Abstract: In a method of 3-D object detection, an image is pre-processed. Using cross-section analysis, a confidence array is built. A plurality of peaks in the confidence array are detected, wherein the peaks signify a likelihood of a 3-D object of interest.

Abstract: A computer-implemented method for building an atlas includes providing a volume data for a plurality of bones, segmenting, individually, the plurality of bones from the volume data, storing locations of a plurality of voxels for each of the plurality of bones, wherein each of the plurality of bones is registered with a dedicated list of locations, wherein the locations are locations in a coordinate system of the volume data, selecting one or more of the plurality of bones, forming a selected structure, and rendering the selected structure in the coordinate system of the volume data according to the dedicated list of locations of each of the plurality of bones in the selected structure, wherein a rendering is displayed by a display.

Abstract: A computer-implemented method for candidate generation in three-dimensional volumetric data comprises forming a binary volumetric image of the three-dimensional volumetric data including labeled foreground voxels, estimating a plurality of shape features of the labeled foreground voxels in the binary volumetric data including, identifying peak voxels and high curvature voxels from the foreground voxels in the binary volumetric image, accumulating a plurality of confidence values for boundary and each peak voxel, and detecting confidence peaks from the plurality of confidence values, wherein the confidence peaks are determined to be the candidate points, and refining the candidate points given detected confidence peaks, wherein refined candidate points are determined to be candidates.

Abstract: A method of identifying a patient from digital medical images includes providing a first digital image volume of an organ of a patient and a second digital image volume of the same organ, segmenting each slice of the first image volume and calculating a cross-sectional area of the organ in each slice to form a first area profile, segmenting each slice of the second image volume and calculating a cross-sectional area of the organ in each slice to form a second area profile, and comparing the first area profile with the second area profile to determine a correlation value for the two profiles. Based on the correlation value between the first area profile and the second area profile, it is determined whether the first digital image volume of the organ and the second digital image volume of the same organ came from the same patient.