Spectral collection during continuous wave laser emission

Abstract

A system for spectral collection during an in-vivo medical procedure can include a processor and memory with instructions stored thereon that cause the processor to emit an illumination signal from an illumination source toward an in-vivo target, collect a first return signal from the in-vivo target in response to the illumination signal, and emit a laser signal from a continuous wave laser source toward the in-vivo target. The instructions can further cause the processor to collect a second return signal from the in-vivo target, determine a difference between the first return signal and the second return signal, and take an action based at least in part on the determined difference.

Description

SPECTRAL COLLECTION DURING CONTINUOUS WAVE LASER EMISSION PRIORITY CLAIM

[0001] This application claims the benefit of priority to U.S. Provisional Patent Application Serial No. 63 / 595,385, filed November 2, 2023, and U.S. Provisional Patent Application Serial No. 63 / 672,329, filed July 17, 2024; the contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present disclosure relates to spectroscopic signal detection during diagnostic or therapeutic laser procedures. BACKGROUND

[0003] A laser system may be used during diagnostic or therapeutic medical procedures such as laser lithotripsy procedures. Some procedures involve a physician interacting with targets such as a tumor or a calculus. Tissue-based procedures, on the other hand, such as vaporesection procedures use continuous wave laser energy. Such laser systems may employ visible light emission, which can function as an aiming beam to provide spatial information of the therapeutic laser either before or while the laser light is emitted. Light reflected or scattered by or otherwise returned from a target may be analyzed using a light detector or analyzer such as a spectrometer to detect and characterize the target or to differentiate the target from non-target tissue or objects. SUMMARY

[0004] A laser of a medical laser system can emit energy in a pulsed mode or as a continuous wave. A pulsed laser produces or emits a series of pulses at a particular pulse width and frequency until it is stopped. Conversely, a continuous wave (CW) laser emits energy (or is continuously ON) until it is stopped. Spectral data from a signal from a target (e.g., in response to a signal emitted toward a target from a sight source) can be collected before and during the CW laser emission. Spectral data can also be collected when the laser emission is stopped or paused, such as for interference-free spectral measurements. Since Attorney Docket No.5409.890WO1 1 Client Reference No. GAP24024-URKT-WO1many therapeutic laser systems do not deploy spectroscopic measurements of targeted anatomy or anatomical environments, the presently disclosed systems and methods may have the potential advantage of characterizing different targets or tissue types and allowing therapy to be adjusted based on the identification of, or a change to, the targets or tissue types in real-time or near real-time with the identification or change. Further, the integration of artificial intelligence (AI) and machine-learning (ML) algorithms can allow for immediate (or near immediate) analysis of spectral and video data. This can enable the system to make rapid adjustments to laser settings or operational parameters of medical equipment to help ensure optimal treatment efficacy.

[0005] A method for spectral collection during a medical procedure (e.g., an in-vivo medical procedure) can include emitting an illumination signal from an illumination source toward a target. The target can include an in-vivo target such as tissue in the bladder or kidney, prostate, or the like. The illumination source can include a source of visible light such as a light-emitting diode (LED), a Xenon-based light source, or the like. At least a portion (e.g., a first portion) of a return signal from the target can be collected by, at, via, or using an optical splitter and passed, transmitted, or the like to a photodetector or a similar optical component such as a spectrometer for analysis. A signal from a continuous wave laser source, such as a therapeutic radiation signal, can be emitted toward the in- vivo target to cut, cauterize, or otherwise treat the in-vivo target.

[0006] A second portion of the return signal from the in-vivo target can be collected via the optical splitter (e.g., at a second time, later time, from collection of the first portion, or the like). The first and second portions of the return signal can be detected, for example using an optical sensor or detector and transduced into a time-domain or spectral electrical signal, such as for signal processing by an optical signal processor, such as, for example, using a spectrometer or a similar component capable of performing spectral analysis or a similar analysis of the return signal. For example, the optical sensor or signal processor can include a Raman spectroscopy sensor to provide molecular-level information about target tissue, which can help the system distinguish between different types of tissues or aid in detecting changes in tissue composition during a laser procedure. In another example, a fluorescence sensor can detect specific wavelengths of light (visible or non-visible) emitted by the target in response to Attorney Docket No.5409.890WO1 2 Client Reference No. GAP24024-URKT-WO1illumination. When a change in the return signal is detected, an action can be taken (based at least in part on the change). For example, the action can include stopping or adjusting (e.g., lowering or reducing) the intensity of the laser energy, pausing the laser emission to collect interference-free spectral data, or automatically adjusting one or more other operational parameters such as the focus or position of the laser emission or the position of the tip of the endoscope to optimize treatment efficiently. Additionally, or alternatively, the method can include emitting a second illumination signal from the illumination source (or from a second illumination source) toward the in-vivo target, such as during emission of the laser signal from the continuous wave laser. At least a portion of the second return signal can be at the optical splitter and transmitted to the optical detector or optical component to analyze the spectra of the portion of the second return signal. The second return signal can be filtered or collected and analyzed to detect a change in the second return signal from the first return signal. An additional action can be taken, based at least in part on the change in the first and second return signals. The additional action can include recalibration of the system's sensitivity to enhance data accuracy, initiating a diagnostic check to ensure system integrity and determine whether the change in the first and second return signals was a result of a system anomaly or irregularity, altering a component of the laser signal (e.g., the intensity, wavelength, pulse-width, or the like) to better target or adapt to tissue characteristics observed in the return signals. The additional action may include pausing the laser emission to collect unobstructed spectral data in a quiet window of time or time period, or adjusting one or more equipment settings (e.g., a position of the endoscope, irrigation or suction intensity, or the like) as conditions warrant. Furthermore, the scope used in the system can be configured to support both a continuous wave laser source and a dedicated illumination channel. Such a design may enhance or increase the precision of treatments and the clarity of the visual field during medical procedures. In an example, the adjustments to the laser settings or the equipment settings can be made based on real-time spectral analysis of the return signals and real-time video data analysis. This real-time analysis and adjustments have the potential advantage of preventing the laser emission from contacting or being redirected by non-target tissue. Attorney Docket No.5409.890WO1 3 Client Reference No. GAP24024-URKT-WO1

[0007] The change in the return signal(s) can be determined by inputting spectra from the first and second portion of the return signal or from the first and second return signals into one or more algorithms. An algorithm can include an artificial intelligence (AI) or machine learning (ML) or other algorithm (e.g., a non-AI or non-ML deterministic algorithm) or process. Additionally, or alternatively, the determination can be made using a hardware-based feedback loop or feedback control. The hardware-based feedback loop or feedback control, the AI or ML algorithms, and the non-AI or non-ML algorithms can be used separately or in conjunction with each other as appropriate or desired. The algorithms can be used to interpret complex data scenarios such as identifying flashing events or distinguishing between types of flashing and identifying and analyzing mixed data signals. These feedback mechanisms and control systems can facilitate real-time decision making, faster than a human operator, and can provide real-time alerts or implement real-time adjustment to equipment settings as conditions warrant.

[0008] In addition to spectral data collection, the system can incorporate video analysis to enhance the detection and characterization of in-vivo targets. This multimodal approach can allow for real-time visual confirmation of target types and conditions such as flashing events, facilitating more accurate and immediate responses during laser procedures. The system can employ data handling techniques and strategies to manage the spectral and video data collected during potential flashing events to help ensure that such data is either appropriately excluded or specially processed to avoid misinterpretation. In another example, when a change is detected in the in-vivo target based on analysis of the imaging data, the system can determine whether to keep collecting spectral data. Based on a determination to stop collecting the spectral data, the system can either stop collecting spectral data (or cause the collection of spectral data to be stopped) or predict an optimal time to stop the collection of the spectral data. Thus, in addition to spectral analysis, the system can incorporate video analysis capabilities to enhance the detection and characterization of in-vivo targets. This multimodal approach allows for real-time visual confirmation of target types, changes in the targets, and conditions such as flashing events or unexpected visual artifacts that might affect the medical procedure, facilitating more accurate and immediate responses during laser procedures. The system can employ data handling techniques Attorney Docket No.5409.890WO1 4 Client Reference No. GAP24024-URKT-WO1and strategies to manage the spectral and video data collected during potential flashing events to help ensure that such data is either appropriately excluded or specially processed to avoid misinterpretation.

[0009] The system can incorporate time-based analysis techniques to manage the spectral data collected during periods of high procedural activity, such as when particles are present in the surgical field. This allows for dynamic adjustment of data collection and analysis based on the amount of time that has elapsed since activation of the laser enhancing the precision of the spectral measurements under varying operational conditions. Thus, the system can be configured to make real-time decisions based on the analysis of collected spectral and video data, and rapidly adjust laser settings or cease emission of the laser to help prevent damage to non-target tissue. Additionally, or alternatively, the system can be enhanced by the integration of various sensors such as pressure, temperature, or electromagnetic sensors to provide additional data during the medical procedure. These sensors can help confirm changes detected by spectral and video analysis ensuring the system's responses are based on comprehensive data assessment. Thus, the system offers a comprehensive monitoring environment, providing additional data points for more nuanced control during laser surgeries. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. Like numerals having different letter suffixes may represent different instances of similar components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document.

[0011] FIG. 1 illustrates an example of a lithotripsy system including an optical detector.

[0012] FIG. 2 illustrates a block diagram for spectra collection at different times during a laser therapy session.

[0013] FIG. 3 illustrates a method for identifying and classifying a target in an image during a medical procedure.

[0014] FIG. 4 illustrates an example of a block diagram of a machine upon which one or more examples described herein may be implemented. Attorney Docket No.5409.890WO1 5 Client Reference No. GAP24024-URKT-WO1

[0015] FIG. 5 illustrates an example of a schematic diagram of an exemplary computer-based clinical decision support system (CDSS). DETAILED DESCRIPTION

[0016] A system for optical (e.g., spectroscopic) signal detection can comprise an optical detector (e.g., spectroscopic sensor such as a spectrometer, a Raman Spectroscopy sensor, a fluorescence sensor, or the like), a laser source such as a laser diode, and an illumination source such as a light emitting diode (LED) or a Xenon light source. The optical detector (e.g., spectrometer) can be coupled to the laser fiber and / or to a surgical fiber, which can in turn be coupled to, or included in a part of an endoscope for performing patient diagnosis or treatment. The optical detector can be coupled to the laser fiber and / or to a surgical fiber, which can in turn be coupled to or included in a part of an endoscope for performing patient diagnosis or treatment. The controller can be configurable or configured to control the laser source and the illumination source and can cause the optical component to collect the signal from a target or tissue and cause the optical detector to perform spectral analysis of the collected signal.

[0017] During surgical procedures, particularly those involving high-energy laser applications, the surgical field can become highly dynamic and chaotic. Particles and other debris resulting from, for example, kidney stone treatment can potentially affect the accuracy of data collection (e.g., spectral data) at the surgical site. As a result, a system of spectroscopic signal detection can be configured to perform time-based analysis that adjusts spectral data collection parameters based on factors such as how much time has elapsed since the laser has been activated. Thus, the system can calculate "quiet" periods or intervals during which the likelihood of particle interference is reduced, allowing for more accurate spectral data collection.

[0018] For example, if the laser has been inactive for a significant period of time, the particulate matter in the surgical field may have settled, providing a clearer path for signal transmission and reflection. Conversely, if the laser is currently active (or has recently been active), the system can either delay spectral data collection to allow for particles in the surgical field to settle or apply filtering techniques such as Adaptive Noise Cancellation (ANC) to the collected data to mitigate the effects of the chaotic environment. Such a time- Attorney Docket No.5409.890WO1 6 Client Reference No. GAP24024-URKT-WO1based approach can enhance the quality of the spectral data collected but can also potentially result in better surgical outcomes by ensuring that decisions based on spectral analysis are made using the most reliable data available.

[0019] FIG. 1 illustrates an example of a lithotripsy system including an optical detector. The system 100 can include a surgical laser 102 and a graphical user interface 104 (GUI). The graphical user interface 104 can include a touchscreen or other input mechanism or can be coupled to an input mechanism (e.g., a button, switch, or other similar actuation member on the handle of a scope 124 such as an endoscope) configured to operate or control the surgical laser 102. In an example, the input mechanism can include a footswitch or pedal. It is understood that the terms "scope" and "endoscope" can be used alternatively to refer to scope 124. The surgical laser 102 can include one or more laser sources configured to emit laser radiation. As shown in the dashed box in the example of FIG. 1, the light sources can include an ablation laser 106, an illumination source 108, and an endoscopic light source 109. The illumination source 108 and the endoscopic light source 109 can be a Light Emitting Diode (LED), a Xenon-based light source, or any similar source of visible light. Thus, the ablation laser 106 can emit infrared radiation while the illumination source 108 can emit an aiming beam or an illumination beam of visible light to show where the tip of the scope 124 (and therefore where the ablation energy from the ablation laser 106) is aimed. Additionally, or alternatively, the endoscopic light source 109 can be used to illuminate a target 126 or the surgical scene or field. The target 126 can be a piece of tissue, a tumor, a prostate capsule, or the like. The emitted light 128 from the ablation laser 106 or the illumination source 108, can be emitted through an optical fiber 116 such as can be connected to a surgical fiber 118 via an optical connector 120. In an example, endoscopic light source 109 can be integrated into a dedicated channel within the scope 124, specifically designed for illuminating the target 126. Such a configuration can allow the light from the endoscopic light source 109 to illuminate the surgical field without utilizing the optical fiber for light transmission thereby enhancing the clarity and focus of the illumination of the surgical field and the target 126. In another example, the endoscopic light source 109 can be attached or affixed to a portion of the scope 124. In an example, the structure of the surgical fiber 118 can be the same or different from that of the optical fiber 116. The surgical fiber Attorney Docket No.5409.890WO1 7 Client Reference No. GAP24024-URKT-WO1118 can be located wholly or partially outside the surgical laser 102. The emitted light 128 can thus be emitted from the illumination source 108, through the optical fiber 116, the optical connector 120, and the surgical fiber 118, to a distal end of the surgical fiber 118. The distal end of the surgical fiber 118 can be inserted into a scope 124, such as an endoscope, a ureteroscope, laryngoscope, or the like. In an example, at least a portion of the emitted light 128 emitted from the distal end of the surgical fiber 118 and the scope 124 can be reflected off of, scattered by, or the like, a target 126 (reflected light 130) through a medium between the tip of the scope 124 and the target 126. The scope 124 can include or be connected to an imaging device 122, such as a camera to capture video or images of the surgical scene, including the target 126.

[0020] The surgical laser 102 can further include or couple to an optical component such as optical splitter 110, configured to collect at least a portion of the reflected light 130 passing through the aperture of the surgical fiber 118. In an example, the optical splitter 110 can be replaced with a dedicated fiber configured to collect at least a portion of the reflected light 130. The portion of reflected light 130 collected by the optical splitter 110 or dedicated fiber can be sent to a processor 112 in connection with or coupled to the surgical laser 102. An optical detector 132 (e.g., a spectrometer or other similar light detector) can be located between the optical splitter 110 and the processor 112, so that spectral analysis of the reflected light 130 can be performed in order to determine one or more characteristics of the target 126 (or a change in the characteristics of the target 126).

[0021] The processor 112 and / or optical detector 132 can analyze the portion of the reflected light 130 collected by the optical splitter 110 (or receive an analysis by a spectrometer connected or coupled to the processor 112 and / or the optical detector 132), to analyze the reflected light 130. The surgical laser 102 can optionally or additionally include a controller 114 (e.g., controller circuitry) communicatively coupled to the processor 112 that can cause the optical detector 132 to collect or analyze the reflected light 130. The controller 114 can be included as a component of the surgical laser 102. Alternatively, the controller 114 can be a component of or included in a separate, stand-alone, machine, computer, device, or the like, coupled or connected to the surgical laser 102. The controller 114 can optionally include video analysis circuitry or components Attorney Docket No.5409.890WO1 8 Client Reference No. GAP24024-URKT-WO1that can work in conjunction with the optical detector 132 or a similar component to analyze spectra to detect and interpret visual phenomena such as flashing events. The video analysis circuitry can analyze video frames in real- time to identify changes in tissue appearance or unexpected visual artifacts that might affect the medical procedure. By integrating video data, the system can verify findings from the spectral data, which can help enhance the reliability of the procedure outcomes and can help increase the efficiency of the medical procedures. The real-time processing capabilities of the system can allow the system to analyze data (video and spectral data) as it is collected. This capability can help ensure that any significant changes in the spectral or video data that indicate potential risks to the patient can trigger immediate (or substantially immediate) adjustments to the laser's operations or settings, which can help minimize the risk of damage to non-target tissue.

[0022] In an example, the spectra from the reflected light 130 can be collected at different times or phases during a medical procedure. The phases can include a Pre-Emission Phase, a During Emission Phase, and an Interference-Free Phase. For example, in a Pre-Emission phase, the spectra can be collected before light or energy from the ablation laser 106 is emitted. Energy from the ablation laser 106 can be controlled via an actuator such as a foot pedal, switch, button, or another similar actuation device that can serve or act as a trigger to activate the ablation laser 106. In a Pre-Emission Spectra Collection, light from the illumination source 108 can be directed toward a target 126, a piece of tissue, or the like, and the optical detector 132 can analyze a signal from the target (e.g., light reflected or scattered by the target such as reflected light 130) before the ablation laser 106 is activated with the actuator.

[0023] During the emission phase, the spectra of the reflected light 130 can be collected during emission of the ablation laser 106. In an example, the ablation laser 106 can be a continuous emission laser source that can emit energy continuously or uninterrupted until stopped or paused (e.g., the laser will not be pulsed). Collecting the spectra during emission of the ablation laser 106 can help identify the interaction between energy from the ablation laser 106 and the target 126 or target tissue. When the energy from the ablation laser 106 is paused, the reflected light 130 can be collected and spectral measurement or analysis can be performed without any interference from the energy from the ablation laser 106. Attorney Docket No.5409.890WO1 9 Client Reference No. GAP24024-URKT-WO1Such a pausing of the energy from the ablation laser 106 can provide a "quiet window" or period of time to gather or collect unbiased reflected spectral data that is not biased by interference by laser emissions from the ablation laser 106, which can enhance the accuracy of the spectral measurements. The pause can represent an insignificant proportion of the total laser ON time since the spectra can be collected in a short time period (e.g., within 0.1 milliseconds (ms) to 500 ms).

[0024] FIG. 2 illustrates a block diagram for spectra collection at different times during a laser therapy session. At 202, a pedal or other actuation member to control emission of laser energy or radiation is not pressed or activated. Thus, the state at 202 can represent a time before an ablation procedure is to start or begin. Before the pedal is pressed at 206, the illumination source (e.g., an endoscopic illumination source) may be used to emit a signal toward a target such as a piece of tissue to be treated, or the like. Light from the target (e.g., reflected off the target, scattered by the target, or the like) can be collected by an optical detector such as a spectrometer. This "Pre-Emission" spectra collection or "Pre-Therapy" spectral collection at 204 can provide a user or physician with information about a target or tissue without interference from the laser emission. The information can also provide a user with "baseline" information about a target, such as target size or composition before the procedure begins. This information can be particularly useful as characteristics of the target can change as the procedure progresses.

[0025] At 206 the actuation member or pedal can be pressed or activated and at 208, spectra of a signal from the target can be collected during the laser emission. Collection of spectra during laser emission can help identify the interaction between the laser radiation or energy and the target. During this collection, at 214, one or more predefined spectroscopic artifacts such as flashing can be filtered out of the signal from the target to help provide a "clean" spectral signal. In an example, during flashing events, the system can automatically categorize the collected data as potentially unreliable. The system (e.g., using the controller 114) can assess whether the data can be used for making informed decisions or should be excluded (e.g., temporarily excluded) from the analysis to maintain the integrity of procedure outcomes. Attorney Docket No.5409.890WO1 10 Client Reference No. GAP24024-URKT-WO1

[0026] At 210, the laser emission can be paused to allow unbiased acquisition of the spectral signal without interference from the laser emission. Collection of spectral data at this time can allow the optical detector to gather and analyze unbiased spectral data which, in turn, can increase or enhance the accuracy of the spectral measurement. At 212, spectral analysis of the collected spectra can be performed and decisions or recommendations can be made (e.g., to adjust one or more settings of the laser, increase or decrease suction or irrigation at the surgical site, or the like) based on the spectral analysis. The analysis of each of the collected spectra can be performed at one time after all of the spectral signals are collected, or spectral analysis can be performed as each spectra is collected. The measurements and analysis of the spectra collected during the different phases can help a spectroscopy system identify unintended targets or non-targets such as muscle, adipose, or connective tissue, which can exhibit different reflectance or optical response profiles, including flashing profiles, than actual targets. In such a case, the spectroscopy system can disable laser emission against these non-target tissues. Additionally, the spectroscopic system can identify changes in the target characteristics such as size, shape, or material composition, and a processor or processing circuitry can cause the laser settings to be adjusted (or recommend adjustment to a physician) based on the changes. This can lead to more efficient medical procedures, better post-treatment recovery for patients, or the like.

[0027] FIG. 3 illustrates a method for spectral collection during an in-vivo medical procedure. The method 300 can include or comprise a number of Operations or Steps. The Operations described herein are examples only, and the method can omit one or more of the listed Operations, can repeat Operations, can include other Operations, or can execute the Operations concurrently, substantially simultaneously, or in another order, as appropriate or desired.

[0028] At 302, the method 300 can include emitting an illumination signal toward a target, such as an in-vivo target. The illumination signal can be emitted from a visible light source such as a light-emitting diode (LED), a Xenon-based light source, or the like. The illumination signal can be emitted before an actuation member (e.g., a pedal) is pressed or otherwise activated to emit or control laser energy or laser radiation to collect spectra (e.g., a return signal from light reflected by, scattered by, or otherwise emitted by the target). At 304, the Attorney Docket No.5409.890WO1 11 Client Reference No. GAP24024-URKT-WO1method 300 can include collecting a portion of the return signal from the target in response to the illumination signal. This "Pre-Emission" spectra collection or "Pre-Therapy" spectral collection can provide a user or physician with information about a target or tissue without interference from the laser emission. The information can also provide a user with "baseline" information about tissue or a target to be treated during the procedure, such as target size or composition or to differentiate target and non-target tissue before the procedure begins. Thus, the user can collect a "clean" spectroscopic signal when the laser is OFF.

[0029] At 306, the method 300 can include emitting a laser signal from a continuous wave laser source toward the target and at 308, at least a second portion of the return signal can be collected from the target. The return signal and the second portion of the return signal can be collected by an optical component, such as an optical splitter or other light collection device and analyzed by an optical detector such as a spectrometer. The return signals can be signals from the target in response to the emitted illumination signal. For example, the response signals can be a reflected signal, a scattered signal. A reflected signal can be a result of a signal emitted from the illumination source or the laser source bouncing off the target. The scattered signal can include a signal resulting from elastic scattering (e.g., via Rayleigh or Mie scattering), inelastic scattering (e.g., via RAMAN scattering), or the like. The response signal can be received at or sent to the optical detector (e.g., via the optical splitter).

[0030] At 310, the method 300 can include determining or detecting a change in the return signal(s) and at 312, the method 300 can include taking an action based at least in part on the determined change in the return signal(s). In an example, the illumination signal can be left ON (be emitted continuously) while the laser is emitting energy. Alternatively, the illumination signal can be dimmed and / or spectra from the return signal may not be collected or analyzed while the laser signal is being emitted. In another example, the laser can be paused providing an unobstructed window or time period for the spectra from the return signal to be analyzed without biasing by interference from the laser signal. Thus, the illumination signal can be emitted continuously resulting in a single return signal, and portions of the return signal can be collected at different times. Conversely, the illumination signal can be turned ON and OFF or pulsed, Attorney Docket No.5409.890WO1 12 Client Reference No. GAP24024-URKT-WO1resulting in a first illumination signal and a second illumination signal. In such a case, the second illumination signal can result in a second return signal and the spectra from the second return signal can be analyzed and compared to the spectra from the first return signal to detect a change in the second return signal from the first return signal.

[0031] The spectra from at least one of the return signal or the second return signal can be inputted to a trained-learning algorithm, such as an artificial intelligence or machine-learning algorithm as discussed below and for FIG. 5. The trained-learning algorithm can include a “CADe” algorithm or a "CADx" algorithm. In this context, "CADe" is an acronym for Computer Aided Detection, which is an AI model to identify abnormal tissue; whereas “CADx” is an acronym for Computer Aided Diagnosis, which is an AI model configured to classify detected abnormal tissue. Computer-Aided Detection (CADe) systems can be configured to locate and highlight potential abnormalities or lesions or other targets in medical images, such as X-rays, mammograms, or CT scans. Their primary purpose is to assist radiologists by flagging suspicious areas that might otherwise be overlooked. However, CADe systems need not provide detailed characterization of the targets; they focus on detection. Computer-Aided Diagnosis (CADx) systems go beyond detection and aim to characterize the detected targets. These systems provide information about the nature of the abnormality, such as whether it is benign or malignant.

[0032] The trained-learning algorithm can be used to determine a cause of the change in the return signal, such as a flashing event. The cause of the change in the return signals can be confirmed using data collected by one or more sensors, such as a temperature or pressure sensor. The temperature and pressure sensors can be incorporated to detect physiological changes (e.g., subtle physiological changes) that may not be captured by spectral or video analysis alone. These sensors can also provide information on the physical conditions at the target site, such as rapid changes or shifts in temperature, pressure fluctuations, or the like, which can be indicative of procedural complications. The one or more sensors can also include sensors such as a photodiode to detect changes in light or signal intensity, Complementary Metal Oxide Semiconductor (CMOS) or Charged Coupled Device (CCD) sensors, or any similar sensor capable of providing high- resolution images and capable of capturing changes in the visual field. Attorney Docket No.5409.890WO1 13 Client Reference No. GAP24024-URKT-WO1

[0033] Additionally, or alternatively, the one or more sensors can include acoustic sensors such as a hydrophone to detect acoustic signals generated by laser-tissue interaction or capturing cavitation events, or other events indicative of energy delivery and tissue response or a piezoelectric or similar sensor capable of measuring acoustic emissions from tissue when subjected to laser energy. The one or more sensors can also include electromagnetic sensors such as Hall Effect sensors or Electromyography (EMG sensors). The electromagnetic sensors can detect changes in magnetic fields, which might be influenced by laser emissions and the electrical equipment used during surgery or the electrical activity produced by skeletal muscles indicative of involuntary muscle response to laser energy providing indirect feedback on the impact the laser emission has on nearby muscle tissue.

[0034] The one or more sensors can also include chemical sensors such as gas or pH sensors. Gas sensors can be configured to detect specific gases released during tissue ablation such as carbon dioxide or smoke, which can provide additional information about tissue being ablated or the efficiency of the ablation process. A PH sensor can detect changes in pH at the surgical site indicating various biochemical processes (e.g., thermal degradation of tissue) triggered by laser interactions.

[0035] The one or more sensors can also include an imaging sensor (e.g., an endoscopic video sensor) that can obtain still or video images of the surgical scene, including the target. The imaging sensor (e.g., video data) can be synchronized with the spectral analysis of the return signals by the optical detector. This synchronization can allow the trained-model to collect data from the various sources and take one or more actions in real-time or near real-time as changes are determined and enhance decision making. For example, during a flashing event, spectral analysis can be paused or suspended. Additionally, or alternatively, when a change to the target or tissue is determined, such as a transition from a target (such as a tumor during a tumor ablation) to non-target tissue (such as muscle), the action can include stopping or adjusting (e.g., lowering or reducing) the intensity of the laser energy. In an example, when an event such as a flashing event is detected during the procedure, a separate trained model that is specifically designed to handle flashing events may be used. Thus, in addition to a primary spectral analysis model, the system can incorporate a Attorney Docket No.5409.890WO1 14 Client Reference No. GAP24024-URKT-WO1specialized machine-learning model designed specifically to handle and analyze data during flashing events. Such a model can be trained to recognize and interpret spectral signatures associated with such events, enabling it to provide accurate assessments in conditions that may result from these events.

[0036] The trained-learning algorithm can use the spectral analysis (and confirm using data from the other sensors) to determine a change in the tissue and stop the laser energy much faster than a human and help prevent damage to non-target tissue (such as perforating muscle tissue). The determinations discussed herein can be made using one or more trained-learning algorithms, one or more non-trained-learning algorithms, or a hardware-based feedback loop or feedback control. The hardware-based feedback loop or feedback control, the AI or ML algorithms, and the non-AI or non-ML algorithms can be used separately or in conjunction with each other as appropriate or desired.

[0037] FIG. 4 is a block diagram illustrating an example of a machine 400 upon which one or more embodiments can be implemented. In some embodiments, the machine 400 can operate as a standalone device or can be connected (e.g., networked) to other machines. Machine 400 can include or be coupled to or connected to the controller 114, the processor 112, and / or optical detector 132 (e.g., a spectrometer) discussed above for FIG. 1, and can include instructions that cause the controller 114 or the optical detector 132 to perform one or more of their operations described above. In a networked deployment, the machine 400 can operate in the capacity of a server machine, a client machine, or both in server-client network environments. In an example, the machine 400 can act as a peer machine in peer-to-peer (P2P) (or other distributed) network environment. The machine 400 can be a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a mobile telephone, 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 that machine. Further, while only a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein, such as cloud computing, software as a service (SaaS), other computer cluster configurations. Attorney Docket No.5409.890WO1 15 Client Reference No. GAP24024-URKT-WO1

[0038] Examples, as described herein, can include, or can operate by, logic or a number of components, or mechanisms. Circuit sets are a collection of circuits implemented in tangible entities that include hardware (e.g., simple circuits, gates, logic, etc.). Circuit set membership can be flexible over time and underlying hardware variability. Circuit sets include members that can, alone or in combination, perform specified operations when operating. In an example, hardware of the circuit set can be immutably designed to carry out a specific operation (e.g., hardwired). In an example, the hardware of the circuit set can include variably connected physical components (e.g., execution units, transistors, simple circuits, etc.) including a computer readable medium physically modified (e.g., magnetically, electrically, moveable placement of invariant massed particles, etc.) to encode instructions of the specific operation. In connecting the physical components, the underlying electrical properties of a hardware constituent are changed, for example, from an insulator to a conductor or vice versa. The instructions enable embedded hardware (e.g., the execution units or a loading mechanism) to create members of the circuit set in hardware via the variable connections to carry out portions of the specific operation when in operation. Accordingly, the computer readable medium is communicatively coupled to the other components of the circuit set member when the device is operating. In an example, any of the physical components can be used in more than one member of more than one circuit set. For example, under operation, execution units can be used in a first circuit of a first circuit set at one point in time and reused by a second circuit in the first circuit set, or by a third circuit in a second circuit set at a different time.

[0039] Machine 400 (e.g., a computer system) can include a hardware processor 402 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, field programmable gate array (FPGA), or any combination thereof), a main memory 404 and a static memory 406, some or all of which can communicate with each other via an interlink (e.g., bus) 430. The machine 400 can further include a display unit 410, an input device 412 (e.g., an alphanumeric input device such as a keyboard), and a user interface (UI) navigation device (UI navigation device 414) (e.g., a mouse). In an example, the display unit 410, input device 412 and UI navigation device 414 can be a touch screen display. The machine 400 can additionally include a Attorney Docket No.5409.890WO1 16 Client Reference No. GAP24024-URKT-WO1storage device 408 (e.g., drive unit), a signal generation device 418 (e.g., a speaker), a network interface device 420, and one or more sensors 416, such as a global positioning system (GPS) sensor, compass, accelerometer, or other sensor. The machine 400 can include an output controller 428, 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 or control one or more peripheral devices (e.g., a printer, card reader, etc.).

[0040] The storage device 408 can include a machine readable medium 422 on which is stored one or more sets of data structures or one or more instructions 424 (e.g., software) embodying or used by any one or more of the techniques or functions described herein. The one or more instructions 424 can also reside, completely or at least partially, within the main memory 404, within static memory 406, or within the hardware processor 402 during execution thereof by the machine 400. In an example, one or any combination of the hardware processor 402, the main memory 404, the static memory 406, or the storage device 408 can constitute machine readable media.

[0041] While the machine readable medium 422 is illustrated as a single medium, the term "machine readable medium" can include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) configured to store the one or more instructions 424.

[0042] The term “machine readable medium” can include any medium that is capable of storing, encoding, or carrying instructions for execution by the machine 400 and that cause the machine 400 to perform any one or more of the techniques of the present disclosure, or that is capable of storing, encoding, or carrying data structures used by or associated with such instructions. Non- limiting machine readable medium examples can include solid-state memories, and optical and magnetic media. In an example, a massed machine readable medium comprises a machine readable medium with a plurality of particles having invariant (e.g., rest) mass. Accordingly, massed machine-readable media are not transitory propagating signals. Specific examples of massed machine readable media can 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 Attorney Docket No.5409.890WO1 17 Client Reference No. GAP24024-URKT-WO1disks and removable disks; magneto-optical disks; and CD-ROM and DVD- ROM disks.

[0043] The one or more instructions 424 can further be transmitted or received over a communications network 426 using a transmission medium via the network interface device 420 utilizing any one of a number of transfer protocols (e.g., frame relay, internet protocol (IP), transmission control protocol (TCP), user datagram protocol (UDP), hypertext transfer protocol (HTTP), etc.). Example communication networks can include a local area network (LAN), a wide area network (WAN), a packet data network (e.g., the Internet), mobile telephone networks (e.g., cellular networks), Plain Old Telephone (POTS) networks, and wireless data networks (e.g., Institute of Electrical and Electronics Engineers (IEEE) 802.11 family of standards known as Wi-Fi®, IEEE 802.16 family of standards), IEEE 802.15.4 family of standards, peer-to-peer (P2P) networks, among others. In an example, the network interface device 420 can include one or more physical jacks (e.g., Ethernet, coaxial, or phone jacks) or one or more antennas to connect to the communications network 426. In an example, the network interface device 420 can include a plurality of antennas to wirelessly communicate using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) techniques. The term “transmission medium” shall be taken to include any intangible medium that is capable of storing, encoding, or carrying instructions for execution by the machine 400, and includes digital or analog communications signals or other intangible medium to facilitate communication of such software.

[0044] FIG. 5 illustrates an example of a schematic diagram of an exemplary computer-based clinical decision support system (CDSS 500) that is configured to determine information or characteristics about a target, such as size, composition, hardness, density, or any similar characteristic or information about the target based on spectroscopic analysis of a signal from the target. The CDSS 500 can also be configured to make adjust one or more laser or scope settings or recommend adjustment based on the information or characteristics about the target. The CDSS 500 can include an input interface 502 through which parameters such as the size of a surgical fiber, information about the light sources, information about the optical components, and / or information about the Attorney Docket No.5409.890WO1 18 Client Reference No. GAP24024-URKT-WO1scope which are specific to a patient’s procedure are provided as input features to an artificial intelligence (AI) model (AI model 504), a processor which performs an inference operation in which the parameters are applied to the AI model 504 to generate the determination of the target characteristics, and an output interface 508 through which the determined target characteristics can be communicated to a user, e.g., a clinician.

[0045] The input interface 502 can include a direct data link between the CDSS 500 and one or more medical devices that generate at least some of the input features. For example, the input interface 502 can transmit information about the light sources and / or the optical components (e.g., frequency or wavelength of signals from the light sources or aiming beam emission sources, or a rejection frequency of the optical components), or information about a signal returned from the target directly to the CDSS 500 during a therapeutic and / or diagnostic medical procedure. In an example, information about the light sources and / or the optical components, the scope, etc., used during the procedure can be stored in a database 506. Additionally, or alternatively, the input interface 502 can be a classical user interface that facilitates interaction between a user and the CDSS 500. For example, the input interface 502 can facilitate a user interface through which the user can manually enter the information about the surgical fiber, the scope, the optical components, signals to block or allow, etc. Additionally, or alternatively, the input interface 502 can provide the CDSS 500 with access to an electronic patient record or the components being used during the procedure from which one or more input features can be extracted. In any of these cases, the input interface 502 is configured to collect one or more of the following input features in association with one or more of a specific patient, a type of medical procedure, a type of scope, signals that should be rejected during spectroscopic analysis, or the like, on or before a time at which the CDSS 500 is used to assess the input features will take place.

[0046] An example of an input feature can include a dimension of the surgical fiber to be used during the procedure.

[0047] An example of an input feature can include a type of light or laser source.

[0048] An example of an input feature can include the type of scope being used during the procedure. Attorney Docket No.5409.890WO1 19 Client Reference No. GAP24024-URKT-WO1

[0049] An example of an input feature can include a wavelength or frequency to be blocked or attenuated.

[0050] An example of an input feature can include signal information of a return signal 512 received at the optical detector 510 from the target, for example during the different time periods or phases of the medical procedure.

[0051] Based on one or more of the above input features, the processor can perform an inference operation using the AI model 504 to generate determined characteristics of the target such as the size of the target, the composition of the target, hardness, density, or any similar characteristic. For example, input interface 502 can deliver the one or more of the input features listed above into an input layer of the AI model 504 which can propagate these input features through the AI model 504 to an output layer. The AI model 504 can provide a computer system the ability to perform tasks, without explicitly being programmed, by making inferences based on patterns found in the analysis of data. The AI model 504 can explore the study and construction of algorithms (e.g., machine-learning algorithms) that can learn from existing data and make predictions about new data. Such algorithms operate by building an AI model from example training data in order to make data-driven predictions or decisions expressed as outputs or assessments.

[0052] Examples of two modes for machine learning (ML) can include: supervised ML and unsupervised ML. Supervised ML uses prior knowledge (e.g., examples that correlate inputs to outputs or outcomes) to learn the relationships between the inputs and the outputs. The goal of supervised ML is to learn a function that, given some training data, best approximates the relationship between the training inputs and outputs so that the ML model can implement the same relationships when given inputs to generate the corresponding outputs. Unsupervised ML is the training of an ML algorithm using information that is neither classified nor labeled and allowing the algorithm to act on that information without guidance. Unsupervised ML is useful in exploratory analysis because it can automatically identify structure in data.

[0053] Tasks for supervised ML can include classification problems and regression problems. Classification problems, also referred to as categorization problems, aim at classifying items into one of several category values (for Attorney Docket No.5409.890WO1 20 Client Reference No. GAP24024-URKT-WO1example, is this object an apple or an orange?). Regression algorithms aim at quantifying some items (for example, by providing a score to the value of some input). Some examples of 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).

[0054] Some possible tasks for unsupervised ML include clustering, representation learning, and density estimation. Some examples of unsupervised- ML algorithms are K-means clustering, principal component analysis, and autoencoders.

[0055] Another type of ML includes federated learning (also known as collaborative learning) that trains an algorithm across multiple decentralized devices holding local data, without exchanging the data. This approach stands in contrast to traditional centralized machine-learning techniques where all the local datasets are uploaded to one server, as well as to more classical decentralized approaches which often assume that local data samples are identically distributed. Federated learning enables multiple actors to build a common, robust machine learning model without sharing data, thus allowing to address critical issues such as data privacy, data security, data access rights and access to heterogeneous data.

[0056] In some examples, the AI model 504 can be trained continuously or periodically prior to performance of the inference operation by the processor. Then, during the inference operation, the patient specific input features provided to the AI model 504 can be propagated from an input layer, through one or more hidden layers, and ultimately to an output layer that corresponds to the information about the target or a change in the return signals. For example, when evaluating the spectroscopic analysis of the signal from the target, the system can determine one or more characteristics of the target or a change from target tissue to non-target tissue.

[0057] During and / or subsequent to the inference operation, the information about the target can be communicated to the user via the output interface 508 (e.g., a user interface (UI)) and / or automatically cause a surgical laser connected to the processor to perform a desired action. For example, based on the composition of the target the system can cause the surgical laser to emit energy Attorney Docket No.5409.890WO1 21 Client Reference No. GAP24024-URKT-WO1to ablate the target, adjust the amount or intensity of ablation energy, move a portion of the scope, etc.

[0058] 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 that can be practiced. These embodiments are also referred to herein as “examples.” Such examples can 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 using any combination or permutation of those elements shown or described (or one or more aspects thereof), either with respect to a particular example (or one or more aspects thereof), or with respect to other examples (or one or more aspects thereof) shown or described herein. ADDITIONAL NOTES AND EXAMPLES

[0059] Example 1 is a system for spectral collection during an in-vivo medical procedure, the system comprising: a processor; and memory, including instructions stored thereon that, when performed by the processor, cause the processor to: emit an illumination signal from an illumination source toward an in-vivo target; collect a first return signal from the in-vivo target in response to the illumination signal; emit a laser signal from a continuous wave laser source toward the in-vivo target; collect a second return signal from the in-vivo target; determine a difference between the first return signal and the second return signal; and take an action based at least in part on the determined difference.

[0060] In Example 2, the subject matter of Example 1 optionally includes subject matter wherein to determine the difference between the first return signal and the second return signal, the instructions cause the processor to: compare a spectral analysis of the second return signal with a spectral analysis of the first return signal.

[0061] In Example 3, the subject matter of Example 2 optionally includes subject matter wherein spectra from at least one of the first return signal or the second return signal are inputted into an artificial intelligence algorithm or a machine-learning algorithm, wherein the artificial intelligence algorithm or the Attorney Docket No.5409.890WO1 22 Client Reference No. GAP24024-URKT-WO1machine-learning algorithm identifies a cause of the difference and / or one or more characteristics of the in-vivo target and determines the action.

[0062] In Example 4, the subject matter of any one or more of Examples 1–3 optionally include subject matter wherein the instructions further cause the processor to: analyze imaging data captured concurrently with the first return signal and the second return signal; detect one or more changes in the imaging data indicative of a condition of the in-vivo target; and based on the detected one or more changes in the imaging data, determine whether to continue collecting spectral data.; and based on a determination to stop collecting spectral data, at least one of: stop collection of the spectral data or predict an optimal time to stop collection of the spectral data.

[0063] In Example 5, the subject matter of Example 4 optionally includes subject matter wherein the instructions further cause the processor to, based on the detected one or more changes in the imaging data, stop collection of the spectral data or predict an optimal time to stop collection of the spectral data.

[0064] In Example 6, the subject matter of any one or more of Examples 1–5 optionally include subject matter wherein the action includes stopping emission of the continuous wave laser source.

[0065] In Example 7, the subject matter of any one or more of Examples 1–6 optionally include subject matter wherein the action include adjusting an intensity level of the continuous wave laser source.

[0066] In Example 8, the subject matter of any one or more of Examples 1–7 optionally include subject matter wherein the instructions further cause the processor to: determine whether the difference between the first return signal and the second return signal exceeds a predetermined threshold.

[0067] In Example 9, the subject matter of Example 8 optionally includes subject matter wherein the action is taken in real-time or near real-time upon the processor determining that the difference between the first return signal and the second return signal exceeds the predetermined threshold.

[0068] In Example 10, the subject matter of any one or more of Examples 1–9 optionally include subject matter wherein the instructions further cause the processor to: determine a cause resulting in the difference between the first return signal and the second return signal based on spectral analysis, video analysis or a combination thereof. Attorney Docket No.5409.890WO1 23 Client Reference No. GAP24024-URKT-WO1

[0069] In Example 11, the subject matter of Example 10 optionally includes subject matter wherein the instructions further cause the processor to: confirm the cause based at least in part on data obtained from one or more sensors connected to or communicatively coupled to a medical scope in which at least one of the illumination source or the continuous wave laser source is included.

[0070]

[0071] In Example 12, the subject matter of any one or more of Examples 10– 11 optionally include subject matter wherein the cause includes at least one of a flashing event, a change between a distance in a distal end of an endoscope and the in-vivo target, a change in the in vivo target, or emission of the laser signal.

[0072] In Example 13, the subject matter of any one or more of Examples 10– 12 optionally include subject matter wherein the instructions further cause the processor to: identify a type of the in-vivo target based at least in part on the spectral analysis of at least one of the first return signal and the second return signal; and stop emission of the continuous wave laser source when a change in a characteristic of the in-vivo target occurs, wherein the change in the in-vivo target includes a change in a tissue type or tissue layer.

[0073] Example 14 is a method for spectral collection during an in-vivo medical procedure, the method comprising: emitting an illumination signal from an illumination source toward an in-vivo target; collecting a first return signal from the in-vivo target in response to the illumination signal; emitting a laser signal from a continuous wave laser source toward the in-vivo target; collecting a second return signal from the in-vivo target; determining a difference between the first return signal and the second return signal; and taking an action based at least in part on the determined difference.

[0074] In Example 15, the subject matter of Example 14 optionally includes subject matter wherein determining the difference between the first return signal and the second return signal includes a comparison of a spectral analysis of the second return signal and a spectral analysis of the first return signal.

[0075] In Example 16, the subject matter of any one or more of Examples 14– 15 optionally include subject matter wherein spectra from at least one of the first return signal or the second return signal are inputted to an artificial intelligence algorithm or a machine-learning algorithm, wherein the artificial intelligence Attorney Docket No.5409.890WO1 24 Client Reference No. GAP24024-URKT-WO1algorithm or the machine-learning algorithm identifies one or more characteristics of the in-vivo target and determines the action.

[0076] In Example 17, the subject matter of any one or more of Examples 14– 16 optionally include subject matter wherein at least one of the action is taken in real-time or near real-time upon determining that difference between the first return signal and the second return signal exceeds a predetermined threshold.

[0077] In Example 18, the subject matter of any one or more of Examples 14– 17 optionally include subject matter determining a cause resulting in the difference between the first return signal and the second return signal based on spectral analysis, video analysis or a combination thereof, wherein the video analysis includes detection of a flashing event, a change in the in-vivo target, or an unexpected visual artifact; and confirming the cause based at least in part on data obtained from one or more sensors connected to or communicatively coupled to a medical scope in which at least one of the illumination source or the continuous wave laser source is included, wherein the cause includes at least one of a flashing event, a change between a distance in a distal end of an endoscope and the in-vivo target, or emission of the laser signal.

[0078] Example 19 is a system for spectral collection during an in-vivo medical procedure, comprising: an endoscope; a continuous wave laser source included in or connected to the endoscope; an illumination source included in or connected to the endoscope; and processing circuitry to: emit an illumination signal from an illumination source toward an in-vivo target; collect a first return signal from the in-vivo target in response to the illumination signal; emit a laser signal from a continuous wave laser source toward the in-vivo target; collect a second return signal from the in-vivo target; determine a difference between the first return signal and the second return signal; and take an action based at least in part on the determined difference.

[0079] In Example 20, the subject matter of Example 19 optionally includes subject matter wherein the processing circuitry is further to: compare a spectral analysis of the second return signal with a spectral analysis of the first return signal; analyze imaging data captured concurrently with the first return signal and the second return signal; detect one or more changes in the imaging data indicative of a condition of the in-vivo target; based on the detected one or more changes in the imaging data, determine whether to continue collecting spectral Attorney Docket No.5409.890WO1 25 Client Reference No. GAP24024-URKT-WO1data; and based on a determination to stop collecting spectral data, at least one of: stop collection of the spectral data or predict an optimal time to stop collection of the spectral data.

[0080] In Example 21, the subject matter of any one or more of Examples 19– 20 optionally include subject matter wherein the processing circuitry is further to: determine a cause resulting in the difference between the first return signal and the second return signal based on spectral analysis, video analysis or a combination thereof, wherein the video analysis includes detection of a flashing event, a change in the in-vivo target, or an unexpected visual artifact; and confirm the cause based at least in part on data obtained from one or more sensors connected to or communicatively coupled to a medical scope in which at least one of the illumination source or the continuous wave laser source is included.

[0081] In this document, the terms “a” or “an” are used, as is common in patent documents, to include one or more than one, independent of any other instances or usages of “at least one” or “one or more.” In this document, the term “or” is used to refer to a nonexclusive or, such that “A or B” includes “A but not B,” “B but not A,” and “A and B,” unless otherwise indicated. In the appended claims, the terms “including” and “in which” are used as the plain-English equivalents of the respective terms “comprising” and “wherein.” Also, in the following claims, the terms “including” and “comprising” are open-ended, that is, a system, device, article, or process that includes elements in addition to those listed after such a term in a claim are still deemed to fall 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.

[0082] The above description is intended to be illustrative, and not restrictive. For example, the above-described examples (or one or more aspects thereof) can be used in combination with each other. Other embodiments can be used, such as by one of ordinary skill in the art upon reviewing the above description. The Abstract is to allow the reader to quickly ascertain the nature of the technical disclosure and 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 can be grouped together to streamline the Attorney Docket No.5409.890WO1 26 Client Reference No. GAP24024-URKT-WO1disclosure. This should not be interpreted as intending that an unclaimed disclosed feature is essential to any claim. Rather, inventive subject matter can lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment. The scope of the embodiments should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. Attorney Docket No.5409.890WO1 27 Client Reference No. GAP24024-URKT-WO1

Claims

CLAIMS WHAT IS CLAIMED IS:

1. A system for spectral collection during an in-vivo medical procedure, the system comprising: a processor; and memory, including instructions stored thereon that, when performed by the processor, cause the processor to: emit an illumination signal from an illumination source toward an in-vivo target; collect a first return signal from the in-vivo target in response to the illumination signal; emit a laser signal from a continuous wave laser source toward the in-vivo target; collect a second return signal from the in-vivo target; determine a difference between the first return signal and the second return signal; and take an action based at least in part on the determined difference.

2. The system of claim 1, wherein to determine the difference between the first return signal and the second return signal, the instructions cause the processor to: compare a spectral analysis of the second return signal with a spectral analysis of the first return signal.

3. The system of claim 2, wherein spectra from at least one of the first return signal or the second return signal are inputted into an artificial intelligence algorithm or a machine-learning algorithm, wherein the artificial intelligence algorithm or the machine-learning algorithm identifies a cause of the difference and / or one or more characteristics of the in-vivo target and determines the action. Attorney Docket No.5409.890WO1 28 Client Reference No. GAP24024-URKT-WO14. The system of claim 1, wherein the instructions further cause the processor to: analyze imaging data captured concurrently with the first return signal and the second return signal; detect one or more changes in the imaging data indicative of a condition of the in-vivo target; based on the detected one or more changes in the imaging data, determine whether to continue collecting spectral data; and based on a determination to stop collecting spectral data, at least one of: stop collection of the spectral data or predict an optimal time to stop collection of the spectral data.

5. The system of claim 4, wherein the instructions further cause the processor to, based on the detected one or more changes in the imaging data, stop collection of the spectral data or predict an optimal time to stop collection of the spectral data.

6. The system of claim 1, wherein the action includes stopping emission of the continuous wave laser source.

7. The system of claim 1, wherein the action include adjusting an intensity level of the continuous wave laser source.

8. The system of claim 1, wherein the instructions further cause the processor to: determine whether the difference between the first return signal and the second return signal exceeds a predetermined threshold. Attorney Docket No.5409.890WO1 29 Client Reference No. GAP24024-URKT-WO19. The system of claim 8, wherein the action is taken in real-time or near real-time upon the processor determining that the difference between the first return signal and the second return signal exceeds the predetermined threshold.

10. The system of claim 1, wherein the instructions further cause the processor to: determine a cause resulting in the difference between the first return signal and the second return signal based on spectral analysis, video analysis or a combination thereof.

11. The system of claim 10, wherein the instructions further cause the processor to: confirm the cause based at least in part on data obtained from one or more sensors connected to or communicatively coupled to a medical scope in which at least one of the illumination source or the continuous wave laser source is included.

12. The system of claim 10, wherein the cause includes at least one of a flashing event, a change between a distance in a distal end of an endoscope and the in-vivo target, a change in the in-vivo target, or emission of the laser signal.

13. The system of claim 10, wherein the instructions further cause the processor to: identify a type of the in-vivo target based at least in part on the spectral analysis of at least one of the first return signal and the second return signal; and stop emission of the continuous wave laser source when a change in a characteristic of the in-vivo target occurs, wherein the change in the in-vivo target includes a change in a tissue type or tissue layer. Attorney Docket No.5409.890WO1 30 Client Reference No. GAP24024-URKT-WO114. A method for spectral collection during an in-vivo medical procedure, the method comprising: emitting an illumination signal from an illumination source toward an in- vivo target; collecting a first return signal from the in-vivo target in response to the illumination signal; emitting a laser signal from a continuous wave laser source toward the in-vivo target; collecting a second return signal from the in-vivo target; determining a difference between the first return signal and the second return signal; and taking an action based at least in part on the determined difference.

15. The method of claim 14, wherein determining the difference between the first return signal and the second return signal includes a comparison of a spectral analysis of the second return signal and a spectral analysis of the first return signal.

16. The method of claim 14, wherein spectra from at least one of the first return signal or the second return signal are inputted to an artificial intelligence algorithm or a machine-learning algorithm, wherein the artificial intelligence algorithm or the machine-learning algorithm identifies one or more characteristics of the in-vivo target and determines the action.

17. The method of claim 14, wherein at least one of the action is taken in real-time or near real-time upon determining that difference between the first return signal and the second return signal exceeds a predetermined threshold.

18. The method of claim 14, further comprising: determining a cause resulting in the difference between the first return signal and the second return signal based on spectral analysis, video analysis or a Attorney Docket No.5409.890WO1 31 Client Reference No. GAP24024-URKT-WO1combination thereof, wherein the video analysis includes detection of a flashing event, a change in the in-vivo target, or an unexpected visual artifact; and confirming the cause based at least in part on data obtained from one or more sensors connected to or communicatively coupled to a medical scope in which at least one of the illumination source or the continuous wave laser source is included, wherein the cause includes at least one of a flashing event, a change between a distance in a distal end of an endoscope and the in-vivo target, or emission of the laser signal.

19. A system for spectral collection during an in-vivo medical procedure, comprising: an endoscope; a continuous wave laser source included in or connected to the endoscope; an illumination source included in or connected to the endoscope; and processing circuitry to: emit an illumination signal from an illumination source toward an in-vivo target; collect a first return signal from the in-vivo target in response to the illumination signal; emit a laser signal from a continuous wave laser source toward the in-vivo target; collect a second return signal from the in-vivo target; determine a difference between the first return signal and the second return signal; and take an action based at least in part on the determined difference.

20. The system of claim 19, wherein the processing circuitry is further to: compare a spectral analysis of the second return signal with a spectral analysis of the first return signal; analyze imaging data captured concurrently with the first return signal and the second return signal; Attorney Docket No.5409.890WO1 32 Client Reference No. GAP24024-URKT-WO1detect one or more changes in the imaging data indicative of a condition of the in-vivo target; based on the detected one or more changes in the imaging data, determine whether to continue collecting spectral data; and based on a determination to stop collecting spectral data, at least one of: stop collection of the spectral data or predict an optimal time to stop collection of the spectral data.

21. The system of claim 19, wherein the processing circuitry is further to: determine a cause resulting in the difference between the first return signal and the second return signal based on spectral analysis, video analysis or a combination thereof, wherein the video analysis includes detection of a flashing event, a change in the in-vivo target, or an unexpected visual artifact; and confirm the cause based at least in part on data obtained from one or more sensors connected to or communicatively coupled to a medical scope in which at least one of the illumination source or the continuous wave laser source is included. Attorney Docket No.5409.890WO1 33 Client Reference No. GAP24024-URKT-WO1

Images