Search

US-20260126778-A1 - SYSTEMS AND METHODS FOR ASSISTING A SURGEON AND PRODUCING PATIENT-SPECIFIC MEDICAL DEVICES

US20260126778A1US 20260126778 A1US20260126778 A1US 20260126778A1US-20260126778-A1

Abstract

Systems and methods for assisting a surgeon with implant during a surgery are disclosed. A method includes defining areas of interest in diagnostic data of a patient and defining an implant type. Post defining the areas of interest, salient points are determined for the areas of interest. Successively, an XZ angle, an XY angle, and a position entry point for an implant are determined based on the salient points of the areas of interest. In spinal procedures, a maximum screw diameter and a length of the spinal screw are successively determined based on the salient points. Based on determined length and diameter, a spinal screw and a matching screw guide is determined. Thereafter, the spinal screw and the screw guide is printed using a Three-Dimensional (3D) printer. Such printed spinal screw and screw guide could be used by the surgeon during the spinal surgery.

Inventors

  • Jeffrey Roh
  • Justin Esterberg

Assignees

  • CARLSMED, INC.

Dates

Publication Date
20260507
Application Date
20251231

Claims (20)

  1. 1 . A computer-implemented method comprising: inputting image data of a patient into at least one trained machine learning model; designing a first patient-specific spinal implant and a second patient-specific spinal implant configured to provide a target correction to a spine of the patient, wherein the designing is based on output, from the at least one trained machine learning model, based on the image data of the patient, and input from a user associated with a surgical procedure to be performed on the patient; after the first patient-specific spinal implant and the second patient-specific spinal implant are implanted in the patient, comparing, by a computer system, a post-operative correction of the patient to the target correction, wherein the computer system is programmed to determine post-operative measurements of the post-operative correction of the patient based on post-operative correction data of the patient, determine an outcome comparison by comparing planned measurements of the target correction to the post-operative measurements, determine whether to perform model retraining based on the outcome comparison, and in response to determining to perform the model retraining, retraining the at least one trained machine learning model using the post-operative correction data of the patient.
  2. 2 . The computer-implemented method of claim 1 , further comprising: identifying salient anatomical features in the image data; determining, based on the salient anatomical features, at least a portion of a surgical plan for the surgical procedure; creating a 3D model of the first patient-specific spinal implant based on a 3D representation of at least part of the patient and the salient anatomical features; converting the 3D model into 3D fabrication data; and manufacturing, using at least one 3D printer, at least a portion of the first patient-specific spinal implant based on the 3D fabrication data.
  3. 3 . The computer-implemented method of claim 1 , further comprising: providing a database comprising type and size information of spinal implants; determining, based on the type and size information in the database and salient anatomical features of the patient, an implant type and one or more dimensions; determining a candidate first patient-specific spinal implant based on the implant type and the one or more dimensions; determining that the candidate first patient-specific spinal implant falls within one or more specified parameters based on a 3D representation of the patient and the salient anatomical features; and in response to determining the candidate first patient-specific spinal implant falls within the one or more specified parameters, selecting the candidate first patient-specific spinal implant as the first patient-specific spinal implant.
  4. 4 . The computer-implemented method of claim 1 , further comprising: using a 3D representation of anatomy of the patient to design the first patient-specific spinal implant, wherein the 3D representation is a topographical map.
  5. 5 . The computer-implemented method of claim 1 , further comprising obtaining a 3D model of the first patient-specific spinal implant from a computer-aided design program on the computer system.
  6. 6 . The computer-implemented method of claim 1 , further comprising: identifying at least one anatomical abnormality of the patient by: automatically measuring a distance between anatomical features of the patient; and based on the distance, identifying one or more anatomical abnormalities of interest; and causing a display to graphically identify the one or more anatomical abnormalities of the patient.
  7. 7 . The computer-implemented method of claim 1 , further comprising: providing a proposed first patient-specific spinal implant that has been determined to conform to a digital surgical plan for the surgical procedure, wherein the digital surgical plan is stored by the computer system; providing a design interface for altering at least one of the digital surgical plan or the proposed first patient-specific spinal implant; and receiving, via the design interface, one or more modifications for the at least one of the digital surgical plan or the proposed first patient-specific spinal implant.
  8. 8 . The computer-implemented method of claim 1 , further comprising automatically changing a design of the first patient-specific spinal implant to account for one or more modifications to a surgical plan for the surgical procedure, wherein the one or more modifications are provided, via a design interface displayed by a screen, by the user.
  9. 9 . A system comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the system to perform a process comprising: inputting image data of a patient into at least one trained machine learning model; designing a first patient-specific spinal implant and a second patient-specific spinal implant configured to provide a target correction to a spine of the patient, wherein the designing is based on output, from the at least one trained machine learning model, based on the image data of the patient, and input from a user associated with a surgical procedure to be performed on the patient; after the first patient-specific spinal implant and the second patient-specific spinal implant are implanted in the patient, comparing, by a computer system, a post-operative correction of the patient to the target correction, wherein the computer system is programmed to determine post-operative measurements of the post-operative correction of the patient based on post-operative correction data of the patient, determine an outcome comparison by comparing planned measurements of the target correction to the post-operative measurements, determine whether to perform model retraining based on the outcome comparison, and in response to determining to perform the model retraining, retraining the at least one trained machine learning model using the post-operative correction data of the patient.
  10. 10 . The system of claim 9 , wherein the process further comprises: identifying salient anatomical features in the image data; determining, based on the salient anatomical features, at least a portion of a surgical plan for the surgical procedure; creating a 3D model of the first patient-specific spinal implant based on a 3D representation of at least part of the patient and the salient anatomical features; converting the 3D model into 3D fabrication data; and manufacturing, using at least one 3D printer, at least a portion of the first patient-specific spinal implant based on the 3D fabrication data.
  11. 11 . The system of claim 9 , wherein the process further comprises: providing a database comprising type and size information of spinal implants; determining, based on the type and size information in the database and salient anatomical features of the patient, an implant type and one or more dimensions; determining a candidate first patient-specific spinal implant based on the implant type and the one or more dimensions; determining that the candidate first patient-specific spinal implant falls within one or more specified parameters based on a 3D representation of the patient and the salient anatomical features; and in response to determining the candidate first patient-specific spinal implant falls within the one or more specified parameters, selecting the candidate first patient-specific spinal implant as the first patient-specific spinal implant.
  12. 12 . The system of claim 9 , wherein the process further comprises: using a 3D representation of anatomy of the patient to design the first patient-specific spinal implant, wherein the 3D representation is a topographical map.
  13. 13 . The system of claim 9 , wherein the process further comprises: obtaining a 3D model of the first patient-specific spinal implant from a computer-aided design program on the computer system.
  14. 14 . The system of claim 9 , wherein the process further comprises: identifying at least one anatomical abnormality of the patient by: automatically measuring a distance between anatomical features of the patient; and based on the distance, identifying one or more anatomical abnormalities of interest; and causing a display to graphically identify the one or more anatomical abnormalities of the patient.
  15. 15 . The system of claim 9 , wherein the process further comprises: providing a proposed first patient-specific spinal implant that has been determined to conform to a digital surgical plan for the surgical procedure, wherein the digital surgical plan is stored by the computer system; providing a design interface for altering at least one of the digital surgical plan or the proposed first patient-specific spinal implant; and receiving, via the design interface, one or more modifications for the at least one of the digital surgical plan or the proposed first patient-specific spinal implant.
  16. 16 . The system of claim 9 , wherein the process further comprises: automatically changing a design of the first patient-specific spinal implant to account for one or more modifications to a surgical plan for the surgical procedure, wherein the one or more modifications are provided, via a design interface displayed by a screen, by the user.
  17. 17 . A non-transitory computer-readable medium storing instructions that, when executed by a computing system, cause the computing system to perform operations comprising: inputting image data of a patient into at least one trained machine learning model; designing a first patient-specific spinal implant and a second patient-specific spinal implant configured to provide a target correction to a spine of the patient, wherein the designing is based on output, from the at least one trained machine learning model, based on the image data of the patient, and input from a user associated with a surgical procedure to be performed on the patient; after the first patient-specific spinal implant and the second patient-specific spinal implant are implanted in the patient, comparing, by a computer system, a post-operative correction of the patient to the target correction, wherein the computer system is programmed to determine post-operative measurements of the post-operative correction of the patient based on post-operative correction data of the patient, determine an outcome comparison by comparing planned measurements of the target correction to the post-operative measurements, determine whether to perform model retraining based on the outcome comparison, and in response to determining to perform the model retraining, retraining the at least one trained machine learning model using the post-operative correction data of the patient.
  18. 18 . The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise: identifying salient anatomical features in the image data; determining, based on the salient anatomical features, at least a portion of a surgical plan for the surgical procedure; creating a 3D model of the first patient-specific spinal implant based on a 3D representation of at least part of the patient and the salient anatomical features; converting the 3D model into 3D fabrication data; and manufacturing, using at least one 3D printer, at least a portion of the first patient-specific spinal implant based on the 3D fabrication data.
  19. 19 . The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise: providing a database comprising type and size information of spinal implants; determining, based on the type and size information in the database and salient anatomical features of the patient, an implant type and one or more dimensions; determining a candidate first patient-specific spinal implant based on the implant type and the one or more dimensions; determining that the candidate first patient-specific spinal implant falls within one or more specified parameters based on a 3D representation of the patient and the salient anatomical features; and in response to determining the candidate first patient-specific spinal implant falls within the one or more specified parameters, selecting the candidate first patient-specific spinal implant as the first patient-specific spinal implant.
  20. 20 . The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise: using a 3D representation of anatomy of the patient to design the first patient-specific spinal implant, wherein the 3D representation is a topographical map.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent application Ser. No. 17/378,379 filed on Jul. 16, 2021, titled “SYSTEMS AND METHODS FOR ASSISTING A SURGEON AND PRODUCING PATIENT-SPECIFIC MEDICAL DEVICES,” which is a continuation of U.S. patent application Ser. No. 16/242,877 filed on Jan. 8, 2019, titled “SYSTEMS AND METHODS FOR ASSISTING A SURGEON AND PRODUCING PATIENT-SPECIFIC MEDICAL DEVICES,” which claims priority to U.S. Provisional Ser. No. 62/583,954 filed on Nov. 9, 2017, titled “SYSTEMS AND METHODS OF ASSISTING A SURGEON WITH SCREW PLACEMENT DURING A SPINAL SURGERY,” all of which are herein incorporated by reference in their entireties. TECHNICAL FIELD The present disclosure is generally related to providing surgical assistance to a surgeon, and more particularly for providing medical devices and surgical assistance for a surgical procedure. BACKGROUND Assessing anatomical features of patient can help a physician perform a surgical procedure. For example, identifying and assessing a spinal deformity is of tremendous importance for a number of disorders affecting human spine. A pedicle is a dense stem-like structure that projects from the posterior of a vertebra. There are two pedicles per vertebra that connect to structures like a lamina and a vertebral arch. Conventionally available screws, used in spinal surgeries, are poly-axial pedicle screws made of titanium. Titanium is chosen as it is highly resistant to corrosion and fatigue, and is easily visible in MRI images. Unfortunately, conventional spine kits with standard screw guides and pedicle screws may not be designed for use with abnormal vertebrae. Pedicle screws were originally placed via a free-hand technique. Surgeons performing spinal surgeries merely rely on their experience and knowledge of known specific paths for performing the spinal surgeries. The free-hand techniques used by spinal surgeons rely on spinal anatomy of a patient. The spinal surgeon relies on pre-operative imaging and intra-operative anatomical landmarks for performing the spinal surgery. Assistive fluoroscopy and navigation are helpful in that they guide pedicle screw placement more or less in a real time, but are limited by time and costs involved in fluoroscopy, and significant radiation exposure during fluoroscopy. Prior prefabricated screw guide insertion methods rely on the patient's diagnostics images. The diagnostics images are studied and a needle mark is made in a surgery film. Thereafter, a screw insertion point and an approach angle for drilling into the spine are determined. Such procedure may lead to several complications. For example, a lateral breach may occur, as shown in FIG. 1A of prior art. The pedicle screw may exit the wall of the vertebra and thus may compromise integrity of the surgery, which may lead to further medical complexities. Further, a medial breach may also occur, as shown in FIG. 1B of prior art. The pedicle screw may come close to or may come in contact with the central nervous system present in the spine, thus leading to medical complexities. Some complications of pedicle screws include (a) mal-positioning of the screw (medial wall breach, intra-foraminal placement, and sacroiliac joint violation), (b) fracture of the pedicle, (c) injury to the cord or nerve roots, and (d) fracture of the implant. An accurate placement of the pedicle screw in the spine is illustrated in FIG. 1C of prior art. The approach entirely relies on experience of the surgeon and involves a lot of risk. Also, locating the appropriate pedicle screw for the screw guide is a painstaking task for the surgeon. Additionally, standard pedicle screws may be not suitable for the patient's anatomy. Improper placement and improper sizing of pedicle screws can lead to significant problems. Thus, an efficient mechanism for providing assistance to a surgeon in screw placement during a spinal procedure and patient-specific surgical systems are much desired. Patient-specific medical technology can also help the assist the surgeon and improve outcomes. The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings illustrate various embodiments of systems, methods, and embodiments of various other aspects of the disclosure. Any person with ordinary skills in the art will appreciate that the illustrated element boundaries (e.g., boxes, groups of boxes, or other shapes) in the figures represent one example of the boundari