Polyp identification through subtraction of models of medical images

• US 7,616,800 B2
• Filed: 11/08/2005
• Issued: 11/10/2009
• Est. Priority Date: 11/08/2004
• Status: Expired due to Fees

• Current Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Original Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Inventors: Paik, David S., Beaulieu, Christopher F., Sundaram, Padmavathi, Napel, Sandy A.
• Primary Examiner(s): Johns; Andrew W
• Application Number:
  US11/666,202
• Publication Number:
  US 20080310693A1
• Time in Patent Office: 1,463 Days
• Field of Search: 382/128, 382/130, 382/131, 382/154, 382/173, 345/419, 345/423, 345/424
• US Class Current: 382/131
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06T 2210/41 Medical
• CPC Class Codes: G06V 20/653 by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A method of identifying polyps and in a medical image is provided. In a first step, a 3-dimensional model is made of the medical image that contains both polyps (if any were present in the original medical image) and folds. Next, a second 3-dimensional model of the medical image, which is a filtered version of the first model, is constructed in which folds are preserved, but polyps are minimized or eliminated. In a third step, any polyps that were contained in the medical image are identified by subtracting the second 3-dimensional model from the first 3-dimensional model. This subtraction results in a third 3-dimensional model, in which polyps are preserved but folds are minimized or eliminated. With the present inventive method, polyps may be easily and quickly identified without interference from folds.

Claims

1. A method of identifying polyps in a medical image having at least one fold and zero or more polyps, comprising:

(a) constructing a first 3-dimensional model of said medical image, wherein said first 3-dimensional model contains said at least one fold and said zero or more polyps contained in said medical image;

(b) constructing a second 3-dimensional model of said medical image from said first 3-dimensional model, wherein said second 3-dimensional model contains said at least one fold but wherein said polyps are minimized or eliminated in the case where said first 3-dimensional model contains one or more of said polyps;

(c) identifying said zero or more polyps by subtracting said second 3-dimensional model from said first 3-dimensional model, wherein said subtracting minimizes or eliminates said at least one fold.

2. The method as set forth in claim 1, wherein said first 3-dimensional model is constructed using wave front propagation.

3. The method as set forth in claim 1, wherein said second 3-dimensional model is a splined surface model of said first 3-dimensional model.

4. The method as set forth in claim 1, wherein said subtracting comprises:

(a) constructing lines normal to a surface of said first model;

(b) calculating the distances between said second model and said first model along said lines;

(d) constructing a third 3-dimensional model based on said distances.

5. The method, as set forth in claim one, wherein said medical image is a computed tomographic image.

6. The method as set forth in claim one, wherein said medical image is a computed tomographic colonographic image.