System for adaptive ablation volume prediction based on tissue temperature measurements and anatomical segmentation

Abstract

A system and method are provided for ablating target tissue during ablation, measuring parameters such as the temperature of the target tissue, and predicting the ablation volume based on the measured parameters. The system may include: a switched antenna used both for heating the target tissue and for radiation measurement to monitor the temperature of the heated tissue; and a processor used for calculating the temperature of the target tissue, segmenting medical images, and predicting the ablation volume based on a radiation signal indicating the temperature of the target tissue. The predicted ablation volume may be adapted to take into account tissue boundaries and anatomical structures. The processor may further determine the properties of the target tissue, such as tissue type.

Description

[0001] Cross-references to related applications

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 595,306, filed November 1, 2023, and European Patent Application No. 23306887.3, filed October 31, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to systems and methods for safely and effectively ablating target tissue by measuring parameters (e.g., the temperature of the target tissue) during ablation and predicting the ablation volume based on the measured parameters. Background Technology

[0004] Tissue ablation can be used to treat a variety of clinical conditions, and several ablation techniques have been developed, including cryoablation, microwave ablation, radiofrequency (RF) ablation, and ultrasound ablation. These techniques are typically performed by clinicians who introduce a catheter with an ablation tip percutaneously or via the venous system or natural lumen into the target tissue. Based on tactile feedback, mapping electrocardiogram (ECG) signals, anatomical and / or fluorescence microscopy imaging, the ablation tip is positioned near an area deemed appropriate by the clinician. A flow of irrigation fluid is actuated to cool the surface of the selected area, and then the ablation tip is actuated for a period deemed sufficient to destroy the tissue in the selected area.

[0005] While commercially available ablation tips may include thermocouples that provide temperature feedback via a digital display, such thermocouples typically do not provide meaningful temperature feedback during perfusion ablation. For example, thermocouples only measure surface temperature, while the heating or cooling of tissue leading to ablation may occur at a depth below the tissue surface. Furthermore, in procedures where the tissue surface is cooled with an irrigating fluid, the thermocouple will measure the temperature of the irrigating fluid, further obscuring any useful information about tissue temperature, especially at deeper sites. Consequently, clinicians lack sufficient feedback regarding the temperature of the tissue as it is being ablated or whether the ablation process is ongoing. Therefore, it is desirable to incorporate thermocouple configurations at the ablation tip that allow for high-level tissue temperature measurement to enable accurate temperature measurement using microwave heating.

[0006] Therefore, it may only be discovered after the procedure that the abnormal target pathway has not been adequately disrupted. In this case, the clinician may not know whether the procedure failed because the wrong tissue area was ablated, because the ablation tip was not actuated for a sufficient period of time to destroy the target tissue, because the ablation tip did not contact the tissue or made insufficient contact, because the ablation energy was insufficient, or some combination of the above. When repeating the ablation procedure to try to ablate the target tissue again, the clinician may have as little feedback as during the first procedure, and therefore may again fail to disrupt the abnormal pathway. In addition, there is a risk that the clinician will re-treat the previously ablated area of ​​the target tissue and damage not only the target tissue but also adjacent tissues.

[0007] In some cases, to avoid the need for repeated ablation procedures, clinicians may ablate a series of areas of the target tissue along its distribution to increase the likelihood of successful ablation. However, there is also insufficient feedback to help clinicians determine whether any of those ablated areas have been adequately destroyed. Although the use of radiometry promises to provide precise temperature measurement sensitivity and control, commercial medical applications of this technique have been rarely successful. One known drawback of previously known systems is the inability to obtain highly repeatable results due to slight variations in the construction of the microwave antenna used in the radiometer, which can lead to significant differences in measured temperatures across different catheters. Problems also arise regarding the orientation of the radiometer antenna onto the catheter to fully capture the radiant energy emitted by the tissue, and the shielding of the high-frequency microwave assembly in the surgical environment to prevent interference between the radiometer assembly and other devices in the surgical setting.

[0008] The capital costs associated with implementing radiation temperature control schemes also hinder the adoption of microwave-based hyperthermia and temperature measurement techniques. Radiofrequency ablation has gained a large following in the medical community, although such systems may have significant limitations, such as the inability to accurately measure the temperature of deep tissues, for example, when irrigation is used. However, widespread acceptance of RF ablation systems, the extensive medical knowledge base of such systems, and the substantial costs required for transitioning to and training in new technologies significantly impede the widespread adoption of radiation measurement.

[0009] U.S. Patents 8,926,605 and 8,932,284 to McCarthy et al. (each of which is incorporated herein by reference) describe a system for measuring temperature radially during ablation.

[0010] In view of the above, it is desirable to provide a system and method that allows for high-radiation measurement of temperature deep within tissues to achieve accurate temperature measurement using microwave heating.

[0011] In addition, it is desirable to use such accurate radiation temperature measurements to predict the ablation volume of the target tissue in real time as a feedback mechanism for detecting and / or preventing overheating of the target tissue during ablation procedures, and it is also desirable to inform the target tissue of additional properties, such as tissue type and / or other physical properties.

[0012] While a variety of energy-based devices exist that promise to improve outcomes, reduce risks, and shorten recovery times for treating a range of diseases, there remains a significant opportunity to leverage the capabilities of dissimilar technologies to deliver optimal treatments that drive outcomes and improve risk profiles. Summary of the Invention

[0013] This disclosure overcomes the shortcomings of previously known systems and methods by providing a system for predicting the ablation volume of tissue. The system may include a controller having instructions that, when executed by one or more processors of the controller, cause the controller to: receive information indicating the temperature of tissue being ablated via an antenna; extract one or more features of the temperature of the tissue from the information, the one or more features including at least one of the area under a curve of the temperature of the tissue, the maximum temperature of the tissue, the heat dose of the temperature of the tissue, the initial slope of the temperature of the tissue, or the average temperature rise of the tissue; and execute an ablation volume prediction algorithm to predict the ablation volume of the tissue based on the extracted one or more features and a trend line derived from a relevant dataset of ablation volumes associated with the extracted one or more features.

[0014] The information indicating the temperature of the tissue being ablated via the antenna may include a radiation signal generated by the antenna. Therefore, the system is configured to use an anti-spiking filter on the radiation signal to remove one or more inaccurate points within the radiation signal. For example, the anti-spiking filter may include at least one of a moving minimum or a first derivative-based algorithm. Furthermore, the system may be configured to use a smoothing filter on the radiation signal to generate a smoother signal. For example, the smoothing filter may include at least one of a Kalman filter or a moving average. Additionally, the system may be configured to detect an uncontrolled rise in the temperature of the tissue based on the radiation signal. The system may be further configured to detect the presence of a heat sink based on the radiation signal and a simulation results dataset. Alternatively or additionally, the information indicating the temperature of the tissue being ablated via the antenna may include the voltage returned by a thermocouple placed on the outer surface of the antenna.

[0015] Additionally, the system can be configured to take the logarithm of the cumulative equivalent minutes at 43°C to extract the thermal dose of the tissue. The system can be further configured to calculate the minor and major axes of an elliptical ablation volume corresponding to the predicted ablation volume of the tissue, the major axis being parallel to the longitudinal axis of the antenna. For example, the system can be configured to calculate the minor axis of the elliptical ablation volume based on the extracted thermal dose and a trend line derived from a relevant dataset associated with the minor axis of the extracted thermal dose. Alternatively, the system can be configured to calculate the minor and major axes of the elliptical ablation volume based on the aspect ratio of the predicted ablation volume of the tissue.

[0016] The system can also be configured to: compare the extracted initial slope of the temperature of the tissue with a dataset of initial slope values ​​and associated electromagnetic tissue properties to determine one or more electromagnetic properties of the tissue; and determine the type of the tissue based on the determined one or more electromagnetic properties of the tissue. For example, the system can be configured to determine whether the tissue is healthy or cancerous based on the determined one or more electromagnetic properties of the tissue. Furthermore, the system can be configured to have the antenna emit energy to the tissue at a predetermined level for a predetermined period of time, such that the predetermined level and the predetermined period of time are insufficient to damage the tissue. Therefore, the initial slope of the temperature of the tissue can be extracted from the information received in response to the energy emitted to the tissue at the predetermined level during the predetermined period of time (e.g., a radiation signal or the voltage returned by the thermocouple). The system can be further configured to: estimate one or more tissue property parameters of the tissue based on the information indicating the temperature of the tissue being ablated and a dataset of tissue temperature and corresponding average tissue property parameter values; and adjust the predicted ablation volume of the tissue based on the one or more tissue property parameters.

[0017] Additionally, the system can be configured to determine at least one of the water content of the tissue or the physical properties of the surrounding tissue based on the extracted initial slope at the temperature of the tissue. Furthermore, the system can be configured to display the predicted ablation volume of the tissue on a display. For example, the system is configured to: receive a medical image including the tissue and the antenna; perform a segmentation algorithm to segment the tissue and the antenna in the medical image; label the segmented tissue and antenna on the medical image; and display the predicted ablation volume of the tissue superimposed on the labeled medical image including the labeled segmented tissue and antenna. The medical image may include a CT scan image, a CBCT scan image, an X-ray-based tomographic composite image, an MRI image, or an echo B-mode image. Furthermore, the system is configured to: receive a preoperative medical image including the tissue, the preoperative medical image including a labeled lesion; execute a segmentation algorithm to segment the tissue in the preoperative medical image; execute a registration toolbox to register the labeled medical image and the preoperative medical image based on the labeled medical image and the segmented tissue in the preoperative medical image; and overlay the labeled lesion onto the registered labeled medical image. Therefore, the displayed predicted ablation volume of the tissue can be overlaid on the registered labeled medical image including the labeled lesion.

[0018] The medical image may include one or more anatomical structures, such as at least one of an airway, blood vessel, or bile duct. Therefore, the system may be configured to: perform a segmentation algorithm to segment the one or more anatomical structures in the medical image; and label the segmented one or more anatomical structures on the medical image. Thus, the displayed predicted ablation volume of the tissue may be superimposed on the labeled medical image including the labeled segmented tissue, the antenna, and one or more anatomical structures. Additionally, the system may be configured to: determine the boundaries of the tissue based on the segmented tissue; and determine the shape of the predicted ablation volume of the tissue based on the boundaries of the tissue, the location of the segmented antenna, the location of the segmented one or more anatomical structures, and a dataset of simulation results. Therefore, the displayed predicted ablation volume of the tissue may include the determined shape.

[0019] The segmentation algorithm can be configured to: threshold the medical image using an adaptive threshold; calculate one or more connected components of the thresholded medical image; discard any of the one or more connected components smaller than a predetermined size; calculate the straightness index of each of the remaining one or more connected components; and classify the connected component with the lowest straightness index as the antenna. For example, the segmentation algorithm can be configured to: (a) select three random points on each of the remaining one or more connected components; (b) calculate the angle between the three random points on each of the remaining one or more connected components; (c) determine a value based on an additional angle and the minimum of the angles on each of the remaining one or more connected components; (d) repeat (a) to (c) multiple times; and (e) calculate the straightness index of each of the remaining one or more connected components as the average of the determined values.

[0020] Furthermore, the system can be configured to simulate the growth of the predicted ablation volume of the tissue over time. For example, the system can be configured to create a patient-specific simulation simulating the growth of the predicted ablation volume of the tissue over time. Additionally, the system can be configured to: calculate the shrinkage of the tissue based on registration of preoperative and postoperative scans; and adjust the patient-specific simulation based on the shrinkage of the tissue. For example, the system can be further configured to: execute a segmentation algorithm to segment the tissue and one or more anatomical structures within the preoperative and postoperative scans; convert the segmented tissue and one or more anatomical structures within the preoperative and postoperative scans into binary masks to create custom volumes for the preoperative and postoperative scans; register the custom volume of the preoperative scan with the custom volume of the postoperative scan; and force the voxel displacement at the antenna to 0 to calculate the shrinkage of the tissue.

[0021] Furthermore, the system can be further configured to: receive a medical image including the tissue, one or more anatomical structures within the tissue, and the antenna; perform a segmentation algorithm to segment the tissue, the one or more anatomical structures, and the antenna in the medical image; crop a predetermined volume of the tissue and the one or more anatomical structures from the segmented medical image based on the position of the antenna within the segmented medical image; and smooth the cropped volume of the tissue and the one or more anatomical structures. Therefore, the patient-specific simulation can be created based on the cropped and smoothed volume of the tissue and the one or more anatomical structures. Additionally, the system can be configured to: calculate one or more connected components of the cropped volume of the tissue and the one or more anatomical structures; and discard any of the one or more connected components smaller than a predetermined size, such that the cropped and smoothed volume of the tissue and the one or more anatomical structures can only include one or more connected components larger than the predetermined size.

[0022] For example, the one or more anatomical structures may include one or more blood vessels, and the medical images may include preoperative medical images containing the tissue and the one or more blood vessels, and medical images acquired during the ablation procedure that include the tissue and the antenna for each procedure. Therefore, the system may be further configured to: register the one or more blood vessels from the preoperative medical images to the medical images of each procedure to crop the predetermined volume of the blood vessels based on the location of the antenna. The predetermined cropped volume of the blood vessels may be smaller than the predetermined cropped volume of the tissue. Furthermore, the system may be configured to determine the shape of the predicted ablation volume of the tissue based at least in part on the patient-specific simulation. The ablation volume prediction algorithm may be configured to predict the ablation volume of the tissue based on the power level of the energy used to ablate the tissue.

[0023] According to another aspect of this disclosure, a system for determining tissue type is provided. The system may include a controller having instructions, which, when executed by one or more processors of the controller, cause the controller to: receive a radiation signal indicating the temperature of a tissue receiving energy via an antenna; extract an initial slope of the temperature of the tissue from the radiation signal; compare the extracted initial slope of the temperature of the tissue with a dataset of initial slope values ​​and associated electromagnetic tissue properties to determine one or more electromagnetic properties of the tissue; and determine the type of the tissue based on the determined one or more electromagnetic properties of the tissue. Furthermore, the system may be configured to determine whether the tissue is healthy or cancerous based on the determined one or more electromagnetic properties of the tissue. Additionally, the system may be configured to cause the antenna to emit energy to the tissue at a predetermined level for a predetermined period of time, such that the predetermined level and the predetermined period of time are insufficient to damage the tissue. Therefore, the initial slope of the temperature of the tissue can be extracted from the radiation signal received in response to the energy emitted to the tissue at the predetermined level during the predetermined period of time. Attached Figure Description

[0024] Figure 1 This is a block diagram of a demonstrative microwave ablation system.

[0025] Figure 2A illustrate Figure 1 A demonstrative radiometer antenna for a microwave ablation system.

[0026] Figure 2B illustrate Figure 2A An exemplary switching network for a radiometer antenna.

[0027] Figure 3 The illustration may be included according to some embodiments Figure 1 Some example components in the controller of a microwave ablation system.

[0028] Figure 4 This is a flowchart illustrating exemplary method steps for segmenting a radiometer antenna in a medical image according to some embodiments.

[0029] Figure 5A It is a graph illustrating the initial slope of temperature for various target tissue types.

[0030] Figure 5B It is a graph illustrating the change in the initial signal of the radiometer relative to the relative permittivity of the tissue.

[0031] Figure 6A This illustrates a trend line for predicting the ablation volume of a target tissue based on the thermal dose at radiation temperature, according to some embodiments.

[0032] Figure 6B This describes a trend line, according to some embodiments, for predicting the ablation volume of a target tissue based on the maximum tissue temperature measured by a thermocouple.

[0033] Figure 7A This illustrates the predicted ablation volume of the target tissue relative to the exemplary size of the radiometer antenna.

[0034] Figure 7B This illustrates a trend line for predicting the minor axis dimension of the ablation volume of a target tissue based on the thermal dose at radiation temperature, according to some embodiments.

[0035] Figure 8A and 8B This describes the adaptive prediction of target tissue ablation volume based on target tissue boundaries according to some embodiments.

[0036] Figure 9 This is a flowchart illustrating the generation of a digital twin of a patient-specific target tissue, based on some embodiments.

[0037] Figures 10A to 10D This describes the trimming and smoothing of patient-specific target tissues for patient-specific simulation according to some embodiments.

[0038] Figures 11A to 11D This describes the measurement of target tissue contraction in response to ablation procedures according to some embodiments.

[0039] Figure 12A This describes another exemplary graphical user interface for displaying the adaptive, predicted ablation volume of target tissue, according to some embodiments.

[0040] Figure 12B This indicates that the adaptive predicted ablation volume of the target tissue increases over time.

[0041] Figure 13 This describes an exemplary graphical user interface, according to some embodiments, for displaying the predicted ablation volume of a target tissue based on radiation signals.

[0042] Figure 14 This is a flowchart illustrating exemplary method steps for adaptively predicting the ablation volume of a target tissue according to some embodiments.

[0043] Figure 15A and 15B This describes an exemplary robotic system, according to some embodiments, for delivering a radiating antenna of a microwave ablation system to a target tissue. Detailed Implementation

[0044] This technology relates to a system and method for predicting the size and location of the volume of ablated tissue in real time during an ablation procedure based on radiation signals indicating the temperature of the ablated tissue and anatomical information. This technology also relates to the non-destructive application of energy via a catheter to determine tissue type, which is very useful during or in preparation for an ablation procedure. The ablation volume prediction algorithm described herein can use radiation signals received from a microwave ablation / radiation measurement system having a radiometer antenna configured for both heating and temperature sensing, as described in Allison U.S. Patents Nos. 11,337,756 and 12,064,174, the entire contents of each of which are incorporated herein by reference. For example, microwave heating may be directed at a target tissue, and a radiometer operating simultaneously with the microwave generator and sharing an antenna can sense / monitor microwave emissions from a region surrounding the antenna and convert these microwave emissions into tissue temperature. In this case, the monitored target tissue includes, for example, tumorous lung tissue. The algorithm calculates a volumetric temperature reading based on the calculated tissue temperature at the target region. Microwave heating of the target tissue and microwave radiation measurement as a means of monitoring the temperature of the heated tissue ensure that the desired temperature is obtained to adequately treat the target tissue and achieve the therapeutic goal.

[0045] Furthermore, to avoid inaccurate radiation temperature measurements including the temperature of the coaxial cable due to dissipation losses in the coaxial cable extending along the length of the conduit (which may not be distinguishable from the emission received by the antenna), the Dicke switch and reference terminal (e.g., internal reference input) are positioned near the end of the coaxial cable connected to the radiometer antenna. This ensures the coaxial cable is part of both the target measurement from the radiometer antenna and the reference measurement from the reference terminal, and heat dissipation from the coaxial cable is not included in the temperature calculation. Unlike the standard thermocouple technology used in existing commercial ablation systems, the radiometer provides useful information about the tissue temperature deep within the tissue—where tissue ablation occurs—and thus provides clinicians with feedback on the extent of tissue damage when ablating a selected area of ​​the target tissue.

[0046] Specifically, this disclosure overcomes the shortcomings of previously known systems by providing an improved system and method for monitoring the growth of ablation volume in target tissue during ablation procedures (e.g., by real-time display of the predicted volume of ablated tissue superimposed on a medical image depicting the target tissue). Furthermore, this disclosure provides an improved system and method for analyzing radiation signals to determine various properties of the ablated tissue, such as tissue type or water content, and the physical properties of surrounding tissues, and for adapting the ablation volume prediction to take into account the surface boundaries and contours of the target tissue and adjacent anatomical structures (e.g., airways, blood vessels, bile ducts, etc.). The novel invention described herein can be applied to catheter / probe-based therapies, including but not limited to targets in the vascular system and soft tissue targets in the liver, kidneys, prostate, and lungs. For example, the principles of this disclosure described herein can be incorporated into known robotic surgical systems (e.g., the Galaxy System) used for navigation surgery. TM (Available from Noah Medical, San Carlos, California)

[0047] Now for reference Figure 1 This provides an exemplary microwave heating and temperature sensing system. For example... Figure 1 As shown, system 10 may include a generator 12, a handle 14 with a transmit / receive (T / R) switch 16, an antenna switch bias duplexer 18, a radiometer 24, and a controller 300 with electronic components operatively coupled to the generator 12 and the handle 14. Additionally, system 10 may include a radiometer antenna (e.g., a switch antenna 200) and a cable 20, such as a coaxial cable, for electrically coupling the switch antenna 200 to the handle 14 and thus the generator 12 and the controller 300. Figure 1 As shown, generator 12 supplies ablation energy to switched antenna 200 via antenna switch bias duplexer 18 after T / R switch 16. Generator 12 can be any previously known commercially available ablation energy generator, such as a microwave energy generator, thereby enabling the use of radiation technology with reduced capital expenditure. Those skilled in the art will readily understand, although the description... Figure 1 This demonstrates a single controller, but controller 300 may contain multiple processors for a single location / housing or multiple locations / housings. Furthermore, Figure 1 Reusable equipment can be housed in a common housing or a separate housing.

[0048] Furthermore, radiometer 24 is configured to receive temperature measurements from switching antenna 200 via cable 20. Switching antenna 200 includes a main antenna having one or more microwave radiating elements for emitting microwave energy and for measuring the temperature of tissue adjacent to the main antenna, and a reference terminal for measuring a reference temperature. Additionally, switching antenna 200 includes a switching network, such as a Dick switch, integrated therein for detecting the volumetric temperature of the ablated tissue. The switching network selects between a signal indicating the measured radiometer temperature (e.g., the temperature of tissue adjacent to the main antenna during the ablation procedure) from the main antenna of switching antenna 200 and a signal indicating the measured reference temperature from the reference terminal of switching network 200.

[0049] The T / R switch 16 and antenna switch bias duplexer 18 may be housed within the handle 14 together with a radiometer 24 for receiving temperature measurements from the switch antenna 200 depending on the state of the T / R switch 16. For example, the T / R switch 16 may be in an ablation state, allowing microwave power to be transmitted from the generator 12 to the switch antenna 200, or the T / R switch 16 may be in a measurement state, allowing the radiometer 24 to receive temperature measurements from the switch antenna 200 (e.g., from the main antenna and / or reference terminal). Therefore, the switch bias duplexer 18 may be in a main antenna state, allowing the radiometer 24 to receive temperature measurements from the main antenna, or the switch bias duplexer 18 may be in a reference terminal state, allowing the radiometer 24 to receive temperature measurements from the reference terminal. The handle 14 may be reusable, while the cable 20 and switch antenna 22 may be disposable. In some embodiments, at least one of the switching components (e.g., the T / R switch 16 and switch bias duplexer 18) may be integrated into the switch antenna 200.

[0050] Microwave power is propagated from generator 12 along cable 20 in the catheter to switching antenna 200 at the tip of the catheter. Microwave power is radiated outward from the main antenna of switching antenna 200 into target tissue, such as target lung tissue, for example, a tumor. The amount of blood flowing through the body cavity at body temperature can cool the surface of the body cavity in direct contact with the blood. Alternatively or additionally, coolant introduced from outside the body through a coolant cavity in the catheter can be used to cool the surface of the body cavity, as described in U.S. Patent No. 12,064,174. Tissue outside the cavity walls that does not undergo this cooling will become hot. Sufficient microwave power can be supplied to heat the target tissue, such as a nerve region, to the temperature at which the target tissue is damaged. Additionally, controller 300 may be operatively coupled to one or more thermocouples configured to measure a reference temperature and optionally the temperature of the tissue surrounding switching antenna 200 during the ablation procedure, as described in more detail below. Therefore, controller 300 can directly receive the voltage returned by the thermocouples, such as… Figure 1 The diagram shows that the received voltage indication is a reference and / or tissue temperature measured by a thermocouple.

[0051] Now for reference Figure 2A and 2B Provides exemplary switching antennas. For example... Figure 2A As shown, the switch antenna 200 may include a main antenna 202 extending distally from and electrically coupled to a switch network 212 (e.g., a Dick switch) disposed within a substrate carrier 204. For example, the main antenna 202 may be electrically coupled to the switch network 212 via an inner conductor 206, and a spacer 208 (e.g., a polycarbonate spacer) may be positioned in the distal region of the substrate carrier 204 and surrounding the inner conductor 206. Furthermore, the distal end of a cable 20 (e.g., a coaxial cable) may be coupled to the proximal end of the substrate carrier 204, such that the cable 20 is electrically coupled to the switch network 212, and therefore, to the main antenna 202 via the inner conductor 22. Figure 2A As shown, one or more thermocouples 210 may be electrically coupled to cable 20, for example, at the junction of cable 20 and substrate carrier 204. For example, the free end of thermocouple 210 may be placed within a coolant cavity in fluid communication with a coolant used to cool the cavity surface, as described above. Therefore, thermocouple 210 may be configured to measure a reference temperature and return a voltage value indicating the measured reference temperature, which may be converted, for example, by controller 300, to the reference temperature at the location of thermocouple 210. For example, the voltage value returned by thermocouple 210 may be much higher than any noise level, for example, about 100 mV.

[0052] Alternatively, the free end of the same or another thermocouple 210 may extend along at least a portion of the outer surface of the switching antenna 200 (e.g., the outer surface of the main antenna 202) such that when the main antenna 202 emits energy during the ablation procedure, the free end of the thermocouple 210 is in direct contact with the tissue surrounding the switching antenna 200. Thus, the thermocouple 210 may be configured to measure the temperature of the tissue surrounding the antenna during the ablation procedure and similarly return a voltage value indicating the measured tissue temperature, which may be converted, for example, by the controller 300, to the tissue temperature at the location of the thermocouple 210.

[0053] The main antenna 202 can be configured to emit energy supplied by the generator 12, such as microwave energy, for example, when the T / R switch 16 is in the ablation state. Additionally, the main antenna 202 can be configured to measure radiometer temperature, such as the temperature of tissue adjacent to the main antenna 202, when the T / R switch 16 is in the measurement state. For example, the main antenna 202 may include components for detecting microwave emissions (e.g., thermal noise) from the area surrounding the antenna and converting these microwave emissions into the temperature of tissue adjacent to the switch antenna 200, such as radiometer temperature. Figure 2BAs shown, the switching antenna 200 may include a reference terminal 216 for measuring a reference temperature, for example, when the T / R switch 16 is in a measuring state, and a first switching diode 214a, a second switching diode 214b, a third switching diode 214c, and a fourth switching diode 214d, as described in U.S. Patent No. 12,064,174. For example, the reference terminal 216 may detect microwave emissions (e.g., thermal noise) from the area surrounding the reference terminal 216 and may convert these microwave emissions into a reference temperature at the location of the reference terminal 216. Therefore, the volumetric temperature output T... tissue It will be the radiometer temperature T tissue_rad The reference temperature T, for example, is measured by reference terminal 216. ref_rad The difference between them and the reference temperature T measured by thermocouple 210 ref_thermo The sum of.

[0054]

[0055] Alternatively, in some embodiments, the volumetric temperature output T tissue T can be measured by thermocouple 210 tissue_thermo As illustrated in the following equations. Therefore, the voltage indicating tissue temperature returned by thermocouple 210 can be directly received by controller 300 for processing.

[0056]

[0057] Switching diodes 214a, 214b, 214c, and 214d can be, for example, microwave PIN diodes, and can be biased with a small forward current in the on-state or reverse biased with a negative voltage in the off-state. The input from the main antenna 202 or reference terminal 216 can be selected by reversing the polarity of the bias current applied to the inner conductor 22 of cable 20. A resistor (e.g., bias component 218) returns the bias current through the outer conductor 21 of cable 20. A bias current duplexer supplies bias to the proximal end of the external catheter. A third switching diode 214c can improve the isolation between reference terminal 216 and radiometer temperature during ablation of target tissue, for example, due to tissue heating caused by ablation. A fourth switching diode 214d can improve the isolation between reference terminal 216 and radiometer temperature during measurement of reference temperature. Figure 2B As shown, the fourth switching diode 214d and the second switching diode 214b can be connected in series with the main antenna 202 and are separated by a microstrip transmission line 220 on the switching network substrate. The microstrip transmission line 220 can improve the isolation achieved by the two switching diodes 214b and 214d, which may be particularly useful for applications using higher ablation frequencies.

[0058] Now for reference Figure 3The controller 300 provides several instance components that can be included within it. As described above, the controller 300 can be operatively coupled to the generator 12 and the switching antenna 200 via, for example, a handle 14 and a cable 20 to coordinate signals between them. The controller 300 thereby provides the generator 12 with the information required for operation, transmits ablation energy to the switching antenna 200 under the control of the clinician, and can display in real-time a graphical representation of the temperature deep within the tissue being ablated, as well as the shape and location of the predicted volume of the ablated tissue, for the clinician's use. The displayed temperature and predicted ablation volume can be calculated using computer algorithms based on signals measured by the switching antenna 200, as described in more detail below.

[0059] like Figure 3 As shown, controller 300 may include one or more processors 302, communication circuitry 304, power supply 306, user interface 308, and / or memory 310 for storing instructions to be executed by controller 300. One or more electrical components and / or circuitry may perform some or all of the roles of the various components described herein. Although described separately, it should be understood that electrical components do not need to be separate structural elements. For example, processor 302 and communication circuitry 304 may be embodied in a single chip. Additionally, although controller 300 is described as having memory 310, the memory chip may be provided separately. Controller 300, together with firmware / software stored in memory, may execute an operating system (e.g., operating system 336), such as (for example) Windows, Mac OS, Unix, or Solaris 5.10. Controller 300 also executes software applications stored in memory. For example, the software may be a program written in any suitable programming language known to those skilled in the art, including, for example, C++, PHP, or Java.

[0060] Processor 302 may include one or more commercially available microcontroller units, which may include a programmable microprocessor, volatile memory, non-volatile memory (e.g., EEPROM) for storing programming data, and non-volatile storage devices, such as flash memory, for storing firmware. Processor 302 may comprise one or more processors and may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any suitable combination thereof designed to perform the functions described herein. Controller 300 may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Processor 302 is configured to be programmable such that programming data is stored in the processor's memory or is accessible via a network.

[0061] The communication circuitry system 304 may include circuitry that allows the controller 300 to communicate with an image capture device and / or other computing device to receive image files, such as medical images, such as CT scan images, CBCT scan images, X-ray-based tomographic images, MRI images, and / or echo B-mode images. Alternatively or concurrently, image files may be directly uploaded to the controller 300. The communication circuitry system 304 may be configured for wired and / or wireless communication via a network (e.g., the Internet, telephone network, Bluetooth network, and / or WiFi network) using techniques known in the art. The communication circuitry system 304 may be a communication chip known in the art, such as a Bluetooth chip and / or a WiFi chip. The communication circuitry system 304 permits the controller 300 to transmit information, such as temperature measurements and predicted ablation volume data, locally and / or to a remote location (e.g., a server).

[0062] The power supply 306 can operate in either AC or DC. In a DC embodiment, the power supply may include a suitable battery, such as a replaceable or rechargeable battery, and the device may include circuitry for charging the rechargeable battery and a detachable power cord. The power supply 306 can be charged by a charger via an inductor coil within the charger. Alternatively, the power supply 306 may have a port that allows the controller 300 to power components within the controller 300, for example, by plugging a cord with an AC-to-DC power converter and / or a USB port into a conventional wall outlet.

[0063] User interface 308 can be used to receive input from a user and / or provide output to a user. For example, user interface 308 may include a touchscreen, display, switch, dial, light, etc. Therefore, user interface 308 can display information such as temperature measurement data, ablation power level and / or duration, medical images superimposed with the predicted ablation volume, etc., to provide useful feedback to the user during the ablation procedure, as described in more detail below. Furthermore, user interface 308 can receive user input, including, for example, manual marking of lesions on preoperative medical images. In some embodiments, user interface 308 is not located on controller 300, but is instead located on a remote external computing device communicatively connected to controller 300 via communication circuitry 304.

[0064] The controller 300 may include memory and / or be coupled via one or more buses to read information from or write information to the memory. The memory 310 may include a processor cache, comprising a multi-level tiered cache, wherein different levels have different capacities and access speeds. The memory 310 may also include random access memory (RAM), other volatile or non-volatile memory devices. The memory 310 may be RAM, ROM, flash memory, EEPROM, other volatile or non-volatile memory devices, or other known memory, or some combination thereof, and preferably includes storage devices in which data can be selectively stored. For example, the storage devices may include, for example, hard disk drives, optical disks, flash memory, and Zip drives. The memory 310 stores program instructions that, when executed by the processor 302, cause the processor 302 and the functional components of the system 10 to provide the functions attributed thereto herein. For example, programmable instructions may be stored on the memory 310 to execute algorithms for calculating target tissue temperature, predicting target tissue ablation volume, and determining target tissue properties (e.g., tissue type).

[0065] Memory 310, as an example of a non-transitory computer-readable medium, can be used to store an operating system (OS) 336, a generator interface module 312, a radiometer interface module 314, a T / R switch interface module 316, a duplexer interface module 318, a feature extraction module 320, a dataset interface module 322, an image receiver module 324, an image segmentation module 326, a tissue property prediction module 328, an ablation volume prediction module 330, a simulation creation module 332, and a superposition generation module 334. The modules are provided in the form of computer-executable instructions, which can be executed by processor 302 to perform various operations according to this disclosure.

[0066] The generator interface module 312, executable by the processor 302, supplies energy, such as microwave energy, to the main antenna of the switch antenna 200 via the cable 20, for example, when the T / R switch 16 is in the ablation state, to be emitted onto the target tissue. As part of a feedback loop, the generator interface module 312 can further continuously modulate the energy level emitted via the main antenna of the switch antenna 200 based on a calculated volumetric temperature of the ablated tissue to ensure that the temperature of the target tissue is maintained within a predetermined threshold.

[0067] The radiometer interface module 314, executable by the processor 302, is configured to receive radiation signals indicating temperature measurements from the switch antenna 200 (e.g., from the main antenna and / or reference terminal) when the T / R switch 16 is in the measurement state, and to receive radiation signals from the radiometer 24. For example, when the switch bias duplexer 18 is in the main antenna state, the radiometer interface module 314 can receive signals indicating the measured radiometer temperature from the main antenna of the switch antenna 200, such as the temperature of tissue adjacent to the switch antenna 200 during ablation procedures, and when the switch bias duplexer 18 is in the reference terminal state, it can receive signals indicating the measured reference temperature from the reference terminal of the switch antenna 200. Therefore, the processor can calculate the volumetric temperature of the ablated tissue based on these signals, as described in U.S. Patent No. 12,064,174.

[0068] Furthermore, the radiometer interface module 314 can initially filter the radiation signal received from the radiometer 24. For example, the radiometer interface module 314 can apply anti-spiking filtering to the radiation signal to remove one or more incorrect points within the radiation signal, and apply smoothing filtering to the radiation signal to generate a smoother signal. For anti-spiking filtering, the radiometer interface module 314 can use a moving minimum or a first derivative-based algorithm. For smoothing filtering, the radiometer interface module 314 can use a Kalman filter, a moving average, or fit the radiation signal to a function of the following form:

[0069]

[0070] As described above, the controller 300 may further receive the temperature of the indicated tissue returned by the thermocouple 210 and / or the voltage of the reference temperature measured by the thermocouple 210 at the switching antenna 200. Therefore, the controller 300 may further include a thermocouple interface module (not shown), which can be executed by the processor 302 to receive the voltages returned by the thermocouple 210 and convert these voltages into temperature values.

[0071] The T / R switch interface module 316, executable by the processor 302, is used to instruct the T / R switch 16 to transition between an ablation state and a measurement state, as described above. For example, in some embodiments, the T / R switch interface module 316 may instruct the T / R switch 16 to be positioned in the ablation state for a significant portion of the ablation cycle (e.g., more than 50%, more than 75%, more than 80%, or preferably more than 90%) to maximize power dissipation. Therefore, the T / R switch interface module 316 may instruct the T / R switch 16 to be positioned in the measurement state for the remaining portion of the ablation cycle (e.g., less than 50%, less than 25%, less than 20%, or preferably less than 10%).

[0072] The duplexer interface module 318, executable by the processor 302, guides the switch bias duplexer 18 to transition between a main antenna state and a reference terminal state, as described above. For example, during the ablation period when the T / R switch 16 is in the measurement state, the duplexer interface module 318 can guide the switch bias duplexer 18 to alternate between being positioned in the main antenna state and being positioned in the reference terminal state. For example, in a one-second cycle, the T / R switch interface module 316 can guide the T / R switch 16 to be positioned in the ablation state for 900 milliseconds, causing the main antenna to emit microwave energy toward the target tissue for 900 milliseconds, and then guide the T / R switch 16 to be positioned in the measurement state for 100 milliseconds. During the 100 milliseconds when the T / R switch 16 is in the measurement state, the duplexer interface module 318 can guide the switch bias duplexer 18 to alternate between the main antenna state and the reference terminal state every, for example, 1, 2, 3, 4, or 5 milliseconds. As will be understood by those skilled in the art, the T / R switch interface module 316 can guide the T / R switch 16 to be positioned in an ablation state for more or less than 900 milliseconds, and the duplexer interface module 318 can guide the switch bias duplexer 18 to alternate between each time period containing any time less than 1 millisecond or greater than 5 milliseconds.

[0073] Feature extraction module 320, executable by processor 302, processes and analyzes radiation signals received from radiometer 24 by radiometer interface module 314, such as filtered radiation signals, to extract one or more features of the radiation signals, including, for example, the area under the temperature curve, the highest tissue temperature, the heat dose at the tissue temperature, the initial slope of the tissue temperature, and / or the average rise in tissue temperature. For example, to calculate the heat dose, feature extraction module 320 may first calculate CEM 43, i.e., the cumulative equivalent minutes at 43°C, and then take the logarithm of CEM 43. CEM 43 can be calculated using the following formula:

[0074]

[0075] Where T is temperature; t is time; if T is less than or equal to 43, then R is 1 / 4, or if T is greater than 43, then R is 1 / 2.

[0076] Furthermore, the feature extraction module 320 can determine the initial slope of the tissue temperature from the initial rise in tissue temperature in response to energy emission from the main antenna of the switching antenna 200 within an initial predetermined time period, for example, within 2 to 15 seconds or preferably 3 seconds after energy is emitted to the target tissue. Alternatively, the feature extraction module 320 can be executed by the processor 302 to process and analyze the temperature measurement obtained by the thermocouple 210, rather than the radiation signal received from the radiometer 24 by the radiometer interface module 314, to extract one or more features of the thermocouple temperature measurement, as described above, such as, for example, the area under the temperature curve, the highest tissue temperature, the heat dose of the tissue temperature, the initial slope of the tissue temperature, and / or the average rise in tissue temperature.

[0077] Dataset interface module 322, executable by processor 302, is used to access one or more datasets stored in memory 310 or remotely stored via communication circuitry system 304. The datasets may contain data generated from previous experiments and / or simulations. For example, the dataset may contain multiple actual ablation volumes for a given thermal dose and / or minor axis value obtained from previous experiments and / or simulations, and trend lines based on the actual ablation volumes and thermal dose / minor axis values ​​and / or initial slopes and corresponding electromagnetic properties of the target tissue, as described in more detail below. Additionally, the dataset may further contain information indicating the temperature of the tissue surrounding the antenna due to energy emitted to it by the antenna, such as radiation signal values ​​and / or thermocouple temperature measurements from previous experiments and / or simulations, and associated average tissue property values ​​for various tissue types, such as the tissue's relative permittivity, conductivity, thermal capacity, etc.

[0078] Image receiver module 324, executable by processor 302, is used to receive medical images, including, for example, CT scan images, CBCT scan images, X-ray-based tomographic images, MRI images, and / or echo B-mode images. For example, image receiver module 324 may receive preoperative images of target tissue within a patient, such as "pre-CT" images, which may include anatomical structures within / near the target tissue, such as airways, blood vessels, etc. Preoperative images may be pre-labeled, for example, before being received by image receiver module 324, or may be manually or automatically labeled by the user to indicate areas of interest, such as lesions of cancerous tissue to be ablated. For example, after image receiver module 324 receives preoperative images, the user may label them via user interface 308. Alternatively or concurrently, preoperative images may be automatically labeled using an automated segmentation algorithm, as described in more detail below.

[0079] Preoperative images of target tissue without an antenna in the appropriate location may have higher quality and make it easier to mark areas of interest. Additionally, the image receiver module 324 can receive medical images of the target tissue taken during the ablation procedure, including the main antenna of the switched antenna 200, such as “per CT” images. The image receiver module 324 can further receive preoperative and postoperative images of the target tissue before and after the ablation procedure, such as those from previous ablation procedures, which can be used to determine the physiological effects of the ablation on the target tissue, such as contraction of the target tissue, as described in more detail below. Those skilled in the art will understand that while “preoperative CT” and “per CT” refer to preoperative CT images and CT images taken during the ablation procedure, respectively, including, for example, images with an antenna, medical images may include medical images other than CT images, as described above.

[0080] Image segmentation module 326, executable by processor 302, is used to automatically segment medical images received by image receiver module 324, such as pre-CT and per-CT images, to classify one or more components and / or anatomical structures in the medical images. For example, image segmentation module 326 can segment and label target tissues, such as target organs, on both pre-CT and per-CT images. As described above, preoperative images of target tissues without antennas in appropriate locations may have higher quality and are easier to label regions of interest; therefore, image segmentation module 326 is preferably capable of executing segmentation algorithms, for example, using... Figure 4 The method 400 shown in the paper only segments and marks the antenna in each CT image.

[0081] like Figure 4 As shown, in step 402, the segmentation algorithm may threshold the medical image using an adaptive threshold. For example, the threshold may be the 99th percentile of the pixel value. The resulting thresholded medical image may be a black and white image. In step 404, the segmentation algorithm may calculate one or more connected components of the thresholded medical image, for example, connected white regions, and discard any connected components smaller than a predetermined size (e.g., less than 1000 voxels). Therefore, the remaining connected components may all be larger than the predetermined size. In step 406, the segmentation algorithm may calculate the straightness index of each of the remaining connected components. For example, for each of the remaining connected components, the segmentation algorithm may select three random points on the connected component, calculate the angle between the three random points, and determine a value based on the additional angle and the minimum of the angles. The segmentation algorithm may repeat these steps multiple times, for example, 200 times, each time producing a corresponding value. As those skilled in the art will understand, the steps may be repeated fewer or more than 200 times.

[0082] Next, the segmentation algorithm calculates the straightness index of each of the connected components as the average of the corresponding determined values. The segmentation algorithm compares the straightness index of each remaining connected component to a predetermined threshold (e.g., 0.4). If no straightness index is below the predetermined threshold, then in step 408, the segmentation algorithm changes the adaptive threshold and returns to step 404 to calculate one or more connected components of the medical image thresholded with the new adaptive threshold. If, in step 406, at least one straightness index is below the predetermined threshold, then in step 410, the segmentation algorithm classifies the connected component with the lowest straightness index as an antenna. Additionally, the segmentation algorithm can label antennas on each CT image. After antenna segmentation, each CT image can be realigned along the antenna's axis to provide a better view of the ablation zone.

[0083] Refer again Figure 3 The image segmentation module 326 can further segment and label one or more anatomical structures present in the medical image, including, for example, airways, blood vessels, bile ducts, etc., which can also be superimposed on each superimposed CT image, as described in more detail below. In addition, the image segmentation module 326 can calculate the surface boundaries and contours of the segmented components and anatomical structures.

[0084] The tissue property prediction module 328, executable by the processor 302, determines one or more properties of the target tissue, such as tissue type, based on received tissue temperature information (e.g., radiation signals received from radiometer 24 and / or temperature measurements received from thermocouple 210). For example, the tissue property prediction module 328 can determine which organ the switching antenna 200 is placed in. Specifically, different tissues may have different electromagnetic properties, including, for example, the tissue's relative permittivity (ε), conductivity (σ), thermal capacity (C), etc., which can cause the corresponding tissue to have different initial slopes for energy emission directed towards it. For example, the liver and lungs may have different combinations of property values. Furthermore, cancerous tissue may have a different combination of electromagnetic properties than healthy tissue.

[0085] Therefore, the tissue property prediction module 328 can determine the type of ablated tissue based on the initial slope extracted from the radiation signal by the feature extraction module 320 and information from the dataset accessed by the dataset interface module 322. For example, the tissue property prediction module 328 can compare the initial slope extracted from the radiation signal with a dataset of initial slope values ​​obtained from previous experiments / simulations to detect the electromagnetic properties of the target tissue and determine the type of target tissue. Figure 5AAs demonstrated, for a calculated initial slope of 1 to 1.6 °C / s at a 45 W power level, the tissue property prediction module 328 can determine that the target tissue is lung tissue based on previous experimental data. Similarly, for a calculated initial slope of 0.4 to 0.6 °C / s at a 45 W power level, the tissue property prediction module 328 can determine that the target tissue is liver tissue based on previous experimental data. The tissue property prediction module 328 can also determine the type of tissue to be ablated based on the initial slope extracted from temperature measurements provided by thermocouple 210.

[0086] Additionally, as described above, the temperature of the tissue heated during ablation for a given patient, such as radiation temperature / thermocouple tissue temperature, can depend on the specific tissue properties of the patient. For example, such as Figure 5B The diagram illustrates the change in the initial slope value extracted from the radiation signal relative to the relative capacitance (ε) of the tissue, demonstrating that changes in tissue property parameters directly affect the initial slope of the radiation signal. Therefore, the tissue property prediction module 328 can further estimate patient-specific tissue property parameters in real time based on the radiation signal measured in real time during the ablation procedure and a dataset of radiation signals obtained from previous experiments / simulations (containing associated average tissue property parameter values ​​for the same tissue type). Examples include the tissue's relative capacitance (ε), conductivity (σ), and thermal capacity (C). For instance, the tissue property prediction module 328 can analyze datasets to find correlations, such as datasets containing radiation signals obtained from previous experiments / simulations that are the same as (or similar to) the real-time radiation signal and corresponding average tissue property parameter values, and use these correlated datasets to estimate patient-specific tissue property parameter values. Patient-specific tissue property parameters calculated using radiation temperature can be averages of the properties of the tissue surrounding the antenna.

[0087] Therefore, based on known types of target tissue and / or patient-specific tissue property parameters, the predicted ablation volume can be further adaptive to account for the influence of the electromagnetic properties of the target tissue on the ablation volume, as described in more detail below. In some embodiments, the tissue property prediction module 328 can similarly estimate patient-specific tissue property parameters in real time, such as the relative capacitance (ε), conductivity (σ), thermal capacity (C), etc., of the tissue, based on tissue temperatures measured in real time by thermocouple 210 during the ablation procedure and a dataset of thermocouple tissue temperatures obtained from previous experiments / simulations (containing associated average tissue property parameter values ​​for the same tissue type). Additionally, the tissue property prediction module 328 can further calculate tissue property parameter values ​​for other anatomical structures (e.g., obtained from image segmentation as described above) near the antenna 200 based on the geometry of other anatomical structures (e.g., obtained from image segmentation as described above) and the estimated patient-specific tissue property parameters of the target tissue. The closer the anatomical structure is to the antenna 200, the greater the visibility of the tissue properties of other anatomical structures in the radiation signal / thermocouple temperature measurement. Therefore, calculated tissue property parameters of other anatomical structures can be used to adapt patient-specific simulations to mimic their behavior during ablation procedures.

[0088] Furthermore, the tissue property prediction module 328 can determine the type of target tissue and / or patient-specific tissue property parameters based on radiation signals / thermocouple temperature measurements obtained during non-destructive / minimally destructive energy emission to the target tissue (e.g., energy emitted to the target tissue at a predetermined power level within a predetermined time period to avoid damage / ablation of the target tissue). Therefore, the generator interface module 312 can be executed by the processor 302 to supply energy, e.g., microwave energy, via cable 20 to the main antenna of the switch antenna 200, for example, when the T / R switch 16 is in the ablation state, to be emitted to the target tissue at a predetermined power level within a predetermined time period. While the power level and duration of the energy emission to the target tissue may not be sufficient to damage / ablate the target tissue, it is sufficient to cause an increase in the temperature of the target tissue, and thus, generate an initial slope for the target tissue. Furthermore, monitoring the initial slope of the target tissue during non-destructive / minimally destructive energy emission to the target tissue can guide clinicians in positioning the antenna within the target tissue. For example, changes in the initial slope when advancing an antenna can indicate changes in the tissue, such as indicating that the antenna is entering a lesion, thereby reducing the planning and positioning procedure time.

[0089] The ablation volume prediction module 330, executable by the processor 302, is used to predict the volume of ablated tissue during an ablation procedure based on one or more features extracted by the feature extraction module 320 from radiation signal / thermocouple temperature measurements and information from a dataset accessed by the dataset interface module 322, in response to energy emission to the target tissue (e.g., via the main antenna of the switching antenna 200). For example, based on a calculated thermal dose extracted from a radiation signal, the ablation volume prediction module 330 can analyze a dataset to find correlations, such as a dataset containing calculated (or similar) thermal doses and corresponding ablation volumes, and use the correlated dataset to predict the ablation volume of the target tissue. Figure 6A The diagram shows that for the calculated thermal dose 5 obtained from the radiation signal, the trend line (R) in the ablation volume and thermal dose graph is used. 2 =0.80), the ablation volume prediction module 330 can predict an ablation volume of 4.1 cm. 3 Furthermore, the ablation volume prediction module 330 can further predict the ablation volume based at least on the power level of the ablation energy. For example... Figure 6B The diagram shows that for the calculated maximum tissue temperature (e.g., Max T antenna) of 47.2°C obtained from thermocouple temperature measurements, the trend line (R) in the ablation volume and thermal dose graph is used. 2 =0.87), the ablation volume prediction module 330 can predict an ablation volume of 12 cm. 3 Used for filling. Figure 6B The data for the “True vs. Predicted Ablation Volume” graph were derived from the experimental data depicted in Table 1, which is copied below.

[0090] Table 1

[0091]

[0092] Refer again Figure 3 The ablation volume prediction module 330 can predict the size of the predicted ablation volume. For example, assuming the ablation volume has an elliptical shape with two equal minor axes and a third axis longer than the minor axes, the ablation volume prediction module 330 can predict the length of the minor axis and the length of the major axis. Figure 7AAs shown, during ablation, the major axis L of the elliptical predicted ablation volume PV can be parallel to the longitudinal axis of the switching antenna 200 within the predicted ablation volume PV, and therefore, the minor axis D of the elliptical predicted ablation volume PV can be perpendicular to the longitudinal axis of the switching antenna 200. The ablation volume prediction module 330 can predict the minor axis of the ablation volume based on one or more features extracted by the feature extraction module 320 from radiation signal / thermocouple temperature measurements and information from a dataset accessed by the dataset interface module 322. For example, based on the calculated thermal dose extracted from the radiation signal, the ablation volume prediction module 330 can analyze the dataset to find correlations, such as a dataset containing calculated (or similar) thermal doses and corresponding minor axis values, and use the correlated dataset to predict the minor axis of the elliptical ablation volume of the target tissue. Figure 7B The diagram shows that for the calculated heat dose (i.e., Log10(CEM43)) 6, the trend line (R) in the Log10(CEM43) graph is based on the real minor axis. 2 =0.69), the ablation volume prediction module 330 can predict the short axis of 1.8cm.

[0093] Refer again Figure 3 Alternatively, the ablation volume prediction module 330 can predict the minor and major axes of the ablation volume based on the predicted ablation volume and aspect ratio described above. For example, the volume of an ellipsoid can be calculated as follows:

[0094]

[0095] In addition, aspect ratio It is more or less constant. Therefore, the ablation volume prediction module 330 can use the aspect ratio and the predicted ablation volume to predict the minor and major axes of the ablation volume. By estimating the size of the predicted ablation volume and the position of the antenna relative to the target tissue in real time, the predicted ablation volume can be displayed as a superposition on each CT image and can grow symmetrically in each direction over time during the ablation procedure.

[0096] The ablation volume prediction module 330 can further adjust the predicted ablation volume to take into account factors such as the presence of surrounding anatomical structures and their impact on target tissue ablation, and the target tissue boundary / contour calculated by the image segmentation module 326. For example, the presence of detected blood vessels near the ablated target tissue can cool the target tissue, thereby affecting the temperature volume of the target tissue and correspondingly influencing the radiation signal and the predicted ablation volume. Furthermore, since tissue cannot be ablated beyond its boundaries, the ablation volume prediction module 330 can adjust the shape of the predicted ablation volume to fit the tissue boundary. For example, Figure 8AThe illustration describes an exemplary predicted ablation volume PV with an elliptical shape having a minor axis SA, anticipated based on the position of the switch antenna 200 within the target tissue T. However, this predicted ablation volume shape is impossible due to the surface boundary SB of the target tissue T. Therefore, the ablation volume prediction module 330 can adjust the shape of the predicted ablation volume to an adaptive predicted ablation volume APV to take into account the surface boundary SB of the target tissue T, such as... Figure 8B Displayed in [the text]. For example... Figure 8B The paper demonstrates that adaptive predicted ablation volume (APV) can have the same characteristics as... Figure 8A The predicted ablation volume (PV) has the same short-axis SA value. Furthermore, the ablation volume prediction module 330 can adjust the shape of the predicted ablation volume based on the segmentation of anatomical structures to account for the presence of anatomical structures within / near the target tissue. For example, the adaptive growth of the predicted ablation volume can be limited to within the target tissue and around anatomical structures. Therefore, the ablation volume prediction module 330 can use the antenna location, the boundary of the target tissue / organ, and segmentation data of adjacent anatomical structures as input to predict the adaptive ablation volume. Additionally, the growth of the adaptive predicted ablation volume can be guided by results obtained from previous experiments / simulations. Alternatively or additionally, the growth of the adaptive predicted ablation volume can be determined at least in part based on a patient-specific simulation created in real time based on the radiation signal, as described in more detail below.

[0097] The simulation creation module 332, executable by the processor 302, is used to create a patient-specific simulation in which the predicted ablation tissue volume increases in response to the energy emitted towards the target tissue during the simulated ablation procedure. Specifically, such as... Figure 9 As shown, the simulation creation module 332 can generate a "digital twin," such as a 3D reconstruction, of the patient-specific target tissue T and an antenna (e.g., antenna 200), based on segmented image data of the patient-specific target tissue T. For example, medical images of the patient-specific target tissue, such as pre-CT and post-CT scan images, can be automatically segmented using the segmentation algorithm described above to classify / label the target tissue (e.g., the patient's liver) and anatomical structures (e.g., blood vessels around and / or within the liver) within the medical images. However, since segmented image data may often be incompatible with simulation software (e.g., COMSOL Multiphysics (provided by COMSOL AG, Stockholm, Sweden)), the simulation creation module 332 can preprocess the segmented image data to ensure compatibility with the simulation software.

[0098] For example, because the segmented volume of the target tissue (e.g., a patient's liver) in the segmented image data may be unnecessarily large—for example, much larger than the potential ablation zone produced by the ablation procedure—may consist of several anatomical components and may have an irregular surface, the simulation creation module 332 can trim a predetermined volume of the segmented target tissue around the antenna and smooth the edges of the trimmed volume, such as... Figures 10A to 10D The display is designed to avoid simulating more points than necessary. Figure 10A This describes segmented image data generated from each CT scan of a patient-specific target tissue T (e.g., the patient's liver), in which the entire liver and portions of the antenna 200 placed within the liver are marked in the medical image.

[0099] like Figure 10B As shown, the simulation creation module 332 can trim a predetermined volume of liver around antenna 200, for example, the intersection of the liver and a cylinder with a predetermined radius aligned with the longitudinal axis of antenna 200. For example, the cylinder may have a radius of 30 mm, such that the volume of the trimmed liver is larger than the potentially maximum predicted ablation volume. Additionally, as described above, the segmented image data may contain several components, including, for example, the target trimmed volume and one or more small segmentation islands SI, such as... Figure 10C As shown in the diagram. Therefore, the simulation creation module 332 can calculate one or more connected components of the trimmed volume, determine the size of the connected components, and discard any connected components smaller than a predetermined size, such as small split islands SI. The remaining connected components with sizes larger than the predetermined size can then be smoothed, such as... Figure 10D As shown in the diagram. For example, the simulation creation module 332 can apply a smoothing filter, such as a Gaussian filter with a standard deviation of 3 mm, to the remaining connected components to smooth the irregular surface of the trimmed volume. Preferably, the target tissue is trimmed first and then smoothed to ensure that the edges of the trimmed volume as a result are also smoothed.

[0100] Additionally, the simulation creation module 332 can also trim and smooth other anatomical structures within the segmented image, including, for example, blood vessels within the liver. Smoothing segmented blood vessels is generally more difficult than smoothing segmented liver, and when combined with trimmed and smoothed liver segmentation, the resulting trimmed and smoothed blood vessels should not form complex geometries. Furthermore, the presence of the antenna 200 in each CT scan can cause artifacts in each CT scan, making it virtually impossible to reliably segment blood vessels in each CT scan. Therefore, the simulation creation module 332 can first register blood vessels from the pre-CT scan to each CT scan. For example, the simulation creation module 332 can create a first custom volume for the pre-CT scan and a second custom volume for each CT scan by converting the liver segmentation in the pre-CT scan and each CT scan into binary masks (e.g., where voxels outside the liver have a value of 0 and voxels inside the liver have a value of 1). The registration of the custom volumes for the pre-CT scan and each CT scan can be calculated using B-spline transformation. Therefore, the location of blood vessels can be registered on each CT scan based on the location of blood vessels in the pre-CT scan and the displacement of liver voxels from the pre-CT scan volume to the volume of each CT scan.

[0101] After registering blood vessels on each CT scan, the simulation creation module 332 can similarly crop a predetermined volume of blood vessels around the antenna 200, for example, the intersection of the blood vessel with a cylinder having a predetermined radius (e.g., 25 mm) aligned with the longitudinal axis of the antenna 200 and preferably smaller than the predetermined radius of the cylinder used to crop the liver, to ensure that there are no problems with the liver at the boundaries of the cropped volume of blood vessels. Specifically, if the space between the edge of the cropped liver volume and the edge of the cropped blood vessel volume is too small, it may cause problems in the simulation software. After obtaining the target cropped volume of blood vessels, the simulation creation module 332 can then smooth the cropped blood vessel volume. For example, the simulation creation module 332 can resample the cropped blood vessel segmentation to have an equidistant spacing of, for example, 0.5 mm, apply a morphological closing operation with a kernel of, for example, 3 mm, resample the cropped blood vessel segmentation to have an equidistant distance of, for example, 0.1 mm, and apply a Gaussian filter with parameters of, for example, 0.4 mm. Resampling the segmented data can improve filtering. Furthermore, the simulation creation module 332 can similarly remove small islands in the vascular segmentation, for example, by calculating the size of all connected components of the vascular segmentation, and discard any connected components smaller than a predetermined size (e.g., less than 250 voxels). Therefore, the cropped and smoothed volumes of the liver and blood vessels can be combined to form a 3D volume of the target tissue around the antenna for patient-specific simulation. As those skilled in the art will understand, the simulation creation module 332 can crop and smooth other anatomical structures adjacent to the target tissue (e.g., the liver) within the segmented image, including, for example, airways, cancerous tissue, etc.

[0102] Furthermore, since ablated tissue may contract during the ablation procedure—for example, the tissue may "burn" due to ablation—this contraction causes movement within the ablation zone, meaning that the predicted ablation volume may be underestimated if contraction is not taken into account. Therefore, the simulation creation module 332 can measure the contraction of the target tissue as a result of the ablation procedure, such as... Figures 11A to 11D The simulation creation module 332 can calculate contraction from the registration between a preoperative scan of the target tissue before ablation and a postoperative scan of the same target tissue after ablation. Firstly, for example, the segmentation algorithm described above is used to segment the preoperative and postoperative scans to classify / label the liver and blood vessels in the medical images. For example, Figure 11A This indicates a preoperative scan following segmentation.

[0103] Preferably, the volumes of the preoperative and postoperative scans are registered via a variant of label-based registration rather than intensity-based registration. For example, the simulation creation module 332 can create a first custom volume for the preoperative scan and a second custom volume for the postoperative scan, respectively, by converting liver and blood segments from the preoperative and postoperative scans into binary masks, where the custom volume is defined as:

[0104]

[0105] Voxels outside the liver and blood vessels have a value of 0, voxels inside the liver but outside the blood vessels have a value of 1, voxels inside the blood vessels but outside the liver have a value of 2, and voxels inside the liver and blood vessels have a value of 3. Figure 11B It is displayed in the middle.

[0106] Registration of custom volumes between preoperative and postoperative scans can be calculated using B-spline transformation, such as... Figure 11C As shown in the diagram, the contraction can be calculated by forcing the displacement of the voxel to be zero at the location of the radiating element (e.g., antenna 200), as... Figure 11D The displacement of the voxel is forced to be zero at antenna 200 to account for patient displacement between different scans. The position of antenna 200 can be determined based on antenna segmentation, as described above. Therefore, the simulation creation module 332 can create patient-specific simulations that take into account the contraction of the target tissue caused by the ablation procedure, as well as the influence of tissue boundaries, the nature of tissue around the antenna, and surrounding anatomy, thereby enhancing the prediction of the actual ablation volume. The patient-specific simulated contracted ablation zone can also be displayed to the user.

[0107] Figure 12A This describes an exemplary graphical user interface (GUI) for real-time display of adaptive, predicted ablation volume during liver tissue ablation, e.g., User Interface 308. Figure 12AAs shown, the graphical user interface can display various views of the target tissue, such as axial, sagittal, coronal, and 3D views, including labeled antennas, labeled target tissue, labeled lesions, and labeled predicted ablation volumes. Furthermore, the user interface can display additional information, including, for example, radiation signals, predicted ablation volume values, calculated dimensions of the predicted ablation volume, ablation time, and power levels of the ablation energy. As described above, the ablation volume prediction module 330 can use a physics-based model to simulate adaptive growth of the predicted ablation volume. This physics-based model uses a 3D model of the antenna, tissue / organ segmentation and ablation parameters, and anatomical structure segmentation as input, and can be used as follows: Figure 12B As shown in the image.

[0108] Figure 12B This describes the directional growth of the adaptive predicted ablation volume over time compared to the actual ablation volume (e.g., the true ablation volume TAV generated based on post-CT images). For example, in the liver, contrast-enhanced CT can provide information about the true ablation volume TAV, which can be displayed as a superposition of the adaptive predicted ablation volume APV to facilitate validation of the accuracy of the adaptive predicted ablation volume APV. Figure 12B As shown, the growth of the true ablation volume TAV may be asymmetrical with respect to the switch antenna 200 within the lesion L because the boundaries of the tissue T (e.g., liver) restrict growth in one direction. For example, the boundaries of the tissue T cause the true ablation volume TAV to grow more on the left side, which is accurately captured by the adaptively predicted ablation volume APV, such as... Figure 12B The results demonstrate the accuracy of the adaptive predicted ablation volume (APV).

[0109] As described above, additional segmented anatomical structures, such as vessels cooling adjacent tissues, will further affect the asymmetric shape of the adaptive predicted ablation volume (APV). As will be understood by those skilled in the art, the predicted ablation volume does not need to be calculated before the adaptive predicted ablation volume. For example, the adaptive predicted ablation volume and the predicted ablation volume may be calculated simultaneously, and / or the adaptive predicted ablation volume may be calculated before the predicted ablation volume.

[0110] Refer again Figure 3The overlay generation module 334, executable by the processor 302, generates an overlay image for display to provide feedback and guide the user during the ablation procedure. As described above, the lesion is marked on the pre-CT image, and the antenna is marked on each CT image. The image segmentation module 326 segments and marks the target tissue, such as the target organ, on both the pre-CT and each CT image, allowing the overlay generation module 334 to then execute a registration toolbox to register each CT image with the pre-CT image based on the segmented target tissue in both the each CT image and the pre-CT image. Once registration is complete, the overlay generation module 334 can then overlay the marked lesion from the pre-CT image onto each CT image, such that the overlay pre-CT image includes the marked antenna, the marked target tissue, and the marked lesion.

[0111] Furthermore, the overlay generation module 334 can further, for example, overlay each CT image with the predicted ablation volume in real time based on the calculated size of the predicted ablation volume, such as... Figure 13 It is displayed in the middle. Figure 13 The demonstration displays an exemplary graphical user interface, such as user interface 308, showing various views (e.g., axial, sagittal, coronal, YZ views) of the target tissue, including the labeled antenna, labeled target tissue, labeled lesion, and the labeled predicted ablation volume. Furthermore, the user interface can display additional information, including, for example, 3D views, radiation signals, values ​​of the predicted ablation volume, the calculated dimensions of the predicted ablation volume, ablation time, and the power level of the ablation energy.

[0112] Now for reference Figure 14 A flowchart outlining an exemplary method 1400 for adaptively predicting the ablation volume of a target tissue according to the principles of this disclosure is provided. Steps 1402 to 1410 may be used to predict the size of the predicted ablation volume of the target tissue based on radiation signals received from radiometer 24 and / or temperature measurements provided by thermocouple 210, as well as relevant datasets from previous experimental / simulation results, as described above. For example, in step 1402, for instance, when T / R switch 16 is in the measurement state causing radiometer 24 to receive temperature measurements from switch antenna 200 (e.g., from the main antenna when switch bias duplexer 18 is in the main antenna state and / or from the reference terminal when switch bias duplexer 18 is in the reference terminal state), controller 300 may receive radiation signals from radiometer 24. As described above, at least one of an anti-spiking filter or a smoothing filter may be used to filter the radiation signals. Alternatively, in step 1402, the controller 300 may receive voltages from the thermocouple 210 indicating the temperature of the tissue surrounding the antenna and convert these voltages into temperature values.

[0113] In step 1404, controller 300 may extract one or more features of the radiation signal / thermocouple tissue temperature, such as the area under the temperature curve, maximum temperature, heat dose, initial slope, average temperature rise, etc. Furthermore, in step 1406, controller 300 may access a database of results datasets from previous experiments / simulations, and in step 1408, controller 300 may analyze the dataset to find correlations with one or more extracted features, such as a related dataset with a predicted ablation volume for a given heat dose value and / or a minor axis value for a given heat dose. In step 1410, controller 300 may use information derived from the related dataset (e.g., trend lines) to predict the size of the predicted ablation volume. Alternatively or additionally, controller 300 may predict the size of the predicted ablation volume based on a patient-specific simulation created in real time during the ablation procedure, as described above. Steps 1406 and 1408 may be pre-calculated, while steps 1402, 1404, and 1410 may be performed in real time.

[0114] Furthermore, based on the predicted ablation volume size obtained in step 1410, steps 1412 to 1416 can be used to calculate an anatomically correct prediction, for example, to account for the presence of target tissue boundaries and / or anatomical structures such as airways, blood vessels, bile ducts, etc., as described above. For example, in step 1412, controller 300 may receive a medical image of the target tissue, and in step 1414, controller 300 may execute one or more segmentation algorithms to automatically segment the target tissue and anatomical structures within the medical image. In step 1416, controller 300 may predict an adaptive ablation volume of the target tissue that takes into account the segmented anatomical structures, which may then be displayed as a superposition on a medical image including labeled target tissue, labeled lesions, labeled antennas, and labeled anatomical structures. Furthermore, as described above, controller 300 may predict the adaptive ablation volume of the target tissue at least in part based on patient-specific tissue property parameters estimated from radiation signals / thermocouple tissue temperatures and a relevant dataset containing corresponding average tissue property parameter values, as described above. Steps 1412 and 1414 can be performed before the ablation procedure, while steps 1410 and 1416 can be performed in real time.

[0115] Now for reference Figure 15A and 15B This provides an exemplary robotic navigation system for delivering a switched antenna 200 to a target tissue. The robotic navigation system 1500 can be used with the Galaxy System. TM (Available from Noah Medical in San Carlos, California), which features a delivery catheter 1502 configured to navigate through the patient's anatomy to target tissue (e.g., lung tissue). Figure 15BAs shown, the delivery catheter 1502 may include an endoscope 1504 configured to generate video data and a lumen 1506 sized and shaped to receive catheters (e.g., switch antenna 200 and cable 20) of system 10. Therefore, the switch antenna 200 can be delivered via the lumen 1506 of the delivery catheter 1502 through the robot navigation system 1500 to perform ablation procedures and measure the temperature of target tissue, as described above.

[0116] While various illustrative embodiments of the invention have been described above, those skilled in the art will understand that various changes and modifications can be made thereto without departing from the invention. The appended claims are intended to cover all such changes and modifications that fall within the true scope of the invention.

Claims

1. A system for predicting the ablation volume of tissue, the system comprising a controller having instructions that, when executed by one or more processors of the controller, cause the controller to: Receive information indicating the temperature of the tissue being ablated via the antenna; Extract one or more features of the temperature of the tissue from the information, the one or more features including at least one of the area under the curve of the temperature of the tissue, the highest temperature of the tissue, the heat dose of the temperature of the tissue, the initial slope of the temperature of the tissue, or the average temperature rise of the tissue; and An ablation volume prediction algorithm is executed to predict the ablation volume of the tissue based on one or more extracted features and a trend line derived from a related dataset of ablation volumes associated with the one or more extracted features.

2. The system of claim 1, wherein the information indicating the temperature of the tissue being ablated via the antenna comprises a radiation signal generated by the antenna.

3. The system of claim 2, wherein the system is configured to use an anti-spiking filter on the radiated signal to remove one or more incorrect points within the radiated signal, the anti-spiking filter comprising at least one of a moving minimum or a first derivative-based algorithm.

4. The system of claim 2 or 3, wherein the system is configured to use a smoothing filter on the radiated signal to generate a smoother signal, the smoothing filter comprising at least one of a Kalman filter or a moving average.

5. The system according to any one of claims 2 to 4, wherein the system is configured to detect an uncontrolled rise in the temperature of the tissue based on the radiation signal.

6. The system according to any one of claims 2 to 5, wherein the system is configured to detect the presence of a heat sink based on the radiation signal and the simulation result dataset.

7. The system according to any of the preceding claims, wherein the information indicating the temperature of the tissue being ablated via the antenna includes voltage returned by a thermocouple disposed on the outer surface of the antenna.

8. The system according to any of the preceding claims, wherein the system is configured to take the logarithm of the cumulative equivalent minutes at 43°C to extract the thermal dose of the tissue.

9. The system according to any of the preceding claims, wherein the system is configured to calculate the minor and major axes of an elliptical ablation volume corresponding to the predicted ablation volume of the tissue, the major axis being parallel to the longitudinal axis of the antenna.

10. The system of claim 9, wherein the system is configured to calculate the minor axis of the elliptical ablation volume based on the extracted thermal dose and a trend line derived from a relevant dataset of the minor axis associated with the extracted thermal dose.

11. The system of claim 9, wherein the system is configured to calculate the minor axis and the major axis of the elliptical ablation volume based on the aspect ratio of the predicted ablation volume of the tissue.

12. The system according to any one of the preceding claims, wherein the system is configured to: The extracted initial slope of the temperature of the tissue is compared with a dataset of initial slope values ​​and associated electromagnetic tissue properties to determine one or more electromagnetic properties of the tissue; and The type of the organization is determined based on one or more electromagnetic properties of the organization.

13. The system of claim 12, wherein the system is configured to determine whether the tissue is healthy or cancerous based on the determined one or more electromagnetic properties of the tissue.

14. The system of claim 12 or 13, wherein the system is configured to: The antenna emits energy at a predetermined level for a predetermined time period, where the predetermined level and the predetermined time period are insufficient to damage the tissue. The initial slope of the temperature of the tissue is extracted from the information received in response to the energy emitted to the tissue at the predetermined level during the predetermined time period.

15. The system according to any one of claims 12 to 14, wherein the system is configured to: Based on the information indicating the temperature of the tissue being ablated and a relevant dataset of tissue temperature and corresponding average tissue property parameter values, one or more tissue property parameters of the tissue are estimated; and The predicted ablation volume of the tissue is adjusted based on one or more tissue property parameters.

16. The system according to any of the preceding claims, wherein the system is configured to determine at least one of the water content of the tissue or the physical properties of the surrounding tissue based on the extracted initial slope at the temperature of the tissue.

17. The system according to any of the preceding claims, wherein the system is configured such that a display shows the predicted ablation volume of the tissue.

18. The system of claim 17, wherein the system is configured to: Receive medical images including the tissue and the antenna; Perform a segmentation algorithm to segment the tissue and the antenna in the medical image; Mark the segmented tissue and antenna on the medical image; and The display shows the predicted ablation volume of the tissue superimposed on the labeled medical image, which includes the labeled segmented tissue and the antenna.

19. The system of claim 18, wherein the medical images include CT scan images, CBCT scan images, X-ray-based tomographic composite images, MRI images, or echo B-mode images.

20. The system of claim 18 or 19, wherein the system is configured to: Receive preoperative medical images including the tissue, the preoperative medical images including labeled lesions; Execute a segmentation algorithm to segment the tissue in the preoperative medical image; The registration toolkit is used to register the labeled medical image and the preoperative medical image based on the segmented tissue in the labeled medical image and the preoperative medical image. and The labeled lesions are superimposed on the registered labeled medical image. The predicted ablation volume of the tissue is superimposed on the registered labeled medical image including the labeled lesion.

21. The system according to any one of claims 18 to 20, wherein the medical image comprises one or more anatomical structures, and wherein the system is configured to: Perform a segmentation algorithm to segment the one or more anatomical structures in the medical image; and Mark the segmented one or more anatomical structures on the medical image. The predicted ablation volume of the tissue is superimposed on the labeled medical image, which includes the labeled segmented tissue, antenna, and one or more anatomical structures.

22. The system of claim 21, wherein the system is configured to: Determine the boundaries of the tissue based on the segmented tissue; and The shape of the predicted ablation volume of the tissue is determined based on the tissue's boundaries, the location of the segmented antenna, the location of the segmented one or more anatomical structures, and a dataset of simulation results. The predicted ablation volume of the tissue mentioned herein includes the determined shape.

23. The system according to claim 21 or 22, wherein the one or more anatomical structures include at least one of the airway, blood vessel or bile duct.

24. The system according to any one of claims 18 to 23, wherein the segmentation algorithm is configured to: The medical image is thresholded using an adaptive threshold. Calculate one or more connected components of the thresholded medical image; Discard any one of the one or more connection components that is smaller than the predetermined size; Calculate the straightness index of each of the remaining one or more connection components; and The connection component with the lowest straightness index is classified as the antenna.

25. The system of claim 24, wherein the segmentation algorithm is configured to: (a) Select three random points on each of the remaining one or more connected components; (b) Calculate the angle between the three random points of each of the remaining one or more connected components; (c) Determine the value based on the minimum of the angles of the additional angle and each of the remaining one or more connected components; (d) Repeat (a) to (c) multiple times; and (e) The straightness index of each of the remaining one or more connection components is calculated as the average of the determined values.

26. The system according to any one of claims 17 to 25, wherein the system is configured to create a patient-specific simulation simulating the growth of the predicted ablation volume of the tissue over time.

27. The system of claim 26, wherein the system is configured to: The contraction of the tissue is calculated based on the registration of preoperative and postoperative scans; and The patient-specific simulation is adapted based on the contraction of the tissue.

28. The system of claim 27, wherein the system is configured to: Execute a segmentation algorithm to segment the tissue and one or more anatomical structures within the preoperative and postoperative scans; The segmented tissue and one or more anatomical structures in the preoperative and postoperative scans are converted into binary masks to create custom volumes of the preoperative and postoperative scans; Register the custom volume from the preoperative scan with the custom volume from the postoperative scan; and The displacement of the voxel at the antenna is forced to be 0 in order to calculate the contraction of the tissue.

29. The system according to any one of claims 26 to 28, wherein the system is configured to: Receive medical images including the tissue, one or more anatomical structures within the tissue, and the antenna; Perform a segmentation algorithm to segment the tissue, the one or more anatomical structures, and the antenna in the medical image; Based on the position of the antenna within the segmented medical image, a predetermined volume of the tissue and one or more anatomical structures is cropped from the segmented medical image. and Smooth the trimmed volume of the tissue and the one or more anatomical structures. The patient-specific simulation is created based on the trimmed and smoothed volume of the tissue and the one or more anatomical structures.

30. The system of claim 29, wherein the system is configured to: Calculate one or more connective components of the trimmed volume of the tissue and the one or more anatomical structures; and Discard any one of the one or more connection components that is smaller than the predetermined size. The trimmed and smoothed volume of the tissue and the one or more anatomical structures includes only the one or more connected components that are larger than the predetermined size.

31. The system of claim 29 or 30, wherein the one or more anatomical structures include one or more blood vessels, and wherein the medical images include preoperative medical images containing the tissue and the one or more blood vessels and per-operative medical images acquired during the ablation procedure and including the tissue and the antenna, the system being further configured to: The one or more blood vessels from the preoperative medical images are registered to each surgical medical image to crop the predetermined volume of the blood vessel based on the location of the antenna. The predetermined cut volume of the blood vessel is smaller than the predetermined cut volume of the tissue.

32. The system according to any one of claims 26 to 31, wherein the system is configured to determine the shape of the predicted ablation volume of the tissue based at least in part on the patient-specific simulation.

33. The system according to any of the preceding claims, wherein the ablation volume prediction algorithm is configured to predict the ablation volume of the tissue based on the power level of the energy used to ablate the tissue.

34. A system for determining an organization type, the system comprising a controller having instructions that, when executed by one or more processors of the controller, cause the controller to: Receives radiation signals indicating the temperature of tissues that receive energy via an antenna; The initial slope of the temperature of the tissue is extracted from the radiation signal; The extracted initial slope of the temperature of the tissue is compared with a dataset of initial slope values ​​and associated electromagnetic tissue properties to determine one or more electromagnetic properties of the tissue; and The type of the organization is determined based on one or more electromagnetic properties of the organization.

35. The system of claim 34, wherein the system is configured to determine whether the tissue is healthy or cancerous based on the determined one or more electromagnetic properties of the tissue.

36. The system of claim 34 or 35, wherein the system is configured to: The antenna emits energy at a predetermined level for a predetermined time period, where the predetermined level and the predetermined time period are insufficient to damage the tissue. The initial slope of the temperature of the tissue is extracted from the radiation signal received in response to the energy emitted to the tissue at the predetermined level during the predetermined time period.

Images