IP Library › Granted Patent US 11,488,717
Granted Patent B2
US 11,488,717 · App. 16/878,533 · Granted Nov 1, 2022

Method and system for analysis of spine anatomy and spine disease

Inventors: Billy Cao (San Francisco, CA); Dave Harrison (San Francisco, CA); Luke Macyszyn (Los Angeles, CA); Sam Elhag (Los Angeles, CA)
Assignee: Theseus AI, Inc.
G16H50/20G06T7/0016G06T7/11G06V10/26G16H10/60G16H20/30G16H20/40G16H30/20G16H30/40G16H50/30G16H50/70G06T2207/20081G06T2207/20084G06T2207/30012G06V2201/033
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,488,717
App. No.
16/878,533
Granted
Nov 1, 2022
Kind
B2
Abstract

A method for analysis of spine anatomy and stenosis is disclosed herein. The method includes preprocessing ( 3203 ) of images and then running segmentation models for each area of interest such as the foramen, disc, canal, vertebra ( 3206 ). In image post processing ( 3207 ), the system runs various heuristics to ensure accuracy ( 3208 ), computes areas ( 3209 ), and then runs a comparison model ( 3210 ). The report template produces HTML that is then converted to a PDF file of the final report ( 3214 ).

Claims (27)

1. A computer-implemented method for generating a diagnosis for a spinal disease, the method comprising:

inputting a plurality of digital images of an axial plane of a patient's spine showing a plurality of successive points along a length of the spine;

identifying a spinal canal or other spine anatomy in each image of the plurality of digital images;

estimating a cross-sectional area of the spinal canal or spinal anatomy of interest in each image of the plurality of digital images;

calculating a plurality of ratios by comparing the cross-sectional area in each image to the cross-sectional area in preceding images of the plurality of digital images; and

generating a diagnosis for a spinal disease according to the plurality of ratios.

2. The method of claim 1 , wherein a sagittal plane of a patient's spine is inputted and used to identify and measure cross-sectional areas.

3. The method of claim 1 , wherein the medical diagnosis comprises a rating for a severity of spinal stenosis or related conditions.

4. The method of claim 1 , wherein the diagnosis comprises a surgical evaluation or recommendation for surgical treatment of spinal stenosis or other spinal disease.

5. The method of claim 1 , wherein the diagnosis comprises a recommendation for physical therapy treatment.

6. The method of claim 1 , wherein the spinal anatomy is one of a spinal canal diameter, a spinal canal radius, or a spinal canal circumference.

7. The method of claim 1 , further comprising calculating a plurality of differences, calculated by subtracting the previous spinal canal area from the current spinal canal area.

8. The method of claim 1 , wherein one or more cross-sectional areas are compared to a sample population to output a degree of difference.

9. The method of claim 1 , wherein one or more cross-sectional areas are compared to a to those of a comparison group to form aspects of a diagnosis.

10. The method of claim 9 , wherein the comparison group is matched to the patient's demographics and health data.

11. The method of claim 1 , wherein data relating to a formed medical diagnosis is sent to one or more external systems.

12. A non-transitory computer-readable medium that stores a program that causes a processor to perform functions to analyze a spine image by executing the following steps:

inputting a plurality of digital images of an axial plane of a patient's spine showing a plurality of successive points along a length of the spine;

identifying a spinal canal or other spine anatomy in each image of the plurality of digital images;

estimating a cross-sectional area of the spinal canal or spinal anatomy of interest in each image of the plurality of digital images;

calculating a plurality of ratios by comparing the cross-sectional area in each image to the cross-sectional area in preceding images of the plurality of digital images, or calculating a plurality of differences by subtracting a previous spinal canal area from a current spinal canal area;

generating a diagnosis for a spinal disease according to the plurality of ratios or the plurality of differences.

13. The non-transitory computer readable medium according to claim 12 , wherein the diagnosis comprises a rating for a severity of spinal stenosis or related conditions.

14. The non-transitory computer readable medium according to claim 12 , wherein the diagnosis comprises a surgical evaluation or recommendation for surgical treatment of spinal stenosis or related conditions.

15. The non-transitory computer readable medium according to claim 12 , wherein the diagnosis comprises a recommendation for physical therapy treatment of spinal stenosis or related conditions.

16. The non-transitory computer readable medium according to claim 12 , wherein the spinal canal area is replaced with a spinal canal diameter, a spinal canal radius, a spinal canal circumference, or other measurement correlated to the spinal canal area.

17. The non-transitory computer readable medium according to claim 12 , wherein the diagnosis is formed according to the plurality of ratios.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 19, 2020
From: CAO, BILLY; HARRISON, DAVE; MACYSZYN, LUKE; ELHAG, SAM
To: THESEUS AI, INC.
Reel/Frame 052705/0638 →
Continuity (4)
Provisional Application 62851602 · May 22, 2019
Provisional Application 62894818 · Sep 1, 2019
Provisional Application 62960149 · Jan 13, 2020
Related Publication 20200373013A1 · Nov 26, 2020