Abstract: A method of segmenting images of biological specimens using adaptive classification to segment a biological specimen into different types of tissue regions. The segmentation is performed by, first, extracting features from the neighborhood of a grid of points (GPs) sampled on the whole-slide (WS) image and classifying them into different tissue types. Secondly, an adaptive classification procedure is performed where some or all of the GPs in a WS image are classified using a pre-built training database, and classification confidence scores for the GPs are generated. The classified GPs with high confidence scores are utilized to generate an adaptive training database, which is then used to re-classify the low confidence GPs. The motivation of the method is that the strong variation of tissue appearance makes the classification problem more challenging, while good classification results are obtained when the training and test data origin from the same slide.

Abstract: The invention relates to a system (100) for computing a risk, the risk relating to injuring an anatomical structure by a medical device during a medical procedure, the system comprising: a structure unit (110) for obtaining a position of the anatomical structure; a device unit (120) for obtaining a position of the medical device; and a risk unit (130) for computing the risk relating to injuring the anatomical structure, based on the position of the medical device and the position of the anatomical structure. The system (100) may be used for planning a path of a medical device, which path minimizes said risk, or for monitoring said risk during the medical procedure.

Abstract: A method of segmenting images of biological specimens using adaptive classification to segment a biological specimen into different types of tissue regions. The segmentation is performed by, first, extracting features from the neighborhood of a grid of points (GPs) sampled on the whole-slide (WS) image and classifying them into different tissue types. Secondly, an adaptive classification procedure is performed where some or all of the GPs in a WS image are classified using a pre-built training database, and classification confidence scores for the GPs are generated. The classified GPs with high confidence scores are utilized to generate an adaptive training database, which is then used to re-classify the low confidence GPs. The motivation of the method is that the strong variation of tissue appearance makes the classification problem more challenging, while good classification results are obtained when the training and test data origin from the same slide.

Abstract: A method and associated method and computer program product for acquiring focused images of a specimen on a slide, by determining optimal scanning trajectories. The method includes capturing a relatively low magnification image of the slide to locate the specimen, forming a grid that includes an arrangement of grid points, overlaying at least part of the grid over a field of view that covers at least part of the specimen, capturing a relatively high magnification Z-stack of images of the specimen within the field of view, determining a best focus for each grid point within said at least part of the grid to form a resulting grid of three dimensional points, and based on the resulting grid, determining one or more three dimensional scanning trajectories.

Abstract: Systems and methods for unmixing of multichannel image data in the presence of locally varying image characteristics. Feature images created from a multi-channel input image form a feature vector for each pixel in the input image. Feature vectors are classified based on the local image characteristics, and areas are formed in the input image that share local image characteristics. Each area is unmixed separately using reference vectors that were obtained from regions in example images that have the same image characteristics. The unmixing results are combined to form a final unmixing result image created from the individually unmixed image areas.

Abstract: Methods and systems for generating a heat map that reduces bias in selecting FOVs are disclosed. Some disclosed methods include annotating a primary stained image, registering the annotation to a secondary serial specific stained image, using an image analysis algorithm to compute a scoring criteria specific to the tissue and assay type for tiled regions in the image, using a sliding window in the annotated tumor region to compute values for each pixel in a heat map which correlate to the specific scoring criteria, displaying the heat map at low resolution, ranking and selecting hot spots, selecting FOVs from the hot spot regions which results in displaying the slide-level score for the FOVs. The systems comprise, among other things, software configured to perform the referenced method.

Abstract: The disclosure relates to devices, systems and methods for generating a digital image of a tissue section that is a composite of two or more source digital images of adjacent tissue sections and which may have a real-time adjustable boundary between different source images. The devices include computer software products for a fused-view visualization tool which permits one or more of generating and displaying the composite image and modifying the location of one or more boundaries between source images comprising the composite image. The systems include computer-implemented systems such as work stations and networked computers for analyzing tissue samples using the fused-view visualization tool. The methods include processes for visualization of a tissue sample as a composite image derived from two or more slides of adjacent tissue sections, for example as an interactive composite image wherein the proportion of each source image in the composite image may be altered.

Abstract: The subject disclosure presents systems and methods for automatically selecting meaningful regions on a whole-slide image and performing quality control on the resulting collection of FOVs. Density maps may be generated quantifying the local density of detection results. The heat maps as well as combinations of maps (such as a local sum, ratio, etc.) may be provided as input into an automated FOV selection operation. The selection operation may select regions of each heat map that represent extreme and average representative regions, based on one or more rules. One or more rules may be defined in order to generate the list of candidate FOVs. The rules may generally be formulated such that FOVs chosen for quality control are the ones that require the most scrutiny and will benefit the most from an assessment by an expert observer.

Abstract: Disclosed, among other things, is a computer device and computer-implemented method of classifying cells within an image of a tissue sample comprising providing the image of the tissue sample as input; computing nuclear feature metrics from features of nuclei within the image; computing contextual information metrics based on nuclei of interest with the image; classifying the cells within the image using a combination of the nuclear feature metrics and contextual information metrics.

Abstract: A nuclear imaging apparatus (8) acquires nuclear imaging data comprising events wherein each event records at least spatial localization information and a timestamp for a nuclear decay event. An event-preserving image reconstruction module (22) reconstructs the nuclear imaging data using an event-preserving reconstruction algorithm to generate an image represented as an event-preserving reconstructed image dataset (ID) comprising for each event the timestamp and at least one spatial voxel assignment. One or more structures are identified in the image and independent motion compensation is performed for each structure. In one approach, an events group is identified corresponding to the structure comprising events assigned to the structure by the event-preserving reconstructed image dataset; a time binning of the events of each events group is optimized based on a motion profile for the structure; time bin images are generated; and the structure is spatially registered in the time bin images.

Abstract: A medical imaging system includes a data store (16) of reconstruction procedures, a selector (24), a reconstructor (14), a fuser (28), and a display (22). The data store (16) of reconstruction procedures identifies a plurality of reconstruction procedures. The selector (24) selects at least two reconstruction procedures from the data store of reconstruction procedures based on a received input, each reconstruction procedure optimized for one or more image characteristics. The reconstructor (14) concurrently performs the selected at least two reconstruction procedures, each reconstruction procedure generates at least one image (26) from the at least one data store of imaging data (12). The fuser (28) fuses the at least two generated medical images to create a medical diagnostic image which includes characteristics from each generated image (26). The display (22) displays the medical diagnostic image.

Abstract: An x-ray computed tomography system (14) includes a gantry (15), a plurality of elements (18), and one or more processors (28). The gantry (15) moves to different orientations and generates x-ray data which includes image projection data at a plurality of the orientations. The plurality of elements (18) connect to the gantry and cause x-ray attenuation of the generated projection data. The one or more processors (28) are programmed to receive (60) the generated x-ray data and decompose (62) the received image projection data into indications of relative positions of the plurality of elements at different orientations of the gantry.

Abstract: A comprehensive strategy is used to determine valid reference time-concentration curves (TCCs) from image data. The image data corresponds to a series of image scans acquired over time for an area of interest of a patient to which a contrast agent was previously administered. The image scans are initially registered to a common coordinate system. Then, observed potential reference TCCs in the image scans are compared to modeled reference TCCs to determine if the potential reference TCCs are plausible reference TCCs. Thereafter, any plausible reference TCCs are evaluated to determine if they contain residual, isolated motion artifacts. If a plausible reference TCC does not include any motion artifacts, the plausible reference TCC is considered a valid reference TCC. If a plausible reference TCC is determined to include motion artifacts, the plausible reference TCC is modified to a valid reference TCC by removing the motion artifacts, or otherwise the plausible reference TCC is rejected.

Abstract: A method and apparatus are provided for locating a mirror line for conducting a mirror analysis of an image by reflecting extracted image content from a portion of the image on one side of the mirror line and overlaying this reflected image content onto the corresponding portion of the image on the opposing side of the mirror line. The extracted image content that is reflected onto the corresponding portion of the image on the opposite side of the mirror line is continuously updated in real-time as the user manipulates the location or orientation of the mirror line.

Abstract: Techniques for acquiring focused images of a microscope slide are disclosed. During a calibration phase, a “base” focal plane is determined using non-synthetic and/or synthetic auto-focus techniques. Furthermore, offset planes are determined for color channels (or filter bands) and used to generate an auto-focus model. During subsequent scans, the auto-focus model can be used to quickly estimate the focal plane of interest for each color channel (or filter band) rather than re-employing the non-synthetic and/or synthetic auto-focus techniques.

Abstract: This disclosure describes methods, kits, and systems for scoring the immune response to cancer through examination of tissue infiltrating lymphocytes (TILs). Methods of scoring the immune response in cancer using tissue infiltrating lymphocytes include detecting CD3, CD8, CD20, and FoxP3 within the sample and scoring the detection manually or scoring the digital images of the staining with the aid of image analysis and algorithms.

Abstract: A method of segmenting images of biological specimens using adaptive classification to segment a biological specimen into different types of tissue regions. The segmentation is performed by, first, extracting features from the neighborhood of a grid of points (GPs) sampled on the whole-slide (WS) image and classifying them into different tissue types. Secondly, an adaptive classification procedure is performed where some or all of the GPs in a WS image are classified using a pre-built training database, and classification confidence scores for the GPs are generated. The classified GPs with high confidence scores are utilized to generate an adaptive training database, which is then used to re-classify the low confidence GPs. The motivation of the method is that the strong variation of tissue appearance makes the classification problem more challenging, while good classification results are obtained when the training and test data origin from the same slide.

Abstract: The subject disclosure presents systems and methods for receiving a plurality of assay information along with a query for one or more features of interest, and projecting anatomical information from an anatomical assay onto a staining assay, for example an immunohistochemical (IHC) assay that is commonly registered with the anatomical assay, to locate or determine features appropriate for analysis. The anatomical information may be used to generate a mask that is projected on one or more commonly registered staining assays. A location of the feature of interest in the staining assay may be correlated with the anatomical context provided by the mask, with any features of interest that match the anatomical mask being selected or indicated as appropriate for analysis.

Abstract: A hybrid imaging system including a first imaging system configured to acquire low resolution anatomical data of a first field of view of an anatomical structure. A second imaging system is configured to acquire functional data of the first field of view of the anatomical structure. A reconstruction processor is configured to reconstruct the functional data based on attenuation data into an attenuation corrected image. In response to the attenuation corrected image showing regions of interest, with the first imaging system or another imaging system acquiring high resolution data of one or more portions of the first field of view containing the regions of interest. The reconstruction processor reconstructs the high resolution anatomical data into one or more high resolution images of the regions of interest.

Abstract: In Positron Emission Tomography, a time window (260) and an energy window (225) are dynamically adjusted, based on an attenuation map, count rate, clinical application, discrimination tailoring, and/or offline discrimination tailoring. Detected radiation events are filtered using the dynamically adjusted energy and time windows into scattered events, random events, and true events. The true events are input to image reconstruction, correction, and error analysis.