Anatomical feature identification and aiming
By using a spectral device and neural network in medical surgery to identify and track target anatomical features, combined with electromagnetic sensors and robotic systems, the positioning and tracking difficulties in the prior art are solved, surgical accuracy and efficiency are improved, and radiation exposure and cost are reduced .
Patent Information
- Application Number
- CN202411173246.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2019-12-31
- Filing Date
- 2020-12-14
- Publication Date
- 2024-12-03
AI Technical Summary
In existing medical procedures, especially nephroscopy and renal stone removal, it is difficult to accurately locate and track target anatomical features, such as the mastoid of the renal calyx, resulting in low surgical accuracy and efficiency, and relying on fluoroscopy increases costs and radiation Exposure risk.
Using a system based on a spectral device and neural network, anatomical feature images are captured through the camera, and a pre-trained neural network is used to identify and track target anatomical features. Combined with electromagnetic sensors and robotic systems, real-time adjustment and guidance of target positions are achieved to reduce fluorescence. Reliance of mirrors.
It improves the accuracy and efficiency of the surgery, reduces radiation exposure to patients and physicians, reduces surgical costs, and simplifies the surgical procedure, making nephroscopy and kidney stone removal more efficient and accurate.
Smart Images

Figure CN119055360A_ABST
Abstract
Description
[0001] Related Applications
[0002] This application claims priority to U.S. Provisional Application No. 62 / 955,991, filed on December 31, 2019, entitled ANATOMICAL FEATURE IDENTIFICATION AND TARGETING, the disclosure of which is hereby incorporated by reference in its entirety. Background Art Technical Field
[0003] The present invention relates to the field of medical surgery.
[0004] Related technologies
[0005] Various medical procedures involve the use of one or more scope-type devices configured with specific image capture functionality that can be utilized to provide visualization of specific anatomical features associated with the respective medical procedure. Specific operating procedures can be guided, at least in part, by image data captured using such devices. Summary of the invention
[0006] Described herein are systems, devices, and methods for facilitating identification and tracking of various anatomical features based on images of such features obtained using a scopist device or other medical instrument. For example, such feature identification and / or tracking can facilitate targeting of specific anatomical features in conjunction with a medical procedure such as a nephroscopy or other procedure approaching the renal anatomy.
[0007] In some implementations, the present disclosure relates to a method for positioning a surgical instrument. The method includes: advancing a first medical instrument to a treatment site of a patient, the first medical instrument including a camera; recording a target position associated with a target anatomical feature at the treatment site; generating a first image of the treatment site using the camera of the first medical instrument; identifying the target anatomical feature in the first image using a pre-trained neural network; and adjusting the target position based at least in part on the position of the identified target anatomical feature in the first image.
[0008] The method may also include adjusting the orientation of the first medical device based at least in part on the position of the identified target anatomical feature in the first image. For example, adjusting the orientation of the first medical device may involve centering the identified target anatomical feature in a field of view associated with the camera.
[0009] In some embodiments, recording the target position involves contacting the target anatomical feature with the distal end of the first medical instrument; generating position data indicating the contact position of the target anatomical feature and the distal end of the first medical instrument; and storing the position data in one or more data storage devices. For example, the method may also include retracting the distal end of the first medical instrument away from the target anatomical feature before generating the first image.
[0010] In some embodiments, the method further comprises generating a second image of the treatment site using the camera of the first medical device after generating the first image; identifying an anatomical feature in the second image using the pre-trained neural network; determining that the anatomical feature of the second image and the target anatomical feature of the first image represent the same feature; and in response to the determination, adjusting the target position based at least in part on the position of the identified anatomical feature in the second image. For example, determining that the anatomical feature of the second image and the target anatomical feature of the first image represent the same feature may involve determining an amount of overlap between at least a portion of the anatomical feature of the second image and at least a portion of the target anatomical feature of the first image; and determining that the amount of overlap is greater than a predetermined threshold. The method may also include generating a first mask for the first image, the first mask obscuring the at least a portion of the target anatomical feature of the first image; and generating a second mask for the second image, the second mask obscuring the at least a portion of the anatomical feature of the second image, wherein determining the amount of overlap is performed using the first mask and the second mask. In some embodiments, determining that the anatomical feature of the second image and the target anatomical feature of the first image represent the same feature may involve tracking the movement of the feature between the first image and the second image. In some embodiments, the method also includes estimating the three-dimensional position of the anatomical feature of the second image based at least in part on the first image and the second image. For example, estimating the three-dimensional position of the anatomical feature is based on one or more of the following: camera focal length, camera principal point, relative motion of the first medical device, rotation of the first medical device, and electromagnetic, structured illumination, and / or time-of-flight sensor readings.
[0011] In some embodiments, adjusting the target position is further based at least in part on the determined movement of the first medical device. The method may also include percutaneously guiding a second medical device through the patient's tissue toward the target position. For example, guiding the second medical device through the patient's tissue toward the target position may be performed using sensor data provided by alignment sensors of both the first medical device and the second medical device. In some embodiments, the method is performed at least in part by a robotic system.
[0012] In some implementations, the present disclosure relates to a method for targeting an anatomical feature. The method includes: receiving target position data indicating a target position associated with a target anatomical feature of a patient; storing the target position data in one or more data storage devices; receiving a first image of a surgical site in the patient; identifying a first morphology in the first image representing the target anatomical feature using an artificial neural network; and storing updated target position data indicating the target position based on the identified morphology in the first image.
[0013] The method may also include causing the medical device to articulate in response to the updated target position data. In some embodiments, the method is performed by a control circuit system of a medical system, and the target position data and the first image are received from an endoscope of the medical system. The target anatomical feature may be an exposed portion of a papilla in a patient's renal calyx. The artificial neural network may be pre-trained based on known images and labeled data. For example, the artificial neural network may include a multi-layer feature pyramid network.
[0014] The updated target position data may be based at least in part on known respiratory information associated with the patient. In some embodiments, the method further includes: receiving a second image of the surgical site; identifying a second morphology representing the target anatomical feature in the second image using an artificial neural network; and determining a three-dimensional position of the target anatomical feature based at least in part on the first morphology and the second morphology. For example, determining the three-dimensional position of the target anatomical feature may be based at least in part on a relative size of the second morphology. In some embodiments, determining the three-dimensional position of the target anatomical feature is based on data generated by one or more external camera sensors such as a structured light sensor, a time-of-flight sensor, or the like.
[0015] In some embodiments, the present disclosure relates to a medical system, the medical system comprising: an endoscope having a camera and an electromagnetic position sensor associated with a distal end of the endoscope; a robotic medical subsystem, the robotic medical subsystem comprising a plurality of articulated arms; and a control circuit system, the control circuit system being communicatively coupled to the endoscope and the robotic medical subsystem. The control circuit system is configured to: advance the endoscope to a treatment site of a patient in response to user input; record the position of the distal end of the endoscope within an electromagnetic field; generate user interface data indicating the position as a target anatomical position; receive a first image from the camera of the endoscope; use a pre-trained neural network to identify the target anatomical feature in the first image; and adjust the target anatomical position based at least in part on the position of the identified target anatomical feature in the first image.
[0016] The control circuitry may also be configured to calibrate the distal end of the endoscope in an electromagnetic field.In some embodiments, the medical system further includes a robotic nephroscope communicatively coupled to the control circuitry.
[0017] In some embodiments, the present disclosure relates to a computing device including an endoscope interface and a control circuit system including one or more processors and one or more data storage devices. The control circuit system is configured to receive alignment sensor data indicating the position of a distal end of an endoscope coupled to the control circuit system on the endoscope interface; generate first user interface data indicating the position of the distal end of the endoscope as a target nephroscopic examination position; receive a first image of a medical site on the endoscope interface; identify a first anatomical morphology in the first image; receive a second image of the medical site on the endoscope interface; identify a second anatomical morphology in the second image; determine that the first anatomical morphology and the second anatomical morphology represent the same target anatomical feature; and update the target nephroscopic examination position based on the determination.
[0018] The control circuit system can also be configured to determine that an amount of overlap of the first morphology and the second morphology in the overlap of the first image and the second image is greater than a predetermined threshold. In some embodiments, the control circuit system is configured to generate second user interface data indicating an updated target nephroscopic position in response to the updating of the target nephroscopic position.
[0019] For purposes of summarizing the present disclosure, certain aspects, advantages, and novel features have been described. It will be appreciated that not necessarily all such advantages may be achieved according to any particular embodiment. Thus, the disclosed embodiments may be performed in a manner that achieves or optimizes one advantage or group of advantages taught herein without necessarily achieving other advantages that may be taught or suggested herein. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Various embodiments are depicted in the accompanying drawings for illustrative purposes and should not be construed as limiting the scope of the present invention in any way. In addition, the various features of the different disclosed embodiments may be combined to form additional embodiments as part of the present disclosure. Throughout the accompanying drawings, reference numerals may be reused to indicate the corresponding relationship between reference elements.
[0021] Figure 1 Embodiments of a robotic medical system are depicted in accordance with one or more embodiments.
[0022] Figure 2 A method for performing a Figure 1 An exemplary device implemented in a medical system.
[0023] Figure 3 A ureteroscope placement portion of a urinary system is depicted according to one or more embodiments.
[0024] 4 is a flow chart illustrating a process for performing guided percutaneous kidney stone removal according to one or more embodiments.
[0025] 5 illustrates certain images corresponding to various blocks, states, and / or operations associated with the process of FIG. 4 , according to one or more embodiments.
[0026] Figure 6 is a flow chart depicting a process for targeting an anatomical feature according to one or more embodiments.
[0027] Figure 7 Depicted is a target recognition and / or classification architecture according to one or more embodiments.
[0028] Figure 8 Depicted is a neural network based image segmentation architecture according to one or more embodiments.
[0029] Fig. 9 is a flow chart depicting a process for tracking a target anatomical feature according to one or more embodiments.
[0030] Figure 10-1 and Figure 10-2 A flow chart depicting a process for tracking a target anatomical feature according to one or more embodiments is provided.
[0031] Fig.11 According to one or more embodiments, the Figure 10-1 and Figure 10-2 Some images of the various blocks, states, and / or operations associated with a process.
[0032] Fig.12 A three-dimensional position estimation framework is depicted in accordance with one or more embodiments. DETAILED DESCRIPTION
[0033] The titles provided herein are for convenience only and do not necessarily affect the scope or meaning of the claimed invention. Although certain preferred embodiments and examples are disclosed below, the subject matter of the present invention extends beyond the specifically disclosed embodiments to other alternative embodiments and / or uses and modifications and equivalents thereof. Therefore, the scope of the claims that may appear herein is not limited by any of the specific embodiments described below. For example, in any method or process disclosed herein, the actions or operations of the method or process may be performed in any suitable sequence and are not necessarily limited to any specific disclosed sequence. Various operations may then be described as multiple discrete operations in a manner that may help understand certain embodiments. However, the order of description should not be interpreted as implying that these operations depend on the order. In addition, the structures, systems and / or devices described herein may be embodied as integrated components or separate components. For the purpose of comparing various embodiments, certain aspects and advantages of these embodiments are described. All such aspects or advantages may not necessarily be realized by any specific embodiment. Therefore, for example, various embodiments may be performed by realizing or optimizing an advantage or a set of advantages taught herein without necessarily realizing other aspects or advantages that may also be taught or proposed herein.
[0034] Certain standard positional anatomical terms are used herein to refer to the anatomical structures of animals, and the animals are humans relative to the preferred embodiment. Although certain spatial relative terms such as "external", "internal", "upper", "lower", "below", "above", "vertical", "horizontal", "top", "bottom" and similar terms are used herein to describe the spatial relationship between a device / element or anatomical structure and another device / element or anatomical structure, it should be understood that these terms are used herein for the convenience of description to describe the positional relationship between the elements / structures, as shown in the accompanying drawings. It should be understood that spatial relative terms are intended to cover different orientations of the elements / structures in use or operation in addition to the orientations depicted in the accompanying drawings. For example, an element / structure described as "above" another element / structure may represent a position below or beside such other elements / structures relative to the subject patient or an alternative orientation of the element / structure, and vice versa.
[0035] The present disclosure relates to systems, devices and methods for identifying and tracking target anatomical features of a patient to assist in certain medical procedures. Although certain aspects of the present disclosure are described in detail herein in the context of renal, urological and / or kidney surgery (such as kidney stone removal / treatment surgery), it should be understood that such background is provided for convenience and clarity, and the anatomical feature identification and tracking concepts disclosed herein are applicable to any suitable medical procedure. However, as described, a description of the renal / urological anatomical structure and associated medical problems and surgeries is presented below to assist in describing the inventive concepts disclosed herein.
[0036] Kidney stone disease, also known as urolithiasis, is a relatively common medical condition that involves the formation of a mass of solid material in the urinary tract, which is referred to as a "kidney stone," "urolith," "renal calculi," "renal lithiasis," or "nephrolithiasis." Urinary stones can form and / or be found in the kidneys, ureters, and bladder (known as "bladder stones"). Such urinary stones form due to concentrated minerals and can cause significant abdominal pain once they reach a size large enough to block the flow of urine through the ureters or urethra. Urinary stones can form from calcium, magnesium, ammonia, uric acid, cysteine, or other compounds.
[0037] In order to remove urinary stones from the bladder and ureter, the surgeon can insert a ureteroscope into the urinary tract through the urethra. Typically, a ureteroscope includes an endoscope at its distal end that is configured to enable visualization of the urinary tract. The ureteroscope may also include a lithotomy mechanism to capture or break up urinary stones. During a ureteroscopy procedure, one physician / technician may control the position of the ureteroscope while another physician / technician may control the lithotomy mechanism.
[0038] In order to remove relatively large stones (i.e., "kidney stones") from the kidney, a physician may use a percutaneous nephrolithotomy ("PCNL") technique, which includes inserting a nephroscope through the skin to break up and / or remove the stones. Fluoroscopy may be used to locate the kidney stones to provide a target for inserting the nephroscope. However, due to the cost of the fluoroscope itself and the cost of the technician operating the fluoroscope, fluoroscopy increases the cost of nephrolithotomy. Fluoroscopy also exposes the patient to radiation for a long time. Even with fluoroscopy, accurately forming a percutaneous incision to approach kidney stones may also be difficult and undesirably imprecise. In addition, some nephrolithotomy techniques involve two or three days of hospitalization. In short, some nephrolithotomy techniques may be relatively expensive and difficult for patients.
[0039] According to certain surgical procedures, an endoscope (e.g., a ureteroscope) may be equipped with a position sensor, wherein the position of the sensor is used as a target for percutaneous approach, such as for PCNL. For example, a ureteroscope equipped with an electromagnetic sensor and / or a percutaneous access needle equipped with an electromagnetic sensor may be used to guide percutaneous renal approach for kidney stone removal, etc. In such procedures, the surgeon / physician may drive the ureteroscope to the target calyx of the kidney and use an electromagnetic sensor (e.g., a beacon) associated with the distal end / tip of the ureteroscope as the percutaneous access target for the needle. In general, the efficacy of the percutaneous axis to the target calyx may depend at least in part on where the physician positions / parks the ureteroscope relative to, for example, the position and / or direction of advancement of the ureteroscope relative to the mastoid through which percutaneous access to the target calyx may be obtained. For some procedures in which the distal end / tip of the ureteroscope is used as a target for percutaneous approach, it may be desirable for the distal tip of the ureteroscope to be as close to the mastoid / calyx interface as possible during percutaneous approach / approach.
[0040] The terms "scope" and "endoscope" are used herein according to their broad and ordinary meanings, and may refer to any type of elongated medical device having image generation, viewing and / or capture functionality and configured to be introduced into any type of organ, cavity, lumen, chamber, or space of the body. For example, references herein to a scope or endoscope may refer to a ureteroscope, cystoscope, nephroscope, bronchoscope, arthroscopy, colonoscope, laparoscope, laparoscope, laparoscope, etc. In some cases, a scope / endoscope may include a rigid or flexible tube and may be sized to pass within an outer sheath, catheter, introducer, or other lumen-type device, or may be used without such a device.
[0041] Robotic-assisted percutaneous surgery may be performed in conjunction with various medical procedures, such as kidney stone removal surgery, where robotic tools may enable a physician / urologist to perform endoscopic target approaches (e.g., ureteroscopy) as well as percutaneous approaches or treatments. However, where the operating physician relies on a fixed percutaneous approach target position, moving target anatomical features during the procedure may be problematic. Advantageously, various aspects of the present disclosure relate to real-time target tracking / guidance in medical procedures, which the operating physician may utilize, such as by automatically adjusting the endoscope position and / or alignment in response to such real-time target tracking information to guide percutaneous approach instruments (e.g., needles or other rigid tools) and / or guide robotic instrumentation. To facilitate such functionality, embodiments of the present disclosure may advantageously provide mechanisms for automatic target detection, tracking, and / or three-dimensional position estimation to assist a physician (e.g., urologist) in achieving relatively efficient and accurate percutaneous approaches for various surgical procedures, such as nephroscopy. Although aspects of the present disclosure are described herein in the context of ureteroscope-guided nephroscopy for convenience, it should be understood that the inventive aspects of the present disclosure may be implemented in any suitable or desired type of percutaneous and / or endoscopic medical procedure, whether robotic or not.
[0042] Medical system
[0043] Figure 1 An exemplary medical system 10 for performing various medical procedures in accordance with aspects of the present disclosure is depicted. The medical system 10 includes a robotic system 11 that is configured to engage and / or control a medical device 32 to perform a procedure on a patient 13. The medical system 10 also includes a control system 50 that is configured to interface with the robotic system 11, provide information about the procedure, and / or perform a variety of other operations. For example, the control system 50 may include a display 42 to present certain information to assist the physician 5. The medical system 10 may include a table 15 configured to hold a patient 130. The system 10 may also include an electromagnetic (EM) field generator (not shown; see Figure 3 ), the electromagnetic field generator may be held by one or more of the robotic arms 12 of the robotic system 11, or may be an independent device.
[0044] In some implementations, the system 10 can be used to perform percutaneous procedures, such as percutaneous nephrolithotomy (PCNL). To illustrate, if the patient 13 has a kidney stone 80 that is too large to be removed through the urinary tract, the physician can perform a procedure to remove the kidney stone through a percutaneous access point on the patient 13. In some embodiments, the physician can interact with the control system 50 and / or the robotic system 11 to control the robotic system 11 to advance and navigate the medical instrument 32 (e.g., a scope) from the urethra 67, through the bladder 65, up the ureter 63 and into the kidney 70 where the stone 80 is located. The control system 50 can provide information about the medical instrument 32 via the display 42, such as real-time endoscopic images captured by the medical instrument, to assist the physician 5 in navigating the medical instrument.
[0045] The renal anatomy is described herein with reference to certain medical procedures related to aspects of the inventive concepts. Figure 1 The kidneys shown in a typical anatomical position in FIG. 6 generally include two bean-shaped organs located on the left and right in the retroperitoneal cavity. In adult humans, the length of the kidney is generally about 11 cm. The kidneys receive blood from the paired renal arteries; the blood exits into the paired renal veins, which are not shown for visual clarity. Each kidney 70 is attached to a ureter 63, which is a tube that carries secreted urine from the kidney to the bladder 65.
[0046] The kidney is usually positioned relatively high in the abdominal cavity and is located in a retroperitoneal position at a slight oblique angle. The asymmetry in the abdominal cavity caused by the position of the liver usually causes the right kidney to be slightly lower than and smaller than the left kidney, and to be placed slightly more in the middle than the left kidney. The top of each kidney is the adrenal gland. The upper part of the kidney is partially protected by the 11th rib and the 12th rib. Each kidney, its adrenal gland is surrounded by two layers of fat: the perinephric fat present between the renal fascia and the renal capsule and the pararenal fat on the renal fascia.
[0047] The kidneys are involved in controlling various body fluid compartments, fluid osmotic pressure, acid-base balance, various electrolyte concentrations, and the amount of toxin removal. The kidneys provide filtering functionality by secreting certain substances and reabsorbing other substances. Examples of substances secreted into the urine are hydrogen, ammonium, potassium, and uric acid. In addition, the kidneys also perform various other functions, such as hormone synthesis, etc.
[0048] The concave region on the concave border of the kidney 70 is the renal hilum 78, where the renal artery (not shown) enters the kidney and the renal vein (not shown) and ureter 63 exit. The kidney is surrounded by tough fibrous tissue, and the renal capsule 74 itself is surrounded by perinephric fat, renal fascia, and pararenal fat. The anterior (front) surface of these tissues is the peritoneum, and the posterior (back) surface is the transverse abdominal fascia.
[0049] The functional substance or parenchyma of the kidney is divided into two main structures: the outer renal cortex 77 and the inner renal medulla 87. These structures take the shape of a plurality of cone-shaped renal lobes, each of which contains the renal cortex surrounding a portion of the medulla called the renal pyramid 72. Between the renal pyramids 72 are cortical projections called renal columns 73. Figure 1 The nephron (not shown in detail) spans the cortex and medulla. The initial filtering part of the nephron is the glomerulus, located in the cortex. This is followed by the renal tubules that extend from the cortex deep into the medullary pyramids. The part of the renal cortex, the medullary rays, is a collection of tubules that drain into a single collecting duct.
[0050] The tip or papilla 79 of each pyramid empties urine into the corresponding calyx 75; the calyx 75 empties into the greater calyx 76, and the greater calyx 76 empties into the renal pelvis 71, which transitions to the ureter 63. At the renal hilum 78, the ureter 63 and the renal vein leave the kidney and the renal artery enters. Hilar fat and lymphatic tissue with lymph nodes surround these structures. The hilar fat is adjacent to a fat-filled cavity called the renal sinus. The renal sinus contains the renal pelvis and calyx together and separates these structures from the renal medullary tissue.
[0051] With further reference to the medical system 10, a medical device (e.g., a scope) 32 can be advanced through the urinary tract into the kidney 70. Once at the site of the kidney stone 80 (e.g., within the calyx of the kidney 70 where the stone 80 is accessible), the medical device 32 can be used to designate / identify a target location for percutaneous access to the kidney 70. In order to minimize damage to the kidney and / or surrounding anatomical structures, the physician 5 can designate a specific papilla 79 of the kidney 70 as a target location for accessing the kidney using a percutaneous access device (e.g., a needle; not shown). However, other target locations can be designated or determined. Once the percutaneous access device has reached the target location (e.g., the calyx), the kidney stone 80 can be extracted from the patient 13 using the utilized percutaneous access path.
[0052] exist Figure 1 In the example of , the medical device 32 is implemented as a speculum. However, the medical devices 32 can each be implemented as any suitable type of medical device, such as a catheter, a guidewire, a lithotripter, a basket retrieval device, etc. In some embodiments, the medical device is a steerable device, while other embodiments, the medical device is a non-steerable device. In some embodiments, a surgical tool refers to a device configured to puncture or insert through a human anatomy, such as a needle, a scalpel, a guidewire, etc. However, a surgical tool can refer to other types of medical devices.
[0053] A scope such as scope 32 may be configured to navigate within a human anatomy, such as within a natural orifice or lumen of a human anatomy. Scopes may include, for example, a ureteroscope (e.g., for accessing the urinary tract), a laparoscope, a nephroscope (e.g., for accessing the kidney), a bronchoscope (e.g., for accessing an airway such as a bronchi), a colonoscope (e.g., for accessing the colon), an arthroscopy (e.g., for accessing a joint), a cystoscope (e.g., for accessing the bladder), and the like.
[0054] The robotic system 11 can be configured to at least partially facilitate performing a medical procedure. The robotic system 11 can be configured in a variety of ways, depending on the particular procedure. The robotic system 11 can include one or more robotic arms 12 configured to engage and / or control the endoscope 32 to perform the procedure. As shown, each robotic arm 12 can include a plurality of arm segments coupled to a joint that can provide a plurality of degrees of movement. Figure 1 In the example of , the robotic system 110 is positioned proximate to the patient's leg, and the robotic arm 12 is actuated to engage and position the scope 32 for access to an entry point, such as the urethra 67 of the patient 13. When the robotic system 110 is properly positioned, the scope 120 may be inserted into the patient 13 either robotically using the robotic arm 12, manually by the physician 5, or a combination thereof.
[0055] The robotic system 11 may be coupled to any component of the medical system 100, such as the control system 50, the table 15, the EM field generator (not shown; see Figure 3 ), a speculum 32, and / or a percutaneous access device (eg, a needle; see Figure 3 ) level. In some embodiments, the robotic system 11 is communicatively coupled to the control system 50. For example, the robotic system 11 can be configured to receive control signals from the control system 50 to perform operations, such as positioning the robotic arm 12 in a particular manner, manipulating the endoscope 32, etc. In response, the robotic system 11 can control components of the robotic system 11 to perform operations. In some embodiments, the robotic system 11 is configured to receive images and / or image data representing the internal anatomy of the patient 13 from the endoscope 32, i.e., images of the internal anatomy of the patient 13. Figure 1 , and / or send images / image data to the control system 50 (which may then be displayed on the display 43 or other output device). In addition, in some embodiments, the robotic system 11 is coupled to components of the medical system 10, such as the control system 50, in a manner that allows for receiving fluids, optics, power, etc. therefrom. Figure 2 Additional exemplary details of the robotic system are discussed in greater detail.
[0056] The control system 50 may be configured to provide various functionalities to assist in performing a medical procedure. In some embodiments, the control system 50 may be coupled to the robotic system 11 and operate in conjunction with the robotic system 11 to perform a medical procedure on the patient 13. For example, the control system 50 may communicate with the robotic system 11 via a wireless or wired connection (e.g., to control the robotic system 11 and / or the scope 32, receive images captured by the scope 32, etc.), provide fluids to the robotic system 11 via one or more fluid channels, provide power to the robotic system 11 via one or more electrical connections, and provide optics to the robotic system 11 via one or more optical fibers or other components. In addition, in some embodiments, the control system 50 may communicate with the needle and / or nephroscope to receive position data therefrom. In addition, in some embodiments, the control system 50 may communicate with the table 15 to position the table 15 in a particular orientation or otherwise control the table 15. In addition, in some embodiments, the control system 50 may communicate with an EM field generator (not shown) to control the generation of an EM field in an area surrounding the patient 13.
[0057] The control system 50 may include various I / O devices configured to assist the physician 5 or others in performing a medical procedure. For example, the control system 50 may include specific input / output (I / O) components configured to allow user input to control the scope 32 so as to navigate the scope 32 within the patient 13. In some embodiments, for example, the physician 5 may provide input to the control system and / or the robotic system, wherein, in response, control signals may be sent to the robotic system 11 to manipulate the scope 32. Also as shown in FIG. Figure 1 As shown in , the control system 50 may include a display 42 to provide various information about the procedure. For example, the display 42 may provide information about the scope 32. For example, the control system 50 may receive real-time images captured by the scope 32 and display the real-time images via the display 42. Additionally or alternatively, the control system 140 may receive signals (e.g., analog, digital, electrical, acoustic / sound wave, pneumatic, tactile, hydraulic, etc.) from medical monitors and / or sensors associated with the patient 13, and the display 42 may present information about the health status or environment of the patient 13. Such information may include information displayed via a medical monitor, including, for example, heart rate (e.g., ECG, HRV, etc.), blood pressure / blood rate, muscle biosignals (e.g., EMG), body temperature, blood oxygen saturation (e.g., SpO2), CO2, brain waves (e.g., EEG), environment and / or local or core body temperature, etc.), CO2, brain waves (e.g., EEG), environment and / or local or core body temperature, etc.
[0058] To facilitate the functionality of the control system 50, the control system may include various components (sometimes referred to as "subsystems"). For example, the control system 50 may include a control electronics / circuitry system, as well as one or more power supplies, pneumatic devices, light sources, actuators, data storage devices, and / or communication interfaces. In some embodiments, the control system 50 includes a control circuit system that includes a computer-based control system that is configured to store executable instructions that cause various operations to be performed when executed. In some embodiments, the control system 50 is movable, while in other embodiments, the control system 50 is a substantially stationary system. Although various functionalities and components are discussed as being implemented by the control system 50, any of such functionalities and / or components may be integrated into and / or performed by other systems and / or devices, such as the robotic system 11, the table 15. Reference is made below to Figure 2 Components of an exemplary robotic system are discussed in greater detail.
[0059] The medical system 10 can provide a variety of benefits, such as providing guidance to assist a physician in performing a procedure (e.g., instrument tracking, instrument alignment information, etc.), enabling a physician to perform a procedure from an ergonomic position without the need for awkward arm movements and / or positions, enabling a single physician to perform a procedure with one or more medical instruments, avoiding radiation exposure (e.g., associated with fluoroscopy techniques), enabling a procedure to be performed in a single operating setting, providing continuous suction to more efficiently remove objects (e.g., removing kidney stones), etc. For example, the medical system 10 can provide guidance information to assist a physician in using various medical instruments to access a target anatomical feature while minimizing bleeding and / or damage to anatomical structures (e.g., critical organs, blood vessels, etc.). In addition, the medical system 10 can provide non-radiation-based navigation and / or positioning technology to reduce the exposure of the physician and patient to radiation and / or reduce the number of devices in the operating room. In addition, the medical system 10 can provide functionality distributed between at least the control system 50 and the robotic system 11, which functionality can be capable of independent movement. This distribution of functionality and / or mobility can enable the control system 50 and / or robotic system 11 to be placed in a position that is optimal for a particular medical procedure, which can maximize the working area around the patient and / or provide an optimized position for the physician to perform the procedure.
[0060] The various components of system 10 may be communicatively coupled to each other over a network, which may include a wireless network and / or a wired network. Exemplary networks include one or more personal area networks (PANs), local area networks (LANs), wide area networks (WANs), Internet area networks (IANs), cellular networks, the Internet, etc. In addition, in some embodiments, the various components of system 10 may be connected via one or more supporting cables, tubes, etc. for data communication, fluid / gas exchange, power exchange, etc.
[0061] Figure 2 Provided in Figure 1 Detailed illustration of an embodiment of a robotic system 11 (e.g., a cart-based robotic enabling system) and a control system 50 is shown in FIG. The robotic system 11 generally includes an elongated support structure 14 (also referred to as a "column"), a robotic system base 25, and a console 16 at the top of the column 14. The column 14 may include a support structure for supporting one or more robotic arms 12 (in Figure 2 The elbow support 17 may include one or more elbow supports 17 (also referred to as "brackets") that are deployed in a manner similar to that of the patient's arm 12 (three are shown in FIG. 1 ). The elbow support 17 may include an individually configurable arm support that rotates along a vertical axis to adjust the base of the robotic arm 12 for better positioning relative to the patient. The elbow support 17 also includes a column interface 19 that allows the elbow support 17 to translate vertically along the column 14.
[0062] The column interface 19 is connected to the column 14 by a slot, such as slot 20, which is positioned on opposite sides of the column 14 to guide the vertical translation of the elbow support 17. The slot 20 contains a vertical translation interface to position and maintain the elbow support 17 at various vertical heights relative to the robotic system base 25. The vertical translation of the elbow support 17 allows the robotic system 11 to adjust the range of the robotic arm 12 to meet a variety of table heights, patient sizes, and physician preferences. Similarly, the individually configurable arm mounts on the elbow support 17 allow the robotic arm base 21 of the robotic arm 12 to be angled in a variety of configurations.
[0063] The robot arm 12 may generally include a robot arm base 21 and an end effector 22 separated by a series of links 23, the series of links being connected by a series of joints 24, each joint including one or more independent actuators. Each actuator may include an independently controllable motor. Each independently controllable joint 24 may provide or represent an independent degree of freedom available to the robot arm. In some embodiments, each arm in the arm 12 has seven joints and thus provides seven degrees of freedom, including "redundant" degrees of freedom. The redundant degrees of freedom allow the robot arm 12 to position its corresponding end effector 22 at a specific position, orientation, and trajectory in space using different link positions and joint angles. This allows the system to position and guide the medical device from a desired point in space while allowing the physician to move the arm joint to a clinically advantageous position away from the patient to create greater access while avoiding arm collisions.
[0064] The robot system base 25 balances the weight of the column 14, the elbow support 17, and the arm 12 on the floor. Thus, the robot system base 25 can accommodate heavier components, such as electronics, motors, power supplies, and components that selectively enable the robot system to be moved and / or fixed. For example, the robot system base 25 includes wheel-shaped casters 28 that allow the robot system to be easily moved around the room before surgery. After reaching the appropriate position, the casters 28 can be secured using wheel locks to keep the robot system 11 in place during surgery.
[0065] The console 16 positioned at the upper end of the column 14 allows both a user interface for receiving user input and a display screen (or dual-purpose device, such as a touch screen 26) for providing preoperative and intraoperative data to the physician user. Potential preoperative data on the touch screen 26 may include preoperative planning, navigation and mapping data derived from a preoperative computerized tomography (CT) scan and / or a record from a preoperative patient interview. The intraoperative data on the display may include optical information provided from tools, sensors and coordinate information from sensors and important patient statistics, such as respiration, heart rate and / or pulse. The console 16 can be positioned and tilted to allow the physician to approach the console from the side of the column 14 opposite the elbow support 17. From this position, the physician can view the console 16, the robotic arm 12 and the patient while operating the console 16 from behind the robotic system 11. As shown, the console 16 may also include a handle 27 to assist in manipulating and stabilizing the robotic system 11.
[0066] The end effector 22 of each of the robotic arms 12 may include an instrument device manipulator (IDM) that may be attached using a mechanism converter interface (MCI). In some embodiments, the IDM may be removed and replaced with a different type of IDM, for example, a first type of IDM may manipulate an endoscope, while a second type of IDM may manipulate a laparoscope. The MCI may include a connector for transmitting pneumatic pressure, power, electrical signals, and / or optical signals from the robotic arm 12 to the IDM. The IDM may be configured to manipulate a medical device (e.g., surgical tool / instrument) such as a scope 32 using technologies including, for example, direct drive, harmonic drive, gear drive, belt and pulley, magnetic drive, etc.
[0067] exist Figure 2 The control system 50 shown in FIG. 1 may be used as a command console for the exemplary surgical robotic system 11 . The control system 50 may include a console base 51 and one or more display devices 42 .
[0068] The system 10 may include specific control circuitry 60 that is configured to perform specific functionality described herein. The control circuitry 60 may be part of the robotic system, the control system 50, or both. That is, references herein to control circuitry may refer to a control circuitry embodied in a robotic system, a control system, or a control system such as in a Figure 1The term "control circuit system" is used herein in accordance with its broad and ordinary meaning, and may refer to any collection of the following: a processor, a processing circuit system, a processing module / unit, a chip, a die (e.g., a semiconductor die including one or more active and / or passive devices and / or connectivity circuit systems), a microprocessor, a microcontroller, a digital signal processor, a microcomputer, a central processing unit, a field programmable gate array, a programmable logic device, a state machine (e.g., a hardware state machine), a logic circuit system, an analog circuit system, a digital circuit system, and / or any device that manipulates signals based on hard coding of circuit systems and / or operating instructions. The control circuit system mentioned herein may also include one or more circuit substrates (e.g., printed circuit boards), conductive traces and through holes and / or mounting pads, connectors and / or components. The control circuit system mentioned herein may also include one or more storage devices, which may be embodied in a single memory device, multiple memory devices, and / or an embedded circuit system of a device. Such data storage devices may include read-only memory, random access memory, volatile memory, non-volatile memory, static memory, dynamic memory, flash memory, cache, data storage registers, and / or any device that stores digital information. It should be noted that in embodiments where the control circuit system includes a hardware and / or software state machine, analog circuit system, digital circuit system, and / or logic circuit system, the data storage device / register storing any associated operating instructions may be embedded within the circuit system including the state machine, the analog circuit system, the digital circuit system, and / or the logic circuit system or external to the circuit system.
[0069] Further references Figure 2 , control circuit system 60 may include a computer-readable medium storing hard-coded and / or operational instructions corresponding to at least some of the steps and / or functions depicted in one or more of the figures in the present figures and / or described herein. In some cases, such computer-readable medium may be included in an article of manufacture. Control circuit system 60 may be entirely maintained / located locally or may be at least partially remotely located (e.g., indirectly communicatively coupled via a local area network and / or a wide area network).
[0070] In some embodiments, at least a portion of the control circuit system 60 is integrated with the robotic system 11 (e.g., integrated in the base 25, column 14, and / or console 14) or integrated with another system communicatively coupled to the robotic system 11. In some embodiments, at least a portion of the control circuit system 60 is integrated with the control system 50 (e.g., integrated in the console base 51 and / or display unit 42). Thus, any description of a functional control circuit system herein may be understood to be embodied in the robotic system 11, the control system 50, or both, and / or at least partially embodied in one or more other local or remote systems / devices.
[0071] System 10 also includes specific user controls 65, which may include any type of user input (and / or output) device or device interface, such as one or more buttons, keys, joysticks, handheld controllers (e.g., video game type controllers), computer mice, trackpads, trackballs, control pads, and / or sensors that capture hand gestures and finger postures (e.g., motion sensors or cameras), and / or interfaces / connectors therefor. User controls 65 are communicatively and / or physically coupled to at least some of the control circuit systems in control circuit system 60.
[0072] In some embodiments, the user control 65 and / or the control circuit system 60 are configured to receive user input to allow the user to control a medical device, such as an endoscope or a nephroscope, such as an instrument that can be at least partially manipulated by the robotic system in a speed mode or a position control mode. In the speed mode, the user may be permitted to directly control the pitch and yaw motion of the distal end of (for example) an endoscope or other instrument based on direct manual control using the control 65. For example, the movement on the joystick may be mapped to the yaw and pitch motion in the distal end of the scope / device. In some embodiments, the user control 65 is configured to provide tactile feedback to the user. For example, a joystick or other control mechanism may vibrate to indicate an invalid or potentially problematic input. In some embodiments, the control system 50 and / or the robotic system 11 may also provide visual feedback (e.g., a pop-up message) and / or audio feedback (e.g., a beep) to indicate problems associated with the operation of the robot.
[0073] In the position control mode, the control circuit system 60 may control a medical instrument (e.g., an endoscope) using a three-dimensional (3D) map of the patient and a predetermined computer model of the patient. For example, the control circuit system 60 may be configured to provide control signals to the robotic arm 12 of the robotic system 11 to manipulate the associated instrument to position the associated instrument at a target position, location, and / or orientation / alignment. For embodiments implementing 3D mapping, the position control mode may require a sufficiently accurate mapping of the patient's anatomy.
[0074] In some embodiments, the user may manually manipulate the robotic arm 12 of the robotic system 11 without using the command controls 65. For example, during a setup in a surgical operating room, the user may move the robotic arm 12 and / or any other medical instrument to provide desired access to a patient. The robotic system 11 may rely on force feedback and inertial control from the user to determine the appropriate configuration of the robotic arm 12 and associated instruments.
[0075] The display device 42 of the control system 50 can be integrated with the user control 65, for example, as a tablet computer device with a touch screen for user input. The display device 42 can be configured to provide data and input commands to the robot system 11 using an integrated display touch control. The display device 42 can be configured to display a graphical user interface that shows information about the position and orientation of various instruments operating in the patient and / or system based on information provided by one or more position sensors. In some embodiments, a position sensor associated with a medical device (e.g., an endoscope) can be configured to generate a signal indicating the position and transmit the signal on a wire and / or a transmitter coupled to the sensor. Such connectivity components can be configured to transmit position information to the console base 51 so that the position information is processed by the control circuit system 60 and presented via the display device.
[0076] Figure 3 A ureteroscope 340 is depicted disposed in a portion of a patient's urinary system in accordance with one or more embodiments of the present disclosure. As mentioned above, ureteroscopic procedures may be performed to investigate abnormalities of a human ureter and / or to treat the abnormalities. For example, ureteroscopic procedures may be performed to treat and / or remove kidney stones. Such procedures may be performed at least partially manually and / or at least partially using robotic technology, such as in Figure 1 and Figure 2 1. The use of robotic devices and / or systems for certain endoscopic procedures may provide relatively high precision, control, and / or coordination, for example, compared to fully manual procedures. In some embodiments, the endoscope 340 includes a working channel 344 for deploying medical instruments (e.g., lithotripters, basketing devices, forceps, etc.), flushing, and / or suction to an operating area at the distal end of the endoscope.
[0077] The scope 340 may be articulatable, such as with respect to at least a distal portion of the scope, such that the scope may be steered within the human anatomy. In some embodiments, the scope 340 is configured to articulate using, for example, five degrees of freedom, including XYZ coordinate movement, as well as pitch and yaw. In some embodiments, the needle sensor provides six degrees of freedom, including X, Y, and Z coordinate position, as well as pitch, roll, and yaw. The position sensor of the scope 340 may also have similar degrees of freedom with respect to the position information generated / provided by the position sensor. The figure illustrates multiple degrees of motion of the scope 340 according to some embodiments. As shown in FIG. Figure 3 As shown in , the tip 342 of the scope 340 can be oriented with zero deflection relative to its longitudinal axis 306 (also referred to as the "roll axis").
[0078] To capture images at different orientations of the tip 342, the robotic system can be configured to deflect the tip 342 on a positive yaw axis 302, a negative yaw axis 303, a positive pitch axis 304, a negative pitch axis 305, or a roll axis 306. The tip 342 or body 345 of the endoscope 342 can be extended or translated in a longitudinal axis 306, an x-axis 308, or a y-axis 309. The endoscope 340 may include a reference structure (not shown) to calibrate the position of the endoscope. For example, the robotic system can measure the deflection of the endoscope 340 relative to the reference structure. The reference structure can be located, for example, on the proximal end of the endoscope 340 and can include a key, a slot, or a flange. The reference structure can be coupled to a first drive mechanism for initial calibration and to a second drive mechanism to perform a surgical procedure.
[0079] For robotic implementations, the robotic arm of the robotic system may be configured / capable of manipulating the endoscope 340 using an elongated moving member. The elongated moving member may include one or more pull wires (e.g., pull wires or push wires), cables, fibers, or flexible shafts. For example, the robotic arm may be configured to actuate multiple pull wires coupled to the endoscope 340 to deflect the tip 342 of the endoscope 118. The pull wires may include any suitable or desirable material, such as metallic and non-metallic materials, such as stainless steel, Kevlar, tungsten, carbon fiber, etc. In some embodiments, the endoscope 340 is configured to exhibit nonlinear behavior in response to the force applied by the elongated moving member. The nonlinear behavior may be based on the stiffness and compressibility of the endoscope, as well as the variability in slack or stiffness between different elongated moving members.
[0080] The scope (e.g., endoscope / ureteroscope) 340 may include a tubular and flexible medical device configured to be inserted into a patient's anatomy to capture images of the anatomy. In some embodiments, the scope 340 may house wires and / or optical fibers to transmit signals to / from the optical assembly and the distal end 342 of the scope 340, which may include an imaging device 348, such as an optical camera.
[0081] The camera / imaging device 348 can be used to capture images of an internal anatomical space, such as a target calyx / mastoid of the kidney 70. The scope 340 can also be configured to receive an optical fiber to carry light from a proximally located light source (such as a light emitting diode) to the distal end 342 of the scope. The distal end 342 of the scope 340 can include a port for the light source to illuminate the anatomical space when the camera / imaging device is used. In some embodiments, the scope 340 is configured to be controlled by a robotic system that is similar in one or more aspects to the robotic system used in the present invention. Figure 1 and Figure 2 The robotic system 11 shown in FIG. The imaging device may include an optical fiber, an optical fiber array, and / or a lens. The optical component moves with the top of the endoscope 340, so that the movement of the top of the endoscope causes a change in the image captured by the imaging device 348.
[0082] For percutaneous nephrolithotomy (PCNL) procedures, the target calyx is accessed through the patient's skin and intervening tissue. Generally speaking, the preferred access to the calyx of the kidney is through the soft tissue papillary structure, where access through such tissue can generally be associated with a reduced risk of bleeding and / or other complications. In addition to being free of bleeding, such a path can provide complete access to the interconnected internal passages of the kidney (e.g., calyx) in addition to being free of bleeding, where the needle is inserted through the papillary structure.
[0083] Although PCNL represents a relatively effective method for treating larger kidney stones, many physicians choose other procedures in part due to the difficulty in accurately aiming at the target mastoid / calyx. More specifically, performing PCNL involves obtaining percutaneous access to the target calyx of the kidney using a needle through the patient's flank. This step can be considered extremely important for the ultimate success of the operation because the physician must select a needle path to the kidney that does not traverse surrounding organs and also allows rigid instruments to reach and treat urinary stones. If the physician is unable to proceed effectively, they will risk causing visceral or pleural damage or failing to fully treat the stone. Due to these challenges, the learning curve associated with obtaining percutaneous needle access to perform PCNL at a suitable patient position (e.g., a modified supine position) is very high.
[0084] In some procedures, the physician studies the patient's preoperative computed tomography (CT) images to determine the location of the urinary stone, the location of the surrounding organs and bony structures, and to examine the morphology of the calyx. Using this knowledge, the physician can mentally generate a preoperative plan for the percutaneous needle path. Typically, the physician must identify the posterior calyx for puncture to accommodate rigid instruments. Specifically, the posterior calyx generally provides a relatively straight path into the renal pelvis. The physician must attempt to insert the needle into the kidney through the mastoid to avoid damaging the renal vasculature and causing bleeding. During the operation, the physician relies on fluoroscopy or ultrasound in some procedures to guide the alignment and insertion of the needle with the target calyx. However, the resolution and interpretation difficulties associated with such imaging techniques can make it relatively difficult to satisfactorily perform needle punctures. Therefore, embodiments of the present disclosure that provide improved tracking and visualization of target anatomical features such as the mastoid and calyx can improve the results of the operation and are attractive to more physicians than other PCNL methods.
[0085] In some embodiments, the medical device (e.g., a scope) 340 includes a sensor configured to generate sensor position data and / or transmit the sensor position data to another device. The sensor position data may indicate the position and / or orientation of the medical device 340 (e.g., its distal end 342), and / or may be used to determine / infer the position / orientation of the medical device. For example, the sensor (sometimes referred to as a "position sensor") may include an electromagnetic (EM) sensor having a coil of conductive material or other forms / embodiments of an antenna.
[0086] Figure 3 An EM field generator 315 is shown, which is configured to broadcast an EM field 90, which is detected by an EM sensor on the medical device. The magnetic field 90 can induce a small current in the coil of the EM position sensor, which can be analyzed to determine the distance and / or angle / orientation between the EM sensor and the EM field generator 315. In addition, the medical device / scope 340 may include other types of sensors, such as shape sensing fibers, accelerometers, gyroscopes, satellite-based positioning sensors (e.g., global positioning system (GPS) sensors), radio frequency transceivers, etc. In some embodiments, the sensors on the medical device can provide sensor data to the control system, which is then used to determine the position and / or orientation of the medical device. In some embodiments, the position sensor is positioned on the distal end 342 of the medical device 340, while in other embodiments, the sensor is positioned at another location on the medical device. The ureteroscope can be driven to a position close to the target mastoid.
[0087] In some embodiments, as described in more detail below, the distal end of the ureteroscope 340 can be advanced to contact a target anatomical feature (e.g., a mastoid). With a position sensor associated with the distal end of the scope 340 in contact with and / or in proximity to the target anatomical feature, the position of the distal end of the scope 340 can be recorded as a target percutaneous access location where a percutaneous access instrument (e.g., a needle) can be guided through the mastoid into the target calyx.
[0088] Certain embodiments of the present disclosure advantageously help automate and guide the physician through the process for obtaining percutaneous access to target anatomical features. For example, electromagnetic localization and endoscope images can be used together to guide the insertion of a needle into a patient. This solution can allow non-expert physicians to obtain access to the kidney and be able to perform PCNL in, for example, a modified supine position.
[0089] Certain embodiments of the present disclosure relate to position sensor-guided percutaneous access to a target treatment site, such as a target location in the kidney. For example, where the scope 340 is equipped with one or more electromagnetic sensors and the nephroscopic access needle also includes one or more electromagnetic sensors and such sensors are subjected to the electromagnetic field 90 generated by the field generator 315, the associated system control circuit system can be configured to detect and track their positions. In some embodiments, the top of the ureteroscope 340 acts as a guiding beacon when the user inserts the percutaneous access needle. This solution can allow the user to hit the target from multiple approaches, thereby avoiding the need to rely on fluoroscopy or ultrasound imaging modalities.
[0090] In some embodiments, a control system associated with the scope 340 (in Figure 3340 and / or a percutaneous access needle (not shown). In some examples, the EM field generator 315 is configured to provide an EM field 90 within the patient's environment, as described above. The scope 340 and / or the percutaneous access needle may include an EM sensor configured to detect EM signals and send sensor data about the detected EM signals to a control system. The control system may analyze the sensor data to determine the position and / or orientation of the scope 340 (e.g., the distance and / or angle / orientation between the EM sensor and the EM field generator 315). Alternatively or additionally, in some examples, the control system may use other techniques to determine the position and / or orientation of the scope 340. For example, the scope 340 (and / or the needle) may include a shape sensing fiber, an accelerometer, a gyroscope, an accelerometer, a satellite-based positioning sensor (e.g., a global positioning system (GPS)), a radio frequency transceiver, etc. The control system can receive sensor data from the scope 340 and determine its position and / or orientation. In some embodiments, the control system can track the position and / or orientation of the scope 340 in real time relative to the patient's coordinate system and / or anatomy.
[0091] The scope 340 can be controllable in any suitable or desirable manner based on user input or automatically. Controls 311, 312 provide examples that can be used to receive user input. In some embodiments, the controls of the scope 340 are located on a proximal handle of the scope, which can be relatively difficult to grasp in some surgical postures / positions when the orientation of the ureteroscope changes. In some embodiments, as in image 312, a two-handed controller is used to control the scope 340. Although controllers 311, 312 are shown as handheld controllers, any type of I / O device can be used to receive user input, such as a touch screen / pad, a mouse, a keyboard, a microphone, etc.
[0092] FIG. 4 (shown in sections 4-1 and 4-2) is a flow chart illustrating a process 400 for accessing a target calyx or other organ of a patient according to one or more embodiments of the present disclosure. FIG. 5 (shown in sections 5-1 and 5-2) shows specific images corresponding to various blocks, states, and / or operations associated with the process of FIG. 4 according to one or more embodiments. Process 400 may involve percutaneous access to a kidney 70 to remove a kidney stone (e.g., PCNL). Such percutaneous access may be desirable for extracting sufficiently large stones that are impractical or undesirable to remove via a ureteroscope. For example, a stone may be greater than 2 cm in diameter, and some ureteroscopes have a working channel of approximately 1.2 mm in diameter through which stones or fragments may be removed. Although in many cases it is effective to break stones into smaller fragments for removal via ureteroscopy, studies have shown that residual stone fragments are often a source of new stone formation, requiring similar treatment in the future.
[0093] At block 402, process 400 involves accessing the kidney through the patient's ureter using ureteroscope 440, as described above. Specifically, operations at block 402 may involve advancing scope 440 through ureter 63, past renal pelvis 71, and into an area at or near one or more calyces.
[0094] At block 404, process 400 involves locating a kidney stone 480 of a patient to be treated using an image capture device (eg, a camera) associated with distal end 442 of an endoscope. For example, kidney stone 480 may be at least partially extracted as a purpose of process 400.
[0095] At box 406, process 400 involves identifying a target papilla 479 exposed within a target calyx 475 through which access to a kidney stone 480 can be achieved. Identifying the target papilla 479 can be important for creating a feasible path through which the kidney stone 480 can be accessed via percutaneous access. For example, it may be necessary to determine an angle suitable for entry through a relatively rigid nephroscope in order to access a calyx (e.g., a calyx 475) through which the kidney stone 480 can be reached. In some specific implementations, it may be desirable or necessary to reach the kidney stone 480 through the posterior calyx in order to provide a sufficiently straight passage to the ureteropelvic junction 71. Generally speaking, the target renal calyx can be considered a relatively small target. For example, the diameter of such a calyx can be approximately 4 mm-8 mm. Therefore, accurate aiming may be critical in order to effectively extract the kidney stone.
[0096] The path through which the needle / nephroscope is accessed to the target calyx 475 may advantageously be as straight as possible so as to avoid encountering the vessels around the renal pyramid 476 associated with the mastoid 479 through which the needle / nephroscope may be positioned. In addition, the location of various critical anatomical structures of the patient may require navigation through a constrained window of the patient's tissue / anatomical structure. For example, the inferior pole calyx below the 12th rib may provide suitable access that avoids the pulmonary pleura. In addition, the access path may advantageously be medial to the posterior axillary line (e.g., approximately 1 cm below the top of the 12th rib and 1 cm medial to the top) to avoid the colon and / or paraspinal muscles. In addition, the access path may advantageously avoid close proximity to the ribs to avoid the intercostal nerves. In addition, by aiming for an entry in the region of the axial center of the calyx 475, the aorta and / or other blood vessels may be avoided in some cases.
[0097] At block 408, process 400 involves identifying / recording the location of the exposed mastoid 479 within the target calyx 479 through which the desired access will be achieved. For example, the location information / data may be represented / identified in a three-dimensional space, such as an electromagnetic field space.
[0098] In order to record the position of the mastoid 179, the scope 440 can be moved forward to physically touch / contact the target mastoid 479, as shown by the forwardly moved scope tip 443, and the scope 440 and / or the operator can identify and / or otherwise indicate such contact position as the target position in conjunction with this. In some specific implementations, an electromagnetic beacon or other sensor device associated with the distal end / tip 442 of the ureteroscope can indicate the target position, thereby recording the target position in the electromagnetic field space. After contacting / touching the mastoid 479 and recording the position, the end 442 of the scope can be retracted, and the depth of such retraction can be measured in some manner. In some specific implementations, the operator can be informed that the distal end 443 of the scope 440 has contacted the mastoid 479 by monitoring the camera image generated thereby, which would normally be blocked / blackened when contact is made.
[0099] At block 410, process 400 involves percutaneously introducing a medical device 450, such as a needle, into a patient's body. For example, in some implementations, such entry may be performed via the patient's flank. At block 412, process 400 involves directing the percutaneously advanced medical device 450 toward a target location to ultimately traverse the target mastoid 479 and pass therethrough into the target calyx 475.
[0100] In some embodiments, visual confirmation of the tip of the needle 450 entering the target calyx 475 can be provided by a camera of the scope 440. For example, as described above, the scope 440 can be retracted from the target location, thereby providing a field of view that includes the mastoid 479 within the calyx 475, so that the tip of the needle 450 can be seen as it protrudes through the surface of the mastoid 479.
[0101] With the target position recorded, a percutaneously inserted medical device (e.g., needle 450) can be guided toward the recorded position. However, where such recorded positions are static, anatomical movement that occurs after the target position is recorded may cause the target position to not accurately reflect the real-time position associated with the target anatomical feature through which entry is desired. For example, the action of inserting needle 450 into the patient's body may cause certain anatomical structures surrounding the target organ (e.g., kidney 70) and / or the target organ itself to migrate and / or deform / deform in some manner, causing the target anatomical feature (e.g., mastoid 479) to assume a position / shape different from when the target entry position was recorded. With respect to renal surgery, the ureteroscope 440 may be fixed to the position of the renal pelvis 71 such that deformation and / or movement of the kidney 70 relative to the ureteroscope may cause such target position to be destroyed. Therefore, once anatomical movement is introduced into the system, the mastoid 479 may be tracked inaccurately.
[0102] Once the needle has entered the calyx 475, the needle 450 can be replaced with a larger diameter device to provide a larger port for removing the stone. In some specific implementations, the needle 450 includes a stylet and a cannula. When the needle tip is advanced into the calyx 475, the stylet can be removed, leaving the cannula to form an open port to the location of the kidney stone. Through the cannula, a guide wire can be placed and used to perform the remainder of the process of removing the stone 480. For example, a balloon or dilator can be passed along the guide wire using the guide wire. The balloon or dilator can be inflated to create a port large enough to introduce a hollow suction tube (such as a renal pelvic drainage tube) directly into the calyx 475. At this point, any one of a nephroscope or many other instruments can be introduced into the suction tube to assist in removing the stone 480. For example, a lithotripter, laser, ultrasound, basket, gripper, drainage tube, etc. can be used to remove the stone or its fragments, and / or a drainage tube such as a nephrostomy catheter can be deployed along the suction tube to reduce intrarenal pressure. Any combination of such functionality may be embodied in a nephroscope (not shown) and / or a ureteroscope 440 .
[0103] Image processing enhanced instrument guidance and automation
[0104] The processes described herein, while described in the context of a ureteroscope, may be applicable to any other type of surgical procedure utilizing a position sensor (e.g., an electromagnetic field sensor) and / or a camera to track a target anatomical feature such as a mastoid or urinary calculi. As described, static position markers may be registered / recorded to identify a target position associated with a target anatomical feature / landmark. In some embodiments, the present disclosure provides systems, devices, and methods for guiding and / or automating an endoscope and / or percutaneous access instrument based at least in part on static position markers in view of specific target recognition and / or target tracking image processing techniques. Target recognition and tracking according to embodiments of the present disclosure may be applicable to any type of robotic endoscopic surgery.
[0105] In some embodiments, specific image data may be collected and used to identify target anatomical features. Such identification may be achieved, at least in part, using a machine learning framework. For example, the systems, devices, and methods of the present disclosure may provide for identification of target anatomical features in real-time endoscopic images, wherein identification of target anatomical features in the image may facilitate specific response actions. For example, a control circuit system communicatively coupled to a robotic endoscope and / or a percutaneous access device may be configured to track the movement of the target feature and take action, such as articulating one or more portions of the endoscope (e.g., a distal end portion) or adjusting target position data. For example, the control circuit system may be configured to articulate the endoscope so as to center the target position / point at or near the center of the field of view of the interface and / or image field of the endoscopic camera.
[0106] By utilizing robotic-assisted percutaneous access, a physician may be able to perform operational target access and treatment. In addition, according to aspects of the present disclosure described in more detail below, percutaneous access may be further assisted by automatic target recognition and tracking, which may be relied upon to accurately maintain the target position for percutaneous access guidance. Scope-enabled target tracking-guided skin access according to aspects of the present disclosure may be relatively non-skill intensive. In some implementations, a single operator or a robotic system may perform the procedure. In addition, the need for fluoroscopy may be avoided.
[0107] Automatic object detection
[0108] Figure 66 is a flow chart illustrating a process 600 for targeting an anatomical feature according to one or more embodiments. Similar to certain other processes disclosed herein, process 600 involves advancing a medical device, such as a scope (e.g., a ureteroscope), to a treatment site, such as a lumen or chamber at least partially disposed within a target organ, at box 610. For example, the operation of box 610 may involve advancing a medical device to a target calyx of a patient's kidney. The relative position between the medical device and the target may change slightly due to anatomical movement and / or as a percutaneous needle device approaches the target according to certain processes disclosed herein. This relative change in position may result in a need or necessity for tracking the position of the target organ. For example, the position may be tracked in two-dimensional space, and the position may be restored in three-dimensional space, as described in more detail below.
[0109] As mentioned above, robotic endoscopically guided percutaneous access according to aspects of the present disclosure can utilize position tracking techniques relative to a target anatomical feature through which access to a treatment site is achieved. For example, a position tracking mechanism / sensor associated with a distal end of a medical device (e.g., a scope) and / or a percutaneous access instrument (e.g., a needle) can be implemented to guide a physician / technician in aligning the percutaneous access instrument with a treatment site (e.g., a target calyx). Accurate, real-time target tracking as enabled by aspects of the present disclosure can enable relatively precise single-stick access to a treatment site.
[0110] At block 620, process 600 involves identifying the location of the target anatomical structure, which is best understood when the image processing method is able to provide the 3D location of the target, and this manual identification process is not required. For example, identifying the location of the target anatomical location may involve determining and / or recording (e.g., capturing in a volatile and / or non-volatile data storage device of a particular control circuit system as shown and described herein). The location of the target anatomical feature may be identified in conjunction with block 620 in any suitable or desirable manner, such as using an at least partially manual identification subprocess 622 or an at least partially image-based identification subprocess 621, which are described below in conjunction with blocks 624 and 623, respectively.
[0111] With respect to a specific manual identification process, at block 622, process 600 involves contacting a target anatomical feature in a treatment site using a distal end of a medical device. For example, the medical device may include a sensor device, such as an electromagnetic sensor / beacon, which may indicate the position of the distal end of the medical device, and thus, in the event that the distal end of the medical device is positioned against and / or adjacent to the target anatomical feature, such position readings may be relied upon to indicate the position of the target anatomical feature. As an example, a user may provide input to notify an associated computing / medical system of the feature contact location of the target anatomical feature by identifying / registering an exposed face of the target anatomical feature (e.g., a mastoid face exposed within a target calyx) in some manner. Such identification may be implemented by providing user input in some manner, or may be substantially automatic based on perceived tissue contact, etc.
[0112] With respect to a particular image-based identification process, at block 623, process 600 involves using image data input and particular neural network functionality to determine the location of a target anatomical feature, as described below with respect to Figure 7 and Figure 8 Detailed Description: In some implementations, a convolutional neural network is used for object location recognition / identification.
[0113] The characteristic contact positions recorded in conjunction with the operations of block 620 may be viewed as static positions relative to a potential dynamic relative position of the target anatomical feature, which may change over time. The characteristic contact positions may be recorded and / or maintained in any suitable or desirable manner, such as by storage in one or more data storage devices.
[0114] Process 600 proceeds to subprocess 630, which may involve tracking the target anatomical feature while advancing a percutaneous access instrument, such as a needle, in the direction of the target anatomical feature during a surgical session. Real-time tracking of the dynamic relative position of the target anatomical feature may advantageously facilitate accurate guidance of the percutaneous access instrument to the treatment site.
[0115] Subprocess 630 may be implemented in various ways. For example, as shown in subprocess 632, live instrument (e.g., endoscope) tracking may be implemented to provide surgical tracking of the target anatomical feature. For example, throughout the relevant surgical period, the distal end of the medical instrument may be maintained in contact with the target anatomical feature (box 634) so that the position sensor data indicated by the medical instrument can provide a real-time accurate position of the target anatomical feature. Therefore, as shown at box 636, the live position of the medical instrument may be aimed to provide a desired percutaneous access path. However, in the case where the distal end of the medical instrument is in close proximity / contact with the target anatomical feature, real-time visualization of the target anatomical feature may not be possible or sufficiently clear due to the feature itself blocking the target anatomical feature in the camera's field of view. That is, the camera associated with the local instrument may be fully blocked or obscured by most of the target anatomical feature, thereby preventing the physician / user from visually confirming that the percutaneous access instrument (e.g., needle) has penetrated the target anatomical feature.
[0116] An alternative sub-process 631 is shown for tracking a target anatomical feature while still maintaining clear vision of the target anatomical feature during percutaneous access instrument approach. This sub-process 631 may utilize a statically identified location of the target anatomical feature, such as in conjunction with the operations of block 620. For example, at block 633, the sub-process 631 may involve recording a feature contact location associated with contact with the target anatomical feature performed in conjunction with the operations of block 620 described above.
[0117] Rather than continuing to maintain the medical instrument in contact / proximity with the target anatomical feature to provide surgical tracking, subprocess 631, like subprocess 632, may involve retracting the medical instrument a distance (e.g., in a proximal direction) from the target anatomical feature, thereby allowing the medical instrument to clearly capture the target anatomical feature in the field of view of a camera associated therewith as indicated at block 635. For example, in some implementations, the physician / user may inform the system in some manner when the medical instrument has been parked at a desired distance away from the target anatomical feature.
[0118] By way of clarification, it should be noted that subprocesses 631, 632 represent alternative implementations of subprocess 630. That is, process 600 may generally relate to a specific implementation of either subprocess 632 or subprocess 631 but not both. For example, subprocess 632 generally illustrates a solution that involves leaving a position tracking device (e.g., an electromagnetic beacon) associated with a wire or a scope at the location / surface of a target anatomical feature (e.g., a mastoid), wherein the position tracking device may be caused / permitted to move with the mastoid during needle insertion. Thus, the target position may be continuously updated as the sensor moves with the target anatomical feature. Subprocess 632 may generally not require / need any real-time image data. However, due to occlusion, the solution of subprocess 632 may not provide immediate visual confirmation of needle puncture of the target mastoid.
[0119] In some cases, it may be assumed that the scope remains within the target calyx and that the mastoid-scope registration is preserved. In the absence of relative movement of the target anatomical feature relative to the scope position sensor, the target position may be continuously updated based on the determined current scope position. For example, the operation associated with box 634 may involve discontinuously maintaining contact between the instrument / sensor and the target anatomical feature, and the scope may be retracted away from the target to allow the camera to view the target. Position data (e.g., EM data) collected during retraction of the scope may be used to align / record the mastoid position relative to the scope. For example, according to one use case, the retraction / positioning of the scope may be approximately 5 mm in front of the mastoid and 2 mm to the left. Such a position offset may be used to determine the position of the target relative to the current position of the scope. However, relative movement between the target anatomical feature and the scope may result in unreliability in the position offset calculation, and therefore, such a process may be insufficient and fail to compensate for relative movement.
[0120] In certain aspects, subprocess 631 may represent an improvement over subprocess 632. For example, reliance on static position data and / or endoscope offset data may generally not, by itself, provide a robust solution to compensate for anatomical shifts relative to the target anatomical feature and / or other motion, which may be due to, for example, insertion of a percutaneous access instrument and / or other factors. In addition to anatomical movement, changes in the physical positioning of the robotic mechanism and / or other components associated with driving / positioning the medical device at the treatment site may also introduce inaccuracies with respect to the relative positioning of the target anatomical feature and the distal end of the medical device. In the event of undesired movement of the target anatomical feature, its static recorded position may not be reliably relied upon to provide the actual tracked position of the target anatomical feature. Therefore, the static target position recorded at box 620 may need to be updated to accommodate anatomical movement and / or other introduced inaccuracies as described above.
[0121] In the case where the medical device is no longer in contact / close to the target anatomical feature, the real-time position of the distal end of the medical device may not itself indicate the real-time position of the target anatomical feature. Instead, subprocess 631 may implement various solutions for tracking the position of the target anatomical feature based on the static position recorded / identified in conjunction with the operation of box 633. For example, at box 637, subprocess 631 may involve tracking the position of the target anatomical feature by processing a real-time image of the target anatomical feature using a neural network circuit system and / or other image tracking functionality implemented by a specific system control circuit system according to an embodiment of the present disclosure. For example, the neural network and / or other image tracking mechanism may receive a real-time image of the target anatomical feature as input, wherein the neural network circuit system and / or other image tracking mechanism is configured to identify and determine the position of the target anatomical feature therein. Such feature recognition functionality can be used to track the target anatomical feature in real time relative to the static position recorded in conjunction with box 633.
[0122] Subprocess 631 may or may not include a contact 624 step and a retract 635 step, in which the user physically contacts the target mastoid location and retracts the scope to show the mastoid in the scope's field of view. For example, in conjunction with block 620 implementing image-based identification 621, it may not be necessary to physically contact the target anatomical feature to determine its position / location. Instead, the target recognition mechanisms disclosed herein may be used to determine the position / location based on image data captured / generated by one or more cameras of the scope / instrument. For example, in some embodiments, multiple frames of image / visual and / or position (e.g., EM) data are used to identify and track the target. In conjunction with Fig.12 An example of such target position determination is described. In some implementations, by observing a target anatomical feature (eg, mastoid) from two different positions and / or alignments, the target position can be estimated / determined relative to three-dimensional space.
[0123] At block 639, subprocess 631 involves targeting the tracked position of the target anatomical feature using the percutaneous access instrument. For example, the centroid of the identified mastoid shape or morphology in the real-time image of the treatment site may be used at the target position of the percutaneous access instrument.
[0124] At box 640, process 600 involves puncturing the target anatomical feature, wherein there is no visual confirmation of the target anatomical feature relative to subprocess 632, or visual confirmation is performed according to subprocess 631, depending on the specific implementation of process 600.
[0125] Various position sensors used in conjunction with embodiments of the present disclosure, such as position sensors used to record feature contact positions at box 633 or to aim at live instrument positions at box 636, can be any type of position sensor. As an example, such a sensor can be an electromagnetic (EM) sensor / probe. With respect to the endoscope, the position sensor can be attached to or integrated with its top, proximal to the top. Alternatively, the sensor can include a coil connected to an electrical wire extending the length of the endoscope, the coil connected to an external control circuit system, and the external control circuit system is configured to interpret the electrical signal generated at the coil and transmitted along the wire. Examples of types of position sensor devices that can be implemented in conjunction with embodiments of the present disclosure include (but are not limited to) accelerometers, gyroscopes, magnetometers, fiber optic shape sensing (e.g., via Bragg gratings, Rayleigh scattering, interferometry, or related techniques), etc. Depending on the specific implementation, registration of a separate modality of patient imaging, such as a CT scan, may or may not require providing a reference frame for locating urinary stones in the patient.
[0126] For reference, a specific position determination / positioning mechanism that may be implemented in some disclosed embodiments is described. With respect to EM-type sensors, such as coils or other antennas, such sensor devices may be configured to detect changes in the EM field as the EM sensor moves within the field (e.g., within the kidney). Thus, certain embodiments are implemented using one or more EM generators configured to emit an EM field that is picked up by the EM sensor. The EM generators may be modulated in any suitable or desirable manner so that when the fields they emit are captured by the EM sensor and processed by appropriate control circuitry, signals from different EM generators may be separated to provide an additional dimension of position information. The EM generators may be modulated in time or in frequency, and orthogonal modulation may be used so that each signal may be completely separated from each other signal despite the possibility of temporal overlap. In addition, the individual EM generators may be oriented relative to each other in Cartesian space at non-zero non-orthogonal angles so that changes in the orientation of the EM sensor will cause the EM sensor to receive at least a certain signal from at least one of the EM generators at any time.
[0127] Further references Figure 6 The recording of the feature contact position at box 633 of EM position data may be registered to an image of the patient captured using a different technique other than EM (or any mechanism for capturing alignment sensor data), such as a CT scan, to establish a reference frame for the EM data. In addition to the scope, the percutaneous access needle may include one or more position / alignment sensors, such as EM sensors. Position / alignment data received from the needle EM sensor may be received and processed similarly to the scope position data as described above. The various processes described herein may be performed in whole or in part manually and / or in whole or in part using a robot.
[0128] The processes disclosed herein can be implemented in conjunction with surgeries other than kidney stone removal surgery, such as gallbladder stone removal, lung (pulmonary / transthoracic) tumor biopsy, etc. Generally speaking, any type of percutaneous surgery can be performed using an endoscope configured to capture image data for feature recognition and tracking using neural network processing according to an embodiment of the present disclosure. Additional examples include gastric surgery, esophageal surgery, and lung surgery, etc. Furthermore, the objects to be removed do not necessarily need to be urinary stones, they can be any objects, such as foreign objects or objects generated within the human body.
[0129] Anatomical feature recognition and tracking based on neural network
[0130] Figure 7 A feature recognition framework for identifying one or more target anatomical features in an endoscopic camera image to dynamically update target location data according to one or more embodiments of the present disclosure is illustrated. Feature recognition framework 700 may be embodied in a specific control circuit system including one or more processors, data storage devices, connectivity features, substrates, passive and / or active hardware circuit devices, chips / die, etc. For example, framework 700 may be embodied in Figure 2 60 and described above. The feature recognition framework 700 can employ machine learning functionality to perform automatic object detection on ureteroscopic images of, for example, internal renal anatomy.
[0131] The feature recognition framework 700 may be configured to operate on specific image type data structures, such as image data representing at least a portion of a treatment site associated with one or more medical procedures. Such input data / data structures may be operated on in some manner by specific transformation circuitry 720 associated with the image processing portion of the framework 700. The transformation circuitry 720 may include any suitable or desirable transformation and / or classification architecture, such as any suitable or desirable artificial neural network architecture.
[0132] The transformation circuit system 720 can be trained based on the known anatomical images 712 and the target labels 732 corresponding to the corresponding images 712 as input / output pairs, wherein the transformation / classification framework 720 is configured to adjust one or more parameters or weights associated therewith to correlate the known input and output image data. For example, the transformation circuit system 720 (e.g., a convolutional neural network) can be trained using labeled data sets and / or machine learning. In some specific implementations, the machine learning framework can be configured to perform learning / training in any suitable or desirable manner.
[0133] The known target markings 732 may be generated at least in part by manually marking anatomical features in the known anatomical images 712. For example, the manual markings may be determined by a relevant medical professional and / or applied to mark where, for example, mastoid anatomical structures are between intercalycal anatomical images. The known input / output pairs may indicate parameters of the transformation circuitry 720, which can be dynamically updated in some embodiments.
[0134] The known target markers 732 may delineate the boundaries and / or interior regions within which the target anatomical feature resides. In some embodiments, the framework 700 may be configured to generate the real-time target markers 735 by indicating in a binary manner whether a particular image of the real-time anatomical images 715 includes the target anatomical feature, wherein further processing may be performed on the images identified as containing one or more instances of the target anatomical feature to further identify the location and / or other aspects of the target anatomical feature. In some embodiments, further processing may be performed to determine the three-dimensional location of the identified target anatomical feature and / or one or more portions thereof.
[0135] The framework 700 may be further configured to generate real-time target markers 735 associated with the real-time anatomical image 715 using a trained version of the transformation circuit system 720. For example, during a medical procedure, a real-time image of a treatment site associated with an endoscope or other medical device positioned at the treatment site may be processed using the transformation circuit system 720 to generate real-time target markers 735 that identify the presence and / or location of one or more target anatomical features in the real-time image. For example, in some embodiments, a ureteroscopic image may be processed by the transformation circuit system 720 to identify the presence, location, and / or shape of a target mastoid, which may be targeted using a percutaneous access instrument as described in detail herein. With respect to ureteroscopic applications, mastoid anatomical structures generally present similarly in appearance between subjects, and thus, it may be possible to identify mastoid anatomical structures across a wide range of demographics.
[0136] In some embodiments, the transformation circuit system 720 can be configured to identify target anatomical features (e.g., mastoids) and out-of-segment regions that contain the identified anatomical features and / or surround the identified anatomical features in the image. The transformation framework 720 can include an artificial neural network, such as a convolutional neural network. For example, the framework 720 can implement a deep learning architecture that accepts an input image, assigns learnable weights / biases to various aspects / objects in the image to distinguish one from another. The filters / features of the framework 720 can be hand-designed or can be learned through machine learning.
[0137] The framework 720 may include a plurality of neurons (e.g., a neuron layer, such as a plurality of neurons) corresponding to an overlapping region of the input image that covers the visual region of the input image. Figure 7). The framework 720 may further operate to flatten the input image or a portion thereof in some manner. The framework 720 may be configured to capture spatial and / or temporal dependencies in the input image 715 by applying specific filters. Such filters may be performed in various convolution operations to achieve desired output data. Such convolution operations may be used to extract features, such as edges, contours, etc. The framework 720 may include any number of convolution layers, wherein more layers may provide recognition of higher-level features. The framework 720 may also include one or more merging layers, which may be configured to reduce the spatial size of the convolution features, which may be used to extract rotationally and / or positionally invariant features, such as specific anatomical features. Once prepared by flattening, merging, and / or other processes, the image data may be processed by a multi-level perceptron and / or a feedforward neural network. In addition, backpropagation may be applied to each iteration of the training. The framework may be able to distinguish between primary and specific low-level features in the input image and classify them using any suitable or desirable technique. In some embodiments, the neural network architecture includes any of the following known convolutional neural network architectures: LeNet, AlexNet, VGGNet, GoogLeNet, ResNet, or ZFNet.
[0138] The input to the framework 720 may be a video or a static image. In some embodiments, the input includes a video, wherein the framework 720 is configured to generate an output indicating how a particular feature of the video changes (e.g., implementing a temporal model). In some embodiments, once the neural network 720 has been trained, the operating input of the neural network framework may include multiple (e.g., two) images, wherein the output 735 includes data indicating the position of one or more objects on the image (e.g., over time). The input 715 may include an image or image data, and / or may include data indicating differences between separate (e.g., consecutive) images. For example, the framework 720 may detect motion or spatial changes between pixels, wherein changes in pixel positions indicate motion between images and / or over time. The output may indicate differences between images. In some embodiments, the neural network framework 720 is trained to estimate optical flow.
[0139] Figure 8 An exemplary neural network feature-classification / recognition framework 800 is depicted in accordance with one or more embodiments of the present disclosure. The framework 800 may represent a convolutional neural network architecture and may include one or more of the depicted components, which may represent specific functional components, each of which may be embodied in one or more portions or components of a control circuit system associated with any of the systems, devices, and / or methods of the present disclosure. The framework 800 may represent Figure 7 An implementation of the conversion circuit system 720 or a portion thereof.
[0140] The neural network framework 800 may include a pre-trained neural network 821, such as a ResNet 50 neural network, etc. The framework 800 may also include a feature extraction component 822 (e.g., a feature extraction network (SDN)), such as a feature pyramid network. The feature extraction component 822 may be configured to extract one or more feature maps of an input image and / or engineer feature-detector profiles. In an embodiment implementing the feature pyramid network functionality, multiple images may be processed at different resolution levels to provide output variants.
[0141] The framework 800 may also include a region proposal network component 823. The region proposal network 823 may be configured to propose a specific bounding box on the image that encloses an object indicated / identified on the feature map generated and / or provided by the feature extraction component 822.
[0142] In some embodiments, a coarse-fine processing map may be performed to extract objects in an image. The proposed bounding boxes provided by the region proposal network 823 may be used by one or more additional components 827. For example, a binary classification network component 826 may be configured to classify bounding boxes based on whether they contain the object feature of interest. In addition, a box regression network 825 may be positioned and configured to refine the bounding boxes proposed by the region proposal network 823. In addition, a mask prediction network component 824 may be configured to calculate and / or represent the body shape or shape / morphology of the identified object feature.
[0143] Target anatomical feature tracking
[0144] The ability to correctly identify a target anatomical feature and its location can advantageously allow a medical instrument to aim at the target anatomical feature during a medical procedure. However, the occurrence of anatomical motion after the target position of the target anatomical feature is determined can cause the target anatomical feature to move away from the known target position. Therefore, embodiments of the present disclosure that provide real-time updates of target position data can help avoid problems associated with intraoperative anatomical motion.
[0145] In some embodiments, a positioning system (e.g., an electromagnetic positioning system as described herein) can be implemented to determine the position of one or more medical devices. In some embodiments, the positioning system can be calibrated using camera images to determine the position of features represented in the camera image in the positioning field.
[0146] Target anatomical feature tracking may be achieved according to various methods. For example, in some embodiments, target tracking may be achieved by comparing the output of a neural network (or other image processing) circuit system of two consecutive or sequentially captured images of the treatment site. For example, if a shape or mask of a target anatomical feature is output as a neural network or other type of target recognition circuit system relative to images captured at different times, the overlap of such shapes / masks (e.g., pairwise intersection-union (IOU)) may be determined, such as in the context of an overlap percentage. In general, it may be assumed that the content differences between consecutive images are not significantly different, at least relative to image capture at a sufficiently high sampling rate. Therefore, if the overlap percentage is above a predefined / predetermined threshold, the masks of consecutively captured images may be considered to represent the same target anatomical feature, where the threshold is related to the maximum movement of the target over the sampling.
[0147] Fig. 9 9 is a flow chart illustrating a process 900 for tracking a target anatomical feature at a treatment site according to one or more embodiments of the present disclosure. At block 902, process 900 involves training a neural network using labeled image data. For example, the neural network may include a plurality of labeled image data, each of which is associated with the labeled image data. Figure 7 and Figure 8 Frames 700, 800 are similar to the frames shown in FIG.
[0148] At block 904, process 900 involves receiving a first image of a treatment site from an endoscope or other medical device disposed at or near the treatment site. At block 906, process 900 involves identifying a first feature in the first image using a neural network architecture / framework. For example, the first feature may be a target mastoid present at the treatment site. For example, one or more machine learning components or modules may be implemented to perform segmentation of the first feature relative to the first image.
[0149] At box 908, process 900 involves receiving a second image of the treatment site. The second image may be captured continuously and / or sequentially relative to the first image. At box 910, process 900 involves identifying a second feature in the second image using a neural network. For example, the second feature may be a mastoid in the target calyx treatment site. At box 912, process 900 involves determining that the first feature and the second feature represent the same target anatomical feature at the treatment site, such as the same target mastoid. The determination that the first feature and the second feature represent the same target anatomical feature may be made in any manner, such as by comparing a determined overlap or shift of the first feature and the second feature and / or portions thereof.
[0150] At box 914, process 900 involves modifying a target tracking position associated with the target anatomical feature based on the identified second feature and / or the instrument position data. For example, the instrument position data may correspond to an initially identified position of a medical device and / or its articulation or relative movement. The modification of the target tracking position may be used to track the target anatomical feature by compensating for the dynamic relative movement of the target anatomical feature. In addition, the endoscope or other medical device used to capture the first image and the second image may have an electromagnetic sensor or other position sensor associated therewith. Such a position sensor may be used to introduce compensation for the movement of the medical device to the target tracking position data.
[0151] Based on the relative motion of the target anatomical feature between the time when the first image was captured and the time when the second image was captured, modification of the target tracking position may be needed and / or desired. As described above, such motion may be caused by the insertion and / or manipulation of a percutaneous access instrument, such as a needle, in the general area of the treatment site. Due to this motion, the target anatomical feature (e.g., the mastoid) may generally not remain fixed relative to the scope, which can be used to determine the initial target position. Therefore, the feature recognition and tracking functionality disclosed in conjunction with the systems, devices, and methods of the present disclosure can allow the target anatomical feature to be tracked over time using camera images. Such tracking can be used to dynamically predict the three-dimensional position of the target anatomical feature, wherein the three-dimensional position can be used as a target tracking position for the percutaneous access instrument, as described herein. As described herein, dynamic target estimation can greatly assist in achieving convergence between the percutaneous access instrument and the target anatomical feature.
[0152] The position of a camera of a medical device (e.g., an endoscope) can be determined relative to the position of a position sensor associated with the distal end of the medical device. Using such camera position information, the position of an object / feature appearing in image space can be determined relative to a position space (e.g., electromagnetic field space) associated with the position sensor. Thus, the position of a second feature in a second image can be determined in three-dimensional space, and the position can be provided to guide a percutaneous access device (e.g., a needle).
[0153] although Fig. 9 Modifying the target tracking position based on the second feature identification and / or position is described, but it should be understood that any type of responsive action may be implemented based at least in part on the updated anatomical feature identification. For example, a specific control circuit system communicatively coupled to a robot that controls the position of the endoscope may be implemented to adjust / articulate the endoscope based on the movement of the target anatomical feature. For example, the endoscope may be moved so that the center of mass or other portion of the target anatomical feature is at or near the center of the field of view of a camera, interface, or other visual representation of the treatment site.
[0154] The neural network and masking concepts disclosed in this article can be implemented according to the publication "MaskR-CNN" (He, Kaiming, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. "Maskr-cnn" In Computer Vision (ICCV), 2017 IEEE International Conference on, pp. 2980-2988. IEEE, 2017), the entire content of which is hereby expressly incorporated by reference into this article.
[0155] Figure 10 is a flow chart illustrating a process for tracking a target anatomical feature at a treatment site in accordance with one or more embodiments of the present disclosure.The tracking process 1000 of Figure 10 may be viewed as a direct tracking embodiment. Fig.11 Specific feature masks and associated images associated with various steps of process 1000 shown in FIG. 10 are shown.
[0156] At block 1002, process 1000 involves generating a target mask 122 for a first image 121 of a treatment site taken at a first time (t). As shown in image 121, the first image includes at least a portion of a target anatomical feature 111, which may represent a papilla visible from a calyx / kidney treatment site. Image 122 represents a mask of the target anatomical feature. Although any mask may be used in accordance with embodiments of the present disclosure, the illustrated mask 122 is a binary mask that includes a feature region 112 representing the shape or morphology of the visible portion of the target anatomical feature 111, and a background portion 119 representing an area of the image 121 that does not correspond to the target anatomical feature 111. Any type of segmentation and / or machine learning mechanism may be used to generate mask 122, wherein segmented regions bifurcate to provide a regional mask, as shown.
[0157] At block 1004, process 1000 involves generating a target mask 124 for a second image 123 captured at a time (t+1) after the time (t) when first image 121 was captured. Through neural network image processing or other target recognition mechanisms in accordance with aspects of the present disclosure, a target anatomical feature 113 may be identified in image 123. Mask 124 of image 123 relative to target feature 113 is shown as image 124, which includes feature regions 114 representing the shape / shape or form of the target anatomical feature 113 and visible portions of image 123, and background portions 127 representing areas of image 123 that do not correspond to target anatomical feature 113.
[0158] At box 1006, process 1000 involves determining the overlap of objects or features in first image 121 and second image 123 using their respective masks 122, 124. Image 125 represents the overlap of first mask 122 and second mask 124. The resulting image 125 includes a portion 115 corresponding to the background of both first image 121 and second image 123, a portion 116 corresponding to the feature area relative to the background of first image 121 but relative to second image 123, and a portion 117 corresponding to the feature area relative to the background of second image 123 but relative to first image 121. The remaining area 118 represents the overlap area between the identified anatomical features 111, 113. For clarity, the overlap area / shape is shown separately as image 126 and represents an area that is no larger than either of the feature areas of masks 122, 124.
[0159] Process 1000 may proceed to decision block 1008, where it may be determined whether the amount of overlap 118, 126 is greater than a predetermined threshold amount of overlap relative to the first feature region 112, the second feature region 114, or both. If the determination is positive, process 1000 proceeds to block 1010, where a responsive action may be taken. For example, at block 1010, it may be assumed that the first identified anatomical feature 111 and the second identified anatomical feature 113 represent the same target anatomical feature. For example, the two identified features may represent the same papilla within a patient's kidney. Thus, any change in position between images 121 and 123 may represent anatomical movement, and thus the responsive action may involve adjusting a target position associated with the target anatomical feature and / or adjusting a position of a utilized medical instrument, such as an instrument (e.g., an endoscope and / or its camera) used to capture images 121, 123. For example, one or more robotic arms may be configured to respond by adjusting the position of the arm and / or the endoscope controlled by the robotic arm. The determination of the overlap of the regions of interest may be based on a two-dimensional X / Y axis. Although the differences between the images 121 , 123 are described as being attributable to anatomical movement, it should be understood that such differences may be attributable, at least in part, to movement of one or more operating tools or instruments.
[0160] If the feature overlap does not meet the predetermined threshold, process 1000 may proceed to box 1012, which may or may not be associated with any response action. For example, at box 1012, it may be assumed that features 111, 113 represent separate anatomical features and / or portions thereof. Therefore, the specific anatomical movement of the target anatomical feature may be represented without relying on the difference in position between features 111, 113. In some embodiments, the predetermined threshold may be dynamically tunable and may be selected and / or determined to produce a desirable or optimal distinguishing performance. For example, the threshold may be determined based on an analysis of previously known data, as described herein. In some embodiments, movement attributable to cyclical breathing action may be filtered out so that such movement is not attributed to the movement of the target anatomical feature. For example, sampling of images 121, 123 may be performed so that they correspond to similar points in the respiratory cycle. In some specific implementations, the image is sampled at approximately 30 frames per second or any other suitable or desirable sampling rate.
[0161] In addition to the direct tracking methods described above, indirect tracking methods may be implemented according to the present disclosure. For example, optical flow tracking may be implemented to track the movement of target anatomical feature portions and / or their corresponding pixel representations across multiple images. For example, tracking pixels representing common image features may provide target anatomical feature movement information. Furthermore, other feature tracking mechanisms may be implemented, such as tracking corners, logs, groups of pixels, and / or any other image features.
[0162] Although segmentation / masking can be performed using image processing methods including neural network frameworks, etc. as described herein, in some embodiments, segmentation / masking is performed at least partially manually by a physician or other technician / operator. For example, a technician can select a target anatomical feature and identify similar features in subsequent images, where the movement represented by successive feature identification / segmentation can be taken into account in any suitable or desirable manner in accordance with the present disclosure. In some embodiments, feature descriptors can be locally operated on the identified feature region, which can be considered as an area with a high probability of the feature existing in the subsequent image.
[0163] Although aspects of the present disclosure are presented in the context of a ureteroscope, it should be understood that such concepts are applicable to any type of endoscopic application. For example, the feature recognition and tracking techniques described herein may be utilized to identify and track polyps or other target anatomical features. With respect to bronchoscopic procedures, the target anatomical feature recognition and tracking concepts of the present disclosure may be utilized to identify tumors and / or manage the position of the scope for collecting samples, etc. With respect to airway procedures, feature recognition and targeting according to the present disclosure may be utilized to identify and / or track nodules within a target airway, the airway itself, and / or other features.
[0164] With respect to any of the embodiments disclosed herein, it should be understood that known scope movement data may be compensated with respect to target anatomical feature identification and / or tracking. In addition, the position sensor information may further provide information indicating movement that may be compensated for for target feature tracking purposes. With further reference to FIG. 10 , in some embodiments, before initiating any response action at block 1010, process 1000 may involve determining whether user-initiated scope movement or unintentional scope movement has occurred. If so, the generated mask may be adjusted to compensate for such movement so that such movement is not reflected in the overlap determination and / or response action.
[0165] With respect to the various embodiments disclosed herein, any suitable or desirable type of sensor, device, or combination thereof may be used to determine and / or generate position information. For example, the position sensor / device of the present disclosure may include one or more of any of the following: an electromagnetic sensor, an impedance spectroscopy sensor, a coaxial sensor, an inertial measurement sensor, an accelerometer, a magnetometer, a gyroscope, and / or any other type of sensor that provides information indicating position, distance, orientation, acceleration, alignment, etc.
[0166] 3D object position estimation
[0167] The three-dimensional (3D) position estimation for tracking target anatomical features according to aspects of the present disclosure may be implemented according to any suitable or desirable technique or mechanism. For example, in some embodiments, the distance between the endoscopic camera and the target anatomical feature may be estimated based on the representative size of the anatomical feature in the image.
[0168] In some embodiments, information related to the angle of movement of the scope and / or anatomical features can be used to determine the 3D position. For example, electromagnetic sensors / beacons in an electromagnetic field / space can provide such movement angle information. By combining electromagnetic sensor data with image data, the mapping between the distance to the target anatomical feature and the size of the target anatomical feature in the resulting image captured after the movement of this distance can be used to estimate the depth / distance of the feature in subsequent images. In some embodiments, when contacting the target anatomical feature (e.g., mastoid) and retracting the scope away from such features to park the scope in a position that provides a desirable field of view, the distance traveled can be aligned using, for example, electromagnetic sensor data. In addition, subsequent images and provide information about how large the anatomical features appear in such images, and therefore the relationship / mapping between the feature size and the distance can be determined and used for future position determination. In some specific implementations, machine learning can be used to classify images and determine position information based on the size of the features in such images.
[0169] In some embodiments, machine learning may be used to train a neural network framework to interpret image data and generate an output indicating the 3D depth of image pixels. Such machine learning may be implemented according to any suitable or desirable process or mechanism described herein. In some embodiments, an external camera sensor (e.g., a speculum) associated with a medical device may be used to obtain the 3D position of a target. For example, a structured illumination sensor and / or a time-of-flight sensor may be used to determine 3D positioning.
[0170] According to some embodiments, a geometric translation method may be implemented to detect the 3D position of a target anatomical feature. For example, as with certain other embodiments of the present disclosure, a latent image associated with a separate timestamp may be captured. In conjunction with such an image, rotational translation information relative to the camera that may be determined based on sensor information from any suitable or desirable sensor or device may be used to triangulate and / or determine the position of such an image in 3D space, thereby providing information indicating the 3D position of the target anatomical feature in 3D space. The rotational translation information may be based on robotic actuator movement and / or position sensor information, such as from an electromagnetic beacon device associated with a camera and / or a scope, and indicates the position of the camera in electromagnetic field space.
[0171] Fig.12 is a diagram illustrating aspects of a 3D position estimation process involving performing a 3D position estimation operation at separate times (ie, times corresponding to time (t) and time (t+1), respectively (referred to as C t and C t+1 ))The first image 91 and the second image 92 captured.
[0172] Given the intrinsic and extrinsic parameters of the camera (principal point, focal length and distortion factors, relative motion), the 3D position of the target anatomical feature can then be calculated based at least in part on the tracked target two-dimensional (2D) position on the image. For the intrinsic parameters, the camera principal point and focal length can be considered. Additional data that can be considered may include radial and tangential distortion factors. Based on sensor readings (e.g., robot- or EM-based sensor readings), extrinsic parameters can also be obtained, including the rotation R and translation T of the scope between the positions where the two images were taken. For convenience, K can be represented as a matrix containing the intrinsic parameters and H can be represented as a matrix containing C t With C t+1 The 4-by-4 matrix of extrinsic rotations and translations between .
[0173] For C t , the 3D-2D projection relationship can be expressed as x t =KX, where X is the 3D coordinate wrtC i and x t2D coordinates on image t (the detected center of mass of the object). Here, K is a three-by-four matrix that can be expressed as:
[0174]
[0175] Where K (n) is the nth row in K.
[0176] Similarly, for C t+1 , x t+1 =K′X, where:
[0177]
[0178] Because x t and KX are parallel vectors, so x t ×KX=0, and similarly, x t+1 ×K′X=0. Here, '×' is the cross product operator. Therefore:
[0179]
[0180] The above can produce: i(v t K (3) XK (2) X)-j(u t K (3) XK (1) X)+k(u t K (2) Xv t K (1) X)=0, where u t and v t is x t 2D coordinates of . Therefore:
[0181]
[0182]
[0183]
[0184] Here, only the first two equations may be needed, since the third equation is a linear combination of the first two equations. Similarly, for C t+1 , we can obtain the following two equations:
[0185]
[0186]
[0187] In stack C t and C t+1 The equations below produce the following results:
[0188] AX=0,
[0189] Where A is a 4 by 4 matrix:
[0190]
[0191] Since the elements in A are known (detected 2D coordinates, intrinsic and extrinsic parameters), X can be calculated by performing a singular value decomposition (SVD) on A:
[0192] A=U∑V T ,
[0193] And the last column of V is the solution of X.
[0194] Thus, in view of the foregoing disclosure, various inventive concepts disclosed herein may be utilized to perform automatic target detection, target tracking, and / or three-dimensional position estimation. In some embodiments, aspects of the present disclosure advantageously allow tracking of target anatomical features without requiring physical contact with the target anatomical features, which may facilitate improved ergonomics for use of ureteroscopes.
[0195] Configured to implement Fig.12 The control circuitry of the system can advantageously generate three-dimensional (3D) position information associated with an object present in two (e.g., temporally consecutive) images. In some implementations, the 3D information can be generated using a neural network framework that can be similar in one or more aspects to the 3D information generated in the present invention. Figure 7 720 and described above as an alternative or in addition to the above-described computational implementations. For example, the input to the neural network may include images, markers, or other data indicating the 3D size, 3D location (e.g., xyz coordinates) of the target anatomical structure, or other data related to image parameters. Depth information may be determined from CT or may be derived from other information. For example, depth and / or pixel coordinate information may be output from the neural network.
[0196] Additional Implementation
[0197] Depending on the implementation, specific actions, events or functions of any one of the processes or algorithms described herein may be performed in a different order, added, merged or completely ignored. Therefore, in certain embodiments, not all described actions or events are necessary for the practice of the process.
[0198] Unless otherwise specifically stated or understood in the context of use, conditional language used herein, such as "may", "can", "might", "could", "for example", etc., refers to its ordinary meaning and is generally intended to convey that certain embodiments include and other embodiments do not include certain features, elements and / or steps. Therefore, such conditional language is generally not intended to imply that one or more embodiments require features, elements and / or steps in any way, or that one or more embodiments must include logic for determining whether these features, elements and / or steps are included in any particular embodiment or whether they will be performed in any particular embodiment with or without author input or prompting. The terms "include", "comprise", "have", etc. are synonymous and are used in their ordinary sense and are used inclusively in an open-ended manner and do not exclude additional elements, features, actions, operations, etc. Moreover, the term "or" is used in its inclusive sense (rather than in its exclusive sense) so that when used, for example, to connect a series of elements, the term "or" refers to one, some, or all of the elements in the series. Unless specifically stated otherwise, conjunctive language such as the phrase "at least one of X, Y, and Z" is understood in the context of general usage to convey that an item, term, element, etc. can be X, Y, or Z. Thus, such conjunctive language is generally not intended to imply that certain embodiments require that at least one of X, at least one of Y, and at least one of Z each be present.
[0199] It should be understood that in the above description of the embodiments, in order to simplify the present disclosure and assist in understanding one or more of the various inventive aspects, various features are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of the present disclosure should not be understood to reflect the following intention: any claim requires more features than the features explicitly described in that claim. In addition, any component, feature, or step illustrated and / or described in the specific embodiments herein may be applied to any other embodiment or used with any other embodiment. In addition, for each embodiment, no component, feature, step, or group of components, features, or steps is necessary or indispensable. Therefore, it is expected that the scope of the present invention disclosed herein and claimed below is not limited to the specific embodiments described above, but should only be determined by a fair reading of the appended claims.
[0200] It should be understood that certain ordinal terms (e.g., "first" or "second") may be provided for ease of reference and do not necessarily imply physical characteristics or ordering. Therefore, as used herein, ordinal terms (e.g., "first," "second," "third," etc.) used to modify elements such as structures, components, operations, etc. do not necessarily indicate the priority or order of the element relative to any other element, but may generally distinguish the element from another element with a similar or identical name (but used to use the ordinal term). In addition, as used herein, indefinite articles ("a" and "an") may indicate "one or more" rather than "one." In addition, an operation performed "based on" a condition or event may also be performed based on one or more other conditions or events that are not explicitly stated.
[0201] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the exemplary embodiments belong. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not interpreted in an idealized or overly formal sense, unless expressly defined as such herein.
[0202] For ease of description, the spatially relative terms "external," "internal," "upper," "lower," "below," "above," "vertical," "horizontal," and similar terms may be used herein to describe the relationship between one element or component and another element or component depicted in the drawings. It should be understood that the spatially relative terms are intended to cover different orientations of the device in use or operation other than the orientation depicted in the drawings. For example, where the device shown in the drawings is flipped, a device that is "below" or "under" another device may be placed "above" the other device. Thus, the illustrative term "below" may include both a lower position and an upper position. The device may also be oriented in another direction, and thus the spatially relative terms may be interpreted differently depending on the orientation.
[0203] Unless otherwise expressly stated, comparative and / or quantitative terms such as "less", "more", "greater", etc., are intended to encompass equivalent concepts. For example, "less" may mean not only "less" in the strictest mathematical sense, but also "less than or equal to".
Claims
1. A system for tracking a feature in an operating environment, the system comprising: an apparatus configured to be advanced to a target location in an operating environment, the apparatus comprising an imaging device; and The control circuit is configured as: generating a first image of at least a portion of the operating environment using the imaging device of the instrument when the distal end of the instrument is in a first position; generating a first shape of a first target feature represented in the first image; generating a second image of at least a portion of the operating environment using the imaging device of the instrument when the distal end of the instrument is in a second position; generating a second shape of a second target feature represented in the second image; and A target location in the operating environment is determined based at least in part on the first shape and the second shape.
2. The system of claim 1, wherein the first target feature and the second target feature represent the same feature.
3. The system of claim 1, wherein said generating the first body shape is performed using an artificial neural network.
4. The system of claim 3, wherein the first body shape is provided as an output of the artificial neural network.
5. The system of claim 1, further comprising determining an amount of overlap between the first body shape and the second body shape.
6. The system of claim 5, wherein the determining an amount of overlap between the first body shape and the second body shape involves determining a percentage of the amount of overlap relative to at least one of the first body shape or the second body shape.
7. The system of claim 6, further comprising determining that the percentage is greater than a predetermined threshold level.
8. The system of claim 7, wherein the predetermined threshold level is based on a maximum expected movement of the first target feature during a time period between the generating the first image and the generating the second image.
9. The system of claim 1, wherein said generating said first body shape is based on an output from a box regression network.
10. A system for tracking a feature within an operating environment, the system comprising: an apparatus configured to be advanced to a target location within an operating environment including a target feature, the apparatus comprising an imaging device; and The control circuit configuration is: generating a first image of at least a portion of the operating environment using the imaging device of the instrument when the instrument is in a first position; identifying a representation of the target feature in the first image; generating a second image of at least a portion of the operating environment using the imaging device of the instrument when the instrument is in a second position; identifying a representation of the target feature in the second image; determining a first set of parameters associated with the instrument in the first position; determining a second set of parameters associated with the instrument in the second position; as well as A three-dimensional position of the target feature is generated based at least in part on the first image, the second image, the first set of parameters, and the second set of parameters.
11. The system of claim 10, wherein the first set of parameters and the second set of parameters include electromagnetic sensor data.
12. The system of claim 10, wherein at least one of the first set of parameters or the second set of parameters indicates a rotational translation of the instrument between the first position and the second position.
13. The system of claim 10, wherein said generating a three-dimensional position is based on sensor position data of said first set of parameters and said second set of parameters.
14. The system of claim 10, wherein each of the first set of parameters and the second set of parameters comprises one or more of the following parameters: focal length, distortion, or relative motion.
15. The system of claim 10, wherein the first set of parameters includes both intrinsic parameters and extrinsic parameters.
16. The system of claim 10, further comprising estimating a distance between the instrument and the target feature when the instrument is in a first position based on a size of the representation of the target feature in the first image. The system of claim 16 , wherein the first set of parameters includes the distance.
18. The system of claim 16, further comprising determining a mapping between a size of the feature representation and a feature distance.
19. The system of claim 18, wherein the estimating the distance between the instrument and the target feature is based on the mapping.
