Systems, methods, and devices for developing patient-specific spinal implants, treatments, operations, and/or procedures

Patent metadata

Field	Value
Publication number	US-11877801-B2
Application number	US-202016837461-A
Country	US
Kind code	B2
Filing date	Apr 1, 2020
Priority date	Apr 2, 2019
Publication date	Jan 23, 2024
Grant date	Jan 23, 2024

Abstract

The disclosure herein relates to systems, methods, and devices for developing patient-specific spinal implants, treatments, operations, and/or procedures. In some embodiments, systems, methods, and devices described herein can comprise using artificial intelligence, machine learning, and/or predictive modeling to predict the outcome of a spinal surgery, one or more parameters of a spine of a patient after spinal surgery, for example after implantation of a spinal rod which can be patient-specific, and/or one or more parameters of one or more recommended patient-specific spinal rods. Furthermore, in some embodiments, systems, methods, and devices described herein can comprise intraoperative tracking for tracking and/or suggesting improvements during spinal surgery based on a pre-operatively determined surgical plan, for example in real-time or substantially real-time. In addition, in some embodiments, systems, methods, and devices described herein can comprise screw planning prior to spinal surgery.

First claim

What is claimed is:

1. A computer-implemented method for generating and assisting patient-specific spinal treatment, the method comprising:
analyzing, using a computer system, one or more preoperative medical images of a spine of a patient to determine one or more preoperative spinopelvic parameters, wherein the one or more spinopelvic parameters comprise one or more of lumbar lordosis (LL), preoperative thoracic kyphosis (TK), pelvic incidence (PI), pelvic tilt (PT), or sagittal vertical axis (SVA) for one or more vertebrae;
transforming, using the computer system, the determined one or more preoperative spinopelvic parameters to obtain one or more preoperative spinopelvic parameters in a frequency domain, wherein the transforming comprises applying a Fourier transformation to the determined one or more preoperative spinopelvic parameters;
filtering, using the computer system, the one or more preoperative spinopelvic parameters in the frequency domain, wherein the filtering comprises filtering out one or more of the one or more preoperative spinopelvic parameters in the frequency domain comprising a frequency level above a predetermined threshold;
applying, using the computer system, one or more predictive models to generate a predicted surgical outcome in the frequency domain based at least in part on the filtered one or more preoperative spinopelvic parameters in the frequency domain and one or more preoperative non-imaging data inputs of the patient, wherein the one or more predictive models comprises one or more of a generative adversarial network (GAN) algorithm, convolutional neural network (CNN) algorithm, or recurrent neural network (RNN) algorithm; and
transforming, using the computer system, the generated predicted surgical outcome in the frequency domain to obtain a generated predictive surgical outcome in a spatial domain, wherein the transforming the generated predicted surgical outcome in the frequency domain comprises applying an inverse Fourier transformation to the generated predicted surgical outcome in the frequency domain,
generating, using the computer system, a patient-specific spinal treatment based at least in part on the generated predictive surgical outcome in the spatial domain, wherein the generated patient-specific spinal treatment comprises one or more patient-specific spinal surgical procedures;
attaching one or more intraoperative tracking modules to one or more vertebral implants for implanting to one or more vertebrae of interest during spinal surgery of the patient, wherein the one or more intraoperative tracking modules comprise at least one sensor and a strip for blocking a power circuit within the one or more intraoperative tracking modules;
removing the strip from the one or more intraoperative tracking modules to initiate tracking of one or more angles between the one or more vertebrae to which the one or more intraoperative tracking modules are attached to; and
generating, by the computer system, intraoperative tracking data in real-time and comparing the generated tracking data in real-time to the generated one or more patient-specific spinal surgical procedures to assist the generated patient-specific spinal treatment,
wherein the computer system comprises a computer processor and an electronic storage medium.

2. The computer-implemented method of claim 1 , wherein the one or more spinopelvic parameters are determined automatically by the computer system.

3. The computer-implemented method of claim 1 , wherein the one or more preoperative medical images of the spine of the patient comprise one or more sagittal x-ray images and one or more frontal x-ray images.

4. The computer-implemented method of claim 1 , wherein the generated predictive surgical outcome in the spatial domain comprises one or more postoperative spinopelvic parameters.

5. The computer-implemented method of claim 1 , wherein the generated patient-specific spinal treatment further comprises one or more specifications of a spinal rod to be implanted to the spine of the patient.

6. The computer-implemented method of claim 1 , wherein the at least one sensor is chosen from the group comprising: accelerometers and/or gyroscopes.

7. The computer-implemented method of claim 1 , wherein the one or more vertebral implants comprise one or more vertebral screws.

8. The computer-implemented method of claim 7 , wherein the one or more vertebral screws comprise one or more tulip screws.

9. The computer-implemented method of claim 7 , wherein the one or more intraoperative tracking modules comprises one or more notches configured to attach or remove the one or more intraoperative tracking modules to the one or more vertebral screws.

10. The computer-implemented method of claim 7 , wherein the one or more intraoperative tracking modules comprises a first conduit adapted to allow insertion of a surgical tool, and wherein the one or more intraoperative tracking modules comprises a second conduit adapted to allow insertion of a spinal rod.

11. The computer-implemented method of claim 10 , wherein a longitudinal axis of the first conduit is substantially perpendicular to a longitudinal axis of the second conduit.

12. The computer-implemented method of claim 10 , wherein the second conduit comprises a top section and a bottom section, wherein a width of the top section is larger than a width of the bottom section.

13. The computer-implemented method of claim 10 , wherein the second conduit is formed by two notches of the one or more intraoperative tracking modules, wherein the two notches are adapted to attach to a horizontal notch of the one or more vertebral screws.

14. A computer-implemented method of predicting a surgical outcome a spinal surgery of a subject, the method comprising:
inputting, into a computer system, one or more preoperative inputs relating to the subject, wherein the one or more preoperative inputs comprise one or more preoperative medical images of a spine of the subject and one or more preoperative non-imaging data inputs of the subject;
determining, using the computer system, one or more measurements from the inputted one or more preoperative medical images of the spine of the subject, wherein the one or more measurements comprise a position of one or more vertebrae of the spine of the subject;
determining, using the computer system, one or more preoperative spinopelvic parameters based at least in part on the one or more determined measurements, wherein the one or more preoperative spinopelvic parameters comprise one or more of lumbar lordosis (LL), preoperative thoracic kyphosis (TK), pelvic incidence (PI), pelvic tilt (PT), or sagittal vertical axis (SVA) for one or more vertebrae;
transforming, using the computer system, the determined one or more preoperative spinopelvic parameters to obtain one or more preoperative spinopelvic parameters in a frequency domain, wherein the transforming comprises applying a Fourier transformation to the determined one or more preoperative spinopelvic parameters;
filtering, using the computer system, the one or more preoperative spinopelvic parameters in the frequency domain, wherein the filtering comprises filtering out one or more of the one or more preoperative spinopelvic parameters in the frequency domain comprising a frequency level above a predetermined threshold;
applying, using the computer system, one or more predictive models to generate a predicted surgical outcome in the frequency domain based at least in part on the filtered one or more preoperative spinopelvic parameters in the frequency domain and the one or more preoperative non-imaging data inputs of the subject; and

Assignees

• Medicrea Int

Inventors

• Mosnier Thomas
• Senac Agathe
• Augagneur Céline
• Javelot Christophe Xavier Guillaume
• Sournac Denys

Classifications

• A61B2034/256

  having a database of accessory information, e.g. including context sensitive help or scientific articles · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/094

  Adversarial learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title