System and method for detecting and matching anatomical structures using appearance and shape

• US 7,536,044 B2
• Filed: 11/18/2004
• Issued: 05/19/2009
• Est. Priority Date: 11/19/2003
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Georgescu, Bogdan, Gupta, Alok, Zhou, Xiang Sean, Rao, R. Bharat, Comaniciu, Dorin
• Primary Examiner(s): Strege; John B
• Application Number:
  US10/991,933
• Publication Number:
  US 20050147303A1
• Time in Patent Office: 1,643 Days
• Field of Search: 382/128, 382/225, 358/1.9
• US Class Current: 382/128
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06T 2207/10132 Ultrasound image
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06V 10/754 involving a deformation of the sample pattern or of the reference pattern; Elastic matching
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting

Abstract

A detection framework that matches anatomical structures using appearance and shape is disclosed. A training set of images are used in which object shapes or structures are annotated in the images. A second training set of images represents negative examples for such shapes and structures, i.e., images containing no such objects or structures. A classification algorithm trained on the training sets is used to detect a structure at its location. The structure is matched to a counterpart in the training set that can provide details about the structure'"'"'s shape and appearance.

Claims

1. A computer readable medium embodying instructions executable by a processor to perform a method for detecting an object in an image that contains invalid data regions, the method comprising the steps of:

determining a data mask for the image to indicate which pixels in the image are valid;

representing the data mask as an integral mask in which each pixel has a value corresponding to a total number of valid pixels in the image above and to left of the pixel;

applying a rectangular feature to the image, the rectangular feature having at least one positive region and one negative region;

determining the number of pixels in the rectangular feature that are valid using the integral mask, wherein the integral mask comprises at least one occlusion and the number of valid pixels in the rectangular feature corresponds to pixels that do not comprise the occlusion;

approximating a mean intensity value for a region that contains invalid pixels, wherein the mean intensity value is approximated by using only the number of valid pixels in the region;

determining a feature value for the rectangular feature by computing a weighted difference between a sum of intensity values in the positive and negative regions of the rectangular feature; and

using the feature value to determine if an object has been detected.

2. The method of claim 1 wherein said data mask assigns those pixels that are invalid a value of zero.

3. The method of claim 2 wherein said data mask assigns those pixels that are valid a value of 1.

4. The method of claim 1 wherein the intensity value is a grayscale value for a pixel.

5. The method of claim 1 wherein the image is an ultrasound image.

6. The method of claim 5 wherein the object is a left ventricle.

7. The method of claim 1 wherein the object is a face.

8. The method of claim 1 wherein the invalid data region is an occlusion that partially obstructs the object.

9. A computer readable medium embodying instructions executable by a processor to perform a method for detecting an object in an image comprising the steps of:

a). computing a feature value for a classifier in a window of the image;

b). determining if the feature value is above a predetermined threshold value;

c). if the feature value is above the threshold value, computing a subsequent feature value for a subsequent classifier in the window of the image;

d). computing a combined feature value comprising the feature value of the classifier and the subsequent feature value of the subsequent classifier;

e). determining if the combined feature value is above a combination threshold value for a current combination, wherein the combination threshold value is updated based on the current combination;

f). if the combined feature value is above the combination threshold value, repeating steps c)-e) until there are no subsequent classifiers or the combined feature value is not above the combination threshold value; and

g). using a final combined feature value to determine if an object has been detected.

10. The method of claim 9 wherein the image is an ultrasound image.

11. The method of claim 10 wherein the object is a left ventricle.

12. The method of claim 9 wherein the object is a face.