Light source independent optical measurements

Abstract

A system for light-source independent optical measurements of a lithotripsy target during a medical procedure using a first light source may comprise controller circuitry configured or configurable to cause a first signal to be emitted from the first light source toward a lithotripsy target and cause an optical detector to receive a response signal from the lithotripsy target in response to the first signal. The controller circuitry may also retrieve, from a database, a spectral profile associated with the first light source and computationally adjust the first response signal to create a light source independent profile based at least in part on the spectral profile associated with the first light source. A characteristic of the lithotripsy target may be determined based at least in part on the light source independent profile.

Description

LIGHT SOURCE INDEPENDENT OPTICAL MEASUREMENTSPRIORITY CLAIM

[0001] This application claims the benefit of priority to U.S. Provisional Patent Application Serial No. 63 / 619,538, filed lanuary 10, 2024, the contents of which are hereby incorporated herein by reference.TECHNICAL FIELD

[0002] The present disclosure relates to spectral analysis of signals from a target during surgical procedures such as lithotripsy procedures.BACKGROUND

[0003] During a medical procedure, such as a lithotripsy procedure, a user such as a physician or a robot may interact with one or more targets of various types and / or sizes. Characteristics of the target (e.g., size, shape, material composition, etc.) may vary depending on the type of procedure and may change during the procedure. One or more characteristics of the target may impact how to proceed during the procedure, what instrument to use during the procedure, instrument settings (e.g., ablation settings) to use during the procedure, or the like.

[0004] Different light sources, such as endoscopic light sources, produce different spectroscopic profiles. The different spectroscopic profiles of the different light sources can create variation in the data being collected and result in inconsistent analysis and determination of target characteristics.SUMMARY

[0005] Analysis of a signal (e.g., a response signal) from a lithotripsy target may be used to identify one or more characteristics of the target. The lithotripsy target may include a calculus such as a kidney stone, or may be a tumor, a piece of tissue, or the like. Spectroscopy can be used to identify the composition of the target (e.g., what material the target is made or composed of) or another characteristic of the target. For example, when the target is a kidney stone, spectroscopy of a signal spectrum of the signal reflected or scattered by, transmitted from, emitted by, or absorbed by the stone may be used to determinewhether the stone is formed from uric acid, calcium oxalate, or a combination of materials. The signal may be a response signal received at an optical sensor, light detector, or charge collection device such as a spectrometer. The response signal may include light scattered by or reflected from the target in response to a signal emitted from a light source toward the target.

[0006] Different light sources (e.g. a Light Emitting Diode (LED) or a Xenon- based bulb) may be used to visualize one or more targets that may be treated during a medical or surgical procedure. The targets may include a calculus such as kidney stones (e.g., a COM stone), gall stones, bladder cancer tissue, or a prostate capsule. The result of spectroscopic analysis of a signal from these targets (e.g., light from the endoscopic light sources reflected off of or scattered by the targets) may be used by an algorithm to identify or determine characteristics of the targets. The algorithm may include an artificial intelligence (Al) or machine learning (ML) or other algorithm (e.g., a non-AI or non-ML deterministic algorithm) or process. Additionally, or alternatively, a portion of the identification and / or classification of targets or decisions regarding the procedure may be made using a hardware-based feedback loop or feedback control.

[0007] The different light sources may produce different spectroscopic profiles. The different spectroscopic profiles of the different light sources may result in inconsistent identification or analysis of the target by the algorithm. The present inventors have determined, among other things, a need to extract information specific to a particular light source (a "light source profile" made up of light source characteristics for a particular light source) from the signal from the target to normalize the return or response signals from the target corresponding to different light sources. The resulting spectra may be used to identify targets (and determine characteristics of the targets) independent of the light source used to collect the data.

[0008] A system for light-source independent optical measurements of a lithotripsy target during a medical procedure using a first light source may include controller circuitry to cause a first signal to be emitted from the first light source toward the lithotripsy target. The controller may cause an optical detector to receive a response signal from the lithotripsy target in response to the first signal. The controller circuitry may retrieve, from a database included in orcoupled to the system, a spectral profile associated with the first light source and computationally adjust the first response signal to create a light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the first light source. One or more characteristics of the lithotripsy target may be determined based at least in part on the light source independent profile.

[0009] In another example, a system for light-source independent optical measurements of a lithotripsy target during a medical procedure using a first light source and a second light source may include controller circuitry to cause a first signal to be emitted from the first light source toward the lithotripsy target. The controller circuitry may cause an optical detector to receive a response signal from the lithotripsy target in response to the first signal and cause a second signal to be emitted from the second light source toward the lithotripsy target. The controller circuitry may cause the optical detector to receive a second response signal from the lithotripsy target in response to the second signal and normalize the first response signal and the second response signal. The normalized first and second response signals may be used to create a light source independent profile of the lithotripsy target, and the controller circuitry may classify the lithotripsy target based on the light source independent profile. The controller circuitry can be included in a system that includes the first and second light source and the optical detector (e.g., such as included in a laser source for a laser system coupled to a scope). The controller circuitry may be external to a system including the source of ablation energy, the light sources, or the optical detector, and may be coupled to one or more of those components.

[0010] In an example, the first and second light sources may be distinct, different light sources such as some combination of an endoscopic light source (e.g., a visible light source of many possible wavelengths), a laser source (e.g., an infrared light source of few possible wavelengths), and an aiming beam (e.g., a second visible light source of few possible wavelengths). At least two response signals can be derived from the endoscopic light source which may emit many wavelengths, or from a combination of the response signals from any of the possible light sources. Alternatively or additionally, the endoscopic light source, the laser source, or the aiming beam can include multiple narrow-band or broadband light sources that can produce separate response signals for normalization.For example, a laser system may be configured with one or more aiming beam emitters at different wavelengths, or an endoscopic light source may be configured with one or more light sources at different wavelengths that can be controlled individually or in combination to produce separate response signals.

[0011] Thus, the second light source may be a separate light source from the first light source. Alternatively, the first light source may be configured to produce separate response signals so that the first light source and the second light source are combined into the same light source. In such an example, computationally adjusting the response signals can include computationally adjusting at least one of the response signals. A system may include one or more light sources and may adjust the response to all, none, or any one or more of the light source profiles, such as depending on, for example, a desired balance between providing a sufficiently large sample size for algorithm development and the increased effort to computationally adjust the response signal for multiple sources of non-response signal variation. A light source profile or a response signal may be derived from one of the light that are not computationally adjusted for reasons such as that the amount of variation does not have a significant effect on the sample size or because it is easier to collect more samples of the required configuration. Thus, which signals are computationally adjusted for can be chosen or selected as desired.

[0012] A computer implemented method for light-source independent optical measurement of a lithotripsy target may comprise emitting a first signal from a first light source toward the lithotripsy target and receiving at an optical detector, a response signal from the lithotripsy target in response to the first signal. The method may further comprise emitting a second signal from a second light source toward the lithotripsy target and receiving, at the optical detector, a second response signal from the lithotripsy target in response to the second signal. The method may further include normalizing the first response signal and the second response signal, creating a light source independent profile of the lithotripsy target using the normalized first and second response signals, and classifying the lithotripsy target based on the light source independent profile.

[0013] A potential advantage of the system described herein is that it may be used to more efficiently train the algorithm discussed above as it may reduce the number of samples required to train or develop the algorithm to identify one ormore targets. This is especially true when one of the light sources supports quickly collecting multiple samples from a target (e.g., a single target or multiple targets). For example, an LED endoscopic light source may pulse ON between 2 and 10 milliseconds (ms) (50 to 60 times per second). When an LED source is set to pulse ON between 2 ms and 4 ms, 60 times per second, synchronized with a 60 Hertz power supply, a surgical field (or endoscope field of view) may be sufficiently illuminated with visible light without overexposing an endoscopic video image. In such a case, optical measurements that depend on reflected light may be collected for 120 ms to 240 ms during the LED emissions. This short time frame is difficult for non-continuous measurements of the target that need to be taken quickly, such as when data needs to be collected between or during laser emission pulses. If measurements must be taken during an LED pulse, and in between laser pulses, the amount of valid or useful data collected may be significantly reduced. The presently disclosed system may allow optical measurements to be taken with any light source, such as those that change their intensity by pulsing or not pulsing (e.g., Xenon-based light sources). This may result in better, more reliable data to be collected, and which may in turn result in better trained algorithms.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] 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.

[0015] FIG. 1 illustrates an example of a lithotripsy system including an optical detector.

[0016] FIG. 2 illustrates an example of a flowchart for creating a light source independent profile of a lithotripsy target and training an algorithm.

[0017] FIG. 3 illustrates an example of a method for light source independent optical measurement of a lithotripsy target.

[0018] FIG. 4 is a block diagram of an example of a machine upon which any one or more of the techniques (e.g., methodologies) discussed herein may perform.

[0019] FIG. 5 illustrates a schematic diagram of an exemplary computer-based clinical decision support system (CDSS).DETAILED DESCRIPTION

[0020] In a medical procedure such as a lithotripsy procedure, there is a desire to identify types of targets. Targets may include a tumor or a calculus, such as a kidney stone. Additionally, it is often desirable to classify or identify one or more characteristics of a target such as material composition, density, or the like. These identifications may be made, at least in part, based on analysis of the spectra of signals from the target, for example, light reflected from or scattered by the target using an optical detector such as a spectrometer. Based on these identifications, decisions about the medical procedure may need to be made quickly. These decisions may include a type and intensity of ablation energy to deliver to the target, whether to interrupt or stop ablation energy, whether to alter a position of a medical device (e.g., an endoscope) being used during the procedure, whether to irrigate or suction the surgical site, or the like.

[0021] These identifications and decisions may be made using an automated system or algorithm. The algorithm may include an artificial intelligence (Al) or machine learning (ML) or other algorithm (e.g., a non-AI or non-ML deterministic algorithm) or process. Additionally, or alternatively, a portion of the identification and / or classification of targets or decisions regarding the procedure may be made using a hardware-based feedback loop or feedback control.

[0022] Different light sources that may be included in or coupled to a medical scope such as an endoscope may produce different spectroscopic signals. As a result, when light from one kind of light source such as an LED source reflects off of, is scattered by, etc., a target, the return signal from the target may be different than a return signal from the same target when a different light source such as a Xenon-based light source illuminates the target. If the different return signals are used as inputs to train an algorithm, such as an Al or ML algorithm, the algorithm may return inconsistent results. For example, the algorithm may classify the target differently if an LED source is used to illuminate the target than it will when a Xenon-based light source is used to illuminate the target.

[0023] It is desirable for an algorithm, when receiving signals from different light sources from the same type of target, to identify and classify the target consistently. Meaning, when the algorithm receives an input X from a target illuminated from one type of light source, the algorithm will identify and classify that target the same way if it receives an input signal Y from the same target but illuminated by a different type of light source. To accomplish this desired consistency, a light source independent profile may be created so that regardless of what type of light source is used to illuminate the target, the algorithm may correctly identify or classify the target. To create a light source independent profile, a profile may be created for each light source over the full range of their lifetimes, to define or establish a window of performance for each light source. For example, a spectral profile may be created for a light source to represent the range of manufacturing tolerances and variance at different percentages of the expected lifetime of the light source remaining (e.g., 100%, 50%, 10%, 1%, etc.). The appropriate average spectra and variances to use in a given medical device or medical system (e.g., an endoscopic system) may be selected by training the algorithm to identify if the light source is new, has 50% of its lifetime remaining, or the like. While, any number of light source age intervals may be selected, smaller age intervals may result in more precise measurements.

[0024] Additionally, or alternatively, a light source profile (or a characteristic of a light source profile) may be measured or determined using a calibration step at different time intervals such as during annual or other maintenance of the equipment including the light source. This calibration step may include illuminating light toward and reflected off of a standard surface, such as at different intensities and measuring or analyzing the corresponding return signals. For example, an LED light source may have multiple intensity adjustment steps. The light profile for the LED may be determined based on light collected at one or more (or all) of the adjustment steps. If data is not collected at all of the adjustment steps, interpolation may be used to calculate the profile data at intensity steps between or adjacent to the measured steps.

[0025] Once the characteristics of the light sources have been determined, response signals from the target corresponding to the light sources may be normalized or otherwise adjusted. The normalization may include removing the characteristics specific to the light sources from the corresponding responsesignals. A light source independent profile of the target may be created using the normalized response signals. The light source independent profile may be used to identify or classify a target or may be used to train an algorithm such that a return signal from the target can provide a correct identification or classification of the target regardless of what type of light source is used to illuminate the target.

[0026] FIG. 1 illustrates an example of a lithotripsy system including an optical detector. The system 100 may include a surgical laser 102 and a graphical user interface 104 (GUI). The graphical user interface 104 may include a touchscreen or other input mechanism (e.g., a button, switch, or other similar actuation member on the handle of the endoscope) configured to operate or control the surgical laser 102. The surgical laser 102 may 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 may include an ablation laser 106 and / or an illumination source 108. The illumination source 108 may include a probe laser, a Light Emitting Diode (LED), a Xenon-based light source, or any similar source of visible light. The ablation laser 106 may emit infrared radiation while the illumination source 108 may emit an aiming beam or an illumination beam of visible light to show where the tip of the scope (and therefore where the ablation energy from the ablation laser 106) is aimed. Additionally, or alternatively, the illumination source 108 may be used to illuminate a target 126. The target 126 can be a piece of tissue, debris, or an object, such as a kidney stone which is to be ablated, a tumor, a prostate capsule, or the like. The emitted light 128 from the ablation laser 106 or the illumination source 108, may 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, the structure of the surgical fiber 118 may be the same or different from that of the optical fiber 116. The surgical fiber 118 may be located wholly or partially outside the surgical laser 102. The emitted light 128 may thus be emitted from 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 may 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 maybe 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.

[0027] The surgical laser 102 may 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 may 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 may 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) may be located between the optical splitter 110 and the processor 112, so that spectral analysis of the reflected light 130 may be performed in order to determine one or more characteristics of the target 126.

[0028] The processor 112 and / or optical detector 132 may 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 may optionally or additionally include controller 114 circuitry communicatively coupled to the processor 112. The processor 112 or the controller 114 may determine one or more characteristics of the reflected light 130 signal that is specific to the illumination source 108 such as a type of light source, a wavelength, an optical component, a pulse width, an optical configuration, or an age of the illumination source 108. In an example, a signal, such as signal from a sensor may correspond to a characteristic of the light source, such as a type of light source, an optical configuration of the light source, etc. Such a signal may be removed from the response signal from the target as a part of the normalization of the response signals from the light sources. Thus, a response signal from a target may include a light-source-specific characteristic response signal component, which may vary according to the type of light source, a characteristic particular to the type of light source or to aging or another operational characteristic of a particular light-source. Such a light-source- specific response signal component can be attenuated or removed from the response signal. This may help provide a “normalized” response signal without the variability that might otherwise be introduced by the light-source-specificcharacteristic response signal component. Removing light-source-specific characteristic response signal component may cause a reduction in the number of samples required to develop an algorithm with a given performance. It may be possible to develop an algorithm that accommodates the specific light sourcefactors, but such an algorithm may require a greater sample size to be adequately developed. While the example of FIG. 1 includes a single illumination source, it is understood that the system 100 may include multiple illumination sources of different types (e.g., an LED source, a Xenon -based source, a broadband illumination source, or the like).

[0029] FIG. 2 illustrates an example flowchart for creating a light source independent profile of a lithotripsy target and training an algorithm. At 200, a signal from one or more illumination sources may be emitted toward a lithotripsy target. In the example illustrated in FIG. 2, a signal from a first light source 202 and a second light source 204 may be emitted toward a target, such as target 126 in FIG. 1. The signal may be a first illumination light from the first light source 202 and a second illumination light from the second light source 204. The first light source 202 and the second light source 204 may be different types of light sources. For example, the first light source 202 may be a LEDbased light source, and the second light source 204 may be a Xenon-based light source. It is understood that even though FIG. 2 illustrates two light sources being used, the techniques described herein may apply to any number of and any type of suitable light sources. In an example, light may be emitted from the first light source 202 and the second light source 204 independently of one another. In another example, light may be emitted from the first light source 202 and the second light source 204 simultaneously or substantially simultaneously or concurrently.

[0030] At 206, return signals from the target may be normalized. To normalize the return signals, one or more light source characteristics specific to the first light source 202 and the second light source 204 may be determined and removed from the response signals. The characteristics may include a wavelength of the first light source 202 or the second light source 204, a type of the first light source 202 or the second light source 204, an optical component specific to the first light source 202 or the second light source 204, an age of the optical component (or a non-optical component of the first and second lightsources), an optical configuration of the first light source 202 or the second light source 204, a pulse width or an intensity of the first light source 202 or the second light source 204, or the like.

[0031] At 208, a light source independent profile of the lithotripsy target may be created. This profile may be based on the light spectra of the return signals from the first light source 202 or the second light source 204 with the characteristics removed during the normalization process at 206. At 210, the target may be classified using the light source independent profile. When the characteristic(s) specific to the light sources are removed, the return signals from the light sources may be similar, identical, or substantially similar or substantially identical, such that at 208 and 210 the return signals may be matched to the type of target or a characteristic of the target (e.g., whether the target is a stone, the material composition of the stone, or the like). At 212, when the target is classified, the result of the classification may be used as an input to train an algorithm, such as an Al or ML, or other similar trained algorithm.

[0032] FIG. 3 illustrates an example of a method 300 for light source independent optical measurement of a lithotripsy target. The method 300 can include or comprise a number of Operations or Steps (302-314). These Operations are examples only, and the executed 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. The operations can be performed automatically by the processor 112 or controller 114 of the system described in FIG. 1, or the processor or controller of a machine or computer, such as described below for FIG. 4.

[0033] At 302, the method 300 may include emitting a first signal from a first light source toward the lithotripsy target. At 304, the method 300 may include receiving a response signal from the lithotripsy target in response to the first signal. The first light source may be an illumination light source, such as an endoscopic light source. The first light source may be an LED, a Xenon-base light source, a laser (e.g., an illumination laser), a broadband illumination source, or any similar light source. The first signal may be a light in the visible light spectrum, and the lithotripsy target may be a calculus, such as a stone (e.g., a kidney stone or a gall stone), a tumor, tissue to be treated, or the like. Theresponse signal may be a signal from the target in response to the emitted first signal or illumination signal. The response signal may be a reflected signal, a scattered signal (e.g., via Raman scattering), or the like, and be received at or sent to an optical detector such as a spectrometer or other similar light detection device.

[0034] At 306 the method 300 may include emitting a second signal from a second light source, and at 308, the method 300 may include receiving a second response signal from the lithotripsy target in response to the second signal. The second light source may be a different light source than the first light source. For example, if the first light source is an LED light source, the second light source may be a Xenon-based bulb. The second response signal may be received at the optical detector in a similar fashion as the first response signal (e.g., reflected, scattered, or the like by the target and received at the optical detector).

[0035] At 310 the method 300 may include normalizing the first and second response signals. To normalize the signals, controller circuitry of a computing device may determine a first light source characteristic corresponding to the first light source and a second light source characteristic corresponding to the second light source. The light source characteristics may include one or more of a type of the first or second light source, an optical configuration of the first or second light source, an optical component of the first or second light source, an age of a component of the first or second light source (e.g. an optical component or another non-optical component), an intensity of the first or second signal, a pulse width of the first or second signal, or the like. From there, the controller circuitry may remove the first light source characteristic and the second light source characteristic from the first and second return signals.

[0036] In an example, a first light source profile may be created for the first light source based on the first light source characteristic. Similarly, a second light source profile may be created for the second light source based on the second light source characteristic. The light source profiles may be calibrated or updated at recurrent or periodic time intervals such as when additional light source characteristics are determined for each light source, and the profile information may be stored in a database so that when the same types of light sources are used during subsequent medical procedures, the profile information (or light source characteristics) can be removed from the response signals. Forexample, if a light source profile for an aging light source is determined later, that profile can be normalized and used to calibrate all response signals in the database, thereby further reducing the non-response signal variation. Response signals with less variation can then be used to develop algorithms with improved performance or with similar performance from a smaller number of response signal samples. Thus, variation from sources other than the target's response to being illuminated can be reduced or removed from the response signals.

[0037] At 312, the method 300 may include creating a light source independent profile of the target using the normalized first and second response signals, and at 314, the method 300 may include classifying the lithotripsy target based at least in part on on the light source independent profile. In an example, when the first and second response signals are normalized and the light source characteristics are removed from the response signals, the return signals from different light sources may be similar or substantially similar. When a target is identified with this normalized response signal, it can be classified by type, such as classified as a kidney stone, and by characteristic such as material composition. In subsequent procedures the light source being used may be known ahead of time, and the light source profile may be accessed by the controller circuitry. When a return signal is received at the optical detector, the light source characteristics may be removed from the response signal and the target may be identified and classified accurately regardless of the type of light source being used.

[0038] FIG. 4 is a block diagram of an example of a machine 400 upon which any one or more of the techniques (e.g., methodologies) discussed herein may perform. The machine 400 may operate as a standalone device or may be connected (e.g., networked) to other machines. For example, the machine 400 may be included in or connected to the surgical laser 102 and / or the scope 124 and may include components such as the graphical user interface 104, the processor 112, the controller 114, or the surgical fiber actuator 122, discussed above. Additionally, or alternatively, the machine 400 may operate the flow discussed above for FIG. 2, the method steps illustrated in FIG. 3, or the computer-based clinical decision support system (CDSS) discussed below for FIG. 5. In a networked deployment, the machine 400 may operate in the capacity of a server machine, a client machine, or both in server-client networkenvironments. In an example, the machine 400 may act as a peer machine in peer-to-peer (P2P) (or other distributed) network environment. The machine 400 may 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.

[0039] Examples, as described herein, may include, or may 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 may be flexible over time and underlying hardware variability. Circuit sets include members that may, alone or in combination, perform specified operations when operating. In an example, hardware of the circuit set may be immutably designed to carry out a specific operation (e.g., hardwired). In an example, the hardware of the circuit set may 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 may be used in more than one member of more than one circuit set. For example, under operation, execution units may be used in a first circuit of a first circuit set at one point intime 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.

[0040] Machine 400 (e.g., computer system) may 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 may communicate with each other via an interlink (e.g., bus) 430. The machine 400 may further include a display unit 410, an alphanumeric input device 412 (e.g., a keyboard), and a user interface (UI) navigation device 414 (e.g., a mouse). In an example, the display unit 410, input device 412 and UI navigation device 414 may be a touch screen display. The machine 400 may additionally include a storage 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 may 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.).

[0041] The storage device 408 may include a machine readable medium 422 (e.g., a non-transitory medium) on which is stored one or more sets of data structures or instructions 424 (e.g., software) embodying or used by any one or more of the techniques or functions described herein. The instructions 424 may 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 may constitute machine readable media.

[0042] While the machine readable medium 422 is illustrated as a single medium, the term "machine readable medium" may 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. The term “machine readable medium” may include any non-transitory medium that is capable of storing, encoding, or carrying instructions for execution by themachine 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. Nonlimiting machine readable medium examples may 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 may 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.

[0043] FIG. 5 illustrates a schematic diagram of an exemplary computer-based clinical decision support system (CDSS) 500 that is configured to create a light source independent profile for a lithotripsy target, identify, or classify the lithotripsy target. In various embodiments, the CDSS 500 may include an input interface 502 through which one or more laser setting ranges, which are specific to a patient, may be provided as input features to an artificial intelligence (Al) model 504, a processor, such as processor 112 or 402, to perform an inference operation in which the information regarding the light sources being used during the procedure are applied to the Al model to generate a light source independent profile for the lithotripsy target, and a user interface (UI) through which identification or classification of the target may be communicated to a user, e.g., a clinician.

[0044] In some embodiments, the input interface 502 may be 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 may transmit information about the light sources (e.g., type, age, etc.) directly to the CDSS 500 during a therapeutic and / or diagnostic medical procedure. Additionally, or alternatively, the input interface 502 may be a classical user interface that facilitates interaction between a user and the CDSS 500. For example, the input interface 502 may facilitate a user interface through which the user maymanually enter information about the medical procedure and / or the devices (including the light source types) that will be used during the procedure. Additionally, or alternatively, the input interface 502 may provide the CDSS 500 with access to an electronic patient record from which one or more input features may be extracted. In any of these cases, the input interface 502 may be configured to collect one or more of the following input features in association with a specific patient on or before a time at which the CDSS 500 is used to assess:

[0045] Information regarding characteristics of the first light source 510, which can include information such as the type of light source, the optical components or configuration of the light source, the intensity of the light source, the age of one or more components of the light source, the wavelength of the light source, the pulse width of the light source, or the like;

[0046] Information regarding characteristics of the second light source 512 (which may be similar to the characteristics of the first light source listed above);

[0047] Information about the medical procedure;

[0048] Spectral analysis of a return signal from the target in response to a signal from the first light source;

[0049] Spectral analysis of a return signal from the target in response to a signal from the second light source; and / or

[0050] a normalized first and second return signal;

[0051] Based on one or more of the above input features, the processors 112 or 402 may perform an inference operation using the Al model to create a light source independent profile of the target and identify or classify the target based on the light source independent profile. For example, input interface 502 may deliver the characteristics of the light sources and the spectral analysis of the return signals received from the target in response to signals from the light sources into an input layer of the Al model which propagates these input features through the Al model to an output layer. The Al model may 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 Al model may explore the study and construction of algorithms (e.g., machine-learning algorithms) that may learn from existing data and make predictions about new data. Such algorithms operate by building an Al model from example trainingdata in order to make data-driven predictions or decisions expressed as outputs or assessments.

[0052] Two modes for machine learning (ML) may 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. A goal of supervised ML includes 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 may include 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] Certain tasks for supervised ML may include classification problems and regression problems. Classification problems, also referred to as categorization problems, may classify items into one of several category values (for example, is this object an apple or an orange?). Regression algorithms may quantify some items (for example, by providing a score to the value of some input). Some examples of commonly used supervised-ML algorithms are Logistic Regression (LR), Naive-Bayes, Random Forest (RF), neural networks (NN), deep neural networks (DNN), matrix factorization, and Support Vector Machines (SVM).

[0054] Some tasks for unsupervised ML may 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 may include federated learning (also referred to as collaborative learning) that trains an algorithm across multiple decentralized devices holding local data, without exchanging the data. This approach stands in contrast to 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 may enable multiple actors to build a common, robust machine learningmodel 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 Al model may be trained continuously, recurrently, or periodically prior to performance of the inference operation by the processor 402. Then, during the inference operation, the patient specific input features provided to the Al model may be propagated from an input layer, through one or more hidden layers, and ultimately to an output layer that corresponds to identification of the target regardless of what type of light source is used to illuminate the target. For example, when the illumination source is an LED, information about the LED, such as wavelength, intensity, age, optical configuration, or the like may be used to create a light source profile for the LED. When a return signal is received at the optical detector, in response to light being emitted from the LED toward the target, the information in the light source profile may be removed from the return signal and information about the target may be propagated to the output layer.

[0057] During and / or subsequent to the inference operation, target information may be communicated to the user via the user interface (UI) . The target information may also be used to automatically cause other settings of an ablation system (e.g., laser settings) to be set or adjusted based on the information about the target.ADDITIONAL NOTES AND EXAMPLES:

[0058] Example l is a system for light-source independent optical measurements of a lithotripsy target during a medical procedure using a first light source, the system comprising: controller circuitry to: cause a first signal to be emitted from the first light source toward the lithotripsy target; cause an optical detector to receive a first response signal from the lithotripsy target in response to the first signal; retrieve, from a database, a spectral profile associated with the first light source; computationally adjust the first response signal to create a light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the first light source; and determine a characteristic of the lithotripsy target based at least in part on the light source independent profile.

[0059] In Example 2, the subject matter of Example 1 optionally includes subject matter wherein the system includes a second light source, and wherein the controller circuitry is further to: cause a second signal to be emitted from the second light source toward the lithotripsy target; cause the optical detector to receive a second response signal from the lithotripsy target in response to a second signal; retrieve, from the database, a spectral profile associated with the second light source; and computationally adjust the second response signal to create the light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the second light source.

[0060] In Example 3, the subject matter of Example 2 optionally includes subject matter wherein to computationally adjust the first response signal and the second response signal includes normalizing the first response signal and the second response signal, and wherein to normalize the first response signal and the second response signal the controller circuitry is further to: determine a first light-source-specific characteristic included in the spectral profile of the first light source in the first response signal; determine a second light-source-specific characteristic included in the spectral profile of the second light source in the second response signal; adjust the first response signal by attenuating or removing the first light-source-specific characteristic from the first response signal; and adjust the second response signal by attenuating or removing the second light-source-specific characteristic from the second response signal.

[0061] In Example 4, the subject matter of Example 3 optionally includes subject matter wherein the spectral profile associated with the first light source includes a component attributable to a lifetime of the first light source, wherein the spectral profile associated with the second light source includes a component attributable to a lifetime of the second light source, and wherein to normalize the first response signal and the second response signal includes: removing the component attributable to the lifetime of the first light source from the first response signal; and removing the component attributable to the lifetime of the second light source from the second response signal.

[0062] In Example 5, the subject matter of any one or more of Examples 3-4 optionally includes subject matter wherein the first light-source-specific characteristic includes one or more of: a wavelength of the first signal, an intensity of the first signal, or a pulse width of the first signal.

[0063] In Example 6, the subject matter of any one or more of Examples 3-5 optionally includes subject matter wherein the second light-source-specific characteristic includes one or more of: a wavelength of the second signal, an intensity of the second signal, or a pulse width of the second signal.

[0064] In Example 7, the subject matter of any one or more of Examples 3-6 optionally includes subject matter wherein the controller circuitry is further to: determine a performance indicator for at least one of the first light-source- specific characteristic or the second light-source-specific characteristic.

[0065] In Example 8, the subject matter of any one or more of Examples 3-7 optionally includes subject matter wherein the spectral profile associated with the first light source is created for the first light source based at least in part on the first light-source-specific characteristic and the spectral profile associated with the second light source is created for the second light source based at least in part on the second light-source-specific characteristic.

[0066] In Example 9, the subject matter of Example 8 optionally includes subject matter wherein at least one of the spectral profile associated with the first light source or the spectral profile associated with the second light source is calibrated at a recurrent or periodic time interval.

[0067] In Example 10, the subject matter of any one or more of Examples 2-9 optionally includes subject matter wherein the first light source is a of a different type than the second light source.

[0068] In Example 11, the subject matter of any one or more of Examples 2-10 optionally includes subject matter wherein at least one of the first light source or the second light source is an endoscopic light source, and wherein the first light source or the second light source includes at least one of a Light Emitting Diode (LED), a laser, a broadband illumination source, or a Xenon-based light source.

[0069] In Example 12, the subject matter of any one or more of Examples 2-11 optionally includes subject matter wherein the optical detector includes a spectrometer to analyze a spectra of the first response signal and the second response signal.

[0070] In Example 13, the subject matter of any one or more of Examples 1-12 optionally includes subject matter wherein the system is used to train a learned model.

[0071] Example 14 is a computer implemented method for light source independent optical measurement of a lithotripsy target during a medical procedure, the method comprising: emitting a first signal from a first light source toward the lithotripsy target; receiving, at an optical detector, a first response signal from the lithotripsy target in response to the first signal; emitting a second signal from a second light source toward the lithotripsy target; receiving, at the optical detector, a second response signal from the lithotripsy target in response to the second signal; retrieving, from a database, a spectral profile associated with the first light source; computationally adjusting the first response signal to create a light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the first light source; and determining a characteristic of the lithotripsy target based at least in part on the light source independent profile.

[0072] In Example 15, the subject matter of Example 14 optionally includes emitting a second signal from a second light source toward the lithotripsy target; receiving at the optical detector a second response signal from the lithotripsy target in response to the first signal; retrieving, from the database, a spectral profile associated with the second light source; and computationally adjusting the second response signal to create the light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the second light source.

[0073] In Example 16, the subject matter of Example 15 optionally includes subject matter wherein to computationally adjust the first response signal and the second response signal includes normalizing the first response signal and the second response signal, wherein to normalize the first response signal and the second response signal the method further comprises: determining a first light- source-specific characteristic included in the spectral profile of the first light source in the first response signal; determining a second light-source-specific characteristic included in the spectral profile of the second light source in the second response signal; adjusting the first response signal by attenuating or removing the first light-source-specific characteristic from the first response signal; and adjusting the second response signal by attenuating or removing the second light-source-specific characteristic from the second response signal.

[0074] In Example 17, the subject matter of Example 16 optionally includes subject matter wherein the spectral profile associated with the first light source includes a component attributable to a lifetime of the first light source, wherein the spectral profile associated with the second light source includes a component attributable to a lifetime of the second light source, and wherein to normalize the first response signal and the second response signal includes: removing the component attributable to the lifetime of the first light source from the first response signal; and removing the component attributable to the lifetime of the second light source from the second response signal.

[0075] Example 18 is a system for light-source independent optical measurements of a lithotripsy target during a medical procedure using a first light source and a second light source, the system comprising: controller circuitry to: cause a first signal to be emitted from a first light source toward a lithotripsy target; cause an optical detector to receive a first response signal from the lithotripsy target in response to the first signal; cause a second signal to be emitted from a second light source toward the lithotripsy target; cause the optical detector to receive a second response signal from the lithotripsy target in response to the second signal; retrieve, from a database, a spectral profile associated with the first light source and a second spectral profile associated with the second light source; computationally adjust at least one of the first response signal or the second response signal to create a light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the first light source and the second spectral profile associated with the second light source; and determine a characteristic of the lithotripsy target based at least in part on the light source independent profile.

[0076] In Example 19, the subject matter of Example 18 optionally includes subject matter wherein the controller circuitry is further to: determine a first light-source-specific characteristic corresponding to the first light source in the first response signal; determine a second light-source-specific characteristic corresponding to the second light source in the second response signal; adjust the first response signal by attenuating or removing the first light-source-specific characteristic from the first response signal; and adjust the second response signal by attenuating or removing the second light-source-specific characteristic from the second response signal.

[0077] In Example 20, the subject matter of any one or more of Examples 18- 19 optionally includes subject matter wherein the spectral profile associated with the first light source includes a component attributable to a lifetime of the first light source, wherein the spectral profile associated with the second light source includes a component attributable to a lifetime of the second light source, and wherein to normalize the first response signal and the second response signal includes: removing the component attributable to the lifetime of the first light source from the first response signal; and removing the component attributable to the lifetime of the second light source from the second response signal.

[0078] 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 this document, the term “and / or” is used to refer to a nonexclusive or, such that “A and / 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.

[0079] The above description is intended to be illustrative, and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. Other embodiments may 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 may be grouped together to streamline the disclosure. This should not be interpreted as intending that an unclaimed disclosed feature is essential to any claim. Rather, inventive subject matter maylie 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.

Claims

CLAIMSWHAT IS CLAIMED IS:

1. A system for light-source independent optical measurements of a lithotripsy target during a medical procedure using a first light source, the system comprising: controller circuitry to: cause a first signal to be emitted from the first light source toward the lithotripsy target; cause an optical detector to receive a first response signal from the lithotripsy target in response to the first signal; retrieve, from a database, a spectral profile associated with the first light source; computationally adjust the first response signal to create a light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the first light source; and determine a characteristic of the lithotripsy target based at least in part on the light source independent profile.

2. The system of claim 1, wherein the system includes a second light source, and wherein the controller circuitry is further to: cause a second signal to be emitted from the second light source toward the lithotripsy target; cause the optical detector to receive a second response signal from the lithotripsy target in response to a second signal; retrieve, from the database, a spectral profile associated with the second light source; and computationally adjust the second response signal to create the light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the second light source.

3. The system of claim 2, wherein to computationally adjust the first response signal and the second response signal includes normalizing the firstresponse signal and the second response signal, and wherein to normalize the first response signal and the second response signal the controller circuitry is further to: determine a first light-source-specific characteristic included in the spectral profile of the first light source in the first response signal; determine a second light-source-specific characteristic included in the spectral profile of the second light source in the second response signal; adjust the first response signal by attenuating or removing the first light- source-specific characteristic from the first response signal; and adjust the second response signal by attenuating or removing the second light-source-specific characteristic from the second response signal.

4. The system of claim 3, wherein the spectral profile associated with the first light source includes a component attributable to a lifetime of the first light source, wherein the spectral profile associated with the second light source includes a component attributable to a lifetime of the second light source, and wherein to normalize the first response signal and the second response signal includes: removing the component attributable to the lifetime of the first light source from the first response signal; and removing the component attributable to the lifetime of the second light source from the second response signal.

5. The system of claim 3, wherein the first light-source-specific characteristic includes one or more of: a wavelength of the first signal, an intensity of the first signal, or a pulse width of the first signal.

6. The system of claim 3, wherein the second light-source-specific characteristic includes one or more of: a wavelength of the second signal, an intensity of the second signal, or a pulse width of the second signal.

7. The system of claim 3, wherein the controller circuitry is further to: determine a performance indicator for at least one of the first light- source-specific characteristic or the second light-source-specific characteristic.

8. The system of claim 3, wherein the spectral profile associated with the first light source is created for the first light source based on at least in part on the first light-source-specific characteristic and the spectral profile associated with the second light source is created for the second light source based at least in part on the second light-source-specific characteristic.

9. The system of claim 8, wherein at least one of the spectral profile associated with the first light source or the spectral profile associated with the second light source is calibrated at a recurrent or periodic time interval.

10. The system of claim 2, wherein the first light source is a of a different type than the second light source.

11. The system of claim 2, wherein at least one of the first light source or the second light source is an endoscopic light source, and wherein the first light source or the second light source includes at least one of a Light Emitting Diode (LED), a laser, a broadband illumination source, or a Xenon-based light source.

12. The system of claim 2, wherein the optical detector includes a spectrometer to analyze a spectra of the first response signal and the second response signal.

13. The system of claim 1, wherein the system is used to train a learned model.

14. A computer implemented method for light source independent optical measurement of a lithotripsy target during a medical procedure, the method comprising: emitting a first signal from a first light source toward the lithotripsy target; receiving, at an optical detector, a first response signal from the lithotripsy target in response to the first signal;emitting a second signal from a second light source toward the lithotripsy target; receiving, at the optical detector, a second response signal from the lithotripsy target in response to the second signal; retrieving, from a database, a spectral profile associated with the first light source; computationally adjusting the first response signal to create a light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the first light source; and determining a characteristic of the lithotripsy target based at least in part on the light source independent profile.

15. The method of claim 14, further comprising: emitting a second signal from a second light source toward the lithotripsy target; receiving at the optical detector a second response signal from the lithotripsy target in response to the first signal; retrieving, from the database, a spectral profile associated with the second light source; and computationally adjusting the second response signal to create the light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the second light source.

16. The method of claim 15, wherein to computationally adjust the first response signal and the second response signal includes normalizing the first response signal and the second response signal, wherein to normalize the first response signal and the second response signal the method further comprises: determining a first light-source-specific characteristic included in the spectral profile of the first light source in the first response signal; determining a second light-source-specific characteristic included in the spectral profile of the second light source in the second response signal; adjusting the first response signal by attenuating or removing the first light-source-specific characteristic from the first response signal; andadjusting the second response signal by attenuating or removing the second light-source-specific characteristic from the second response signal.

17. The method of claim 16, wherein the spectral profile associated with the first light source includes a component attributable to a lifetime of the first light source, wherein the spectral profile associated with the second light source includes a component attributable to a lifetime of the second light source, and wherein to normalize the first response signal and the second response signal includes: removing the component attributable to the lifetime of the first light source from the first response signal; and removing the component attributable to the lifetime of the second light source from the second response signal.

18. A system for light-source independent optical measurements of a lithotripsy target during a medical procedure using a first light source and a second light source, the system comprising: controller circuitry to: cause a first signal to be emitted from a first light source toward a lithotripsy target; cause an optical detector to receive a first response signal from the lithotripsy target in response to the first signal; cause a second signal to be emitted from a second light source toward the lithotripsy target; cause the optical detector to receive a second response signal from the lithotripsy target in response to the second signal; retrieve, from a database, a spectral profile associated with the first light source and a second spectral profile associated with the second light source; computationally adjust at least one of the first response signal or the second response signal to create a light source independent profile of the lithotripsy target based at least in part on the spectral profile associated with the first lightsource and the second spectral profile associated with the second light source; and determine a characteristic of the lithotripsy target based at least in part on the light source independent profile.

19. The system of claim 18, wherein the controller circuitry is further to: determine a first light-source-specific characteristic corresponding to the first light source in the first response signal; determine a second light-source-specific characteristic corresponding to the second light source in the second response signal; adjust the first response signal by attenuating or removing the first light- source-specific characteristic from the first response signal; and adjust the second response signal by attenuating or removing the second light-source-specific characteristic from the second response signal.

20. The system of claim 18, wherein the spectral profile associated with the first light source includes a component attributable to a lifetime of the first light source, wherein the spectral profile associated with the second light source includes a component attributable to a lifetime of the second light source, and wherein to normalize the first response signal and the second response signal includes: removing the component attributable to the lifetime of the first light source from the first response signal; and removing the component attributable to the lifetime of the second light source from the second response signal.

Images