Abstract: Hyperspectral imaging calibration devices and methods for their use are described that generate images of three dimensional samples. A calibration device may assume the shape of a desired imaging sample such as a body part and may be sterile prior to placement. The calibration device may include openings or may be modified to expose a region of the sample during use. Spectral images, typically obtained at multiple wavelengths, are made of the calibration device. Algorithms are provided that utilize the spectral images of the calibration device to determine the effects of lighting conditions and sample shape on the sample image to form a calibrated image. Calibrated images produced by these devices and methods can provide information, including clinical data that are less sensitive to lighting and sample shape compared to alternative technologies.

Abstract: The database organization and searching systems disclosed herein provide techniques for organizing large-scale image data sources such as medical image databases. Database records such as medical images may be pre-processed, such as through registration, segmentation, and extraction of feature vectors, to effectively normalize data among different images. Each image, or a portion thereof, is then labeled according to some observed characteristic or other attribute. A model, such as a linear regression model, may then be trained to associate the feature vectors with the labels. The model is then available for labeling other images. In this manner, search techniques for well-organized or indexed databases may be applied automatically to databases that are not well-organized, but that have the same underlying data type. Data that is organized in this way may also be used to construct diagnostic aids or other tools.