US-20260123817-A1 - SYSTEMS AND METHODS FOR INTRAOPERATIVE SEGMENTATION

Abstract

A method comprises navigating a patient's anatomy with a medical instrument, the instrument comprising a sensing tool. The method further includes correlating a position of the instrument with a model of the patient's anatomy. The method further includes, while navigating the patient's anatomy, updating the model based on data obtained by the sensing tool.

Inventors

• Tao Zhao
• Vincent Duindam
• Caitlin Q. Donhowe
• Timothy D. Soper
• Federico Barbagli

Assignees

• Intuitive Surgical Operations, Inc.

Dates

Publication Date

20260507

Application Date

20251007

Claims (20)

1. 1 . A method for intraoperative segmentation, the method comprising: navigating a patient's anatomy with a medical instrument, the instrument comprising a sensing tool; correlating a position of the instrument with a model of the patient's anatomy; and while navigating the patient's anatomy, updating the model based on data obtained by the sensing tool.
2. 2 . The method of claim 1 , wherein the sensing tool comprises a position sensor.
3. 3 . The method of claim 2 , wherein the position sensor comprises at lease one of: a shape sensor, an electromagnetic position sensor, a fluoro-based system, an impedance sensor, a range sensor and a camera.
4. 4 . The method of claim 1 , wherein the data comprises at least one of: spatially integrated data and temporally integrated data.
5. 5 . The method of claim 1 , wherein updating the model occurs in response to detecting a difference between the model and the anatomy.
6. 6 . The method of claim 5 , wherein the method further includes communicating the detected difference to an operator of the medical instrument.
7. 7 . The method of claim 5 , wherein the difference is automatically detected based on an image analysis from data received by an imaging element associated with the medical instrument.
8. 8 . The method of claim 1 , wherein updating the model comprises adding additional or removing voxels associated with a difference between the model and the anatomy.
9. 9 . The method of claim 1 , wherein updating the model comprises: adding additional seeds to a segmentation function, the seeds corresponding to a newly discovered passage; and reapplying the segmentation function with the additional seeds.
10. 10 . The method of claim 1 , wherein updating the model comprises adjusting a shape of a passageway.
11. 11 . The method of claim 10 , wherein adjusting the shape of a passageway in the model is done in response to determining, with a measurement tool on the medical instrument, that the diameter of the patient's anatomy is different than a corresponding diameter of that passageway in the model.
12. 12 . The method of claim 1 , wherein updating the model comprises adding an additional passage within the model.
13. 13 . The method of claim 1 , wherein updating the model comprises at least one of: adjusting a position of a passage within the model and adjusting a diameter of the passage within the model.
14. 14 . A method for intraoperative segmentation, the method comprising: with a sensing tool of a medical instrument, obtaining data of a patient's anatomy while navigating through the anatomy; comparing the data to a model of the patient's anatomy; and updating the model in response to determining that there is a difference between the model and the patient's anatomy as defined by the data.
15. 15 . The method of claim 14 , wherein the model is obtained by applying a segmentation function to an image of the patient's anatomy.
16. 16 . The method of claim 15 , wherein updating the model comprises reapplying the segmentation function with additional seeds, the additional seeds based on the difference between the model and the patient's anatomy.
17. 17 . The method of claim 15 , wherein the image comprises a computed tomography scan.
18. 18 . The method of claim 15 , wherein the image comprises a Magnetic Resonance Imaging (MRI) scan.
19. 19 . The method of claim 14 , wherein the sensing tool comprises a camera and the data comprises a temporal series of two dimensional images obtained by the camera.
20. 20 . The method of claim 14 , wherein the sensing tool is to obtain a point cloud to create a surface representation of the patient's anatomy.

Description

RELATED APPLICATIONS This patent application claims priority to and the benefit of the filing date of U.S. Provisional Patent Application 62/029,927, entitled “SYSTEMS AND METHODS FOR INTRAOPERATIVE SEGMENTATION,” filed Jul. 28, 2014, which is incorporated by reference herein in its entirety FIELD The present disclosure is directed to systems and methods for creating models of a patient's anatomy using a process referred to as segmentation, and more particularly, to systems and methods for segmentation while navigating a patient's anatomy with a medical instrument. BACKGROUND Minimally invasive medical techniques are intended to reduce the amount of tissue that is damaged during medical procedures, thereby reducing patient recovery time, discomfort, and harmful side effects. Such minimally invasive techniques may be performed through natural orifices in a patient anatomy or through one or more surgical incisions. Clinicians may insert medical tools through these natural orifices or incisions to reach a target tissue location. Medical tools include instruments such as therapeutic instruments, diagnostic instruments, and surgical instruments. To reach the target tissue location, a minimally invasive medical tool may navigate natural or surgically created passageways in anatomical systems such as the lungs, the colon, the intestines, the kidneys, the heart, the circulatory system, or the like. An image guided surgery process typically includes performing some type of pre-operative imaging of a target anatomy of a patient. For example, a Magnetic Resonance Imaging (MRI) image or a Computed Tomography (CT) image may be obtained. Through a manual and/or a computer software-based process, the images are partitioned into segments (e.g., pixels or voxels) that share certain characteristics or computed properties such as color, density, intensity, and texture. This segmentation process results in a two- or three-dimensional reconstruction that forms a model of the target anatomy based on the obtained image. To represent the model, the segmentation process may delineate sets of voxels representing the target anatomy and then apply a function, such as marching cube function, to obtain a 3D surface that encloses the voxels. Segmentation may be particularly useful in modeling anatomic passageways. After the segmentation process, the obtained model may be used to navigate a medical instrument through the segmented passageways of the patient anatomy. In some cases, various branches within the patient's anatomy may not be properly segmented by the segmentation process. For example, some passageways that exist within the patient anatomy may be omitted from the model. Or, the segmentation process may indicate the existence of branches where there are, in fact, none. Thus, a surgeon or an operator of the medical instrument who is using the model for navigation to a particular anatomic location may be hampered by inaccuracies in the model. To avoid such issues, it is desirable to have accurate segmentation capability. SUMMARY The embodiments of the invention are summarized by the claims that follow below. In one embodiment, a method comprises navigating a patient's anatomy with a medical instrument, the instrument comprising a sensing tool. The method further includes correlating a position of the instrument with a model of the patient's anatomy. The method further includes, while navigating the patient's anatomy, updating the model based on data obtained by the sensing tool. In another embodiment, a method includes for intraoperative segmentation includes, with a sensing tool of a medical instrument, obtaining data of a patient's anatomy while navigating through the anatomy. The method further includes comparing the data to a model of the patient's anatomy. The method further includes updating the model in response to determining that there is a difference between the model and the patient's anatomy as defined by the data. In one embodiment, a computing system includes a processor and a memory comprising machine readable instructions that when executed by the processor, cause the system to apply a segmentation function to a three-dimensional image of a patient's anatomy to create a model, receive position data from a medical instrument while navigating the patient's anatomy, register a position of the instrument with the model, receive data related to the patient's anatomy from a sensing tool of the medical instrument, and update the model in response to detecting a difference between the model and the patient's anatomy. In one embodiment, a method for intraoperative segmentation includes navigating a patient's anatomy with a medical instrument, the instrument comprising a sensing tool. The method further includes correlating a position of the instrument with a generic anatomy model. The method further includes, while navigating the patient's anatomy, updating the generic anatomy model to match the patient's anatomy based on d