Abstract: Disclosed herein are systems and methods of estimating the autofluorescence (AF) signal and other non-target signals in each channel of a multi-channel image of a biological sample that is stained with one or more fluorescent labels. In some embodiments, the estimated autofluorescence signal can then be subtracted or masked from the multi-channel image. In some embodiments, the autofluorescence-removed multichannel image can then be use for further processing (e.g. image analysis, etc.).

Abstract: Embodiments disclosed herein generally relate to identifying auto-fluorescent artifacts in a multiplexed immunofluorescent image. Particularly, aspects of the present disclosure are directed to accessing a multiplexed immunofluorescent image of a slice of specimen, wherein the multiplexed immunofluorescent image comprises one or more auto-fluorescent artifacts, processing the multiplexed immunofluorescent image using a machine-learning model, wherein an output of the processing corresponds to a prediction that the multiplexed immunofluorescent image includes one or more auto-fluorescent artifacts at one or more particular portions of the multiplexed immunofluorescent image, adjusting subsequent image processing based on the prediction, performing the subsequent image processing, and outputting a result of the subsequent image processing, wherein the result corresponds to a predicted characterization of the specimen.

Abstract: Disclosed herein are systems and methods of estimating the autofluorescence (AF) signal and other non-target signals in each channel of a multi-channel image of a biological sample that is stained with one or more fluorescent labels. In some embodiments, the estimated autofluorescence signal can then be subtracted or masked from the multi-channel image. In some embodiments, the autofluorescence-removed multichannel image can then be use for further processing (e.g. image analysis, etc.).

Abstract: A method includes obtaining an image of a document against a background. A bounding box that bounds a region of the image that is distinguishable from the background is found. Coordinates of a plurality of points of the distinguishable region are found, each point being a point of the distinguishable region that is closest to each corner of the bounding box. The document is identified within the image as a region of the image whose corners are defined by the found coordinates.

Abstract: In at least some examples, a system comprises a processor and a memory coupled to the processor. The memory stores an image defect visibility predictor that, when executed by the processor, compares an original image with a defect image and outputs a predicted defect visibility image (PDVI) that accounts for defect masking by the original image.

Abstract: A method to generate an image in which a plurality of offset vectors for portions of a first image are determined by comparing the similarity of the portions to portion of a second image.

Abstract: A method to generate a histogram matched image in which a portion of a first reference image is partitioned into a plurality of regions. Histogram matching is performed separately on the plurality of regions of the first reference image and corresponding regions in a second image to generate a plurality of first histogram matched reference images. Histogram matching is also performed on the portion of the first reference image and a corresponding portion in the second image to generate a second histogram matched reference image. An area from one of at least a first histogram matched reference image and the second histogram matched reference image is selected to generate a finalized histogram matched reference image.

Abstract: A method to generate an image in which a plurality of offset vectors for portions of a first image are determined by comparing the similarity of the portions to portion of a second image.

Abstract: A method to generate a histogram matched image in which a portion of a first reference image is partitioned into a plurality of regions. Histogram matching is performed separately on the plurality of regions of the first reference image and corresponding regions in a second image to generate a plurality of first histogram matched reference images. Histogram matching is also performed on the portion of the first reference image and a corresponding portion in the second image to generate a second histogram matched reference image. An area from one of at least a first histogram matched reference image and the second histogram matched reference image is selected to generate a finalized histogram matched reference image.

Abstract: In at least some examples, a system comprises a processor and a memory coupled to the processor. The memory stores an image defect visibility predictor that, when executed by the processor, compares an original image with a defect image and outputs a predicted defect visibility image (PDVI) that accounts for defect masking by the original image.

Abstract: A method includes obtaining an image of a document against a background. A bounding box that bounds a region of the image that is distinguishable from the background is found. Coordinates of a plurality of points of the distinguishable region are found, each point being a point of the distinguishable region that is closest to each corner of the bounding box. The document is identified within the image as a region of the image whose corners are defined by the found coordinates.

Abstract: Segregating object images from an image is accomplished by a method that includes intensity thresholding and generating isolabel contour lines at image regions of constant image intensity. The shapes of the isolabel contours are quantified by calculating turning angle sequences. The turning angle sequences of contours compared to discern which contours to group and label as belonging to an object image. The method uses information obtained from intensity thresholding in combination with the inherent shapes of the object images to group isolabel contours and segregate the object images. The method is general and is used for segregating object images from continues images such as photographs and film. The method is extended to 3-dimensional image volumes and further includes modeling cross sections of object images as ellipses. An overlap criteria is used to group cross sectional object images in an images volume from 2-dimensional slices of the image volume.