Prediction of shapes

Patent metadata

Field	Value
Publication number	US-2016335776-A1
Application number	US-201615218067-A
Country	US
Kind code	A1
Filing date	Jul 24, 2016
Priority date	Jan 27, 2014
Publication date	Nov 17, 2016
Grant date	—

Abstract

Systems and methods for predicting shape are provided. A system for predicting shape can include a database, a training analysis module, a subject analysis module, and a prediction module. The database can store two sets of training models characterized by first and second parameters, respectively (e.g., bone and cartilage), as well as a subject model characterized by the first parameter (e.g., a bone model). The relationships between these models can be determined by a training analysis module and a subject module. Based on these relationships, the prediction module can generate a predicted shape characterized by the second parameter (e.g., a predicted cartilage model corresponding to the bone model).

First claim

What is claimed is:

1 . A system for predicting a shape, the system comprising:
at least one database configured to store a first set of training models, a second set of training models, and a subject model, wherein each model in the first set of training models corresponds to an model in the second set of training models, wherein the first set of training models and the subject model are characterized by a first parameter, and wherein the second set of training models is characterized by a second parameter; a training analysis module configured to determine a relationship between the first set of training models and the second set of training models; a subject analysis module configured to determine a relationship between the subject model and the first set of training models; and a prediction module configured to generate a predicted shape based on the relationship between the first set of training models and the second set of training models and on the relationship between the subject model and the first set of training models.

2 . The system of claim 1 , wherein the training analysis module is configured to:
determine an average shape for the first set of training models; determine a decomposition of the first set of training models; determine an average shape for the second set of training models; and determine a decomposition of the second set of training models.

3 . The system of claim 1 or 2 , wherein the subject analysis module is configured to determine a fitting vector.

4 . The system claim 3 , wherein the prediction module is configured to generate a predicted shape by modifying a subject model.

5 . The system of claim 4 , wherein the prediction module is configured to generate a predicted shape based at least in part on a fitting vector.

6 . A computer implemented method of predicting a shape, the method comprising:
determining a relationship between a first set of training models and a second set of training models, each model in the first set of training models corresponding to an model in the second set of training models, the first set of training models being characterized by a first parameter; the second set of training models being characterized by a second parameter; determining a relationship between a subject model and the first set of training models, the subject model being characterized by the first parameter; and generating a predicted shape based on the relationship between the first set of training models and the second set of training models and on the relationship between the subject model and the first set of training models, the predicted shape being characterized by the second parameter.

7 . The computer implemented method of claim 6 , wherein the first set of training models comprises anatomical models and the first parameter is bone.

8 . The computer implemented method of claim 7 , wherein the second set of training models comprises anatomical models and the second parameter is cartilage.

9 . The computer implemented method of claim 8 , wherein the first set of training models and the second set of training models are derived from MRI images, and wherein the subject model is derived from an x-ray image.

10 . The computer implemented method of claim 9 , wherein determining a relationship between the first set of training models and the second set of training models comprises:
determining an average shape for the first set of training models; determining a decomposition of the first set of training models; determining an average shape for the second set of training models; and determining a decomposition of the second set of training models.

11 . The computer implemented method of claim 10 , wherein determining a relationship between the subject model and the first set of training models comprises determining a fitting vector.

12 . The computer implemented method of claim 11 , wherein generating a predicted shape comprises modifying the subject model.

13 . The computer implemented method of claim 11 , wherein generating a predicted shape is based at least in part on the fitting vector.

14 . The computer implemented method of claim 11 , further comprising identifying at least one region of the predicted shape having an accuracy above a threshold accuracy level.

15 . A non-transitory computer readable medium comprising computer executable instructions stored thereon which when executed by a processor cause a computer to perform a method of predicting a shape, the method comprising:
determining a relationship between a first set of training models and a second set of training models, each model in the first set of training models corresponding to an model in the second set of training models, the first set of training models being characterized by a first parameter; the second set of training models being characterized by a second parameter; determining a relationship between a subject model and the first set of training models, the subject model being characterized by the first parameter; and generating a predicted shape based on the relationship between the first set of training models and the second set of training models and on the relationship between the subject model and the first set of training models, the predicted shape being characterized by the second parameter.

Assignees

• Mat Nv

Inventors

• Maes Jan
• Cluckers Tom
• Van Deun Joris

Classifications

• G06F18/2148

  characterised by the process organisation or structure, e.g. boosting cascade · CPC title

• G06T7/50

  Depth or shape recovery · CPC title

• H04N21/61

  Network physical structure; Signal processing (H04B takes precedence) · CPC title

• G06T7/586

  from multiple light sources, e.g. photometric stereo · CPC title

• G06T2207/10116

  X-ray image · CPC title