US-12622753-B2 - Method for tracking a medical tool during a medical procedure using deep learning

US12622753B2US 12622753 B2US12622753 B2US 12622753B2US-12622753-B2

Abstract

Provided is a method for tracking a medical tool inside a subject's body during a medical procedure including receiving one or more signals from an array of magnetic sensors detecting a change in magnetic field generated by a magnetic element coupled to the medical tool, applying the received one or more signals to a deep learning algorithm, and determining, using the deep learning algorithm, the spatial location and/or orientation of the medical tool in relation to the array of sensors and/or within the body of the subject.

Inventors

Daniel Messinger

Assignees

Epidutech Ltd.

Dates

Publication Date: 20260512
Application Date: 20220104

Claims (20)

1 . A method for tracking a medical tool during a medical procedure, the method comprising: providing a tracking system comprising a medical tool comprising a magnetic element; and an array of magnetic sensors; wherein the array of magnetic sensors is configured to detect a change in a magnetic field generated by movement of the magnetic element within the body; and determining, utilizing a processor, the spatial location and/or orientation of the medical tool within a body of a subject, based on one or more deep learning algorithms trained on a database comprising signal sets corresponding to known and predicted coordinates, the deep learning algorithms correlating the change of the magnetic field with spatial location and/or orientation of the magnetic element.
2 . The method according to claim 1 , wherein determining the spatial location and/or orientation of the medical tool comprises compensating for a dimension of the medical tool in relation to the location of the magnetic element in relation to the medical tool.
3 . The method according to claim 1 , wherein the array of magnetic sensors is configured in a cartesian, radial, or cylindrical coordinate system.
4 . The method according to claim 1 , wherein the array of magnetic sensors is configured to wirelessly associate with the magnetic element and/or the medical tool.
5 . The method according to claim 1 , wherein determining the spatial location and/or orientation of the medical tool comprises compensating for variations in the magnetic field associated with one or more of a type of tissue, a type of procedure, a type of medical tool, and characteristics of the subject.
6 . The method according to claim 1 , further comprising registering the determined spatial location and/or orientation of the medical tool within the body to a scan of the subject.
7 . The method according to claim 1 , wherein the processor is configured to train the deep learning algorithm on a training set comprising a database associated with the changes of the magnetic field due to a change of one or more coordinates of the magnetic element.
8 . The method according to claim 7 , wherein the database comprises data obtained by receiving one or more signals associated with a change of the magnetic field generated by a change in the spatial location and/or orientation of the magnetic element between a plurality of pairs of coordinates; and/or wherein the database comprises data sets obtained using the array of magnetic sensors, and wherein each of the data sets comprises three signals from each individual sensor of the array of magnetic sensors for each change in spatial location or orientation of the magnetic element.
9 . The method according to claim 7 , wherein a change in the spatial location and/or orientation of the magnetic element comprises a translation of the magnetic element in one or more axes at a specified distance.
10 . The method according to claim 7 , wherein a change in the spatial location and/or orientation of the magnetic element comprises a rotation of the magnetic element at a specified degree of rotation.
11 . The method according claim 10 , wherein the rotation of the magnetic element comprises rotation about at least one of a longitudinal axis of the magnetic element, a lateral axis of the magnetic element, and a vertical axis of the magnetic element.
12 . The method according to claim 7 , wherein the database is generated by: providing the tracking system comprising the magnetic element and the array of magnetic sensors; positioning the magnetic element at a sample set of coordinates; receiving one or more signals associated with each coordinate of the sample set of coordinates of the magnetic element; and calculating a plurality of predicted signals for a predicted set of coordinates of the magnetic element, based, at least in part, on the received signals associated with the sample set of coordinates, wherein the coordinates of the predicted set of coordinates are different from coordinates of the sample set of coordinates.
13 . The method according to claim 12 , wherein the sample set of coordinates comprises a plurality of different spatial locations and/or plurality of orientations of the magnetic element in relation to the array of magnetic sensors; and/or wherein the predicted set of coordinates comprises a plurality of spatial locations and/or plurality of orientations of the magnetic element in relation to the array.
14 . The method according to claim 12 , wherein the sample set of coordinates comprises a plurality of coordinates with a same x-axis value and a same y-axis value, wherein the z-axis value of two or more different coordinates in the sample set of coordinates is different; and/or wherein the sample set of coordinates comprises a plurality of coordinates having a same x-axis value, a same y-axis value, a same z-axis value, and a different orientation or different degree of rotation in relation to the array of magnetic sensors.
15 . The method according to claim 12 , wherein the deep learning algorithm is further configured to determine the spatial location and/or orientation of a plurality of medical tools within the body.
16 . A system for tracking a medical tool during a medical procedure, the system comprising: a tracking system comprising: a magnetic element configured to be placed onto a remote controlled medical tool, and an array of magnetic sensors, wherein the array of magnetic sensors is configured to detect a change in a magnetic field generated by movement of the magnetic element; and a processor configured to receive the detected change in the magnetic field and determine the spatial location and/or orientation of the medical tool, based on one or more deep learning algorithms trained on a database comprising signal sets corresponding to known and predicted coordinates, said deep learning algorithm(s) correlating the change of the magnetic field with spatial location and/or orientation of the magnetic element.
17 . A method for operating a remote medical tool, the method comprising: providing a magnetic element and an array of magnetic sensors, wherein the array of magnetic sensors is configured to detect a change in a magnetic field generated by a movement of the magnetic element; detecting, utilizing a processor, the change in the magnetic field and determining the spatial location and/or orientation of the magnetic element, based on one or more deep learning algorithm trained on a database comprising signal sets corresponding to known and predicted coordinates, said deep learning algorithms correlating the change of the magnetic field with spatial location and/or orientation of the magnetic element; and translating the movement of the magnetic element into a command for a remote medical tool, based, at least in part, on the determined spatial location and/or orientation of the magnetic element.
18 . The method according to claim 17 , wherein the remote medical tool comprises a motor configured to receive the command from the processor and operate the remote medical tool.
19 . The method according to claim 17 , further comprising generating a simulation of a medical operation, wherein the remote medical tool is a simulated medical tool in the simulation of a medical operation, and wherein translating the movement of the magnetic element into a command comprises displaying the movement of the simulated medical tool in the simulated medical operation.
20 . The method according to claim 17 , wherein translating the movement of the magnetic element into a command further comprises adjusting the proportion between the movement of the magnetic element and the command such that movement of the remote medical tool may be proportionately smaller or larger than the movement of the magnetic element.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application is a National Phase of PCT Patent Application No. PCT/IL2022/050011 having International filing date of Jan. 4, 2022, which claims the benefit of priority of U.S. Provisional Patent Application No. 63/139,955, filed Jan. 21, 2021, the contents of which are all incorporated herein by reference in their entirety. FIELD OF THE INVENTION The present invention, in some embodiments thereof, relates to tracking methods for tracking of medical tools during a surgical procedure using deep learning, and, more particularly, but not exclusively, to magnetic tracking methods including a magnetic element and an array of magnetic sensors. BACKGROUND In certain cases of minimal invasive surgery, the surgical procedure is performed by inserting a medical device into the body through a small cut in the skin of the subject. The target region of the surgery can therefore be difficult to access and may be blocked from the visual field of the physician performing the surgery. Systems for tracking of medical tools within the body during operation usually include one or more sensors configured to measure a distance from the medical tool. Thus, techniques for determining the position of the medical tool during operations have a limited accuracy due to the limitations of the resolution of signals received from the sensors as well as the accuracy of the mathematical formulas used in the calculation. Thus, there is a need in the art for improved tracking systems and methods that can allow an accurate, reliable detection and tracking of medical tools during a surgical procedure. The foregoing examples of the related art and limitations related therewith are intended to be illustrative and not exclusive. Other limitations of the related art will become apparent to those of skill in the art upon a reading of the specification and a study of the figures. SUMMARY The following embodiments and aspects thereof are described and illustrated in conjunction with systems, tools and methods which are meant to be exemplary and illustrative, not limiting in scope. There is provided, in accordance with some embodiments, a method for tracking a medical tool during a medical procedure, the method includes providing a tracking system which includes a medical tool having a magnetic element, and an array of magnetic sensors, wherein the array is configured to detect a change in magnetic field generated by the movement of the magnetic element within the body, and determining, utilizing a processor, the spatial location and/or orientation of the medical tool within the body, based on one or more deep learning algorithms correlating the change of the magnetic field with the spatial location and/or orientation of the magnetic element. There is provided, in accordance with some embodiments, a system for tracking a medical tool during a medical procedure, the system including: a medical tool including a magnetic element, an array of magnetic sensors, the array is configured to detect a change in magnetic field generated by the movement of the magnetic element within the body, and a processor configured to receive the detected change in magnetic field and determine the spatial location and/or orientation of the medical tool, based on one or more deep learning algorithm(s) correlating the change of the magnetic field with the spatial location and/or orientation of the magnetic element. Advantageously, the array of magnetic sensors may be wirelessly associated with the magnetic element and/or the medical tool, thereby enabling the user (for example, a physician/operator of the medical tool to freely operate without physical limitations that would have been present if the array of magnetic sensors would have been mechanically coupled to the medical tool. Advantageously, the array of magnetic sensors may be configured to detect a change in magnetic field generated by the movement of the magnetic element, thereby enabling the detection of the position of the medical tool without a need to apply a magnetic field in the operation room, and thereby allowing the user to detect the position of the medical tool without causing interference to other devices in the operation room during a medical procedure. Advantageously, the method may include detecting the spatial location and/or orientation of the medical tool inside a subject's body during a medical procedure using one or more deep learning algorithms and therefore does not require applying the one or more signals received from the sensor array to a mathematical formula, thus increasing the resolution of the determined spatial location and/or orientation in relation to tracking methods which use mathematical formulas. According to some embodiments there is provided a system for tracking a medical tool during a medical procedure, the system including: a tracking system including: a magnetic element configured to be placed onto a remote control, and an array of mag