Abstract: A system for identifying melanoma and other skin cancer in a dermoscopy image comprises: an image analyzer having at least one processor that instantiates at least one component stored in a memory, the at least one component comprising: a segmenter configured to segment a lesion from the rest of the image, a handcrafted feature component including: a median color splitting model for separating the image into a plurality of color regions, a vessel detection model for detecting elevated vascularity, an atypical pigment network detection model for identifying a pigment network whose structure varies in size and shape, a salient point detection model for detecting salient points based on an intensity plane of the image, a color detection model for detecting at least one of a white area, a pink shade, a pink blush, and a semi-translucency, a hair detection model for characterizing detected hairs and ruler marks, an outside model that finds the above model features on non-dark-corner areas outside the segmented are

Abstract: A system for identifying melanoma and other skin cancer in a dermoscopy image comprises: an image analyzer having at least one processor that instantiates at least one component stored in a memory, the at least one component comprising: a segmenter configured to segment a lesion from the rest of the image, a handcrafted feature component including: a median color splitting model for separating the image into a plurality of color regions, a vessel detection model for detecting elevated vascularity, an atypical pigment network detection model for identifying a pigment network whose structure varies in size and shape, a salient point detection model for detecting salient points based on an intensity plane of the image, a color detection model for detecting at least one of a white area, a pink shade, a pink blush, and a semi-translucency, a hair detection model for characterizing detected hairs and ruler marks, an outside model that finds the above model features on non-dark-corner areas outside the segmented are

Abstract: Provided herein are classifying systems for classifying a lesion border of a dermoscopy image. Provided systems generally include an image analyzer that includes a border generator configured to automatically generate a plurality of borders based on a plurality of segmentation algorithms, wherein each of the plurality of borders is generated based on a different one of the plurality of segmentation algorithms; a feature detector configured to detect one or more features on the dermoscopy image for each of the plurality of borders; and a classifier configured to assign a classification to each of the plurality of borders based on the one or more features detected by the feature detector; wherein the image analyzer is configured to select a best border from the plurality of borders based on the classification assigned by the classifier. Also provided are methods for classifying a lesion border of dermoscopy images using the provided systems.

Abstract: Systems and methods facilitate segmenting a dermoscopy image of a lesion to facilitate classification of the lesion. A dermoscopy image is received from an image source; pre-processed; and segmented. Segmenting the pre-processed dermoscopy image includes applying a thresholding algorithm to the dermoscopy image. The thresholding algorithm includes at least one of a Huang auto-thresholding algorithm, a Li auto-thresholding algorithm, a Shanbhag auto-thresholding algorithm, an Otsu auto-thresholding algorithm, or an Isodata thresholding algorithm. A weighted border error metric is provided to allow prediction of whether segmentation is likely to avoid excluding portions of the lesion. A test is provided for determination of whether image inversion is needed for the methods to provide optimal borders. An iterative expansion algorithm is provided to for determine whether expansion is needed for the methods to provide optimal borders and to determine the degree of expansion needed for more inclusive segmentation.

Abstract: A method for automatic segmentation of dermoscopy skin lesion images includes automating a Geodesic Active Contour (GAC) initialization to be sufficiently large to encompass the lesion yet lie near the actual lesion contour. In addition, a new image plane is found by transforming the original RGB image to a smoothed image that allows the GAC to move without sticking on the minimum local energy. This method can eliminate the need for separate hair or noise removal algorithms. The method may include extraction of designated color planes to improve the initial contour and to automatically correct false segmentations. The method includes an algorithm to correct false protuberances and/or false inlets that may be present in the GAC border. A method is given to increase likelihood of including more actual lesion area. The method yields multiple border choices which may be presented to a classifier for optimal border selection.

Abstract: Systems and methods facilitate segmenting a dermoscopy image of a lesion to facilitate classification of the lesion. A dermoscopy image is received from an image source; pre-processed; and segmented. Segmenting the pre-processed dermoscopy image includes applying a thresholding algorithm to the dermoscopy image. The thresholding algorithm includes at least one of a Huang auto-thresholding algorithm, a Li auto-thresholding algorithm, a Shanbhag auto-thresholding algorithm, an Otsu auto-thresholding algorithm, or an Isodata thresholding algorithm. A weighted border error metric is provided to allow prediction of whether segmentation is likely to avoid excluding portions of the lesion. A test is provided for determination of whether image inversion is needed for the methods to provide optimal borders. An iterative expansion algorithm is provided to for determine whether expansion is needed for the methods to provide optimal borders and to determine the degree of expansion needed for more inclusive segmentation.

Abstract: A method for automatic segmentation of dermoscopy skin lesion images includes automating a Geodesic Active Contour (GAC) initialization to be sufficiently large to encompass the lesion yet lie near the actual lesion contour. In addition, a new image plane is found by transforming the original RGB image to a smoothed image that allows the GAC to move without sticking on the minimum local energy. This method can eliminate the need for separate hair or noise removal algorithms. The method may include extraction of designated color planes to improve the initial contour and to automatically correct false segmentations. The method includes an algorithm to correct false protuberances and/or false inlets that may be present in the GAC border. A method is given to increase likelihood of including more actual lesion area. The method yields multiple border choices which may be presented to a classifier for optimal border selection.