IP Library Granted Patent US 11,227,385
Granted Patent B2
US 11,227,385 · App. 16/535,566 · Granted Jan 18, 2022

Methods of classifying and/or determining orientations of objects using two-dimensional images

Inventors: Michael Patrick Murphy (Downers Grove, IL); Cameron James Killen (Chicago, IL); Karen Wu (Chicago, IL)
Assignee: Loyola University Chicago
G06T7/0012G06T7/62G06T7/74G06T2207/10124G06T2207/20081G06T2207/20084G06T2207/30052
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 11,227,385
App. No.
16/535,566
Granted
Jan 18, 2022
Kind
B2
Abstract

Methods for classifying and measuring orientations of objects, as nonlimiting examples, implants utilizing two-dimensional radiographs. One such method determines a three-dimensional orientation of an object based on its area projected onto a two-dimensional image and known or measured geometry. Another such method provides an automated solution to computationally determine the orientation and characterizing features of an implant based on two-dimensional radiographs. Orientations and characteristics of one or more objects in the vicinity of an object of interest may also be determined.

Claims (18)

1. A method of determining a three-dimensional orientation of a first object that is partially obscured by a second object, the first and second objects having known or measured geometries and shapes, the method comprising:

capturing radiopaque areas of each of the first and second objects in a single two-dimensional radiographic image, the radiopaque areas comprising a first two-dimensional area of the first object, a second two-dimensional area of the second object, and a two-dimensional area of overlap of the first and the second two-dimensional areas of the first and second objects within the two-dimensional radiographic image;

calibrating the two-dimensional radiographic image to a known dimension of at least one of the first object, the second object, or another object that is visible in the two-dimensional radiographic image;

determining the first and second two-dimensional areas of the first and second objects within the two-dimensional radiographic image;

identifying an outline of the radiopaque areas of the first and second objects displayed in the two-dimensional radiographic image;

measuring a combined two-dimensional area of the first and second objects within the outline; and

subtracting the combined two-dimensional area from the first and the second two-dimensional areas of the first and second objects to determine the two-dimensional area of overlap and therefrom the three-dimensional orientation of the first object.

2. The method of claim 1 , further comprising determining other characteristics of the object, wherein the other characteristics of the object comprise one or more of make, model, and material of the object based on the area thereof projected onto the two-dimensional radiographic image and the known or measured geometry and radiographic opacity thereof.

3. The method of claim 1 , further comprising determining a three-dimensional orientation of the first object relative to the second object in the two-dimensional radiographic image.

4. The method of claim 1 , wherein the method uses artificial intelligence to determine the three-dimensional orientation of the first object.

5. The method of claim 1 , wherein the method uses deep learning to determine the three-dimensional orientation of the first object.

6. The method of claim 1 , wherein the method uses a convolutional neural network to determine the three-dimensional orientation of the first object.

7. The method of claim 1 , wherein the first object is a first prosthetic component.

8. The method of claim 7 , wherein the second object is a second prosthetic component.

9. The method of claim 8 , wherein the first and second prosthetic components are an acetabular cup and a femoral head of a hip prosthesis.

10. The method of claim 8 , further comprising determining other characteristics of the first object based on its area projected onto the two-dimensional radiographic image and the known or measured geometry thereof.

11. The method of claim 10 , wherein the other characteristics of the first object comprise one or more of make, model, and material of the first object based on the area thereof projected onto the two-dimensional radiographic image and the known or measured geometry and radiographic opacity thereof.

12. The method of claim 10 , further comprising determining the orientation and characteristics of the second object and determining therefrom a relative orientation of the first object to the second object.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 25, 2019
From: MURPHY, MICHAEL PATRICK; KILLEN, CAMERON JAMES; WU, KAREN
To: LOYOLA UNIVERSITY CHICAGO
Reel/Frame 051108/0151 →
Continuity (3)
Provisional Application 62715891 · Aug 8, 2018
Provisional Application 62818929 · Mar 15, 2019
Related Publication 20200082526A1 · Mar 12, 2020