Method and system for detection of lesions in medical images

A method for the automated detection of mass lesions in mammographic images, comprising:

• generating a mammogram;
• segmenting said mammogram to produce a segmented mammogram;
• performing a morphological operation on said segmented mammogram;
• performing mass filtering;
• and
• detecting whether a lesion is present in said image;
• wherein performing said mass filtering comprises:
• determining a filter value for a plurality of edge orientation bins;
• and
• wherein determining said filter value comprises:
• calculating said filter value using:
• f(Bi)=(1/N)ΣP in K{MAX(0, cosφ)*EDGE STRENGTH (at P)}
• where:
• f(Bi) is said filter value at an orientation bin;
• K is a filter kernel;
• P is a neighbor point in K;
• N is a number of points in K;
• and
• Φ is an angle between a gradient vector and a connection line between said neighbor point and a center point.

A system for detecting lesions in a medical image, comprising:

• a data input device;
• a segmenting circuit connected to said input device;
• a modified morphological circuit connected to receive an output of said segmenting circuit;
• and
• a lesion detecting circuit operably connected to the modified morphological circuits;
• wherein said modified morphological circuit comprises:
• a gray level value determining circuit adapted to determine a first gray-level value of a pixel in said segmented mammogram using morphological processing;
• a difference circuit adapted to obtain a difference between a second gray level value of said pixel before performing said morphological operation and said first value;
• and
• a pixel substitution circuit adapted to substitute said first value for said second value in said segmented mammogram if said difference is greater than a gray-level threshold value.