Abstract: Real-time focusing in a slide-scanning system. In an embodiment, focus points are added to 500 an initialized focus map while acquiring a plurality of image stripes of a sample on a glass slide. For each image stripe, a plurality of frames, collectively representing the image stripe, may be acquired using both an imaging line-scan camera and a tilted focusing line-scan camera. Focus points, representing positions of best focus for trusted frames, are added to the focus map. Outlying focus points are removed from the focus map. In some cases, one or more image stripes may be reacquired. Finally, the image stripes are assembled into a composite image of the sample.

Abstract: Real-time focusing in a slide-scanning system. In an embodiment, focus points are added to an initialized focus map while acquiring a plurality of image stripes of a sample on a glass slide. For each image stripe, a plurality of frames, collectively representing the image stripe, may be acquired using both an imaging line-scan camera and a tilted focusing line-scan camera. Focus points, representing positions of best focus for trusted frames, are added to the focus map. Outlying focus points are removed from the focus map. In some cases, one or more image stripes may be reacquired. Finally, the image stripes are assembled into a composite image of the sample.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: Automated stain finding. In an embodiment, an image of a sample comprising one or more stains is received. For each of a plurality of pixels in the image, an optical density vector for the pixel is determined. The optical density vector comprises a value for each of the one or more stains, and represents a point in an optical density space that has a number of dimensions equal to a number of the one or more stains. The optical density vectors are transformed from the optical density space into a representation in a lower dimensional space. The lower dimensional space has a number of dimensions equal to one less than the number of dimensions of the optical density space. An optical density vector corresponding to each of the one or more stains is identified based on the representation.

Abstract: Real-time focusing in a slide-scanning system. In an embodiment, focus points are added to an initialized focus map while acquiring a plurality of image stripes of a sample on a glass slide. For each image stripe, a plurality of frames, collectively representing the image stripe, may be acquired using both an imaging line-scan camera and a tilted focusing line-scan camera. Focus points, representing positions of best focus for trusted frames, are added to the focus map. Outlying focus points are removed from the focus map. In some cases, one or more image stripes may be reacquired. Finally, the image stripes are assembled into a composite image of the sample.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: Automatic nuclear segmentation. In an embodiment, a plurality of superpixels are determined in a digital image. For each of the superpixels, any superpixels located within a search radius from the superpixel are identified, and, for each unique local combination between the superpixel and any identified superpixels located within the search radius from the superpixel, a local score for the local combination is determined. One of a plurality of global sets of local combinations with an optimum global score is identified based on the determined local scores.

Abstract: Automated stain finding. In an embodiment, an image of a sample comprising one or more stains is received. For each of a plurality of pixels in the image, an optical density vector for the pixel is determined. The optical density vector comprises a value for each of the one or more stains, and represents a point in an optical density space that has a number of dimensions equal to a number of the one or more stains. The optical density vectors are transformed from the optical density space into a representation in a lower dimensional space. The lower dimensional space has a number of dimensions equal to one less than the number of dimensions of the optical density space. An optical density vector corresponding to each of the one or more stains is identified based on the representation.

Abstract: Automatic nuclear segmentation. In an embodiment, a plurality of superpixels are determined in a digital image. For each of the superpixels, any superpixels located within a search radius from the superpixel are identified, and, for each unique local combination between the superpixel and any identified superpixels located within the search radius from the superpixel, a local score for the local combination is determined. One of a plurality of global sets of local combinations with an optimum global score is identified based on the determined local scores.