Automated method and system for the detection of abnormalities in sonographic images

A system implementing a method of detecting a candidate abnormality in a sonographic medical image, said method comprising steps of:

• obtaining a sonographic medical image;
• determining a radial gradient index (RGI) at plural pixels to produce an RGI image;
• thresholding the RGI image;
• determining a candidate abnormality in the RGI image based on the thresholding step;
• locating a center point of the candidate abnormality in the RGI image and a corresponding center point in the sonographic image;
• and
• segmenting the candidate abnormality in the sonographic image to indentify a margin of the candidate abnormality, said segmenting including identifying a plurality of potential candidate margins based on the center point in the sonographic image, determining an average radial derivative for each of the plurality of potential candidate margins, and selecting the margin of the candidate abnormality from the plurality of potential candidate margins based on the determined average radial derivative.

A computer program product storing program code for execution on a computer system, said program code including:

• a first program code to obtain a sonographic medical image;
• a second program code to determine a radial gradient index (RGI) at plural pixels to produce an RGI image;
• a third program code to threshold the RGI image;
• a fourth program code to determine a candidate abnormality in the RGI image based on the thresholding step;
• a fifth program code to locate a center point of the candidate abnormality in the RGI image and a corresponding center point in the sonographic image;
• and
• a sixth program code to segment the candidate abnormality in the sonographic image to identify a margin of the candidate abnormality, said sixth program code including identifying a plurality of potential candidate margins based on the center point in the sonographic image, determining an average radial derivative for each of the plurality of potential candidate margins, and selecting the margin of the candidate abnormality from the plurality of potential candidate margins based on the determined average radial derivative.