Assessment of lesions in an image

A method for assessing the presence or absence of lesion(s) in an image, comprising

• a) estimating, using at least one computer, at least one subset of the image, whereby each subset is a candidate lesion area having a visibility, and estimating the background variation of the image in an area surrounding the candidate lesion area, the visibility of an area is determined as a vector of features including variance measure of a part of the image, wherein the variance measure of a part of the image is estimated by
• a4) defining a band of pixels of a predetermined width and being at a predetermined distance from the candidate lesion area,
• a5) estimating the mean and standard deviation of the intensity of the band, and
• a6) estimating the variance measure of a part of image from the mean and standard deviation estimated in a5,
• b) correcting the visibility of the candidate lesion area with the background variation, comparing the corrected visibility with a predetermined visibility threshold for lesions in that area, or correcting a predetermined visibility threshold with the background variation, comparing the visibility of the candidate lesion area with the corrected predetermined visibility threshold,
• c) classifying the candidate lesion area detected in a) with respect to the threshold obtained in step b) and as a lesion or not,
• d) optionally repeating steps a) until all candidate lesion areas have been classified.

A method for assessing the presence or absence of lesion(s) in an image, comprising

• a) estimating, using at least one computer, at least one starting point representative for a lesion in the image,
• b) selecting at least one starting point, estimating a subset of the image corresponding to a candidate lesion by growing q isocurves around the starting point, q being an integer of at least 1, until the periphery of the candidate lesion is established, the isocurves being grown from a vector of one or more visibility features,
• c) determining the visibility of the candidate lesion area, the visibility being determined from a visibility feature different from the visibility features used for growing in step b), and comparing the visibility of the candidate lesion with a predetermined threshold, the visibility of an area is determined as a vector of features including variance measure of a part of the image, wherein the variance measure of a part of the image is estimated by
• c4) defining a band of pixels of a predetermined width and being at a predetermined distance from the candidate lesion area,
• c5) estimating the mean and standard deviation of the intensity of the band, and
• c6) estimating the variance measure of a part of image from the mean and standard deviation estimated in c5,
• d) classifying the candidate lesion area detected in a) with respect to the threshold obtained in step b) and as a lesion or not,
• e) optionally repeating steps b) to d) until all candidate lesion areas have been classified.

A system for assessing the presence or absence of lesion(s) in an image, comprising

• a) an algorithm for estimating at least one subset of the image, whereby each subset is a candidate lesion area having a visibility, and estimating the background variation of the image in an area surrounding the candidate lesion area, wherein the background variations is estimated by
• a1) estimating the mean and standard deviation of the gradient magnitude pixels of an area defined surrounding the candidate lesion area, determining a lower threshold or above an upper threshold for the gradient magnitude pixels,
• a2) iteratively removing an out-lying gradient magnitude pixel below a lower threshold or above an upper threshold, and re-estimating the mean and standard deviation of the remaining gradient magnitude pixels, determining a second lower and a second upper threshold for the gradient magnitude pixels, until no out-lying gradient magnitude pixels are found, and
• a3) estimating the background variation from the mean and standard deviation estimated in a2),
• b) an algorithm for correcting the visibility of the candidate lesion area with the background variation, comparing the corrected visibility with a predetermined visibility threshold for lesions in that area, or correcting a predetermined visibility threshold with the background variation, comparing the visibility of the candidate lesion area with the corrected predetermined visibility threshold,
• c) an algorithm for classifying the candidate lesion area detected in a) with respect to the threshold obtained in step b) as a lesion or not,
• d) an algorithm for optionally repeating steps a) to c) until all candidate lesion areas have been classified, and at least one computer for implementing the algorithms.

A system for assessing the presence or absence of lesion(s) in an image, comprising

• a) an algorithm for establishing at least one starting point representative for a lesion in the image,
• b) an algorithm for selecting at least one starting point, estimating a subset of the image corresponding to a candidate lesion by growing q isocurves around the starting point, q being an integer of at least 1, until the periphery of the candidate lesion is established, the isocurves being grown from a vector of one or more visibility features,
• c) an algorithm for determining the visibility of the candidate lesion area, the visibility being determined from a visibility feature different from the visibility features used for growing in step b), and comparing the visibility of the candidate lesion with a predetermined threshold, the visibility of an area is determined as a vector of features including variance measure of a part of the image, wherein the variance measure of a part of the image is estimated by
• c4) defining a band of pixels of a predetermined width and being at a predetermined distance from the candidate lesion area,
• c5) estimating the mean and standard deviation of the intensity of the band, and
• c6) estimating the variance measure of a part image from the mean and standard deviation estimated in c5,
• d) an algorithm for classifying the candidate lesion area detected in a) with respect to the threshold obtained in step b) as a lesion or not,
• e) an algorithm for and optionally repeating steps b) to d) until all candidate lesion areas have been classified, and at least one computer for implementing the algorithms.