Granted Patent B2

US 8,517,945 · App. 11/414,759 · Granted Aug 27, 2013

Abstract

Claims (22)

1. A method for determining a candidate lesion region in a digital ultrasound medical image of anatomical tissue, the method comprising using a processor or computer to perform automatically steps of:

accessing the digital ultrasound medical image of anatomical tissue;

applying an anisotropic diffusion filter to the ultrasound image to generate a filtered ultrasound image;

performing a normalized cut operation on the filtered ultrasound image to partition the filtered ultrasound image into a plurality of regions;

merging the plurality of regions into merged regions based on predetermined threshold values; and

selecting, from the merged regions, at least one region as a candidate lesion region.

2. The method of claim 1 , wherein the selected candidate lesion region has: (1) an intensity value lower than a pre-determined intensity value and (2) morphological or texture features in accordance with pre-determined lesion criteria.

3. The method of claim 1 , wherein a first threshold value is applied to the merged regions having an average gray value lower than a pre-determined value G 0 , and a second threshold value is applied to the merged regions having an average gray value higher than pre-determined value G 0 .

4. The method of claim 1 , further comprising the step of segmenting the selected at least one candidate lesion region in the ultrasound image.

5. The method of claim 1 , wherein the step of performing a normalized cut is accomplished by segmenting spatially contiguous pixels in the filtered ultrasound image into a plurality of regions in accordance with substantially similar features.

6. The method of claim 5 , wherein the normalized cut is accomplished to minimize a similarity between each of the plurality of regions and maximize a similarity within each of the plurality of regions.

7. The method of claim 6 , wherein the features include intensity-based features and/or texture-based features.

8. A method for determining a candidate lesion region in a digital ultrasound medical image of anatomical tissue, the method comprising using a processor or computer to perform automatically steps of:

accessing the digital ultrasound medical image of anatomical tissue;

applying an anisotropic diffusion filter to the ultrasound image to generate a filtered ultrasound image;

performing a normalized cut operation on the filtered ultrasound image to partition the filtered ultrasound image into a plurality of regions, wherein the normalized cut is performed by segmenting spatially contiguous pixels in the filtered ultrasound image into a plurality of regions in accordance with substantially similar features;

merging the plurality of regions into merged regions based on pre-determined threshold values; and

selecting, from the merged regions, at least one region as a candidate lesion region, wherein the selected candidate lesion region has: (1) an intensity value lower than a pre-determined intensity value and (2) morphological or texture features in accordance with pre-determined lesion criteria.

9. The method of claim 8 , wherein a first threshold value is applied to the merged regions having an average gray value lower than a pre-determined value G 0 , and a second threshold value is applied to the merged regions having an average gray value higher than pre-determined value G 0 .

10. The method of claim 8 , further comprising the step of segmenting the selected at least one candidate lesion region in the ultrasound image.

11. The method of claim 8 , wherein the normalized cut is accomplished to minimize a similarity between each of the plurality of regions and maximize a similarity within each of the plurality of regions.

12. The method of claim 11 , wherein the features include intensity-based features and/or texture-based features.

Assignments (11)