Breast cancer detection
AssigneeInternational Business Machines Corporation
InventorsJuan Manuel A. Vega, Ramón Oswaldo G. Medina, Rubén Ruelas-Lepe
Life of this patent
Estimating the term…
Abstract
A hybrid detection model may be used for breast cancer detection. A system can identify a region of interest on a received mammogram. The region of interest may have a particular level of grey at each pixel of the image. A morphological and entropy filter may then each be applied to the region of interest. Based on the filters, the system may generate a hybrid result that is the average of a combination of the two filters. The system may then segment the region of interest using a selected clustering algorithm.
Claims21
A computer-implemented method for a hybrid detection model for use in breast cancer detection, the method comprising:
- identifying, responsive to receipt of a digital image, a region of interest on the digital image, wherein the region of interest is described using a level of grey for each pixel in the region of interest;
- applying, to each level of grey for each pixel in the region of interest in the digital image, a predetermined morphological filter to produce a first output, wherein the morphological filter reduces grey levels of the digital image to generate a first set of values;
- applying, to each level of grey for each pixel in the region of interest in the digital image, a predetermined entropy filter to produce a second output that captures a set of maximum grey values, wherein the maximum grey values reflect a local maximum relative to other grey values in the digital image;
- generating a hybrid result that is a combination of the first output of the predetermined morphological filter and the second output of the predetermined entropy filter;
- and
- segmenting, using the hybrid result, the digital image into potential microcalcifications by using a selected clustering algorithm with sub-segmentation.
A computer system comprising:
- A computer readable storage medium with program instructions stored thereon;
- and
- one or more processors configured to execute the program instructions to perform a method comprising:
- identifying, responsive to receipt of a digital image, a region of interest on the digital image, wherein the region of interest is described using a level of grey for each pixel in the region of interest;
- applying, to each level of grey for each pixel in the region of interest in the digital image, a predetermined morphological filter to produce a first output, wherein the morphological filter reduces grey levels of the digital image to generate a first set of values;
- applying, to each level of grey for each pixel in the region of interest in the digital image, a predetermined entropy filter to produce a second output that captures a set of maximum grey values, wherein the maximum grey values reflect a local maximum relative to other grey values in the digital image;
- generating a hybrid result that is a combination of the first output of the predetermined morphological filter and the second output of the predetermined entropy filter;
- and
- segmenting, using the hybrid result, the digital image into potential microcalcifications by using a selected clustering algorithm with sub-segmentation.
A computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a computer processor to cause the processor to perform a method comprising:
- identifying, responsive to receipt of a digital image, a region of interest on the digital image, wherein the region of interest is described using a level of grey for each pixel in the region of interest;
- applying, to each level of grey for each pixel in the region of interest in the digital image, a predetermined morphological filter to produce a first output, wherein the morphological filter reduces grey levels of the digital image to generate a first set of values;
- applying, to each level of grey for each pixel in the region of interest in the digital image, a predetermined entropy filter to produce a second output that captures a set of maximum grey values, wherein the maximum grey values reflect a local maximum relative to other grey values in the digital image;
- generating a hybrid result that is a combination of the first output of the predetermined morphological filter and the second output of the predetermined entropy filter;
- and
- segmenting, using the hybrid result, the digital image into potential microcalcifications by using a selected clustering algorithm with sub-segmentation.
Dependencies are inferred from the claim text.