System and method for detecting and matching anatomical structures using appearance and shape
First Claim
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.
5 Assignments
0 Petitions
Accused Products
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.
29 Citations
12 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
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. - View Dependent Claims (10, 11, 12)
-
Specification