on the size of the polyp estimated using the techniques described above, one treatment option may be to "snare" the polyp. This type of treatment may be feasible if the polyp is under a certain size, but if the polyp is over a certain size, a different approach may be taken. In another example, in a gynecological procedure, the size of a uterine fibroid may determine what type of treatment should be applied or used.

[0026] Similarly, in laser procedures, the laser settings may differ based on the type and / or size of the target (e.g., stone). For example, if the stone is large, the surgeon may decide to break the stone into smaller fragments and then switch settings (e.g., laser intensity) to reduce the smaller fragments to dust. The system may first recommend breaking the target into smaller fragments once the size of the target is estimated using the techniques described above. The surgeon may then choose to accept or reject this recommendation. Alternatively, the system may automatically perform the proposed procedure based on the estimated target size. Whether the surgeon accepts the system's recommendation or the system automatically performs the recommended procedure, the system may adjust the laser intensity or other parameters (e.g., pulse width, duty cycle, frequency, etc.) to break the target and reduce the broken fragments of the target, either automatically or upon receiving approval.

[0027] Such a process has the advantage of significantly reducing the time required to perform a medical procedure. For example, breaking a large stone into fragments and then reducing the smaller fragments to dust can reduce the overall procedure time by 60 to 70 percent compared to the time required to reduce the large stone itself to dust without fragmenting it. Thus, allowing the system to automatically estimate target size and perform a corresponding procedure based on the size of the target can allow the medical procedure to proceed and be terminated more quickly and efficiently.

[0028] FIG. 2 shows an example of a theoretically obtained calibration curve 200. In the example shown in FIG. 2, various parameters may be known, such as the dimensions of the laser beam footprint, such as the diameter of the 200 μm laser beam footprint / aiming beam, the number of vertical pixels for the endoscope sensor, and the vertical field of view in the medium (based on the refractive index of the medium and laser fiber used). For example, the diameter of the aiming beam emitted from a 200 μm laser fiber may be known to be 0.4 mm at the target. Furthermore, the endoscope video sensor may be known to have a particular size array, such as a 200×200 array, and the vertical field of view of the video sensor underwater may be known to be 70 degrees. Using this information, the distance from the tip of the endoscope to the target, and the total number of pixels of the laser beam diameter on the endoscope image may be plotted to obtain the calibration curve 200.

[0029] More specifically, for each distance, a height corresponding to the half angle of the field of view in the medium can be calculated based on known parameters. For example, at each distance, the corresponding height of the field of view can be calculated by multiplying the distance by the tangent of the half angle of the vertical field of view (35 degrees). The number of pixels per mm can be calculated, for example, using 100 pixels (i.e., the number of pixels in half of a 200x200 array) divided by the height of the field of view. Multiplying this number by the diameter of the aiming beam (e.g., 0.4 mm) can provide the number of pixels per 200 μm fiber at a particular distance.

[0030] Once the distance and pixel count are plotted, a calibration curve 200 similar to calibration curve 108 of Figure 1C can be obtained and used to determine the distance from the tip of the scope to the target at any distance. The advantage of this calibration approach is that the relationship between the number of pixels of the laser beam diameter on the endoscopic image and the distance from the tip of the endoscope to the target correlates to the refractive index of the medium close to the target, so once the system is calibrated, it does not need to be recalibrated (as treatment is always performed endoscopically in a medium such as water).

[0031] FIG. 3 is a block diagram of an example machine 300 on which any one or more of the techniques (e.g., methodologies) discussed herein may be executed. In alternative embodiments, the machine 300 may operate as a standalone device or may be connected (e.g., networked) to other machines. In a network deployment, the machine 300 may operate in the capacity of a server machine, a client machine, or both, in a server-client network environment. In one example, the machine 300 may function as a peer machine in a peer-to-peer (P2P) (or other distributed) network environment. The machine 300 may be a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a web appliance, a network router, a switch or bridge, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by the machine. Additionally, although only a single machine is shown, the term "machine" shall be taken to include any collection of machines that individually or collectively execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein, such as cloud computing, software as a service (SaaS), or other computer cluster configurations.

[0032] The examples described herein may include or operate by logic or some components or mechanisms. A circuit set is a collection of circuits implemented in a tangible entity that includes hardware (e.g., simple circuits, gates, logic, etc.). The membership of a circuit set may be flexible over time and the variability of the underlying hardware. A circuit set includes members that may perform a specified operation, either alone or in combination, when operated. In one example, the hardware of a circuit set may be immutably designed (e.g., hardwired) to perform a specific operation. In one example, the hardware of a circuit set may include variably connected physical components (e.g., execution units, transistors, simple circuits, etc.) that include computer-readable media that are physically modified (e.g., magnetic, electrical, movable arrangements of particles of immutable mass, etc.) to encode instructions for a specific operation. Upon connecting to the physical components, the underlying electrical properties of the hardware components are changed, for example, from insulators to conductors or vice versa. The instructions enable the built-in hardware (e.g., execution units or loading mechanisms) to create the members of the circuit set in the hardware through the variable connections to perform some of the specific operations when operated. Thus, the computer-readable medium is communicatively coupled to other components of the circuit set members when the device is operating. In one example, any of the physical components may be used in more than one member of more than one circuit set. For example, during operation, an execution unit may be used in a first circuit of a first circuit set at one time and reused by a second circuit in the first circuit set or by a third circuit in the second circuit set at a different time.

[0033] The machine (e.g., computer system) 300 may include a hardware processor 302 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, a field programmable gate array (FPGA), or any combination thereof), a main memory 304, and a static memory 306, some or all of which may communicate with each other via an interlink (e.g., a bus) 330. The machine 300 may further include a display unit 310, an alphanumeric input device 312 (e.g., a keyboard), and a user interface (UI) navigation device 314 (e.g., a mouse). In one example, the display unit 310, the input device 312, and the UI navigation device 314 may be touch screen displays. The machine 300 may additionally include a storage device (e.g., a drive unit) 308, a signal generation device 318 (e.g., a speaker), a network interface device 320, and one or more sensors 316, such as a Global Positioning System (GPS) sensor, a compass, an accelerometer, or other sensor. The machine 300 may include an output controller 328, such as a serial (e.g., Universal Serial Bus (USB)), parallel, or other wired or wireless (e.g., infrared (IR), near field communication (NFC)) connection for communicating with or controlling one or more peripheral devices (e.g., a printer, a card reader, etc.).

[0034] The storage device 308 may include a machine-readable medium 322 on which is stored one or more sets of data structures or instructions 324 (e.g., software) that embody or are used by any one or more of the techniques or functions described herein. The instructions 324 may reside, completely or at least partially, within the main memory 304, within the static memory 306, or within the hardware processor 302 during its execution by the machine 300. In one example, one or any combination of the hardware processor 302, the main memory 304, the static memory 306, or the storage device 316 may constitute a machine-readable medium.

[0035] Although the machine-readable medium 322 is shown as a single medium, the term “machine-readable medium” may include a single or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) configured to store one or more instructions 324.

[0036] The term "machine-readable medium" may include any medium capable of storing, encoding, or carrying instructions for execution by the machine 300 and causing the machine 300 to perform any one or more of the techniques of this disclosure, or any medium capable of storing, encoding, or carrying data structures used by or related to such instructions. Non-limiting machine-readable media may include solid-state memory, as well as optical and magnetic media. In one example, a massed machine-readable medium comprises a machine-readable medium having a plurality of particles having an unchanging (e.g., stationary) mass. Thus, a massed machine-readable medium is not a transitory propagating signal. Specific examples of massed machine-readable media may include semiconductor memory devices (e.g., non-volatile memories such as electrically programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), and flash memory devices, magnetic disks such as internal hard disks and removable disks, magneto-optical disks, and CD-ROM and DVD-ROM disks.

[0037] The instructions 324 may further be transmitted or received over a communications network 326 using a transmission medium via a network interface device 320 utilizing any one of a number of transport protocols (e.g., Frame Relay, Internet Protocol (IP), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), etc.). Exemplary communications networks may include local area networks (LANs), wide area networks (WANs), packet data networks (e.g., the Internet), mobile phone networks (e.g., cellular networks), Plain Old Telephone (POTS) networks, and wireless data networks (e.g., the Institute of Electrical and Electronics Engineers (IEEE) 802.11 family of standards, known as Wi-Fi, the IEEE 802.16 family of standards, the IEEE 802.15.4 family of standards, peer-to-peer (P2P) networks, among others. In one example, the network interface device 320 may include one or more physical jacks (e.g., Ethernet jacks, coaxial jacks, or telephone jacks) or one or more antennas for connecting to the communications network 326. In one example, the network interface device 320 may include multiple antennas for wireless communication using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) techniques. The term "transmission medium" shall be taken to include any intangible medium capable of storing, encoding, or carrying instructions for execution by the machine 300 and including digital or analog communications signals or other intangible media that facilitate communication of such software.

[0038] The calibration curves discussed in Figure 1C and / or Figure 2 may be obtained empirically or theoretically. The calibration curves may represent a relationship between (i) the number of pixels of the laser beam diameter (or other dimensions discussed above) on an image, or the number of pixels of an object dimension (such as the diameter, cross-sectional area, perimeter, radius, or arc length of an object) on an image (e.g., an endoscopic image), and (ii) the distance from the tip of the scope to the target. The endoscopic image may be obtained from a video sensor, such as a camera, coupled to the endoscope (e.g., located at the distal end of the endoscope).

[0039] FIG. 4 illustrates an exemplary flow diagram of a method 400 for empirically acquiring a calibration curve according to the present invention. Operation 402 includes measuring a first number of pixels from an endoscope sensor at a first location. In one example, the first number of pixels can be the number of pixels of a dimension of a laser beam aiming footprint (or other dimension as described above) or the number of pixels of an object (e.g., a portion of a surgical fiber, such as the tip of a surgical fiber) located in close proximity to (or in some embodiments, in contact with) a target on an endoscope image (e.g., an image taken from a video sensor, such as a camera associated with the endoscope). The first location can be a first distance from the target. The distance from the target can be measured in operation 404. The measurement can be based on the amount of laser fiber extending from the tip of the scope, for example, using one or more markings on an insulating jacket of the fiberscope that can be seen by the endoscope video sensor. Operation 406 can include moving at least a portion of the endoscope or fiber tip to a second location relative to the first location. In one example, the distal end of the endoscope (e.g., the end of the endoscope from which the fiber tip protrudes and / or which includes the video sensor) may be moved away from or closer to the target. Additionally or alternatively, the portion of the fiber tip extending from the tip of the endoscope may be extended or made longer, or retracted or shortened, such that the tip of the endoscope is closer or further away from the target in the second position.

[0040] Operation 408 may include measuring a second number of pixels from the endoscope sensor at a second location, and operation 410 may include measuring a second distance from the target (e.g., distance from the target at the second location). As discussed above with respect to FIG. 1A and FIG. 1B, at each of the first and second locations, there will be a corresponding number of pixels on the endoscope image (X1 pixels at the first location and X2 pixels at the second location). In general, the closer the scope and / or fiber tip is to the target, the more pixels there will be on the corresponding endoscope image. For example, at 10 millimeters, the number of pixels may be 14.3 pixels per millimeter, and at 5 millimeters, the number of pixels may be 28.6 pixels per millimeter. Operation 412 may include plotting the first number of pixels, the first distance, the second number of pixels, and the second distance to obtain a calibration curve that represents a relationship between the number of pixels of the laser beam aiming footprint dimension (or other dimension described above) or the number of pixels of an object located in close proximity to (or in some embodiments, touching) the target on the endoscopic image and the distance from the tip of the endoscope to the target. From this determined relationship, the distance from the target and / or the target dimension may be determined when the tip of the scope is at any distance from the target. It should be noted that although FIGS. 1A, 1B, and 4 show measurements at two positions, the calibration curve may be established based on measurements at three or more positions. In general, the more positions used, the more accurate the calibration curve will be.

[0041] In one example, the dimensions of the laser beam footprint and / or aiming beam may be known or measured at a particular distance from the target. Also, the number of pixels in the array of a video sensor may be a known quantity, as may the viewing angle of the video sensor in a given medium. For example, as discussed above, a 200x200 array video sensor may have a viewing angle of 70 degrees in water. These known values / quantities may be used to theoretically generate a calibration curve, as discussed with respect to FIG. 2.

[0042] FIG. 5 illustrates an exemplary flow diagram of a method 500 for theoretically obtaining a calibration curve. Operation 502 can include determining an aiming beam dimension of a laser fiber. For example, a 200 μm laser fiber can have an aiming beam with a diameter of 0.4 mm, which is a known quantity or can be measured directly by pointing the laser at a target. Operation 504 can include determining an endoscope array size. This can also be a known quantity based on the type of video sensor (e.g., camera) used in the endoscope. For example, the video sensor may be known to have a 200×200 array. Operation 506 can include determining the refractive index of a medium, such as air, water, etc. The type of medium can be determined based on the medical procedure being performed. For example, for gastrointestinal (GI) procedures and gynecological procedures, the medium is air. Thus, the system can automatically select / select the appropriate medium based on the procedure selected by the user or input into the system. For example, the surgeon can identify a GI procedure and the system can automatically select air. Conversely, if the procedure is to treat gallstones, the system may select saline as the medium. Based on the medium, the vertical field of view within the medium may be estimated.

[0043] Based on these (or other similar) known parameters, operation 508 may include determining a height corresponding to a half-angle field of view in the medium at a particular distance. Based thereon, the number of pixels per millimeter in the half-angle field of view may be calculated. For example, a 200x200 array may be known to have a 70 degree vertical field of view in water (hence a half-angle of 35 degrees). Thus, at any distance, the corresponding field height may be calculated by multiplying the distance by the tangent of the half-angle of the vertical field of view in the medium (35 degrees). The number of pixels per mm may then be calculated using 100 pixels (the number of pixels in half of the 200x200 array) divided by twice the field angle height.

[0044] Operation 512 can include determining the number of pixels corresponding to a fiber with a known diameter of the aiming beam and plotting the number of pixels versus distance to obtain a calibration curve. In one example, the number of pixels per millimeter can be multiplied by the diameter of the aiming beam (e.g., 0.4 mm) to calculate the number of pixels per 200 μm at a particular distance. The number of pixels per fiber can be plotted at a particular distance generating a calibration curve such as that discussed with respect to FIG. 2. Again, based on the calibration curve, the distance from the target and / or the size of the target can be determined regardless of where the scope or fiber is located.

[0045] Essentially, a calibration curve can be obtained because the cone of view of the array is known for a particular medium, so long as the fiber (or other suitable object) is visible within the field of view of the video sensor. For example, if the fiber is at the edge of the field of view, the distance from the tip of the endoscope to the fiber is known (based on the design of the scope), and the diameter (or other dimension discussed above) of the fiber (or other suitable object) is known. Thus, a calibration can be performed based on those known parameters and parameters specific to the medium in which the scope is placed.

[0046] 6 illustrates an exemplary computer-based clinical decision support system (CDSS) 600 configured to determine information about a target, such as the distance from the tip of the scope to the target, the size of the target, etc., based on the number of pixels in an image captured by a video sensor coupled or attached to the scope, or any other similar information about the target. In various embodiments, the CDSS 600 includes an input interface 602 in which the size of the surgical fiber specific to the patient's procedure, information about the video or imaging sensor, e.g., the size of the camera array, and / or information about the scope, are provided as input features to an artificial intelligence (AI) model 604, a processor that performs inference operations in which parameters are applied to the AI ​​model to generate a determination of the distance from the target and / or the size of the target, and an output interface 608 in which the determined distance from the target or size of the target is communicated to a user, e.g., a clinician.

[0047] In some embodiments, the input interface 602 may be a direct data link between the CDSS 600 and one or more medical devices that generate at least some of the input features. For example, the input interface 602 may directly transmit the dimensions or size of a surgical fiber to the CDSS 600 during a therapeutic and / or diagnostic medical procedure. In one example, information regarding the surgical fiber and / or scope used during the procedure may be stored in the database 606. Additionally or alternatively, the input interface 602 may be a classic user interface that facilitates interaction between a user and the CDSS 600. For example, the input interface 604 may facilitate a user interface in which a user may manually input information regarding the surgical fiber and / or scope. Additionally or alternatively, the input interface 602 may provide the CDSS 600 with access to an electronic patient record or the scope and / or surgical fiber being used during the procedure and any of its dimensions discussed above from which one or more input features may be extracted. In any of these cases, the input interface 602 is configured to collect the following input characteristics associated with one or more of a particular patient, type of medical procedure, type of scope, type of video sensor connected to the scope, or type of surgical fiber to be used at or before the CDSS 600 is used to evaluate information regarding the size of the surgical fiber, the video or imaging sensor, the scope, or the medium in which the procedure is to be performed:

[0048] Examples of input characteristics can include the dimensions of a surgical fiber used during a procedure.

[0049] Examples of input features may include parameters such as what type of video or imaging sensor is coupled to the scope and the size of the sensor's camera or video array.

[0050] Examples of input characteristics may include the type of scope used during the procedure.

[0051] An example of an input characteristic can include the amount of surgical fiber extending from the tip of the scope.

[0052] Examples of input characteristics may include the type of medium in which the procedure will be performed and / or in which the scope is placed.

[0053] Examples of input features may include a video image from a video sensor 610 .

[0054] An example of an input characteristic may include the number of pixels 612 in the field of view of a video sensor.

[0055] Based on one or more of the above input features, the processor performs an inference operation using the AI ​​model 604 to generate a determined distance from the tip of the scope to the target and / or the size of the target. For example, the input interface 602 may deliver one or more of the above listed input features to the input layer of the AI ​​model 604, which propagates these input features to the output layer via the AI ​​model 604. The AI ​​model 604 can provide a computer system with the ability to perform tasks without being explicitly programmed by making inferences based on patterns found in the analysis of data. The AI ​​model 604 explores 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 an AI model from exemplary training data to make data-driven predictions or decisions, which are represented as outputs or evaluations.

[0056] There are two common modes of machine learning (ML): supervised ML and unsupervised ML. Supervised ML uses prior knowledge (e.g., examples that associate inputs with outputs or outcomes) to learn relationships between inputs and outputs. The goal of supervised ML is to learn a function that best approximates the relationship between training inputs and outputs, such that, given some training data, the ML model can implement the same relationship given the input to produce the corresponding output. Unsupervised ML is to train ML using information that is not classified or labeled, allowing the algorithm to act on that information without guidance. Unsupervised ML is useful in exploratory analysis because it can automatically identify structures in data.

[0057] 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 values ​​of some inputs). Some commonly used examples of supervised ML are logistic regression (LR), naive Bayes, random forest (RF), neural network (NN), deep neural network (DNN), matrix decomposition, and support vector machine (SVM).

[0058] Some common tasks in 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.

[0059] Another type of ML is federated learning (also called 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 important issues such as data privacy, data security, data access rights, and access to heterogeneous data.

[0060] In some examples, the AI ​​model 604 may be trained continuously or periodically prior to execution of an inference operation by the processor. Then, during the inference operation, patient-specific input features provided to the AI ​​model 604 may be propagated from an input layer, through one or more hidden layers, and finally to an output layer that corresponds to information about the target. For example, when evaluating an image, the system may determine the number of pixels on the endoscopic image, determine how far the surgical fiber extends from the tip of the endoscope, determine the dimensions of the laser aiming beam footprint on the endoscopic image, determine the height of the field of view of the video sensor, and determine a calibration curve. The system may then use the calibration curve to determine the distance from the tip of the scope and / or surgical fiber to the target and characteristics of the target, such as the target height or target width.

[0061] During and / or after the inference operation, information regarding the target may be communicated to a user via output interface 608 (e.g., a user interface (UI)) and / or a surgical laser connected to the processor may automatically perform a desired action. For example, based on the size of the target, the system may cause a surgical laser to emit energy to ablate the target, adjust the amount of ablative energy, or move a portion of the scope.

[0062] FIG. 7 illustrates an exemplary method of determining target characteristics according to the present disclosure. Operation 701 may include measuring a number of pixels associated with a beam dimension (e.g., a laser beam diameter footprint, a cross-sectional area of ​​the laser beam, a laser beam radius, or an arc length of a footprint of the laser beam) and / or (ii) an object dimension (e.g., a diameter, a cross-sectional area, a circumference, a radius, or an arc length of a laser fiber tip) on an endoscopic image in a laser procedure. Operation 702 may include obtaining a calibration curve for the surgical fiber. The calibration curve may be obtained theoretically or empirically, such as by the methods described in FIGS. 1A-1C, 2, or 4-5, or by any other suitable process. Operation 704 may include using the measured number of pixels on the endoscopic image obtained in operation 701 and using the calibration curve obtained in operation 702 to determine a distance from the target. Additionally or alternatively, operation 706 may include determining a target characteristic, e.g., a size of the target, such as a height or width of the target. For example, the pixel size may be calculated by dividing the diameter of the laser aiming beam by the corresponding total number of pixels on the endoscopic image, and the height / width of the target may be estimated based on the calculated pixel size and the total number of pixels corresponding to the height / width of the target on the endoscopic image. In one example, once the calibration process is completed, the aiming beam may be projected from the fiber tip onto the surface of the target, the projection conforming to the calibrated parameters. Thus, the user may know how many pixels are visible based on the amount of the fiber tip that can be seen in the endoscopic image, and therefore how far the tip of the fiber and / or the tip of the scope are located from the target. Similarly, the user may know the number of pixels corresponding to the dimension of the aiming beam on the surface of the target, and may determine the height and / or width of the target in pixels, which may be used to determine the estimated size of the target.

[0063] In one example, once a calibration curve is obtained in operation 702, whether it is obtained theoretically or empirically, the calibration curve may be used to determine a distance from a target in operation 704 or may be used to determine a target characteristic in operation 706. Or stated another way, operations 704 and 706 may be performed independently of one another or in any order (e.g., the size of the target may be determined first and then the distance from the target may be determined), or operations 704 and 706 may be performed simultaneously or substantially simultaneously with one another.

[0064] Additional Notes and Examples Example 1 is a method for acquiring target characteristics, comprising: (i) acquiring a relationship between a number of pixels associated with a light beam reflected from a target or an object located in proximity to the target on an endoscopic image acquired from a video sensor coupled to the endoscope, and (ii) a distance from the tip of the endoscope to the target; (ii) measuring a number of pixels associated with a light beam reflected from the target or an object located in proximity to the target during a procedure; and (iii) determining at least one of a size of the target or a distance from the tip of the endoscope to the target based at least in part on the relationship acquired in step (i) and the number of pixels measured in step (ii).

[0065] In Example 2, the subject matter of Example 1 optionally includes the step of obtaining a relationship between (i) a number of pixels associated with a light beam reflected from a target or an object located proximate to the target on the endoscopic image and (ii) a distance from the tip of the endoscope to the target, including measuring a first number of pixels associated with a dimension of the light beam or a dimension of the object when the target is a first distance from the tip of the endoscope, measuring the first distance from the tip of the endoscope to the target, measuring a second number of pixels associated with the dimension of the light beam or the dimension of the object when the target is a second distance from the tip of the endoscope, measuring the second distance from the tip of the endoscope to the target, and establishing the relationship based at least in part on the measured first number of pixels, second number of pixels, first distance, and second distance.

[0066] In Example 3, the subject matter of Example 2 optionally includes, wherein the dimensions of the light beam include at least one of a diameter footprint of the laser beam, a cross-sectional area of ​​the laser beam, a radius of the laser beam, or an arc length of the footprint of the laser beam.

[0067] In Example 4, the subject matter of any one or more of Examples 2-3 optionally includes that the dimensions of the object include at least one of a diameter, a cross-sectional area, a circumference, a radius, or an arc length of the laser fiber tip.

[0068] In Example 5, the subject matter of any one or more of Examples 1-4 optionally includes a step of recommending a therapeutic procedure based at least in part on the determined size of the target and / or the determined distance from the tip of the endoscope to the target.

[0069] In Example 6, the subject matter of any one or more of Examples 1-5 optionally includes a step of determining a type of medium in which the target is located, wherein the obtained relationship is based at least in part on a calibration curve corresponding to the type of medium.

[0070] In Example 7, the subject matter of Example 6 optionally includes wherein the type of media is determined based at least in part on one of a type of medical procedure, a comparison of the observed size of the target to the actual size of the target, or user input.

[0071] In Example 8, the subject matter of any one or more of Examples 6-7 optionally includes that the type of medium is at least one of water, air, or saline.

[0072] In Example 9, the subject matter of any one or more of Examples 1-8 optionally includes determining whether a new type of medium exists in which the target is located, and if so, (i) obtaining an updated relationship corresponding to the new type of medium, and (ii) determining a size of the target and / or a distance from the tip of the endoscope to the target based at least in part on the updated relationship.

[0073] In Example 10, the subject matter of any one or more of Examples 1-9 optionally includes, wherein the step of obtaining a relationship between (i) a number of pixels associated with a light beam reflected from a target or an object located proximate to the target on the endoscopic image and (ii) a distance from the tip of the endoscope to the target includes the steps of obtaining (i) a dimension of the light beam or a dimension of the object, (ii) a corresponding number of pixels from the video sensor, and (iii) a reflectivity of the medium in which the target is located, a step of computationally determining a number of pixels associated with the dimension of the light beam or the dimension of the object for each distance from the tip of the endoscope to the target, and a step of establishing the relationship based at least in part on the distance from the tip of the endoscope to the target and the corresponding number of pixels associated with the dimension of the light beam or the dimension of the object.

[0074] In Example 11, the subject matter of any one or more of Examples 1-10 optionally includes calculating a pixel size associated with the endoscopic image, determining a number of pixels corresponding to a target on the endoscopic image, and determining a size of the target based at least in part on the calculated pixel size and the determined number of pixels corresponding to the target.

[0075] Example 12 provides a system comprising at least one processor and a memory coupled to the at least one processor, the memory configured to store instructions that, when executed by the at least one processor, cause the at least one processor to perform operations including: (i) obtaining a relationship between a number of pixels associated with a light beam reflected from a target or an object located in proximity to the target on an endoscopic image obtained from a video sensor coupled to the endoscope and (ii) a distance from a tip of the endoscope to the target; (ii) measuring a number of pixels associated with the light beam reflected from the target or an object located in proximity to the target during a procedure; and (iii) determining at least one of a size of the target or a distance from the tip of the endoscope to the target based at least in part on the relationship obtained in step (i) and the number of pixels measured in step (ii).

[0076] In Example 13, the subject matter of Example 12 optionally includes the step of obtaining a relationship between (i) a number of pixels associated with a light beam reflected from a target or an object located proximate to the target on the endoscopic image and (ii) a distance from the tip of the endoscope to the target, including measuring a first number of pixels associated with a dimension of the light beam or a dimension of the object when the target is at a first distance from the tip of the endoscope, measuring the first distance from the tip of the endoscope to the target, measuring a second number of pixels associated with the dimension of the light beam or the dimension of the object when the target is at a second distance from the tip of the endoscope, measuring the second distance from the tip of the endoscope to the target, and establishing the relationship based at least in part on the measured first number of pixels, second number of pixels, first distance, and second distance.

[0077] In Example 14, the subject matter of Example 13 optionally includes, wherein the dimensions of the light beam include at least one of a diameter footprint of the laser beam, a cross-sectional area of ​​the laser beam, a radius of the laser beam, or an arc length of the footprint of the laser beam.

[0078] In Example 15, the subject matter of any one or more of Examples 13-14 optionally includes that the dimensions of the object include at least one of a diameter, a cross-sectional area, a circumference, a radius, or an arc length of the laser fiber tip.

[0079] In Example 16, the subject matter of any one or more of Examples 12-15 optionally includes, wherein the operations further include recommending a therapeutic procedure based at least in part on the determined size of the target and / or the determined distance from the tip of the endoscope to the target.

[0080] In Example 17, the subject matter of any one or more of Examples 12-16 optionally includes, the operations including determining a type of medium in which the target is located, and the obtained relationship being based at least in part on a calibration curve corresponding to the type of medium.

[0081] In Example 18, the subject matter of Example 17 optionally includes wherein the type of media is determined based at least in part on one of a type of medical procedure, a comparison of the observed size of the target to the actual size of the target, or user input.

[0082] In Example 19, the subject matter of any one or more of Examples 12-18 optionally includes the operations further including determining whether a new type of medium is present in which the target is located, and if so, (i) obtaining an updated relationship corresponding to the new type of medium, and (ii) determining a size of the target and / or a distance from the tip of the endoscope to the target based at least in part on the updated relationship.

[0083] In Example 20, the subject matter of any one or more of Examples 12-19 optionally includes the step of obtaining a relationship between (i) a number of pixels associated with a light beam reflected from a target or an object located proximate to the target on an endoscopic image, and (ii) a distance from the tip of the endoscope to the target, including obtaining (i) a dimension of the light beam or a dimension of the object, (ii) a number of pixels corresponding to the video sensor, and (iii) a reflectivity of a medium in which the target is located.

[0084] In Example 21, the subject matter of any one or more of Examples 12-20 optionally includes the operations further including calculating a pixel size associated with the endoscopic image, determining a number of pixels corresponding to a target on the endoscopic image, and determining a size of the target based at least in part on the calculated pixel size and the determined number of pixels corresponding to the target.

[0085] The above detailed description includes references to the accompanying drawings, which form a part of the detailed description. The drawings show, by way of illustration, certain embodiments that may be implemented. These embodiments are also referred to herein as "examples." Such examples may include elements in addition to those shown or described. However, the inventors also contemplate examples in which only those elements shown or described are provided. Furthermore, the inventors also contemplate examples that use any combination or permutation of those elements (or one or more aspects thereof) shown or described with respect to a particular example (or one or more aspects thereof) or with respect to other examples (or one or more aspects thereof) shown or described herein.

[0086] All publications, patents, and patent documents referenced in this document are incorporated herein by reference in their entirety as if individually incorporated by reference. In the event of a conflict in usage between this document and those documents incorporated by reference, the usage in the incorporated references should be deemed to capture the usage in this document, and in the event of any conflicting inconsistencies, the usage in this document will take precedence.

[0087] In this document, the terms "a" or "an" are used to include one or more, as is common in patent documents, regardless of any other instances or usages of "at least one" or "one or more." In this document, the term "or" is used to refer to a non-exclusive or, such as "A or B" including "A but not B," "B but not A," and "A and B," unless otherwise indicated. In the appended claims, the terms "including" and "in which" are used as the plain English equivalents of the respective terms "comprising" and "wherein." Also, in the appended claims, the terms "including" and "comprising" are open-ended, i.e., a system, device, article, or process that includes elements in addition to the elements listed after such terms in a claim will still be deemed to be within the scope of that claim. Furthermore, in the appended claims, terms such as "first," "second," and "third" are used merely as labels and are not intended to impose numerical requirements on their objects. [Explanation of symbols]

[0088] 100 Scopes, endoscopes 102 Laser Fiber 104 Target 106A Endoscopic Image 108 scales, calibration curves 200 Calibration Curves 300 Machines 302 Hardware Processor 304 Main Memory 306 Static Memory 308 Storage Devices 310 Display Unit 312 Alphanumeric Input Device 314 User Interface (UI) Navigation Devices, UI Navigation Devices 316 Sensors 318 Signal Generating Devices 320 Network Interface Device, Network Interface 322 Machine-Readable Media 324 command 328 Output Controller 330 Interlink 600 Clinical Decision Support Systems (CDSS), CDSS 602 Input Interface 604 Artificial Intelligence (AI) Model, AI Model 606 Database 608 Output Interface 610 Video Sensor 612 pixels

Claims

1. A processor; a memory containing stored instructions; wherein, when executed by the processor, the instructions cause the processor to: determining a relationship between a number of pixels associated with a light beam reflected from a target or an object located proximate to a target on an endoscopic image acquired from an imaging sensor coupled to the endoscope and a distance from a tip of the endoscope to the target; measuring the number of pixels associated with the light beam reflected from the target or the object located proximate to the target during a procedure; and determining one or more characteristics of the target using the trained learning model based at least in part on a relationship between the determined relationship and the measured number of pixels; system.

2. 2. The system of claim 1, wherein the relationship between the number of pixels associated with the light beam and the distance from the tip of the endoscope to the target is based on one or more parameters input into the trained learning model, and the one or more characteristics of the target include the size of the target and / or the distance from the tip of the endoscope to the target.

3. The system of claim 2 , wherein the one or more parameters include a dimension of a surgical fiber used during the procedure.

4. The system of claim 3 , wherein the one or more parameters include an amount of the surgical fiber extending from the tip of the endoscope.

5. The system of claim 2 , wherein the one or more parameters include a type of imaging sensor coupled to the endoscope.

6. The system of claim 5 , wherein the one or more parameters include an array size of the imaging sensor.

7. The system of claim 5 , wherein the one or more parameters include an image acquired from the imaging sensor.

8. The system of claim 5 , wherein the one or more parameters include a number of pixels in a field of view of the imaging sensor.

9. The system of claim 2 , wherein the one or more parameters include a type of medium in which the procedure is performed and / or in which the endoscope is placed.

10. The system of claim 1 , wherein the trained learning model comprises an artificial intelligence and / or machine learning model.

11. The relationship between the number of pixels associated with the light beam and the distance from the tip of the endoscope to the target is: measuring a first number of pixels related to a dimension of the light beam or a dimension of the object when the target is a first distance from the tip of the endoscope; measuring the first distance from the tip of the endoscope to the target; measuring a second number of pixels related to a dimension of the light beam or a dimension of the object when the target is a second distance from the tip of the endoscope; measuring the second distance from the tip of the endoscope to the target; using the trained learning model to establish a relationship based at least in part on the first number of measured pixels, the second number of measured pixels, the first distance, and the second distance; The system of claim 1 , which is based on

Images