Spectroscopic system for identifying light sources

Abstract

To provide medical devices, systems and methods that can identify the type of light being used for spectral analysis of a target tissue.SOLUTION: A method of identifying an illumination light source in a surgical system comprises steps of: receiving a signal from a target after the target is illuminated by the illumination light source; performing spectroscopic analysis of the received signal; and, based at least in part on the spectroscopic analysis, determining a characteristic of the illumination light source. A method of treating a target comprises: receiving a signal from the target after the target is illuminated by the illumination light source; performing spectroscopic analysis of the received signal; based at least in part on the spectroscopic analysis, determining a first characteristic of the illumination light source and a second characteristic of the target; and, based at least in part on the determined characteristics of the illumination light source and the target, operating the surgical system to treat the target.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] This specification relates generally, but not by way of limitation, to systems and methods for performing spectroscopy on materials. More particularly, but not by way of limitation, this application relates to systems and methods for identifying light sources in endoscopy systems that use spectroscopy systems. [Background technology]

[0002] Many surgical procedures involve the treatment or removal of target tissue, such as diseased, potentially diseased, or otherwise unwanted tissue located inside a patient. Accordingly, some of these procedures require access to the patient's internal structures via an open procedure or through a smaller opening in a minimally invasive (e.g., endoscopic or laparoscopic) procedure.

[0003] It may be useful to reliably identify the type or composition of tissue being ablated or treated from a structure before it is ablated or treated, particularly to ensure that the appropriate tissue is being ablated or treated. For example, it may be useful to distinguish between healthy tissue and diseased tissue, such as cancerous tissue, to facilitate ablation of the diseased tissue rather than the healthy tissue. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] U.S. Patent Application Publication No. 2022 / 0039641 [Patent Document 2] U.S. Patent Application Publication No. 2021 / 0038300 [Patent Document 3] U.S. Patent Application Publication No. 2021 / 0038306 [Patent Document 4] U.S. Patent Application Publication No. 2021 / 0038310 [Patent Document 5] U.S. Patent Application Publication No. 2021 / 0038064 Summary of the Invention [Problem to be solved by the invention]

[0005] In particular, the inventors of the present invention have recognized that a problem to be solved when performing spectroscopic characterization of tissue is the different spectroscopic responses of different types of light sources to tissue. A typical surgical instrument, such as an endoscope, can include various light delivery systems for projecting different types of light at the distal end of the instrument. For example, different types of light can be used for illumination, aiming, and treatment. The illumination system can use various types of light sources, such as xenon, light-emitting diodes (LEDs), halogen, and laser diodes (LDs). Furthermore, lasers used in medical instruments for illumination or treatment can use various laser technologies, such as holmium:yttrium-aluminum-garnet (Ho:YAG) and thulium-fiber (Tm-Fiber).

[0006] Medical instruments typically include only a light guide extending along the length of the device and a light emitter that projects light from the medical instrument. However, the light source that generates the light, whether illumination or treatment, can be located outside the medical instrument, such as in an external computing system mounted on a stand or tower. Hospitals can have generators that produce various types of laser light and illumination light for the same instrument. Thus, different light sources can be used with the same medical instrument.

[0007] The inventors of the present invention have recognized that it may be difficult to identify the characteristics (e.g., type, composition, etc.) of target tissue using spectroscopic analysis without identifying the characteristics (e.g., type) of a light generator that can accommodate a variety of different types of light for the same or different tissue types. Specifically, the spectral analysis of the tissue is analyzed based on a specific pairing of a light source and a target tissue. For example, the target tissue is analyzed by comparing the spectral analysis of a specific light source with predetermined spectrographs for various target tissues. Therefore, if different light sources are used, the spectral analysis of the tissue may be biased or inaccurate.

[0008] The present subject matter can provide solutions to this and other problems, such as by providing medical devices, systems, and methods that can identify the type of light being used for spectral analysis of target tissue. The type of light can be identified before spectral analysis of the tissue is performed. For example, to reliably identify the illumination source, spectral analysis of light from a light source reflected from a white surface or collected from ambient reflections can be performed. Then, identification information of the target tissue can be determined by analyzing the light reflected from the target tissue using spectral analysis using a spectrograph of the appropriate light type to identify the target tissue. In an example, the light source for performing the spectroscopic analysis can be the illumination source.

[0009] The results of the spectral analysis can be compared to library information for various tissues and various types of light sources (or generators) combinations. The library of information can be accessed at will via the cloud and analyzed using artificial intelligence. The artificial intelligence analysis can be used to make or suggest adjustments to light generation for any or all of the treatment light source, spectral light source, and illumination light source, or surgical procedure, such as settings for the light source or surgical device (e.g., laser system) generation / operation mode, power level, geometry, etc. The light generation and / or surgical device operation can then be adjusted automatically, semi-automatically, or manually based on the artificial intelligence output to improve the light's ability to reliably identify tissue types.

[0010] Spectroscopic techniques are widely used to identify materials through the spectrum of light reflected, transmitted, emitted, or absorbed by the material. Examples of spectroscopic systems are described in U.S. Patent Application Publication Nos. 2022 / 0039641, 2021 / 0038300, 2021 / 0038306, and 2021 / 0038310, as well as U.S. Patent Application Publication No. 2021 / 0038064. [Means for solving the problem]

[0011] In one example, a method for identifying an illumination source in a surgical system includes receiving a signal from a target after the target is illuminated by the illumination source, performing a spectroscopic analysis of the received signal, and determining a characteristic of the illumination source based at least in part on the spectroscopic analysis.

[0012] In another example, a method for treating a target comprises receiving a signal from the target after the target is illuminated by an illumination source; performing a spectroscopic analysis of the received signal; determining a first characteristic of the illumination source and a second characteristic of the target based at least in part on the spectroscopic analysis; and operating a surgical system to treat the target based at least in part on the determined characteristics of the illumination source and the target.

[0013] This summary is intended to provide an overview of the subject matter of this patent application. It is not intended to provide an exclusive or exhaustive description of the invention. A detailed description is included to provide further information about this patent application. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a schematic diagram of a surgical system having a surgical instrument connected to a laser system, an imaging system including an illumination source, and a spectroscopy system that may be connected to the cloud and artificial intelligence (AI) input via the Internet of Things (IoT). [Figure 2] 1 is a graph showing light intensity versus wavelength plots for various light sources. [Figure 3] FIG. 1 is a schematic diagram illustrating an exemplary computer-based clinical decision support system (CDSS) configured to provide operating parameters for an optical system of a medical device system based on a reflected or emitted spectroscopic signal. [Figure 4] FIG. 1 illustrates an example of a feedback-controlled laser treatment system. [Figure 5] 1 is a block diagram illustrating operations in a method for identifying and adjusting a light source in a spectroscopic surgical system. [Figure 6] FIG. 1 is a block diagram illustrating an example machine on which any one or more of the techniques (e.g., methodologies) described herein may be performed. DETAILED DESCRIPTION OF THE INVENTION

[0015] In the drawings, which are not necessarily drawn to scale, like numerals may represent like components in different figures. Like numerals with different subscripts may represent different instances of like components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in this document.

[0016] The present disclosure relates to identifying an illumination light source that illuminates an anatomical target during a surgical procedure that may be performed using an endoscope, laparoscope, or the like. The illumination light may additionally be used to identify the anatomical target (e.g., target tissue) using spectroscopy. In additional examples, other types of light sources may be identified, such as light sources that may be used to perform a treatment or intervention and light sources that may be used to perform spectroscopic analysis. Because spectroscopic analysis may rely on correlating reflected spectroscopic signals with a spectrograph dataset to known light sources, it is desirable to identify all light sources, but particularly light sources used to perform spectroscopic analysis of anatomical targets. As mentioned, hospitals may use different light sources with the same surgical instruments, thereby introducing potential variables into the spectroscopic analysis. The present disclosure provides a method for identifying a light source type using a first spectroscopic analysis, which is then used to identify the target tissue using a second spectroscopic procedure. For example, a spectroscopic system may first be used to identify an illumination light source, such as a xenon light, an LED light, a halogen light source, or a laser diode, so that an appropriate spectrograph may be used to analyze the spectroscopic signal produced by the target tissue. Treatment of the anatomical target can then be performed using a different light source, such as a laser. Identifying the illumination source can be performed with or without the laser source emitting light. These methods can be part of algorithms and operations to identify the light source and anatomical target and, in response, control and adjust the composition, formation, or emission of light (spectroscopic, therapeutic, and illumination) used in the surgical procedure or control and adjust the operation of a surgical device during the surgical procedure. Thus, controlled and adjusted light or surgical devices can have other positive benefits, such as helping to prevent endoscopic or tissue damage from inappropriate or suboptimal laser emission, detecting broken light-emitting fibers, and optimizing the therapeutic effect at the anatomical target.

[0017] The optical signal from the anatomical target can be rapidly detected and delivered to a spectroscopy system by a delivery system, for example, through a laser fiber or a separate fiber channel. The delivery and spectroscopy system can continuously collect spectral data from the target, deliver the signal to a spectrometer, and send digital spectral data from the spectrometer to a feedback analyzer.

[0018] The feedback analyzer can analyze the spectroscopic signal data and compare it to available database libraries. Based on the data analysis, the feedback analyzer can identify the illumination source type (or treatment source type) and / or target characteristics. Anatomical target identification helps optimize the laser module operating setup, preferred laser operating mode (pulsed or continuous wave (CW)), power and energy, pulse shape and profile, laser emission pulse regime, and combining all generated pulses into a combined output pulse train. The optimized signal with suggested settings is sent directly to the laser controller (automatic mode) or requests operator approval for automatic adjustment of the laser controller settings (semi-automatic mode).

[0019] In the present invention, an Internet of Things (IoT) system is a network that allows components of a laser system to communicate and interact with one another via the Internet. In an example, spectral data may be delivered via the IoT for subsequent analysis. Data may also be delivered to the laser system via the IoT. This data may include, but is not limited to, configuration parameters, software update files, messages for users of the laser system, etc. In an example where a spectral database library is at least partially accessible through an IoT connection, the laser system may communicate with a remotely stored spectral database library to provide data to a feedback analyzer. Additionally, all components of the laser system may be remotely monitored and controlled, if desired, through the network.

[0020] 1 is a schematic diagram of a surgical system 100 having a surgical instrument 102 connected to a laser system 104, an imaging system 106, a spectroscopy system 108, and a feedback control system 110. The feedback control system 110 may include a feedback analyzer 112 and an artificial intelligence (AI) engine 114. The spectroscopy system 108 and the AI ​​engine 114 may be connected to the cloud 118 via the Internet of Things (IoT) 116.

[0021] The surgical instrument 102 may be coupled to a delivery system 120. The surgical instrument 102 may comprise an endoscope, and the delivery system 120 may comprise a light-emitting device, such as a laser-emitting lithotripsy device, and / or optical components (e.g., optical fibers) associated with the light-emitting device for transmitting light to the target.

[0022] Laser system 104 may include any number of laser modules, such as laser module 122A, laser module 122B, up to laser module 122N. Laser module 122A and laser module 122B may be connected to laser controller 124, such as via laser coupling system 125. Again, output from laser system 104 may be transmitted to the target via delivery system 120 (e.g., fiber optics).

[0023] Imaging system 106 may be connected to a light source 126 ("illumination source") and / or a camera module 128. Camera module 128 may include light-sensitive elements, such as a charge-coupled device ("CCD") sensor or a complementary metal-oxide semiconductor ("CMOS") sensor. Camera module 128 may be coupled to imaging system 106 (e.g., via a wired or wireless connection) to transmit signals from the light-sensitive elements to imaging system 106, which represent images (e.g., video signals) to be subsequently displayed on an output unit or display, such as a video monitor (e.g., display 482 of FIG. 4). In various examples, camera module 128 and imaging system 106 may be configured to provide output at a desired resolution suitable for an endoscopy procedure (e.g., at least 480p, at least 720p, at least 1080p, at least 4K UHD, etc.).

[0024] The light source 126 may include an output port for transmitting light to the surgical instrument 102, such as via a fiber optic link. The light source 126 may be configured to illuminate the anatomical region proximate to the target tissue using light of a desired spectrum (e.g., broadband white light, narrowband imaging using suitable electromagnetic wavelengths, etc.). In an example, the light source 126 may generate visible spectrum light using at least one xenon generator or at least one light emitting diode (LED).

[0025] An endoscope, for example, surgical instrument 102, may be configured to be delivered through a patient's structure to reach the site of a target structure to be treated or diagnosed. A delivery system 120 may be inserted into surgical instrument 102 (e.g., via its working channel) to deliver therapeutic and diagnostic capabilities to the target structure. In the illustrated example, delivery system 120 includes optical components that may be connected to a camera module 128 to acquire video images of the target structure. In addition, visible light from a light source 126 may additionally be delivered through delivery system 120 to the target structure. Delivery system 120 may use the same or different optical components to deliver imaging data from the target structure to camera module 128 and to deliver visible light from light source 126 to the target structure.

[0026] Laser system 104 can be used to deliver laser light to a target structure for a variety of uses. Each of laser modules 122A-122N can deliver a different type of laser light to laser controller 124. Laser controller 124 can coordinate the delivery of laser light from laser modules 122A-122N with the operation of appropriate controls on surgical instrument 102. Laser controller 124 can additionally be used to set parameters of the laser light emitted from laser modules 122A-122N, such as mode, power, and shape.

[0027] As described herein, the light generated by the xenon and LED generators of light source 126 may both appear white to a user. Similarly, the light emitted by laser modules 122A-122N may be difficult to distinguish via a user's naked eye. However, spectroscopic analysis from different light sources, even of the same type (e.g., illumination or laser), may have very different results. Therefore, it is important to identify the light generated by light source 126 and laser modules 122A-122N, as well as any other light sources used within the endoscope, to ensure that a correct spectroscopic analysis of the light generated by the light source is performed. Using the present disclosure, light from light source 126 and laser modules 122A-122N may be analyzed to identify the type of light being emitted, thereby ensuring that the spectroscopic analysis applied to such light is performed correctly or optimally, and to facilitate corresponding appropriate or optimal configurations for spectroscopic system 108, laser controller 124, and light source 126. In an example, positive identification of the light source is performed before spectroscopic analysis is performed. Positive identification of a light source can be performed, for example, using a spectrograph of various light sources, showing light sources of substantially full intensity (e.g., not absorbed or fully reflected) across the wavelength spectrum, as shown in FIG.

[0028] FIG. 2 shows an example of a typical spectrum for an endoscopic light source that may be used for anatomical target identification. FIG. 2 shows a graph 200 with an x-axis 202 indicating wavelength in nanometers (nm) and a y-axis 204 indicating light intensity in lumens per square meter (lux). Graph 200 shows plot 206 for a first type of illumination light, such as from light source 126, and plot 208 for a second type of illumination light, such as from light source 126. Thus, plots 206 and 208 may represent two different types of light source 126, or a light source that can switch between producing two different light types. In an example, plot 206 may comprise an LED light, and plot 208 may comprise a xenon light. Plots 206 and 208 show baseline spectrographs that include the full spectrum and intensity of a light source, without any light being absorbed by a reflective surface. For example, plots 206 and 208 may represent light reflected from a white surface or light emitted directly from a light source without reflection. Therefore, plots 206 and 208 are not affected by light absorption from tissue.

[0029] Plots 206 and 208 show the light intensity differences for various wavelengths of various light sources. As can be seen, the waveforms for plots 206 and 208 are different, producing differences in intensity across almost the entire range of wavelengths. There are several individual locations where the intensity differences are particularly large, thereby resulting in discrepancies that can be easily recognized by feedback analyzer 112. For example, feedback analyzer 112 can compare the numerical data representing the actual reflected light spectra with the numerical data representing plots 206 and 208 to determine which plot the actual reflected light most closely resembles. Specifically, graph 200 includes four distinct zones (zone 1, zone 2, zone 3, and zone 4) within which the light source for plot 206 and the light source for plot 208 can be distinguished.

[0030] In an example, zone 1 may be located closest to a wavelength of approximately 450 nm, zone 2 may be located closest to a wavelength of approximately 525 nm, zone 3 may be located closest to a wavelength of approximately 650 nm, and zone 4 may be located closest to a wavelength of approximately 450 nm.

[0031] For Zone 1, Zone 2, and Zone 4, the intensity of plot 206 for the xenon light source is significant, and may be readily recognizable, for example, by machine interpretation, and is greater than the intensity of plot 208 for the LED light source. Thus, the + / - light intensity difference may be used to distinguish and identify the light sources.

[0032] For Zone 2 and Zone 3, the slopes of plot 206 and plot 208 may differ. Specifically, the slope of plot 206 may be descending or at a trough in Zone 2, while the slope of plot 208 in Zone 2 may be ascending, and the slope of plot 206 in Zone 3 may be ascending, while the slope of plot 208 in Zone 3 may be flat. Thus, the + / - slope difference, slope rise / fall, and slope deflection point may be used to distinguish and identify light sources.

[0033] Spectroscopic analysis of the signal strength and spectral slope of plots 206 and 208 within zones 1, 2, 3, and 4 can enable identification of the illumination source type. Such information can be stored in a memory (e.g., memory 604 or memory 606 of FIG. 6 ) of feedback analyzer 112 or in cloud 118 for reference and comparison by feedback analyzer 112 to waveforms collected by spectroscopy system 108. In particular, the numerical data sets for forming plots 206 and 208 can be stored in a memory, such as memory 604 and memory 606 of FIG. 6 , for comparison with data generated by spectroscopy system 108. Thus, spectroscopy system 108 can identify a light intensity value, or range of values, for light emitted from light source 126, and the magnitude of such identified light intensity value can be compared to values ​​at the same wavelength from plots 206 and 208. In an example, feedback analyzer 112 can compare the actual reflected light in zone 1, zone 2, zone 3, and zone 4 to look for common characteristics with plot 206 or plot 208.

[0034] Returning to FIG. 1 , in operation, the light source 126 can generate a light beam 140 that can be passed to the surgical instrument 102 via an appropriate light conductor, such as a fiber optic cable. The light beam 140 can be directed to the patient 130. In particular, the light beam 140 can be incident on a structure within the patient, such as the anatomical target 422 in FIG. 4 , via the delivery system 120. The light beam 140 can be incident on the anatomical target 422 and then reflected back to the delivery system 120 as a reflected illumination light beam 142. Additionally, the light beam 140 can be incident on the test target 170 and reflected back to the delivery system 120 as the reflected illumination light beam 142. As described herein, identification of the light source 126 can be performed using the reflected illumination light beam 142, and spectroscopic analysis of the anatomical target 422 can be performed using the reflected illumination light beam 142.

[0035] The laser controller 124 can receive the laser beams 144A, 144B, and 144N from the laser modules 122A, 122B, and 122N, respectively. The laser beams 144A, 144B, and 144N can be transmitted to the laser controller 124 via a laser combining system 125. The laser controller 124 can receive a combined laser beam 146. The laser controller 124 can perform various treatments on the combined laser beam 146, such as by adjusting settings to control the output power, emission range, pulse shape, and pulse train. The laser controller 124 can output a therapeutic laser 148 to the anatomical target 422. The therapeutic laser 148 can be directed to the anatomical target 422 via the delivery system 120. The therapeutic laser 148 can be incident on the anatomical target 422 and then reflected back to the delivery system 120 as a reflected laser beam 150. In an example, spectroscopic analysis of anatomical target 422 can be performed using reflected laser beam 150, and treatment of anatomical target 422 can be performed using treatment laser 148. Although not shown, treatment laser 148 can additionally be reflected from test target 170 to facilitate identification of the source of treatment laser 148.

[0036] 4, spectroscopic system 108 can include spectrometer 411 and spectroscopic light source 430 (which can be the same as or different from endoscopic light source 126), which can additionally be incident on anatomical target 422 and reflected back to spectroscopic system 108. Although not shown, light from spectroscopic light source 430 can additionally be reflected off test target 170 to facilitate identification of the type of light produced by spectroscopic light source 430.

[0037] The spectroscopy system 108 can perform spectroscopic analysis on the reflected illumination light beam 142 and the reflected laser beam 150, as well as the reflected light from the light source 430, whether reflected from the anatomical target 422 or the test target 170. The spectroscopy system 108 can provide a spectrometer signal 152 to the feedback analyzer 112 and a data signal 154 to the IOT 116, which can communicate with the cloud 118. The IOT 116 can provide a signal 156 to the AI ​​engine 114. The AI ​​engine 114 can provide a signal 158 to the feedback analyzer 112. The feedback analyzer 112 can provide a light signal 160 to the light source 126 and a laser signal 162 to the laser controller 124.

[0038] In examples where light from light source 126 is used for spectroscopic analysis of an anatomical target 422 ( FIG. 4 ) on patient 130, before a surgical procedure is performed, surgical system 100 can be operated to produce light beam 140 and reflected light beam 172. Light beam 140 can be reflected from test target 170. Test target 170 can comprise an object or surface capable of reflecting all or substantially all of the light of light beam 140, such that none or nearly none of light beam 140 is absorbed by test target 170. In examples, test target 170 can comprise a surface of surgical system 100, such as a surface on a cabinet or housing of imaging system 106. In examples, reflected light beam 172 can be light of light beam 140 that is simply transmitted back through delivery system 120 without being specifically reflected from a target, e.g., a portion of light beam 140 that is reflected from ambient light. Spectroscopy system 108 can then analyze reflected light beam 172 so that feedback analyzer 112 can determine the type of light being generated by light source 126. For example, the feedback analyzer 112, with or without the assistance of the AI ​​engine 114, can compare the output of the spectroscopy system 108 based on the reflected light beam 172 with plots of the full spectra of known light sources (e.g., FIG. 2 ) to identify the light source 126. Spectroscopy of the reflected light beam 172 can be performed by matching the intensity values ​​of the reflected light beam 172 at various wavelengths with intensity-wavelength pairs from plots 206 and 208 of FIG. 2 . If a match is found, the feedback analyzer 112 can confirm that the light source 126 is compatible with the feedback analyzer 112, i.e., that the feedback analyzer 112 has access to spectrographs of different target tissues for the light type of the light source 126. Thus, the feedback analyzer 112 can be used in subsequent steps in conjunction with the reflected illumination light beam 142 from the patient 130 to provide an indication of the type of structure upon which and from which the reflected illumination light beam 142 was incident (e.g., identification of the anatomical target 422).The feedback analyzer 112 can then provide recommendations for the settings of the laser controller 124 to perform the surgical procedure, as well as potential adjustments for the light source 126. However, if the feedback analyzer 112 is unable to find a match between the spectroscopic analysis of the reflected light beam 172 and the baseline spectrograph of the non-reflected light (e.g., FIG. 2 ), the surgical system 100 can provide feedback to the user that an unknown illumination light source is being used. In other words, the feedback analyzer 112 does not have access, either in local memory or in the cloud 118, to the combination of the light source used and the spectroscopic analysis of that light type with the anatomical target 422, and therefore cannot provide confirmation of the target tissue type. In an example, the surgical system 100 can shut down or disable the surgical system 100, in whole or in part, if the illumination light source is incompatible with the tissue identification capabilities of the feedback analyzer 112. For example, the surgical system 100 can shut down only the tissue identification capabilities of the surgical system 100 so that the surgeon can continue to use the laser system 104 to perform the surgical procedure using the surgeon's skills to manually identify the anatomical target 422. In scenarios where the feedback analyzer 112 is unable to confirm the type of light source and the anatomical target, the surgical system 100 can still provide the spectroscopic output to the cloud 118 so that the AI ​​engine 114 can learn new pairings of light sources and anatomical targets.

[0039] 1, a surgical system 100 is shown schematically in accordance with various examples of the present disclosure. Further details of the structure and operation of surgical system 100 are described below, which are additionally applicable, where indicated, to laser treatment system (surgical system) 400 of FIG.

[0040] Laser System 104 The surgical system 100 may include a laser system 104 configured to deliver laser energy directed toward a target, and a feedback control system 110 configured to couple to the laser system 104. The laser system 104 may include one or more laser modules 122A-122N (e.g., solid-state laser modules) capable of emitting similar or different wavelengths from UV to IR. The number of integrated laser modules, their output power, emission range, pulse shape, and pulse train are selected to balance system cost and the performance required to deliver a desired effect to the target. In an example, some or all of these factors, e.g., output power, emission range, pulse shape, and pulse train, may be adjusted either by a user or automatically by the laser controller 124 or feedback analyzer 112 to provide improved performance.

[0041] Laser modules 122A-122N can be integrated with fiber and included in laser controller 124. Fiber-integrated laser systems can be used for endoscopic procedures due to their ability to pass laser energy through flexible endoscopes and effectively treat hard and soft tissues. These laser systems produce laser output beams within a wide wavelength range from the UV to the IR (e.g., 200 nm to 10,000 nm). Some fiber-integrated lasers produce output within wavelength ranges that are significantly absorbed by soft or hard tissues, such as 1900-3000 nm for water absorption or 400-520 nm for oxyhemoglobin and / or deoxyhemoglobin absorption. Various IR lasers can be used as laser sources in endoscopic procedures, such as those described with reference to Table 1.

[0042] [Table 1]

[0043] Each of the laser modules 122A-122N may consist of several solid-state laser diodes integrated into an optical fiber to increase output power and deliver the emission to the target. Some fiber-integrated lasers can produce output within wavelength ranges minimally absorbed by target soft or hard tissue. These types of lasers can provide effective tissue coagulation due to penetration depths similar to the 5-10 μm diameter of thin capillaries. The laser modules 122A-122N may comprise fiber-integrated laser modules, which may have several advantages as described in accordance with various examples in this disclosure. In one example, the light emitted by one of the laser modules 122A-122N has a symmetric beam quality, a circular, and a smooth (homogenized) intensity profile. A compact cooling configuration is integrated into the laser module, making the overall system compact. The laser modules 122A-122N may be easily combined with other fiber-optic components. Additionally, the fiber-integrated laser modules 122A-122N can support standard fiber optic connectors, which allows the modules to work well with most optical modules without alignment. Moreover, the fiber-integrated laser modules 122A-122N can be easily replaced without changing the alignment of the laser coupling system 125.

[0044] In some examples, one or more of the laser modules 122A-122N can produce laser output in wavelength ranges that are highly absorbed by some substances, such as soft or hard tissue, stone, bone, or teeth, e.g., 1900-3000 nm for water absorption, or 400-520 nm for oxyhemoglobin and / or deoxyhemoglobin absorption. In some examples, one or more of the laser modules 122A-122N can produce laser output in wavelength ranges that are poorly absorbed by targets, such as soft or hard tissue, stone, bone, or teeth. These types of lasers can provide more effective tissue coagulation due to penetration depths similar to the diameter of thin capillaries (e.g., 5-10 μm). Commercially available solid-state lasers are potential emission sources for the laser modules. Examples of laser sources for laser modules 122A-122N include UV-VIS emitting lasers such as GaN (emission 515-520 nm) or InXGa1-XN semiconductor lasers such as InXGa1-XN (emission 370-493 nm), GaXAl1-XAs lasers (emission 750-850 nm), or InXGa1-Xas lasers (emission 904-1065 nm). Such laser sources may also be applicable for tissue coagulation applications.

[0045] The feedback control system 110 may comprise one or more subsystems including, for example, the spectroscopy system 108 , the feedback analyzer 112 , and the laser controller 124 .

[0046] Spectroscopic System 108 Spectroscopy system 108 may include spectrometer 411 (FIG. 4) that may be used to analyze light from various sources, such as light source 126 used for laser modules 122A-122N used for treatment, as well as light source 430 (FIG. 4) included for spectroscopy system 108 used for spectroscopic purposes.

[0047] The spectroscopy system 108 can send a control light signal from a light source 430 to a target, such as, but not limited to, a stone, soft or hard tissue, bone, or tooth, or an industrial target, and collect spectral response data reflected from the target. The response can be delivered to a spectrometer 411 through a separate fiber, a laser fiber, or an endoscopic system, such as a surgical instrument 102 (FIG. 1). The spectrometer 411 can send digital spectral data to a feedback analyzer 112. Examples of light sources for a spectroscopy system covering the optical range from UV to IR include the light sources described above with reference to Table 2.

[0048] [Table 2]

[0049] The spectroscopy system 108 may additionally be used to perform spectroscopic analysis of the light from the light source 126. The surgical instrument 102 may include a suitable fiber for delivery of light from the light source 126. Examples of light sources suitable for use as the light source 126 are listed in Table 3.

[0050] [Table 3]

[0051] Spectroscopy system 108 may additionally be used to perform spectroscopic analysis of the light from laser modules 122A-122N, such as those listed in Table 1.

[0052] Optical spectroscopy is a powerful method that can be used for simple and rapid analysis of organic and inorganic materials. Any light used for spectroscopic analysis can be integrated into a separate fiber channel, a laser fiber, or an endoscope system. The light source signal reflected from the target can be rapidly collected and delivered to the spectrometer 411 by an imaging system 106, including a detector such as a CCD sensor or a CMOS sensor, which may be included in a digital endoscope, for example. Other imaging systems, such as laser scanning, can also be used to collect the spectroscopic response. Optical spectroscopy has several advantages. It can be easily integrated with a laser fiber in the delivery system 120. Detecting and analyzing material chemical composition is a nondestructive technique, and analysis can be performed in real time. Optical spectroscopy can be used to analyze various types of materials, including, for example, hard and soft tissues, stone structures, and the like.

[0053] Various spectroscopic techniques can be used alone or in combination to analyze target chemical composition and generate spectroscopic feedback. Examples of such spectroscopic techniques include UV-VIS reflectance spectroscopy, fluorescence spectroscopy, Fourier-Transform Infrared Spectroscopy (FTIR), or Raman spectroscopy, among others. Table 2 presents examples of light sources for the spectroscopy system 108, covering the optical range from UV to IR and applicable to one example. Tungsten-halogen light sources are typically used to perform spectroscopic measurements in the visible and near-IR range. Deuterium light sources are known for their stable output and are used for UV absorption or reflectance measurements. Mixing halogen light with deuterium light creates a broad-spectrum light source that provides a smooth spectrum from 200 to 2500 nm. Xenon light sources are used in applications where long life and high output power are required, such as in fluorescence measurements. LED and laser diode light sources provide high power at precise wavelengths and have long life, short warm-up times, and high stability. The spectroscopic light source can be integrated into a separate fiber channel, a laser fiber, or into the endoscope system. The light source signal reflected from the target can be rapidly detected and delivered to the spectrometer through a separate fiber channel or laser fiber.

[0054] Feedback Analyzer 112 Feedback analyzer 112 can receive input from various sources, including spectrometer 411 of spectroscopy system 108 and spectroscopic response data from AI engine 114, to suggest or directly adjust laser system operating parameters, including parameters of laser modules 122A-122N or operating parameters of light source 126. In an example, feedback analyzer 112 can compare spectroscopic response data, such as from beam 142, beam 150, and reflected light beam 172, with available database libraries of baseline spectrographs for various light sources 126, such as the baseline spectrograph of FIG. 2, and anatomical target composition data for various combinations of light source 126 or laser modules 122A-122N and anatomical targets. Examples of tissue spectrographs for various types of light sources are described in U.S. Patent Application Publication No. 2021 / 0038064 to Shelton et al., which is incorporated herein by reference in its entirety. Based on the different spectroscopic system feedback, the feedback analyzer 112 can detect the composition of the light source 126 and the anatomical target 422 and suggest a laser operating mode (also referred to as a laser setup), such as operating parameters for at least one of the laser modules 122A-122N, to prevent damage to the optical fiber, achieve effective tissue treatment for the identified tissue composition, and suggest an illumination light operating mode (also referred to as an illumination light setup), such as operating parameters for the light source 126. Examples of operating parameters for the laser modules 122A-122N that can be adjusted include at least one laser wavelength, pulsed or continuous wave (CW) emission mode, peak pulse power, pulse energy, pulse rate, pulse shape, and simultaneous or sequential emission of pulses from at least one laser module. Sequential pulses include bursts of pulses that combine to deliver a selected pulse energy. As described herein, a pulse generally refers to the time between starting and stopping laser emission from a laser module.The intensity of the laser energy during each pulse can be varied to have a rising or falling ramp or sinusoidal profile, or any other shape, alone or in combination with a series of pulses, as long as the selected average laser power is maintained. For example, if there is only one pulse, a 2 W average power setting with 1 J pulse energy at a frequency of 2 Hz is used. However, the energy can also be delivered as two 0.5 J pulses in rapid succession occurring at a rate of 2 Hz. Each of the pulses can have a similar or different pulse shape. The feedback analyzer 112 can utilize algorithms and input data to directly adjust or suggest laser operating parameters, such as those described in the example above. Examples of operating parameters for the light source 126 that can be adjusted include amplitude, brightness, power, wavelength, and intensity. In an example, light intensity can be adjusted within a range of values ​​depending on the target material, application, and ambient light. Additionally, the wavelength range and spectral shape can be adjusted with additional optical filters. LED light source optical characteristics can also be adjusted by controlling the intensity of the component LEDs.

[0055] Laser Controller 124 The laser controller 124 may be integrated with a laser coupling system 125. The laser coupling system 125 may couple one or more of the laser modules (e.g., solid-state laser modules) 122A-122N into a fiber. The laser controller 124 may be coupled to a feedback analyzer 112, which may send an optimized signal with suggested settings directly to the laser controller 124 (automatic mode) or may request operator approval to adjust the laser settings (semi-automatic mode). FIG. 1 is a schematic diagram of a fully automated laser system, in which the laser controller 124 may be automatically adjusted by the feedback analyzer 112. FIG. 4 is a schematic diagram of a semi-automated laser system, in which the surgical system 100 requires user approval, such as via a display 482 including a user interface 484. In one example, the laser settings may be adjusted within a setting range, which, in one example, may be predetermined by a user at the start of a procedure.

[0056] In some examples, the laser controller 124 can combine two or more laser pulse trains to create a combined laser pulse train. The laser controller 124 can generate several (e.g., N) laser pulse trains, combine the laser pulse trains into a combined pulse train, and present the combined pulse train to the target. Different laser trains can be turned on at different times and / or turned off at different times according to a feedback analyzer signal. The output combined laser pulse train can include portions where two or more of the laser trains overlap in time.

[0057] Using the combination of laser modules 122A-122N, the spectroscopy system 108, feedback analyzer 112, and feedback control system 110 as described herein can continuously identify the composition of the target through the endoscope and update the laser settings throughout the procedure.

[0058] The major components of the laser system 104 can be easily customized depending on the targeted medical procedure. For example, the laser controller 124 can support different laser types and their combinations. This allows for a wider range of output signal options, including power, wavelength, pulse rate, pulse shape and profile, single laser pulse trains, and combined laser pulse trains. The operating mode of the laser system 104 can be automatically adjusted or suggested for each desired optical effect. The spectroscopy system 108 can gather information about the target material, which is useful for diagnostic purposes and to ensure that laser parameters are optimal for the target. The feedback analyzer 112 can automatically optimize the operating mode of the laser system, reducing the risk of human error.

[0059] Internet of Things (IoT) Systems 116 In some examples, the surgical system 100 can include an IoT system 116 that supports storing a spectral database library on the cloud 118, supports rapid access to the spectra and optimal setup database library, and enables communication between the cloud 118 and the feedback analyzer 112. The spectral database library can include 1) predetermined spectrographs for various combinations of light sources that can be used to identify the light source, and 2) predetermined spectrographs for various combinations of light sources and anatomical structures that can be used to identify the anatomical target. Cloud storage of data supports the use of artificial intelligence (AI) techniques to provide input to the feedback analyzer 112 and supports immediate access to algorithms and database improvements, as described in more detail with reference to FIG. 3.

[0060] According to various examples described herein, the IoT system 116 can include a network through which components of the surgical system 100 can communicate and interact with one another via the Internet. The IoT supports rapid access to a spectral database library stored on the cloud 118 and facilitates communication between the cloud 118 and the feedback analyzer 112. Additionally, all of the components of the surgical system 100 can be remotely monitored and controlled, if necessary, through the network. One example of such a successful connection is the Internet of Medical Things (also known as the Internet of Health Things), which is an available application of the IoT for medical and health-related purposes, including data collection and analysis for research and monitoring.

[0061] In various examples, the IoT system 116 may support access to various cloud resources, including cloud-based detection, recognition, or classification of spectral light sources and target structures (e.g., stone structures or anatomical tissues). In some examples, a machine learning (ML) engine, such as the AI ​​model 304 of FIG. 3, may be implemented in the cloud 118 to provide cloud-based target detection, identification, or classification services. The ML engine may include a trained ML model (e.g., machine-readable instructions executable on one or more microprocessors).

[0062] The ML engine can receive spectroscopic data from laser system 104 or retrieve target spectrometer data stored in cloud 118 for spectroscopic light sources, e.g., light source 126 and light source 430, perform light source detection, identification, or classification, and generate output such as a label representing the light source type (e.g., xenon or LED).

[0063] The ML engine can receive target spectroscopic data from the laser system 104 or retrieve target spectroscopic data stored in the cloud 118, perform target detection, identification, or classification, and generate output such as a label representing a tissue type (e.g., normal tissue or a cancerous lesion, or tissue at a particular anatomical location) or a stone type (e.g., a kidney stone, a bladder stone, a pancreatic gallstone, or a gallbladder stone with a particular composition).

[0064] Among the clinical data collected from the patient before or during the procedure, the light source and target spectroscopic data may be automatically uploaded to the cloud 118 at the end of the procedure or at other scheduled times. Alternatively, a system user (e.g., a clinician) can be prompted to upload the data to the cloud 118. In some examples, the output may additionally include the probability that the target is identified as tissue or a stone, or the probability that the target is classified as a particular tissue type or stone type. A system user (e.g., a clinician) can use such a cloud service to obtain information about the target tissue or stone in vivo in near real time, such as while performing an endoscopic laser procedure.

[0065] In some examples, the ML engine may include a training module configured to train the ML model using training data as stored in the cloud 118. The training data may include target information, such as spectroscopic data associated with the light source and tags identifying the target type (e.g., stone type or tissue type). The training data may include laboratory data based on spectroscopic analysis of various light sources and tissue and / or stone types. Additionally or alternatively, the training data may include clinical data acquired from multiple patients in vitro or in vivo. In some examples, patient-identifying information may be removed from patient clinical data (e.g., spectroscopic data) before such data is used or uploaded to the cloud 118 to train the ML model or to perform target detection, identification, or classification using the trained ML model. The system 100 may associate de-identified patient clinical data with tags identifying the source of the data (e.g., hospital, laser system-specific information, time of procedure). A clinician may analyze and confirm the target type (e.g., stone type or tissue type) during or after the procedure, and associate the light source and target type with the de-identified patient clinical data to form the training data. The use of de-identified patient clinical data can advantageously improve the robustness of the cloud-based ML model, as additional data from a large patient population can be included to train the ML model, which can also improve the performance of the ML model for recognizing unusual stone types, as spectroscopic data from these types is difficult to obtain clinically or from a laboratory.

[0066] Various ML model architectures and algorithms may be used, such as decision trees, neural networks, deep learning networks, and support vector machines. In some examples, training of the ML model may be performed continuously or periodically, or in near real time, as additional spectroscopic data becomes available. Training involves algorithmically adjusting one or more ML model parameters until the ML model being trained meets specified training convergence criteria. The resulting trained ML model may be used in cloud-based target detection, recognition, or classification. Using ML models trained by leveraging large amounts of data stored in the cloud 118 and additional data added thereto continuously or periodically, ML-based target recognition using cloud connectivity as described herein can improve the accuracy and robustness of in vivo target detection, recognition, and classification.

[0067] 3 shows a schematic diagram of an exemplary computer-based clinical decision support system (CDSS) 300 configured to identify light and tissue types and generate light-generation parameters to better identify and treat tissue and improve system performance based on the spectrum of light reflected from anatomical tissue, such as wavelength and light intensity. The CDSS 300 may comprise an example of the AE engine 114 of FIG. 1.

[0068] The CDSS 300 may include an input interface 302, an AI model 304, an output interface 306, and may be connected to a database 308. The input interface 302 may be connected to a feedback control system 110 and thus may receive input from the spectroscopy system 108, the feedback analyzer 112, and the delivery system 120, including the reflected illumination light beam 142 and the reflected laser beam 150.

[0069] In various embodiments, the CDSS 300 includes an input interface 302 through which spectral analysis or spectroscopic information, such as wavelength, light intensity, and spectral shape, specific to a treatment for a patient is provided as input features to an artificial intelligence (AI) model 304. Additional inputs may include an illumination light type, a treatment light type, a target tissue type, and a surgical treatment type. Additional other inputs, such as whether the AI ​​model 304 is performing a light source-specific or tissue-specific treatment, may also be provided. The processor may perform estimation operations in which the spectral analysis output is applied to the AI ​​model to generate light parameters and a user interface (UI) through which the light parameters are communicated to a user, e.g., a clinician.

[0070] In some embodiments, the input interface 302 can be a wired or wireless or direct data link via the Internet or IoT system 116 (FIG. 1) between the CDSS 300 and one or more medical devices that generate at least some of the input features. The database 308 can reside on the cloud 118 (FIG. 1). The input interface 302 can transmit spectral analysis data directly to the CDSS 300 during a therapeutic and / or diagnostic medical procedure. Additionally or alternatively, the input interface 302 can be a classic user interface that facilitates interaction between a user and the CDSS 300. For example, the input interface 302 can facilitate a user interface through which a user can manually input optical parameters such as mode, power, and geometry. Additionally or alternatively, the input interface 302 can provide the CDSS 300 with access to an electronic patient record from which one or more input features can be extracted. In any of these cases, the input interface 302 may be configured to collect one or more of the following input features associated with a particular patient at or before the time the CDSS 300 is used to assess light type and tissue type:

[0071] In an example, the first input feature may comprise a light type, such as an illumination or a laser.

[0072] In an example, the second input characteristic may comprise a particular light type, such as xenon, LED, halogen, LD, etc.

[0073] In an example, the third input feature may comprise a particular light type, such as Ho:YAG, Tm-Fiber, etc.

[0074] In an example, the fourth input feature may comprise tissue type, such as healthy tissue, diseased tissue, etc.

[0075] In an example, the fifth input feature may comprise an anatomical tissue type such as kidney, uterus, intestine, stomach, etc.

[0076] In an example, the sixth input characteristic may comprise an optical wavelength.

[0077] In an example, the seventh input feature may comprise light intensity.

[0078] In an example, the eighth input feature may comprise a spectral shape, such as a slope.

[0079] Other input features may additionally be used consistent with this disclosure, and not all of the input features may be used.

[0080] Based on one or more of the above input features, the processor performs an inference operation using the AI ​​model to generate light parameters. For example, the input interface 302 can deliver light type and tissue, light intensity and wavelength, and spectral shape type into the input layer of the AI ​​model, which propagates these input features through the AI ​​model to the output layer. The AI ​​model can provide a computer system with the ability to perform tasks without being explicitly programmed by making inferences based on patterns found in analyzing data. The AI ​​model explores the exploration 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 example training data to make data-driven predictions or decisions, which are expressed as outputs or assessments. In one example, the AI ​​model 304 can suggest the type of laser to be used to treat a particular type of tissue based on laser performance and tissue combinations from previous surgical procedures stored in the database 308. In another example, the AI ​​model 304 can suggest pulse trains for a particular tissue and surgical procedure to perform the surgery better or more quickly based on the results of previous surgical procedures stored in the database 308. The results of the current surgical procedure being performed can then be stored in the database 308, so that the AI ​​model 304 can include additional data points for suggesting parameters for the laser modules 122A-122N. Thus, as the database 308 grows, such as when a surgeon uses their own preferences over the parameters suggested by the AI ​​model 304, new surgical results can be included that can facilitate the AI ​​model 304 adapting to suggest different parameters for the laser modules 122A-122N.

[0081] There are two general modes of machine learning (ML): supervised ML and unsupervised ML. Supervised ML uses prior knowledge (e.g., examples correlating inputs with outputs or outcomes) to learn the relationship between inputs and outputs. The goal of supervised ML is to learn a function that best approximates the relationship between training inputs and training outputs, given some training data, so that the ML model can enforce that same relationship when given inputs to generate corresponding outputs. Unsupervised ML is the training of an ML algorithm using information that is not classified or labeled, allowing the algorithm to operate on that information without guidance. Unsupervised ML is useful in exploratory analysis because it can automatically identify structures in data.

[0082] Common tasks for supervised ML are classification and regression problems. Classification problems, also called categorization problems, aim to classify items 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 assigning scores to the values ​​of some inputs). 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).

[0083] 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.

[0084] Another type of ML is federated learning (also known as collaborative learning), which trains algorithms across multiple decentralized devices that maintain local data without exchanging data. This approach contrasts with traditional centralized machine learning techniques, in which all local datasets are uploaded to a single server, as well as more classical decentralized approaches that often assume equal distribution of local data samples. 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.

[0085] In some examples, the AI ​​model may be continuously or periodically trained prior to execution of an estimation operation by the processor. Then, during the estimation 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 corresponding to light parameters. For example, spectroscopic wavelengths and intensities may be provided to the AI ​​model 304 from the spectroscopy system 108. The wavelengths and intensities may be used to identify the light source and / or the specific tissue, such as with the feedback analyzer 112. The AI ​​model 104 may analyze the spectroscopic characteristics of the reflected light, e.g., wavelength and intensity, and identify the light source used to generate the wavelengths and intensities. The AI ​​model 104 may analyze the spectroscopic characteristics of the reflected light, e.g., wavelength and intensity, and identify the anatomical tissue from which the light was reflected. The AI ​​model 104 can analyze the identified tissue for a given wavelength and intensity, generate parameters for the identified light source, and modify the output parameters of the laser modules 122A-122N to improve the surgical procedure, such as the laser operating mode (pulsed or continuous wave (CW)), power and energy, pulse shape and profile, laser emission pulse regime, and combine all of the generated pulses into a combined output pulse train. The modified parameters generated by the AI ​​model 304 can result in a spectral shape that can provide a clearer indication of tissue type identification, thereby improving the likelihood that the appropriate target tissue will be the recipient of the surgical procedure. The modified parameters generated by the AI ​​model 304 can provide laser parameters that are more effective in treating diseased tissue or that prevent damage to optical fibers, for example.

[0086] During and / or after the estimation operation, the light parameters can be communicated to a user via a user interface (UI) and / or automatically cause the light generator to change the light-generation parameters to the parameters identified and suggested by the AI ​​model 304. For example, the light generator can automatically change the light-generation parameters, or the input interface 302 can provide a prompt or message to the clinician via an output device, such as a screen or display 482 (FIG. 4), with the suggested changes and request the clinician to accept the changes, for example, using the user interface 484 (FIG. 4). Further, the output interface 306 can output a tissue type so the clinician can verify the tissue on which the medical procedure should be performed. Additionally or alternatively, a medical device, such as an endoscope or treatment device, can generate an ablation signal or ultrasound signal to treat the target tissue, either automatically or with the guidance of a clinician.

[0087] FIG. 4 illustrates an exemplary feedback-controlled laser therapy system 400. In FIG. 4, the laser therapy system 400 includes an endoscope 402 integrated with the feedback-controlled laser therapy system 400, which receives light source feedback. The laser therapy system 400, which is an example of the surgical system 100 (FIG. 1), includes an endoscope 402, a laser source 420, an illumination source 425 (e.g., light source 126), and a spectroscopic light source 430. In various examples, a portion or the entire feedback-controlled laser therapy system 400 may be incorporated into the endoscope 402. The feedback-controlled laser therapy system 400 may operate similarly to the surgical system 100 of FIG. 1, with the addition of a light source 430 that may be used to provide input to a spectrometer 411, instead of the spectroscopic system 108 of FIG. 1 using input from the light source 126, and with the addition of a user input system 480 that allows user adjustment of the laser controller 413, instead of the feedback analyzer 112 that directly adjusts the laser controller 124 of FIG. 1. FIG. 4 additionally shows that imaging signal 450 from endoscopic camera module 416 is being provided to spectrometer 411 .

[0088] The feedback-controlled laser therapy system 400 may include a spectrometer 411, which may be included in the spectroscopy system 108, a feedback analyzer 412 (an example of at least a portion of the feedback analyzer 112), and a laser controller 413 (an example of the laser controller 124). The laser source 420 may comprise an example of a laser module 122A-122N and may be coupled to a laser fiber 404. Fiber-integrated laser systems may be used for endoscopic procedures due to their ability to deliver laser energy through flexible endoscopes and effectively treat hard and soft tissues. These laser systems produce laser output beams within a wide wavelength range from the UV to the IR (200 nm to 10,000 nm). Some fiber-integrated lasers produce output within wavelength ranges that are significantly absorbed by soft or hard tissues, such as 1900-3000 nm for water absorption or 400-520 nm for oxyhemoglobin and / or deoxyhemoglobin absorption. Table 2 above is a summary of IR lasers that emit in the high water absorption range of 1900-3000 nm and are suitable for use as light source 430.

[0089] Some fiber-integrated lasers produce output in wavelength ranges that are minimally absorbed by target soft or hard tissue. These types of lasers result in effective tissue coagulation due to penetration depths similar to the diameter of thin capillaries, 5-10 μm. Examples of laser sources 420 include GaN lasers with emissions in the 515-520 nm range, In lasers with emissions in the 370-493 nm range, among others. X Ga 1-X N laser, Ga with emission in the range 750-850 nm X Al 1-X As laser, or In with emission in the range 904-1065 nm X Ga 1-X In such as As laser X Ga 1-X N semiconductor laser, UV-VIS emitting.

[0090] The light source 430 can produce an electromagnetic radiation signal that can be transmitted to the anatomical target 422 via a first optical pathway extending along the elongated body of the endoscope 402. The first optical pathway can be located within the working channel 418. In one example, the first optical pathway can be an optical fiber separate from the laser fiber 404. In another example, the electromagnetic radiation signal can be transmitted through the same laser fiber 404 used to transmit the laser beam. The electromagnetic radiation exits the distal end of the first optical pathway and projects onto the target structure and the surrounding environment. The anatomical target 422 is within the field of view of the endoscopic camera module 416 (e.g., camera module 128). As a result, in response to the projection of the electromagnetic radiation onto the target structure and the surrounding environment, the endoscopic camera module 416, such as a CCD or CMOS camera, can collect a signal reflected from the anatomical target 422, produce an imaging signal 450 of the target structure, and deliver the imaging signal to the feedback-controlled laser therapy system 410. In some examples, imaging systems other than CCD or CMOS cameras, such as laser scanning, may be used to collect the spectroscopic response.

[0091] In addition to or instead of the feedback signal (e.g., imaging signal 450) generated and transmitted through the endoscopic camera module 416, in some examples, a signal reflected from the anatomical target 422 can additionally or alternatively be collected and transmitted to the feedback-controlled laser therapy system 410 through a separate fiber channel or laser fiber, such as that associated with the endoscope 402. In a further example, the laser therapy system 400, including the endoscope 402 integrated with the feedback-controlled laser therapy system 400, can be configured to receive spectroscopic sensor feedback. The reflected spectroscopic signal 470 (which can function similarly to the reflected illumination light beam 142 and reflected laser beam 150 of FIG. 1 ) can travel back to the feedback-controlled laser therapy system 410 through the same optical path, such as the laser fiber 404, used to transmit electromagnetic radiation from the light source 430 to the anatomical target 422. In another example, the reflected spectroscopic signal 470 can travel from a first optical fiber transmitting electromagnetic radiation from the light source 430 to the target structure to the feedback-controlled laser therapy system 410 through a second optical path, such as a separate optical fiber channel.

[0092] The feedback-controlled laser therapy system 400 can analyze one or more feedback signals (e.g., the imaging signal 450 of the target structure, or the reflected spectroscopic signal 470, or the spectrometer signal 152 or the reflected illumination light beam 142 or the reflected laser beam 150 of FIG. 1 ) to determine the light source, tissue type, and operating conditions for one or more of the laser source 420, the illumination light source 425, and the spectroscopic light source 430, such as by using the procedures outlined with reference to FIG. 5 . The spectrometer 411 can generate one or more spectroscopic characteristics from the one or more feedback signals, such as by using one or more of an FTIR spectrometer, a Raman spectrometer, a UV-VIS spectrometer, a UV-VIS-IR spectrometer, or a fluorescence spectrometer. The feedback analyzer 412 can be configured to identify or classify the target structure as one of a plurality of structure categories or types, such as by using one or more of a target detector or target classifier. Laser controller 413 may be configured to determine the operating modes of laser source 420, illumination source 425, and light source 430, as also described above with reference to FIG.

[0093] 4 additionally shows that the feedback-controlled laser therapy system 400 includes a user input system 480, which may include a display 482 and a user interface 484. The user input system 480 may receive a signal from the feedback analyzer 412 to provide an output on the display 482 including information related to proposed changes to the laser controller 413, the illumination source 425, and the light source 430. In an example, the settings for the laser source 420 may be adjusted within a range of settings provided by the display 482, which may, in one example, be predetermined by the user at the start of treatment. The display 482 may receive a signal 485 from the feedback analyzer 412 indicating recommended settings or ranges of settings for the light source 430, the illumination source 425, and the laser controller 413. The display 482 may display a recommendation 486 to the user, including an audio signal or a visual or graphical representation of the recommended settings or ranges of settings for the light source 430, the illumination source 425, and the laser controller 413. The user can provide input 488 to either affirm or reject the recommendation of signal 485 or to select a particular setting from a range of recommended settings.

[0094] 5 is a block diagram illustrating operations in a method 500 of identifying and adjusting a light source using a spectroscopic surgical system described herein. FIG. 5 illustrates one example of a sequence of operations that may be used in method 500, although other steps may be included that are not inconsistent with the disclosure provided herein. Additionally, some operations may be performed in a different order or omitted in additional examples.

[0095] In operation 502, a light beam may be generated using a light source. For example, light source 126 (FIG. 1) may generate light beam 140. Different types of light source 126 may be used with surgical system 100 (FIG. 1). For example, light source 126 may be configured to generate xenon light or LED light. The light beam may be reflected from test target 170. The reflected light beam 172 may be received by spectroscopy system 108. For example, reflected light beam 172 may be received by delivery system 120 within surgical instrument 102 and passed through a light guide, e.g., optical fiber, to spectrometer 411 (FIG. 4). Surgical instrument 102 and delivery system 120 (FIG. 1) may be used to direct the light beam to anatomical target 422, for example, using optical fiber.

[0096] In operation 504, spectroscopy system 108 may perform a spectroscopic analysis of reflected light beam 172. For example, the intensity and wavelength of reflected light beam 172 may be compared to database information of intensities and wavelengths for different types of light sources. The light intensity may be compared to database information comprising light intensity values ​​for different wavelengths of different types of light sources, such as different types of light sources 126 that produce xenon light and LED light. In an example, the spectroscopic information for the different types of light sources may be stored in spectroscopy system 108. In an additional example, spectroscopy system 108 may retrieve the spectroscopic information for the different types of light sources from cloud 118 ( FIG. 1 ) or memory 604 ( FIG. 6 ).

[0097] In operation 506, the intensity and wavelength data set that most closely matches that of reflected light beam 172 may be used to identify the type of light coming from light source 126 or another light source. Thus, spectroscopic analysis of light beam 140 for light source 126 may be used to verify the type of light source being used for spectroscopic tissue analysis to ensure that subsequent spectroscopic analysis of the tissue is performed correctly. In an example, spectroscopic analysis of light beam 140 for light source 126 may be used to determine the manufacturer of light source 126.

[0098] Operations 502-506 are described with reference to determining the type of light emanating from light source 126. However, similar operations may be performed using light source 430 and laser modules 122A-122N. That is, pure, or unattenuated, light from light source 430 and laser modules 122A-122N may be analyzed before being incident on the target tissue.

[0099] In operation 508, a light beam may be generated using a light source, such as the same light beam generated in operation 502. For example, light source 126 (FIG. 1) may generate light beam 140. Light beam 140 may be reflected from target tissue on which a medical procedure is to be performed. For example, light beam 140 may be incident on anatomical target 422 of patient 130. Light beam 140 may be reflected from anatomical target 422 as reflected illumination light beam 142. Surgical instrument 102 and delivery system 120 (FIG. 1) may be used to direct the light beam to anatomical target 422, for example, using optical fibers.

[0100] In operation 510, the reflected light from operation 504 may be received by a spectroscopy system. For example, the reflected illumination light beam 142 can be received by the delivery system 120 in the surgical instrument 102 and passed through a light guide, e.g., an optical fiber, to a spectrometer 411. The received light may be analyzed by a spectroscope. For example, the spectrometer 411 may analyze the light intensity versus wavelength of the reflected illumination light beam 142. The light intensity may be compared to database information comprising light intensity values ​​for different wavelengths of different types of anatomical tissue, such as stones or cancerous cells. In an example, the spectroscopic information for different types of anatomical targets may be stored in the spectroscopy system 108. In a further example, the spectroscopy system 108 may retrieve the spectroscopic information for different types of anatomical targets from the cloud 118 (FIG. 1) or memory 604 (FIG. 6).

[0101] In operation 512, the type of anatomical tissue that reflected the light beam 142 may be determined. For example, the light intensity versus wavelength of the reflected illumination light beam 142 may be matched with a corresponding set of data points from predetermined reference data. Thus, the spectroscopy system 108 may reliably identify the type of tissue that produced the combination of wavelength and light intensity. Thus, the anatomical target 422 may be identified. Thus, spectroscopic analysis of the light beam 140 relative to the anatomical target 422 may be used to verify the tissue type and ensure that the surgical procedure is performed correctly. In an example, the method 500 may proceed directly from operation 512 to operation 526.

[0102] In operation 514, a surgical procedure being performed may be analyzed in conjunction with method 500. For example, the surgical procedure may be analyzed to determine suggested settings or a range of settings for the components of surgical system 100 to perform the surgical procedure. The suggested settings may be used to improve the surgical outcome or facilitate easier performance of the surgical procedure. The surgical procedure may be analyzed using input from surgical system 100 in operation 516 and input from AI engine 114 in operation 515.

[0103] In operation 516, the surgical data may be combined with the identified light source and identified tissue type to analyze the surgical procedure. In an example, the surgical data may include the type of laser module being used in the surgical procedure, e.g., the type of laser modules 122A-122N, the settings for the laser modules 122A-122N being used, the type of surgical instrument 102 being used, the type of delivery system 120 being used, etc. Additionally, the surgical system 100 may be initially configured to perform a particular type of procedure, such as ablating, dissecting, or cauterizing an anatomical target 422 (FIG. 4), such as a stone or cancerous tissue, using one or more of the laser modules 122A-122N. The surgeon may input parameters such as output power, emission range, pulse shape, and pulse train into the laser controller 124 to generate the desired type of therapeutic laser 148 (FIG. 1) to engage the anatomical target 422. Thus, the input in operation 516 may include the surgeon's preferences based on the surgeon's own past experience or judgment.

[0104] In operation 515, the AI ​​input may be combined with the surgical data, the identified tissue type, and the identified light source type. The AI ​​engine 114 (FIG. 1) may include or be connected to a storage system having a database, such as database 308, of information related to multiple different types of surgical procedures that may be performed using the light source 126 (FIG. 1) and one or both of the laser modules 122A-122N. In an example, the cloud 118 may be connected to a server having a memory (e.g., memory 604 or 606 of FIG. 6) on which such information is stored. The information stored in the cloud 118 or the AI ​​engine 114 may include combinations of parameters, including different types of light source 126, different types of laser modules 122A-122N, and different settings (e.g., output power, emission range, pulse shape, and pulse train), for different types of surgical procedures (e.g., cancer resection, kidney stone resection, gallbladder stone resection, etc.). For example, for each type of procedure, the information may include outcome data (e.g., patient recovery, recurrence, etc.) for different combinations of surgical parameters.

[0105] In operation 517, adjustments for the ongoing surgical procedure may be determined in conjunction with method 500. For the type of light from light source 126 identified in operation 510, AI engine 114 may recommend parameters that will produce the best patient outcome. In an example, operation 517 may utilize AI model 304 to determine adjustments for the surgical procedure.

[0106] In operation 518, the determined adjustment values ​​for the surgical procedure of operation 517 may be displayed for user reference. In an example, a spectral analysis of the light beam 140 for the light source 126 may be used to suggest settings for the light source 126, the light source 430, and the laser modules 122A-122N. For example, the display 482 (FIG. 4) may provide a visual or graphical output of recommended settings for the surgical system 100, or ranges of values ​​for the settings. The recommended settings may include, but are not limited to, output power, emission range, pulse shape, and pulse train for different types of laser modules 122A-122N for different types of surgical procedures (e.g., cancer resection, kidney stone resection, gallbladder stone resection, etc.). Similarly, operating parameters for the light source 126 that may be suggested may include amplitude, brightness, power, wavelength, and intensity.

[0107] Settings for the surgical procedure may be automatically adjusted in operation 520. For example, the feedback analyzer 112 may provide a light signal 160 to the light source 126 and a laser signal 162 to the laser controller 124 to apply the proposed changes without user input.

[0108] In operation 522, adjustments to the surgical procedure may be presented to the user as suggested adjustments. For example, display 482 (FIG. 4) may provide a visual or graphical output of recommended settings for surgical system 100, or ranges of values ​​for settings. Display 482 may request Yes / No acceptance of various parameters, or may request entry or selection of values ​​within the proposed range. Display 482 may also provide an option to reject any or all of the proposed parameter changes, such as allowing the surgeon to utilize previously entered parameters.

[0109] Surgeon approval for the recommended changes, or surgeon selection from a recommended range of settings, may be obtained in act 524. The user may interact with user interface 484 by providing voice commands or tactile input to select and / or confirm the proposed settings presented in act 522.

[0110] In operation 526, the surgical procedure may be performed. The surgical procedure may be performed using an appropriate or desired combination of illumination light source, anatomical target, and therapeutic light. The surgical procedure may be performed using parameters originally entered by the surgeon based on surgeon skill, preference, and assessment, the surgical procedure may be performed using parameters determined by the AI ​​model 304, or a combination thereof.

[0111] In operation 528, tissue identification functionality may be shut down. In an example, spectroscopic analysis of light beam 140 and reflected light beam 172 for light source 126 may be used to disable the tissue verification system. For example, if operation 506 is unable to determine the output of light source 126, the surgical system's ability to perform tissue type confirmation may be disabled. An appropriate warning may be provided on display 482. The surgeon may then allow the system to continue performing the surgical procedure using the user-entered parameters.

[0112] 6 is a block diagram of an example machine 600 on which any one or more of the techniques (e.g., methodologies or operations) described herein may be executed. Portions of this description may apply to the computing framework of various portions of example laser therapy and spectroscopy systems as described herein.

[0113] In an example, machine 600 can operate as a standalone device or can be connected (e.g., networked) to other machines. In a networked deployment, machine 600 can operate in the capacity of a server machine, a client machine, or both in a server-client network environment. In one example, machine 600 can function as a peer machine in a peer-to-peer (P2P) (or other distributed) network environment. Machine 600 can 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, switch, or bridge, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by the machine. Furthermore, while only a single machine is illustrated, the term “machine” shall also be understood to include any collection of machines, individually or collectively, that execute a set (or sets) of instructions to perform any one or more of the methodologies described herein, such as cloud computing, software as a service (SaaS), other computer cluster configurations, etc.

[0114] Examples such as those described herein may include or operate through logic or several components or mechanisms. A circuit set is a collection of circuits (e.g., simple circuits, gates, logic, etc.) implemented in a tangible entity, including hardware. Circuit set membership may be flexible over time and subject to hardware variability. A circuit set includes members that, alone or in combination, can perform the operations for which they are specified to operate. In one example, the hardware of a circuit set may be invariably 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.) including computer-readable media that are physically modified (e.g., magnetically, electrically movable arrangements of immutable aggregated particles, etc.) to encode instructions for a specific operation. When connecting the physical components, the underlying electrical properties of the component hardware are changed, for example, from insulator to conductor or vice versa. The instructions, when in operation, enable the embedded hardware (e.g., an execution unit or a loading mechanism) to create a member of a circuit set in the hardware via a variable connection to perform a particular portion of the operation. 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 can be used in two or more members of two or more circuit sets. For example, under operation, an execution unit can 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.

[0115] The machine (e.g., a computer system) 600 may include a hardware processor 602 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 604, and a static memory 606, some or all of which may communicate with each other via an interlink (e.g., a bus) 608. The machine 600 may further include a display unit 610 (e.g., a raster display, a vector display, a holographic display, etc.), an alphanumeric input device 612 (e.g., a keyboard), and a user interface (UI) navigation device 614 (e.g., a mouse). In one example, the display unit 610, the input device 612, and the UI navigation device 614 may be touchscreen displays. The machine 600 may additionally include a storage device (e.g., a drive unit) 616, a signal generating device 618 (e.g., a speaker), a network interface device 620, and one or more sensors 621, such as a global positioning system (GPS) sensor, a compass, an accelerometer, or other sensors. The machine 600 may include an output controller 628, such as a serial (e.g., Universal Serial Bus (USB)), parallel, or other wired or wireless (e.g., infrared (IR), near field communication (NFC), etc.) connection, to communicate with or control one or more peripheral devices (e.g., a printer, a card reader, etc.).

[0116] The storage device 616 may include a machine-readable medium 622 on which are stored one or more sets of data structures or instructions 624 (e.g., software) embodied or utilized by any one or more of the techniques or functions described herein, such as the operations described with reference to Figure 5. The instructions 624 may also reside, completely or at least partially, within the main memory 604, within the static memory 606, or within the hardware processor 602 during their execution by the machine 600. In one example, one or any combination of the hardware processor 602, the main memory 604, the static memory 606, or the storage device 616 may constitute a machine-readable medium.

[0117] Although the machine-readable medium 622 is illustrated as a single medium, the term “machine-readable medium” may include a single medium or multiple media (e.g., centralized or distributed databases, and / or associated caches and servers) configured to store one or more instructions 624.

[0118] The term "machine-readable medium" may include any medium capable of storing, encoding, or carrying instructions for execution by machine 600 and causing machine 600 to perform any one or more of the techniques of this disclosure, or capable of storing, encoding, or carrying data structures used by or associated with such instructions. Non-limiting examples of machine-readable media include solid-state memory and optical and magnetic media. In one example, a concentrated machine-readable medium comprises a machine-readable medium having a plurality of particles having a non-changing (e.g., stationary) mass. Thus, the concentrated machine-readable medium is not a transitory, propagating signal. Specific examples of concentrated machine-readable media include non-volatile memory such as semiconductor memory devices (e.g., electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM)) and flash memory devices, magnetic disks such as internal hard disks and removable disks, magneto-optical disks, and CD-ROM and DVD-ROM disks.

[0119] The instructions 624 may further be transmitted or received over a communications network 626 using a transmission medium via a network interface device 620 utilizing any one of several 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 telephone 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 called WiFi®, the IEEE 802.16 family of standards called WiMax®), the IEEE 802.15.4 family of standards, peer-to-peer (P2P) networks, among others. In one example, the network interface device 620 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 626. In one example, the network interface device 620 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 understood to include any intangible medium capable of storing, encoding, or carrying instructions for execution by the machine 600, including digital or analog communications signals or other intangible media for facilitating communication of such software.

[0120] Additional notes 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, specific embodiments in which the invention may be practiced. These embodiments are also referred to herein as "examples." Such examples may include elements in addition to those shown or described. However, the present inventors also contemplate examples in which only those elements shown or described are provided. Moreover, the present inventors also contemplate examples (or one or more aspects thereof) using any combination or permutation of those elements shown or described, either with respect to the particular example (or one or more aspects thereof) or with respect to other examples (or one or more aspects thereof) shown or described herein.

[0121] As used herein, the terms "a" or "an" are used, as is common in patent documents, to include one or more, independently of any other instance or use of "at least one" or "one or more." As used herein, the term "or" refers to a non-exclusive or, such that "A or B" includes "A but not B," "B but not A," and "A and B," unless otherwise specified. As used herein, the terms "including" and "in which" are used as the plain-English equivalents of the respective terms "comprising" and "wherein." Also, in the following claims, the terms "including" and "comprising" are open-ended, i.e., systems, devices, items, compositions, formulations, or processes that include elements in addition to those recited after such terms in a claim are still deemed to be within the scope of that claim. Moreover, in the following claims, the terms "first," "second," and "third," etc. are used merely as labels and are not intended to impose numerical requirements on their objects.

[0122] The above description is intended to be illustrative, not limiting. For example, the examples described above (or one or more aspects thereof) can be used in combination with each other. Other embodiments may be employed by those of ordinary skill in the art upon review of the above description. This Abstract is provided to comply with 37 CFR §1.72(b) to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. Also, in the above Detailed Description, various features may be grouped together to streamline the disclosure. This should not be construed as intending that an unclaimed disclosed feature is essential to any claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description as an example or embodiment, with each claim standing on its own as a separate embodiment, and it is contemplated that such embodiments can be combined with each other in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

[0123] (Example) Example 1 is a method for identifying an illumination source in a surgical system, the method comprising the steps of receiving a signal from a target after the target is illuminated by the illumination source, performing a spectroscopic analysis of the received signal, and determining a characteristic of the illumination source based at least in part on the spectroscopic analysis.

[0124] In Example 2, the subject matter of Example 1 optionally includes comparing the spectroscopic analysis to database information containing spectroscopic information for various light types and / or various substances of the target, and determining the characteristics of the illumination source is based at least in part on the comparison of the spectroscopic analysis.

[0125] In Example 3, the subject matter of Example 2 optionally includes where the spectroscopic analysis comprises comparing at least one of the intensities or spectra of the received signal to intensities or spectra associated with various types of illumination sources from the target located in the database information.

[0126] In Example 4, the subject matter of any one or more of Examples 2-3 optionally includes, wherein the target comprises a test target configured to reflect illumination light without light absorption.

[0127] In Example 5, the subject matter of any one or more of Examples 2-4 optionally includes, wherein the illumination source comprises at least one of a xenon light source and an LED light source.

[0128] In Example 6, the subject matter of any one or more of Examples 2-5 optionally includes retrieving the database information from a server connected to the Internet.

[0129] In Example 7, the subject matter of Example 6 optionally includes wherein the database information comprises an artificial intelligence engine.

[0130] In Example 8, the subject matter of any one or more of Examples 1-7 optionally includes adjusting at least one of the parameters or characteristics of the illumination source to improve spectroscopic analysis of the tissue based on the identified illumination source.

[0131] In Example 9, the subject matter of Example 8 optionally includes, wherein the parameters include at least one of brightness, power, wavelength, and intensity, and the characteristics include a type of illumination source.

[0132] In Example 10, the subject matter of any one or more of Examples 1-9 optionally includes illuminating anatomical tissue with illumination light, performing spectroscopic analysis of reflection of the illumination light, and determining characteristics of the anatomical tissue using the spectroscopic analysis.

[0133] In Example 11, the subject matter of Example 10 optionally includes wherein the characteristics include one or more of anatomical tissue type, material, composition, composition profile, structure, and / or hardness.

[0134] In Example 12, the subject matter of any one or more of Examples 10-11 optionally includes adjusting at least one of the parameters or characteristics of the therapeutic light source to improve treatment of the anatomical tissue based on the type of the anatomical tissue.

[0135] Example 13 is a method of treating a target, comprising receiving a signal from the target after the target is illuminated by an illumination source; performing a spectroscopic analysis of the received signal; determining a first characteristic of the illumination source and a second characteristic of the target based at least in part on the spectroscopic analysis; and operating a surgical system to treat the target based at least in part on the determined characteristics of the illumination source and the target.

[0136] In Example 14, the subject matter of Example 13 optionally includes wherein operating the surgical system comprises generating or adjusting one or more parameters of the surgical system, including an operating mode, power or energy, pulse shape profile, emitted pulse regime, and / or combined output pulse train.

[0137] In Example 15, the subject matter of Example 14 optionally includes adjusting the one or more parameters automatically performed by a controller.

[0138] In Example 16, the subject matter of any one or more of Examples 14-15 optionally includes that adjusting the one or more parameters comprises prompting a user to accept the proposed adjustment to the illumination source.

[0139] In Example 17, the subject matter of any one or more of Examples 14-16 optionally includes at least one of the spectroscopic analysis, the parameters of the illumination source, or the characteristics of the illumination source being communicated via the Internet.

[0140] In Example 18, the subject matter of Example 17 optionally includes utilizing an artificial intelligence engine to generate the one or more parameters.

[0141] In Example 19, the subject matter of any one or more of Examples 13-18 optionally includes receiving a signal from the target after the target is illuminated by the illumination source, comprising receiving a first signal from the test target after the test target is illuminated by the illumination source, and receiving a second signal from the anatomical target after the anatomical target is illuminated by the illumination source.

[0142] In Example 20, the subject matter of Example 19 optionally includes wherein performing spectroscopic analysis of the received signal comprises performing spectroscopic analysis of the first signal to identify a type of light emitted by the illumination light source, and performing spectroscopic analysis of the second signal to identify a tissue characteristic of the anatomical target.

[0143] In Example 21, the subject matter of Example 20 optionally includes, wherein the characteristics include one or more of tissue type, material, composition, composition profile, structure, and / or stiffness.

[0144] In Example 22, the subject matter of any one or more of Examples 20-21 optionally includes, wherein the test target comprises a reflective surface and the illumination source comprises a xenon light source or an LED light source.

[0145] Each of these non-limiting examples can stand on its own or can be combined in various permutations or combinations with one or more of the other examples. [Explanation of symbols]

[0146] 100 Surgical Systems 102 Surgical instruments 104 Laser System 106 Imaging System 108 Spectroscopic System 110 Feedback Control System 112 Feedback Analyzer 114 Artificial Intelligence (AI) Engine 116 Internet of Things (IOT) 118 Cloud 120 Delivery System 122 Laser Module 124 Laser Controller 125 Laser Coupling System 126 Light source 128 Camera Module 130 patients 140 Light Beam 142 Reflected illumination light beam 144 Laser Beam 146 Combined Laser Beams 148 Therapeutic Laser 150 Reflected Laser Beam 152 Spectrometer signal 154 Data Signal 156 Signal 158 Signal 160 Optical Signal 162 Laser Signal 170 Test Targets 172 Reflected Light Beam 300 Clinical Decision Support Systems (CDSS) 302 Input Interface 304 AI models 306 Output Interface 308 Database 400 Laser Therapy System 402 Endoscope 404 Laser Fiber 410 Feedback Control Laser Treatment System 411 Spectrometer 412 Feedback Analyzer 413 Laser Controller 416 Endoscope Camera Module 418 Working Channel 420 Laser Source 422 Anatomical Targets 425 Lighting source 430 Spectral light source 450 imaging signal 470 Reflection spectroscopic signal 480 User Input System 482 Display 484 User Interface 485 Signal 486 Recommended 488 input 600 machines 602 Hardware Processor 604 main memory 606 Static Memory 608 Interlink 610 Display Unit 612 Alphanumeric Input Device 614 User Interface (UI) Navigation Devices 616 Storage Devices 618 Signal Generating Device 620 Network Interface Device 621 Sensor 622 Machine-readable medium 624 Command 626 Communication Network 628 Output Controller

Claims

1. 1. A system for remotely operating a laser system, comprising: a light source configured to transmit an optical signal to at least one of a test target or an anatomical target for spectral analysis of the at least one of the test target or the anatomical target; a photodetector configured to detect a response signal from at least one of the test target or the anatomical target and generate a detector signal; a feedback analyzer configured to analyze the detector signal from the light detector to identify a type of light generated by the light source, determine target characteristics of the test target or the anatomical target based at least in part on the type of light identified by the feedback analyzer, and issue control signals for the laser system based on the target characteristics, the feedback analyzer being located remotely from the light detector and in communication with the light detector via a first network connection; A system comprising:

2. 10. The system of claim 1, wherein the control signal is configured to adjust laser light or output energy of the laser system for treatment of at least one of the test target or the anatomical target.

3. The system of claim 1 , wherein the target characteristic comprises tissue type.

4. The system of claim 1 , wherein the feedback analyzer is configured to adjust the control signal based on the target characteristic determined by the feedback analyzer.

5. 3. The system of claim 2, wherein the control signals are configured to adjust the laser light to vary at least one of output power, emission range, pulse shape, and pulse train for different types of laser modules of the laser system.

6. 6. The system of claim 5, further comprising a user interface that requests user confirmation before adjusting the laser light or the output energy.

7. The system of claim 2, wherein the laser system is configured to supply the laser light to an endoscopy system.

8. The system of claim 7 , wherein the light source further comprises an illumination source for the endoscopy system.

9. 9. The system of claim 8, wherein the control signal is configured to adjust a filter, intensity, brightness, amplitude, power, and wavelength of the illumination source based on the identified light type.

10. 3. The system of claim 2, wherein the feedback analyzer is located remotely from the laser system and configured to communicate with the laser system via a second network connection.

11. The system of claim 10 , wherein the first network connection and the second network connection comprise a cloud-based server.

12. The system of claim 1 , further comprising an artificial intelligence engine configured to provide input to the feedback analyzer to facilitate light type identification.

13. a first value correlating the response signal to different types of light for the light source; a second value correlating the response signal to different characteristics of at least one of the test target or the anatomical target; a computer-readable storage medium having stored thereon a database including: The system of claim 1 , wherein the computer-readable storage medium is located remotely from the feedback analyzer and is accessible to the feedback analyzer via a third network connection.

14. the computer-readable storage medium comprises: Spectroscopic plots of intensity versus wavelength for different types of light and different types of tissue; Laser settings for different tissue types The system of claim 13, comprising:

15. 1. A method of operating a system for remotely operating a laser system, comprising: receiving, at an optical detector, a response signal from at least one of a test target or an anatomical target that has received an optical signal from a light source, the optical signal being an optical signal for spectral analysis of at least one of the test target or the anatomical target; generating a detector signal using the photodetector; transmitting the detector signal to a feedback analyzer located remotely from the photodetector; analyzing the detector signal to identify a light type of the light source; determining target characteristics of the test target or the anatomical target based at least in part on the identified light type, and generating control signals for adjusting parameters of the laser system based on the target characteristics; A method comprising:

16. The method described in claim 15, further comprising a step of adjusting the laser light of the laser system for treatment of at least one of the test target or the anatomical target based on the target characteristics.

17. The method of claim 15 , wherein the target characteristic comprises tissue type.

18. The method of claim 15 , further comprising adjusting the control signal based on the target characteristic determined by the feedback analyzer.

19. 20. The method of claim 18, wherein generating the control signals to adjust the parameters of the laser system comprises adjusting at least one of output power, emission range, pulse shape, and pulse train for different types of laser modules of the laser system based on the target characteristic.

20. 16. The method of claim 15, wherein transmitting the detector signal to the feedback analyzer comprises transmitting the detector signal over a first cloud-based network connection.

21. 16. The method of claim 15, wherein the feedback analyzer is located remotely from the laser system and configured to communicate with the laser system via a second cloud-based network connection.

22. 16. The method of claim 15, wherein analyzing the detector signal to identify the light type of the light source comprises determining the light type using an artificial intelligence engine.

23. 16. The method of claim 15, wherein analyzing the detector signal to identify the type of light from the light source comprises comparing the intensity of the detector signal at different wavelengths against graphs of different light sources reflected from different backgrounds.

24. 24. The method of claim 23, further comprising accessing a memory in which the graph is stored, the memory being located on a cloud-based server.

25. The method of claim 15, wherein the light source further comprises an illumination light source, and further comprising a step of adjusting the illumination light of the light source based on the identified type of light.

Images