Probabilistic segmentation in computer-aided detection

A computer usable medium having a computer readable program code tangibly embodied therein, said computer readable program code adapted to be executed by a processor to implement a method of segmentation, comprising:

• receiving at least one difference image;
• extracting at least one histogram of the difference image;
• determining a noise component by fitting a symmetric Gaussian distribution to the histogram such that a negative portion of the Gaussian distribution coincides with a negative portion of the histogram;
• subtracting the noise component from the histogram to generate a probability distribution function;
• converting the probability distribution function to a cumulative distribution function;
• and
• applying the cumulative distribution function to the difference image to generate a probabilistic representation of contrast enhancement (ICE).

An image segmentation system, comprising:

• a memory device for storing computer readable program code;
• and
• a processor in communication with the memory device, the processor being operative with the computer readable program code to:
• receive at least one difference image;
• extract at least one histogram of the difference image;
• determine a noise component by fitting a symmetric Gaussian distribution to the histogram such that a negative portion of the Gaussian distribution coincides with a negative portion of the histogram;
• subtract the noise component from the histogram to generate a probability distribution function;
• convert the probability distribution function to a cumulative distribution function;
• and
• apply the cumulative distribution function to the difference image to generate a probabilistic representation of contrast enhancement (ICE).