Endoscopic laser triggered aspiration automatic on / off

Abstract

To repeatedly turn on and off or otherwise control suction or other components of an endoscopic system without requiring direct user input.SOLUTION: Current or past status of the laser generator, blurriness or other information from images of the working area, number of stone fragments, intraoperative pressure, intraoperative temperature, or one or more other characteristics of the laser generator or target stone may be used automatically or semi-automatically.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 262,924, filed October 22, 2021, the entire contents of which are incorporated herein. [Background technology]

[0002] Medical scopes, such as endoscopes, were first developed in the early 1800s and have been used to examine the inside of patients' bodies. Such scopes include endoscopes, laparoscopes, ureteroscopes, duodenoscopes, arthroscopes, and others sometimes referred to as endoscopes or scopes. Endoscopes can be used to move fluids through organs. Some endoscopes provide irrigation, suction, or both, such as for moving fluids. Laser energy can also be used inside the body. For example, a laser generator can provide laser energy inside the body via a laser fiber or fiber bundle. Laser energy can be used for diagnostic or therapeutic purposes, such as performing laser lithotripsy to ablate one or more stones. Ablation can break down stones into smaller fragments that can pass naturally or can be grasped, aspirated, or otherwise removed from the body via an endoscope or auxiliary tools. Summary of the Invention [Means for solving the problem]

[0003] In the drawings, which are not necessarily drawn to scale, like numerals may represent like components in different views. Like numerals with different letter suffixes may represent different instances of like components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments described herein. [Brief explanation of the drawings]

[0004] [Figure 1] FIG. 1 illustrates an example of a portion of an endoscopic system having a suction component and a laser generator for controlling suction. [Figure 2] 10A-10C illustrate examples of methods for controlling aspiration and / or irrigation based on laser energy. [Figure 3] 10A-10C illustrate an example method for controlling aspiration and / or irrigation based on imaging of a working area. [Figure 4] 10A-10C illustrate examples of methods for controlling aspiration and / or irrigation based on imaging of the field of action. [Figure 5] 10A-10C illustrate examples of methods for controlling aspiration and / or irrigation based on imaging of the field of action. [Figure 6] 10A-10C illustrate examples of methods for controlling aspiration and / or irrigation based on imaging of the field of action. [Figure 7] 1 illustrates an example of a method for determining a treatment plan based on imaging of a stone. [Figure 8] 1 is an exemplary schematic diagram of an exemplary computer-based clinical decision support system (CDSS). DETAILED DESCRIPTION OF THE INVENTION

[0005] The systems and techniques described herein relate to medical devices, such as endoscopes, that use aspiration or "suction" to move fluids, stones, stone dust, and / or stone fragments, etc., through organs, such as kidneys, during lithotripsy. The endoscopic suction can be activated by, synchronized with, or coordinated with laser energy delivery, although the suction can additionally or alternatively be coordinated with one or more additional or different functions. This can be done automatically, with no user input required to control the suction.

[0006] Endoscopes can be used to visualize targets within the body for diagnosis, treatment, or both. Endoscopes can be configured to facilitate the infusion (e.g., "irrigation") and removal (e.g., "aspiration") of fluids, such as to flush debris from organs and improve visualization during endoscopic procedures. For example, a ureteroscope can include an irrigation fluid channel for delivering saline to the kidney and an aspiration channel for aspirating stone dust and fragments during laser lithotripsy. While stone dust and small fragments can be naturally expelled by the patient, it is beneficial to actively remove the debris during the procedure.

[0007] The inflow and outflow of fluid through the kidney may be accompanied by increases and decreases in renal pressure, which may benefit from monitoring, control, or both. Continuously having suction "on" throughout the entire procedure may not be desirable. Always "on" suction may involve continuous monitoring and control, or a continuous inflow of irrigation fluid to replace fluid removed from suction. Furthermore, suction and / or passage of fluid through the kidney may be unnecessary during periods when pulverization or other stone fragmentation is paused. Therefore, it is advantageous to control suction so that it is activated only when needed.

[0008] The systems and techniques described herein can be used to activate endoscopic suction when deemed important or desirable and suspend suction at other times. While suction can be manually controlled by the endoscope user (e.g., using a foot pedal or other actuator), the present systems and techniques can provide the ability to automatically control suction, such as based on one or more criteria, such as without requiring separate direct user input to activate and / or deactivate suction. For example, suction can be automatically controlled based on the state of the laser or other energy source (or associated control signal), such as being turned on in response to when the laser source is on or is on during laser lithotripsy, and being turned off in response to when the laser source is off or is off.

[0009] A time-shift delay of suction control relative to laser generator activation / deactivation can be provided. For example, suction can be automatically turned off when the laser is turned off, but a programmed off delay can be used to continue suction for a period of time after the laser is turned off or before the laser is turned on. For example, suction can remain "on" for a programmable or otherwise specified time (e.g., 1 / 2 second, 1 second, X seconds, etc.) before the laser begins delivering laser energy or after the laser stops delivering it, such as to move stones or debris to a desired location for ablation by energy delivery or to provide time for dust / debris removal after laser activity.

[0010] One or more criteria other than time may be used to automatically delay when suction is discontinued, such as when the image sensor produces one or more images that are deemed to be sufficiently clear of powder, debris, and / or other debris. For example, a comparison of image clarity, haze, or one or more other individual or combined characteristics may be compared to a specified tolerance or a specified acceptable image. This may be performed algorithmically or using a trained model, such as to help determine or improve results using artificial intelligence and / or machine learning (AI / ML).

[0011] For example, criteria for automatically delaying when suction is discontinued may be based on sensor measurements of intraoperative pressure, such that suction may continue for some time after laser pulverization has ceased depending on when intraoperative pressure has settled to some acceptable level or range.

[0012] In gravity IV, where irrigation or other fluid delivery is based on an active mechanism such as a pump, fluid delivery can be similarly controlled, e.g., based at least in part on one or more laser activation times. For example, when laser pulverization / fragmentation has ended (or after a short delay), both fluid delivery and aspiration can be automatically suspended (e.g., without requiring separate direct user input).

[0013] FIG. 1 is a schematic diagram illustrating an example of a portion of an endoscopic system 100 having a suction component 104 and a laser generator 106 for controlling suction.

[0014] The endoscopic system 100 may include an endoscope 102, a suction component 104, a laser generator 106, and a fluid source 108. The endoscopic system 100 may interact with a patient 110. For example, the endoscopic system 100 may be used to access an organ of the patient 110, such as a kidney 112. The kidney 112 may have a stone 114.

[0015] The endoscope 102 may include one or more channels, such as a working channel, that allows a distal portion of an auxiliary device to be introduced to a target site within the patient 110. Separate irrigation and suction channels may be included in the body of the endoscope 102, or such functions may be performed using the working channel of the endoscope 102. Regardless of which channel is used, it can provide a distal portion of the suction component 104, a distal portion of a laser fiber from the laser generator 106, or a distal portion of an irrigation channel in fluid communication with the fluid source 108 with access to a target site within an organ (e.g., a kidney 112). The endoscope 102 may include an illumination light source (which may be different from the laser generator 106) or be coupled to an illumination light source via an illumination fiber or fiber bundle. This can serve to provide a means of illuminating the kidney 112 at the distal end of the endoscope, such as to aid in endoscopic visual observation via endoscope visualization optics. The endoscope 102 may be disposable or reusable. The endoscope 102 may be flexible, such as to allow the endoscope 102 to pass through an incision in the patient 110, through the urethra of the patient 110, or other means of accessing the kidney 112 or other target organ of the patient 110.

[0016] The irrigation fluid source 108 may provide saline or other fluid through the endoscope 102 to a treatment site within the kidney 112 or other organ. The fluid source 108 may include an intravenous (IV) bag on a pole that provides fluid by gravity. Irrigation using the fluid source 108 may be controlled by a pressure cuff, such as squeezing a component of the IV bag, by raising or lowering the IV bag, by a thumbwheel actuator, such as adjusting the valve opening of a valve, or by other means capable of modifying the rate at which irrigation or other fluid is provided. The fluid source 108 may be controlled to provide a continuous supply of fluid, or to provide a fluid at a constant rate, or to provide a fluid at an adjustable or even varying rate. The flow rate from the fluid source 108 may be controlled manually, such as by a user of the endoscope or another caregiver. The flow rate from the fluid source 108 may be controlled automatically or semi-automatically without user intervention, such as based on one or more detected or anticipated events, although such user intervention may be permitted.

[0017] The laser generator 106 may provide energy to the stone 114 through the endoscope 102, for example, via one or more optical fibers or fiber optic bundles, either of which may be referred to as a laser fiber. For example, the laser generator 106 may generate laser pulses to ablate the stone 114 into smaller fragments (such as fine powder or shards) that can be removed or passed through the patient 110. Ablation by the laser generator 106 may result in stone powder or shards. The stone powder or shards may be large enough to allow the stone to pass naturally, may be removed using suction applied from the suction component 104, or may be removed with the assistance of a retrieval device or other medical equipment. In some embodiments, the laser generator 106 may be replaced by (or augmented by) another energy source, such as an ultrasonic energy source. The laser generator 106 may be manually controlled by a user to trigger the delivery of laser energy to the target. Alternatively or additionally, the laser generator 106 may be controlled automatically, without requiring user intervention to trigger delivery of laser energy to the target, such as when an AI / ML or other trained model identifies a stone at which the laser is directed. Alternatively or additionally, the laser generator 106 may be controlled semi-automatically, such as when an AI / ML or other trained model identifies a stone at which the laser is directed but requests user confirmation before actually triggering delivery of laser energy. Alternatively or additionally, the energy level of the laser pulses emitted by the laser generator 106, or the pulse repetition rate or pattern of the laser generator 106, may be determined automatically or semi-automatically. Such automatic energy level, repetition rate, or pattern may be issued automatically, semi-automatically, or by a user. Controlling any of the aspiration, irrigation, ablation, or other functions may involve controlling the positioning or movement of the endoscope 102 itself, such as by a fully robotic or robot-assisted approach, or controlling one or more other end effectors associated with the endoscope 102.

[0018] The suction component 104 may provide suction to a target, or working area of ​​an organ (e.g., kidney 112), through the endoscope 102, such as through a suction channel or working channel of the endoscope 102. The suction component 104 may use suction to remove fluid from the kidney 112. The suction component 104 may use suction to remove stone dust or debris from the kidney 112. The suction rate may be established or adjusted to be substantially similar to the rate at which irrigation or other fluid is provided so that a substantially constant amount of fluid is present within the working area and organ. For example, if the fluid delivery rate is fast, the suction rate may be fast. Similarly, if the fluid rate is slow, the suction rate may be slow. The fluid delivery rate may be established or modified based at least in part on the suction rate. Conversely, the suction rate may be established or modified based at least in part on the fluid delivery rate.

[0019] The endoscopic system 100 may include an imaging device, imaging optics, or both. For example, a camera or other imaging device may be incorporated within the endoscope 102. The imaging device may be separate from the endoscope 102, completely separate, or separate but insertable through the endoscope 102 toward a target. The imaging device may provide one or more still or video images of a working area of ​​an organ (e.g., kidney 112). Object recognition or other image processing may be performed on the images, as described herein.

[0020] The endoscopic system 100 may include or be coupled to a computing device or other controller circuitry, which may be implemented in hardware, software, firmware, or some combination thereof. The computing device may include a processor and a memory device. The memory device may include instructions that, when executed by the processor, cause the computing device to perform one or more actions or operations. The computing device may be capable of image processing, activating and / or deactivating the suction component 104, varying the suction rate of the suction component 104, activating and / or deactivating the laser generator 106, varying the energy level of the laser generator 106, activating and / or deactivating the fluid source 108, varying the fluid delivery rate of the fluid source 108, receiving sensed indications of one or more characteristics of the working environment from one or more sensors (e.g., temperature sensors, pressure sensors, etc.), or combinations thereof.

[0021] FIG. 2 illustrates a method 200 for controlling suction and / or irrigation based on laser energy. A computing device or controller circuit may implement method 200. At 202, an indication that the laser generator 106 is activated may be received such that the laser generator 106 provides laser energy. A user may activate the laser generator 106 to deliver laser energy by direct user input. At 204, suction may be modified. Suction may be modified without direct user input. For example, when the laser generator 106 is providing laser energy, the computing device may responsively trigger turning on the suction component 104 to provide suction or increase suction from a lower ambient or standby level of suction, etc. At 206, an indication that the laser generator 106 is deactivated may be received such that the laser generator 106 is not delivering laser energy. At 208, suction may be modified. Suction may be modified without additional user input. When the laser generator 106 stops providing laser energy, the computing device can responsively trigger turning off the suction component 104 to stop providing suction or reduce suction from a relatively higher "active" suction level to a relatively lower ambient or standby level. The laser generator 106 may stop providing laser energy by direct user input to the laser generator 106. The fluid delivery rate of the fluid source 108 may likewise be automatically controllably adjusted by the computing device in a manner similar to method 200. In one example, one or more parameters associated with the relative energy or power of the laser generator 106 may additionally or alternatively be used to trigger the computing device to, for example, change the fluid delivery rate of the fluid, the aspiration rate of the suction, or both.For example, decreasing the laser energy may trigger the computing device to decrease the suction rate of the suction component 104, and increasing the laser energy may trigger the computing device to increase the suction rate of the suction component 104. Rather than waiting for an indication that the laser energy has been deactivated, the computing device may predict when to again modify suction based on the current suction rate, the current fluid rate, the current energy level, and the current pulse pattern of the energy laser. Thus, suction can be modified at 204 based on the indication received in step 202, or modified at 208 without an additional indication in step 206.

[0022] The timing of the suction component 104 can also be established or manipulated in conjunction with or in response to changes or activation / deactivation of the laser generator 106, such as to modify the suction rate and / or adjust the activation or amount of suction, and need not be adjusted precisely simultaneously. For example, the computing device may turn off (or power down) the suction component 104 in step 204 at a time lag after (or even before) the laser generator 106 is turned off (or de-energized) in step 206. For example, the laser generator 106 may have a predetermined pattern of laser energy delivery when the laser generator 106 is activated, such that the computing device may turn off (or power down) the suction before deactivating (or reducing the laser energy) the laser generator 106. The time lag may additionally or alternatively be based in whole or in part on a time delay, temperature in the working area, pressure in the working area, and / or other measured characteristics. Thus, the computing device may activate (in step 204) or deactivate (in step 208) the suction component 104 and / or the fluid source 108 based on a combination of settings or measurements (e.g., temperature, pressure, laser energy, or other measured characteristics). For example, in step 202, the laser generator 106 may begin delivering laser energy at time 0, and two seconds later, in step 204, the suction component 104 and / or the fluid source 108 may be activated or increased. Similarly, in step 206, the laser generator 106 may stop delivering laser energy at time x, and two seconds later, in step 208, the suction component 104 and / or the fluid source 108 may be deactivated or decreased. As another example, the laser generator 106 may be activated, but the laser energy may be set to a delay so that suction can be activated or modified before the delivery of laser energy. For example, suction may move the stone 114 to the location where laser energy is delivered.The method 200 may be repeated as the laser generator 106 is activated and deactivated to ablate the stone 114 .

[0023] The imaging device can capture one or more images of the working area that the computing device analyzes, such as for use in determining how to automatically or semi-automatically control suction, irrigation, or another operating parameter. FIG. 3 illustrates an exemplary method 300 for controlling suction and / or irrigation based on imaging of the working area. In step 302, the imaging device can capture one or more images of the working area. Stone debris may blur the image. In step 304, image processing by the computing device can be used to determine the degree of blur in the image. If some degree of blur is not present, the imaging device can continue to capture images in step 302, and the image processing device can continue to determine the degree of blur in the image in step 304. In step 306, the computing device can activate the suction component 104 or modify the suction rate if it determines that some degree of blur is present in the image. Similarly, the computing device can deactivate the suction component 104 if it determines that less blur is present in the image. For example, the computing device can compare two or more images of the working area based on blur, such as to determine blur trends. The computing device may predict when to activate or deactivate the suction component 104 based on the blur trend. Alternatively or additionally, the method 300 may be used to control irrigation, or both irrigation and suction, of the fluid source 108. The method 300, or portions thereof, may be repeated throughout the duration of the procedure. The computing device may calculate a composite index, such as one that can use one or more indications of blur, aspiration rate, fluid rate, laser energy or state, or one or more other conditions of the working area, to determine or predict when to activate or deactivate the suction component 104.

[0024] FIG. 4 illustrates an example method 400 for controlling suction and / or irrigation based on imaging of a working area. In step 402, an imaging device can provide one or more images of the working area. In step 404, a computing device can determine or track the proximity between the stone 114, or the dust or debris caused by the stone 114, and the distal end of the endoscope 102. In step 406, based on the determination of such distance or proximity, the computing device can activate the suction component 104 or modify the suction rate when the distal end of the endoscope 102 is within a desired distance from the dust or debris caused by the stone 114. The computing device can deactivate the suction component 104 when the distal end of the endoscope 102 is outside a specified or desired distance from the dust or debris caused by the stone 114. Alternatively or additionally, the method 400 can be used to control irrigation of the fluid source 108, or both irrigation and suction. The method 400, or portions thereof, can be repeated throughout the duration of the procedure.

[0025] FIG. 5 illustrates an example method 500 for controlling suction and / or irrigation based on imaging of a working area. In step 502, an imaging device may provide one or more images of the working area. In step 504, image processing by a computing device may be used to count the number of debris in the image of the working area. Other image processing may be performed by the computing device, such as to determine the size of one or more of the debris. Using this information or similar information, in step 506, the computing device may activate the suction component 104, such as if the number of debris is greater than a certain number. The computing device may activate the suction component 104 if the size of at least one of the debris is below a certain size. For example, the computing device may activate the suction component 104 if the size of at least one of the debris is small enough to pass through the endoscope 102, such as through its working channel or another suction channel. Additionally or alternatively, using this information or similar information, the computing device may issue a control signal to the suction component 104 to deactivate or reduce the suction applied by the suction component 104, such as when the number of debris falls below a certain number. For example, the computing device may issue a control signal to the suction component 104 to deactivate or power down the suction component 104 if the number of debris reaches zero. In one example, the computing device may issue a control signal to the suction component 104 to deactivate or power down the suction component 104 if no debris below a specified threshold size is detected. Alternatively or additionally, the method 500 may be used to control irrigation, or both irrigation and suction, of the fluid source 108. The method 500, or portions thereof, may be repeated throughout the duration of the treatment.

[0026] FIG. 6 illustrates an exemplary method 600 for controlling suction and / or irrigation based on imaging of a working area. In step 602, an imaging device can provide one or more images of the working area. In step 604, image processing by a computing device can be used to distinguish between the stone 114 or powder or fragments of the stone 114 and the patient's organ. For example, the computing device can determine that powder or fragments of the stone 114 have settled in the tissue of the organ. In that case, in step 606, the computing device can issue a control signal to activate the suction component 104 when the distal tip of the endoscope 102 is within a specified distance from the powder or fragments of the stone 114 and can issue a control signal to deactivate the suction component 104 when the distal tip of the endoscope 102 is outside the specified distance of the tissue. For example, the computing device can issue a control signal to deactivate the suction component 104 if the image processing indicates that the tissue has dislodged or substantially dislodged the powder or fragments of the stone 114. Alternatively or additionally, method 600 may be used to control irrigation, or both irrigation and aspiration, of fluid source 108. Method 600, or portions thereof, may be repeated throughout the duration of the treatment.

[0027] FIG. 7 illustrates an exemplary method 700 for determining a treatment plan based on imaging of a concretion 114. In step 702, an imaging device can provide one or more images of a working area including the concretion 114. In step 704, a computing device can be programmed to determine one or more characteristics of the concretion 114 and / or stone 114 debris or fragments, such as using information from one or more images from the imaging device or by using spectroscopic information from the response of the target concretion 114 to illumination. The computing device can determine the size of the concretion 114 and / or stone 114 debris or fragments. The computing device can determine the material composition or characteristics of the concretion 114 and / or stone 114 debris or fragments. In step 706, the computing device can determine a treatment plan based on one or more characteristics of the concretion 114 and / or stone 114 debris or fragments. For example, the computing device can determine the energy level of laser pulses emitted by the laser generator 106. As another example, the computing device may determine the pulse repetition rate or pattern of the laser generator 106. As another example, the computing device may determine the suction rate and / or suction pattern of the suction component 104. The computing device may determine the fluid delivery rate and / or fluid delivery pattern of the fluid source 108. Method 700, or portions thereof, may be repeated throughout the duration of the treatment. For example, the treatment plan may be modified throughout the treatment depending on the effectiveness of the current treatment plan. Modification of the treatment plan may include pausing the delivery of ablation energy. For example, treatment may be paused until the image is substantially clear and the stone 114 (or the location of the stone 114) can again be identified. The methods described in FIGS. 2-7 may be used alone or in combination.

[0028] 8 shows a schematic diagram of an exemplary computer-based clinical decision support system (CDSS) 800 configured to activate fluid or suction, deactivate fluid or suction, modify the rate of fluid flow or suction, or predict when to provide such functions based on characteristic information of the working area, such as laser energy status and / or information about the kidney 112 or stone 114. The characteristic information may include images, intraoperative temperature, or intraoperative pressure. In various embodiments, the CDSS 800 includes an input interface 802 in which patient-specific characteristic information (e.g., images, temperature, pressure) is provided as input features to an artificial intelligence (AI) model 804, a processor that performs inference operations in which the characteristic information (e.g., images, temperature, pressure) is applied to the AI ​​model to generate control signals to activate, deactivate, or adjust the rate of suction or fluid flow, and a user interface (UI) through which the rate and / or status of fluid and suction are communicated to a user, e.g., a clinician.

[0029] In some embodiments, the input interface 802 may be a direct data link between the CDSS 800 and one or more medical devices that generate at least a portion of the input features, such as an imaging device, a spectroscopic device, a thermometer, a pressure sensor, or other sensors for providing imaging, spectroscopic, temperature, pressure, or other characteristic information. For example, the input interface 802 may transmit laser energy status and / or characteristic information (e.g., images, temperature, pressure) directly to the CDSS during a therapeutic and / or diagnostic medical procedure. Additionally or alternatively, the input interface 802 may be a classic user interface that facilitates interaction between a user and the CDSS 800. For example, the input interface 802 may facilitate a user interface through which a user may manually input a laser energy treatment protocol for the laser generator 106. Additionally or alternatively, the input interface 802 may provide the CDSS 800 with access to an electronic patient record from which one or more input features, such as previous imaging of the working area, may be extracted. In any of these cases, as described above, the input interface 802 is configured to collect one or more of the following input features associated with a particular patient at or before the time the CDSS 800 is used to assess laser energy conditions and / or characteristic information of the working area, such as information about the kidney 112 or stone 114:

[0030] Based on one or more of the above input features, the processor performs inference operations using the AI ​​model to generate control signals to activate fluid or suction, deactivate fluid or suction, modify the rate of fluid flow or suction, or predict when to provide such functions. For example, the input interface 802 may deliver images of the work area containing the stone 114 to the input layer of the AI ​​model, which propagates these input features through the AI ​​model to the output layer. By making inferences based on patterns found in analyzing the data, AI models can provide computer systems with the ability to perform tasks without being explicitly programmed. AI models explore the research 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 crafting AI models from example training data to make data-driven predictions or decisions, which are expressed as outputs or evaluations.

[0031] Machine learning (ML) has two general modes: supervised ML and unsupervised ML. Supervised ML uses prior knowledge (e.g., examples relating inputs to outputs or outcomes) to learn relationships between inputs and outputs. The goal of supervised ML is to learn a function that best approximates the relationship between training inputs and outputs, given training data, so that the ML model can implement that same relationship to generate a corresponding output given an input. Unsupervised ML is the training of an ML algorithm using uncategorized or unlabeled information, allowing the algorithm to act on that information without guidance. Unsupervised ML is useful for exploratory analysis because it can automatically identify structure in data.

[0032] Common tasks in supervised ML are classification and regression problems. Classification problems, also known as categorization problems, aim to classify items into one of several categorical values ​​(e.g., is this object an apple or an orange?). Regression algorithms aim to quantify some items (e.g., by providing a score for some input values). Some examples of commonly used supervised ML algorithms are logistic regression (LR), naive Bayes, random forests (RF), neural networks (NN), deep neural networks (DNN), matrix decomposition, and support vector machines (SVM).

[0033] Common tasks in unsupervised ML include clustering, representation learning, and density estimation. Some examples of commonly used unsupervised ML algorithms are K-means clustering, principal component analysis, and autoencoders.

[0034] Another type of ML is federated learning (also known as collaborative learning), in which algorithms are trained across multiple distributed devices that hold local data without exchanging data. This approach contrasts with traditional centralized machine learning techniques, in which all local datasets are uploaded to a single server, as well as more classical distributed approaches that often assume that local data samples are similarly distributed. Federated learning allows multiple actors to build a common, robust machine learning model without sharing data, addressing important issues such as data privacy, data security, data access rights, and access to heterogeneous data.

[0035] In some examples, the AI ​​model may be continuously or periodically trained prior to execution of an inference operation by the processor. During the inference operation, patient-specific input features provided to the AI ​​model may then be propagated from an input layer, through one or more hidden layers, to an output layer that ultimately corresponds to a control signal for activating fluid or suction, deactivating fluid or suction, modifying the rate of fluid flow or suction, or predicting when to provide such a function. For example, the AI ​​model 804 may be trained to implement the methods described in any of Figures 2-7, alone or in combination.

[0036] Examples of the methods described herein may be at least partially machine- or computer-implemented. Some examples may include computer-readable or machine-readable media encoded with instructions operable to configure an electronic device to perform the methods described in the examples above. Implementations of such methods may include code, such as microcode, assembly language code, high-level language code, etc. Such code may include computer-readable instructions for performing various methods. The code may form part of a computer program product. Further, in one example, the code may be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer-readable media, such as during execution or at other times. Examples of these tangible computer-readable media may include, but are not limited to, hard disks, removable magnetic disks, removable optical disks (e.g., compact disks and digital video disks), magnetic cassettes, memory cards or sticks, random access memory (RAM), read-only memory (ROM), etc.

[0037] [Additional note 1] 1. An endoscopic system for coordinating the operation of an ablation modality with at least one of ancillary aspiration and irrigation modalities, comprising: An endoscopic system comprising: a controller circuit configured to issue control signals to coordinate the timing or other parameters of at least one of the ancillary suction and irrigation modalities with the ablation timing or other ablation parameters of ablation energy emitted by the ablation modality toward an ablation target within a patient, wherein the control signals are issued automatically without requiring direct user input to control at least one of the ancillary suction and irrigation modalities to relatively increase at least one of the ablation and irrigation in temporary coordination with the emission of the ablation energy by the ablation modality. [Additional note 2] and at least one of an imaging device, a spectroscopic device, and other sensor for providing imaging, spectroscopic, or other characteristic information regarding at least one of the ablation target within the patient and an environment of the ablation target within the patient; The endoscopic system of claim 1, wherein the controller circuit generates the control signal based at least in part on information from the sensor regarding at least one of the ablation target within the patient and the ablation target environment within the patient. [Additional note 3] the controller circuit receiving a first image of the ablation target environment from the imaging device; identifying dust or debris from the ablation target from the first image; generating the control signal based on characteristic information about the powder or debris identified in the first image; The endoscope system according to claim 2, [Additional note 4] An endoscopic system as described in Appendix 3, wherein the characteristic information is blur caused by the fine dust of the ablation target in the first image. [Additional note 5] The endoscope system described in Appendix 3, wherein the characteristic information is the number of fragments of the ablation target in the first image. [Additional note 6] An endoscopic system as described in Appendix 3, wherein the characteristic information is the amount of fine powder or debris of the ablation target that has settled in the ablation target environment in the first image. [Additional note 7] the controller circuit receiving a second image of the ablation target environment from the imaging device; identifying powder or debris of the ablation target from the second image; generating the control signal based on characteristic information about the powder or debris identified in the second image; and The endoscope system according to claim 3, [Additional note 8] An endoscopic system as described in Appendix 7, wherein the characteristic information is a change in blur caused by the fine particles of the ablation target between the first image and the second image. [Additional note 9] An endoscopic system as described in Appendix 7, wherein the characteristic information is a tendency of blur caused by the fine dust of the ablation target based on the first image and the second image. [Additional Note 10] An endoscopic system as described in Appendix 9, wherein the controller circuit predicts when to generate the control signal based on the trend of the blur caused by the fine dust of the ablation target based on the first image and the second image. [Additional Note 11] The endoscopic system described in Appendix 7, wherein the characteristic information is a change in the number of fragments of the ablation target between the first image and the second image. [Additional Note 12] An endoscopic system as described in Appendix 7, wherein the characteristic information is a change in the amount of fine powder or debris of the ablation target that has settled in the ablation target environment between the first image and the second image. [Additional Note 13] The endoscopic system described in Appendix 2, wherein the characteristic information is intraoperative pressure or intraoperative temperature of the ablation target environment. [Additional Note 14] An endoscopic system as described in Appendix 2, wherein the controller circuit predicts the duration between the first control signal and the second control signal based on the characteristic information. [Additional Note 15] The endoscopic system described in Appendix 1, wherein the control signal for coordinating the timing or other parameters of at least one of the ancillary suction and irrigation modalities with the ablation timing or other ablation parameters of the ablation energy emitted by the ablation modality is emitted at a time shift from the ablation timing of the ablation energy. [Additional Note 16] 1. A method for coordinating the operation of an ablation modality with at least one of ancillary aspiration and irrigation modalities, comprising: issuing control signals to coordinate timing or other parameters of at least one of the ancillary suction and irrigation modalities with ablation timing or other ablation parameters of ablation energy emitted by the ablation modalities toward an ablation target within the patient; A method wherein the control signal is automatically issued to relatively increase at least one of suction and irrigation in temporary coordination with the emission of the ablation energy by the ablation modality without requiring direct user input to control at least one of the concomitant aspiration and irrigation modalities. [Additional Note 17] receiving imaging, spectroscopic, or other characteristic information regarding at least one of the ablation target within the patient and an ablation target environment within the patient; generating the control signal based at least in part on information from a sensor regarding at least one of the ablation target within the patient and an ablation target environment within the patient; The method according to claim 16, further comprising: [Additional Note 18] receiving a first image of the ablation target environment; identifying dust or debris from the ablation target from the first image; generating the control signal based on characteristic information about the powder or debris identified in the first image; The method according to claim 17, further comprising: [Additional Note 19] 19. The method of claim 18, wherein the characteristic information is blur caused by the fine dust of the ablation target in the first image. [Additional Note 20] 19. The method of claim 18, wherein the characteristic information is the number of fragments of the ablation target in the first image. [Additional Note 21] 19. The method of claim 18, wherein the characteristic information is the amount of powder or debris of the ablation target that has settled in the ablation target environment in the first image. [Additional note 22] receiving a second image of the ablation target environment; identifying dust or debris from the ablation target from the second image; generating the control signal based on characteristic information about the powder or debris identified in the second image; The method according to claim 18, further comprising: [Additional Note 23] 23. The method of claim 22, wherein the characteristic information is a change in blur caused by the fine particles of the ablation target between the first image and the second image. [Additional note 24] 23. The method of claim 22, wherein the characteristic information is a tendency of blur caused by the fine particles of the ablation target based on the first image and the second image. [Additional note 25] The method described in Appendix 24, further comprising a step of predicting when to generate the control signal based on the trend of the blur caused by the fine dust of the ablation target based on the first image and the second image. [Additional note 26] 23. The method of claim 22, wherein the characteristic information is a change in the number of fragments of the ablation target between the first image and the second image. [Additional note 27] 23. The method of claim 22, wherein the characteristic information is a change in the amount of powder or debris of the ablation target settled in the ablation target environment between the first image and the second image. [Additional note 28] The method described in Appendix 17, wherein the characteristic information is intraoperative pressure or intraoperative temperature of the ablation target environment. [Additional note 29] 1. An endoscopic system for coordinating the operation of an ablation modality with at least one of ancillary aspiration and irrigation modalities, comprising: a controller circuit configured to generate a treatment plan for adjusting timing or other parameters of ablation energy delivered by the ablation modality to an ablation target within the patient; and at least one of an imaging device, a spectroscopic device, and other sensors for providing imaging, spectroscopic, or other characteristic information regarding at least one of the ablation target within the patient and an ablation target environment within the patient; Equipped with An endoscopy system, wherein the controller circuit generates the treatment plan based at least in part on information from the sensors regarding at least one of the ablation target within the patient and an ablation target environment within the patient. [Additional note 30] 30. The endoscopic system of claim 29, wherein the treatment plan further adjusts the timing or other parameters of at least one of the additional suction and irrigation modalities. [Explanation of symbols]

[0038] 100 Endoscopic system, 102 Endoscope, 104 Suction component, 106 Laser generator, 108 Fluid source, 110 Patient, 112 Kidney, 114 Stone, 200 Method, 300 Method, 400 Method, 500 Method, 600 Method, 700 Method, 800 Computer-based clinical decision support system (CDSS), 802 Input interface, 804 AI model

Claims

1. An endoscope system including a controller circuit, the controller circuit receiving one or more images of a working region including an ablation target; determining a degree of visibility within one or more of said images; issuing control signals to coordinate timing and other parameters of the fluid aspiration or irrigation member with timing and other parameters of the ablation member; It is structured as follows: the control signal causes a delay in actuation of the ablation member until the visibility falls below a threshold criterion; the control signal is generated automatically using a trained learning model; the trained learning model coordinates timing and other parameters of the fluid aspiration or irrigation member with timing or other parameters of the ablation member based at least in part on at least one of historical and real-time data from one or more sensors communicatively coupled to the controller circuit; An endoscopic system, wherein the controller circuit is configured to automatically control at least one of: 1) the position of an endoscope coupled to the endoscopic system; and 2) an end effector connected to the endoscope.

2. The endoscopic system of claim 1 , wherein the controller circuit is configured to control suction based on intraoperative pressure of an ablation target environment.

3. 3. The endoscopic system of claim 2, wherein the controller circuit is configured to maintain suction for a predetermined period of time after ceasing laser ablation based on when the intraoperative pressure is within an acceptable level or range.

4. 10. The endoscopic system of claim 1, wherein the controller circuitry is configured to make one or more predictable adjustments to at least one of suction, irrigation, and ablation based on trends derived from historical data.

5. The endoscopic system of claim 4 , wherein the controller circuit is configured to predict when to generate the control signal based on a trend of blur from ablation of an ablation target.

6. The endoscopic system of claim 1 , further comprising an illumination light source coupled to an endoscope of the endoscopic system via an illumination fiber or fiber bundle for enhanced imaging of a target site.

7. The endoscopic system of claim 1 , wherein the controller circuit is configured to automatically suspend both fluid delivery and suction upon completion of laser ablation.

8. the controller circuitry is configured to determine a treatment plan based on one or more characteristics of the ablation target; The endoscopic system of claim 1 , wherein the one or more characteristics of the ablation target include at least one of a size, a material composition, and another characteristic of the ablation target.

9. 9. The endoscopic system of claim 8, wherein the treatment plan includes at least one of an energy level of laser pulses from a laser generator coupled to the endoscopic system, at least one of a pulse repetition rate and pattern of the laser generator, at least one of an aspiration rate and pattern, and at least one of a fluid delivery rate and pattern.

10. The endoscopic system of claim 1 , wherein the controller circuit is configured to maintain suction for a predetermined period of time before initiating laser ablation to position the ablation target for delivery of laser energy.

Images