Method and system for wavelet based detection of colon polyps

1. A method of identifying colon polyps in a digital volume, wherein said volume comprises a plurality of values corresponding to a domain of points in a 3D space, said method comprising the steps of:

selecting a mother wavelet scaling function that corresponds to a polyp;

calculating a first derivative of said volume, and selecting the mother wavelet function to be similar to a first derivative of a polyp;

performing a forward wavelet transformation on said volume to obtain a set of wavelet coefficients, wherein each wavelet coefficient is associated with a length scale;

determining, for each length scale, a transformation magnitude, wherein the transformation magnitude comprises a threshold magnitude;

forming, for each length scale, a transformed set of wavelet coefficients associated with said length scale, wherein said forming comprises selecting, for each length scale, those wavelet coefficients whose magnitudes exceeds the threshold for said length scale, to form a template subset of wavelet coefficients associated with said length scale;

performing a forward wavelet transform of a second volume, to obtain a second set of wavelet coefficients; and

comparing, for each length scale, coefficients of the second set of wavelet coefficients with coefficients of a template subset for said length scale, wherein a match between said coefficients of said template subset and coefficients of said second set of wavelet coefficients indicates the presence of a polyp corresponding to said length scale.

2. A method of identifying colon polyps in a digital volume, wherein said volume comprises a plurality of values corresponding to a domain of points in a 3D space, said method comprising the steps of:

selecting a mother wavelet scaling function that corresponds to a polyp;

calculating a first derivative of said volume, selecting the mother wavelet function to be similar to a first derivative of a polyp;

performing a forward wavelet transformation on said volume to obtain a set of wavelet coefficients, wherein each wavelet coefficient is associated with a length scale;

determining, for each length scale, a threshold magnitude;

selecting, for each length scale, those wavelet coefficients whose magnitudes exceeds the threshold for said length scale, to form a template subset of wavelet coefficients associated with said length scale;

calculating a first derivative of said second volume;

performing a forward wavelet transform of a second volume, to obtain a second set of wavelet coefficients;

comparing, for each length scale, coefficients of the second set of wavelet coefficients with coefficients of a template subset for said length scale, wherein a match between said coefficients of said template subset and coefficients of said second set of wavelet coefficients indicates the presence of a polyp corresponding to said length scale.

3. A program storage device readable by a computer, tangibly embodying a program of instructions executable by the computer to perform method steps for identifying colon polyps in a digital volume, wherein said volume comprises a plurality of values corresponding to a domain of points in a 3D space, said method comprising the steps of:

selecting a mother wavelet scaling function that corresponds to a polyp;

calculating a first derivative of said volume, and selecting the mother wavelet function to be similar to a first derivative of a polyp;

performing a forward wavelet transformation on said volume to obtain a set of wavelet coefficients, wherein each wavelet coefficient is associated with a length scale;

determining, for each length scale, a transformation magnitude, wherein the transformation magnitude comprises a threshold magnitude;

forming, for each length scale, a transformed set of wavelet coefficients associated with said length scale, wherein said forming comprises selecting, for each length scale, those wavelet coefficients whose magnitudes exceeds the threshold for said length scale, to form a template subset of wavelet coefficients associated with said length scale;

performing a forward wavelet transform of a second volume, to obtain a second set of wavelet coefficients; and

comparing, for each length scale, coefficients of the second set of wavelet coefficients with coefficients of a template subset for said length scale, wherein a match between said coefficients of said template subset and coefficients of said second set of wavelet coefficients indicates the presence of a polyp corresponding to said length scale.