There are provided system and method of classifying defects in a specimen. The method includes: obtaining one or more defect clusters detected on a defect map of the specimen, each cluster characterized by a set of cluster attributes comprising spatial attributes including spatial density indicative of density of defects in one or more regions accommodating the cluster, each given defect cluster being detected at least based on the spatial density thereof meeting a criterion. The defect map also comprises non-clustered defects. Defects of interest (DOI) are identified in each cluster by performing respective defect filtrations for each cluster and non-clustered defects.

A microscope comprises a microscope stand, a camera for recording microscope images and a computing device, which is configured to carry out image processing of the recorded microscope images. The computing device is configured to: define relevant image structures; localize relevant image structures in the microscope images; derive stitching parameters from locations of the relevant image structures; and create a result image with the aid of the microscope images, with the stitching parameters being taken into account. Moreover, a corresponding method is described.

The method of labeling an image of cells of a patient, in particular an immunocytochemistry image comprises the following steps. First, a digital image of a stained immunocytochemistry biological sample of the patient is received. Following by the step that a computerized classification of cells in the digital image based on color, shape or texture in the digital image, the digital image is labeled by application of a trained neural network on at least one portion of the digital image which comprises a digital image of one cell classified under a first category during the computerized classification.

The invention relates to a method for determining information for distinguishing between tissue fluid cells and tissue cells in a high-resolution image (34) of a tissue area. In the method, images (33A-E) stored temporarily with a low resolution and a high image rate before the high-resolution image (34) is recorded are accessed and the information for distinguishing between tissue fluid cells and tissue cells is obtained from the temporarily stored images (33A-E) with the low resolution and the high image rate.

Examples relate to a system, a method and a computer program for training a machine-learning model, to a machine-learning model, a method and computer program for detecting at least one property of a sample of organic tissue, and to a microscope system. The system comprises one or more storage modules and one or more processors. The system is configured to obtain a plurality of images of a sample of organic tissue. The plurality of images are taken using a plurality of different imaging characteristics. The system is configured to train a machine-learning model using the plurality of images. The plurality of images are used as training samples and information on at least one property of the sample of organic tissue is used as a desired output of the machine-learning model. The machine-learning model is trained such that the machine-learning model is suitable for detecting the at least one property of the sample of organic tissue in image input data reproducing (only) a proper subset of the plurality of different imaging characteristics. The system is configured to provide the machine-learning model.

A method of analyzing a specimen includes detecting a specimen integrity error in the specimen; capturing an image of the specimen; sending the image of the specimen to a customer support center at a remote location; analyzing the image of the specimen at the customer support center; and determining a cause of the specimen integrity error in response to analyzing the image of the specimen. Diagnostic analyzers and diagnostic systems are also disclosed.

A method of implementing an artificial intelligence based neuroradiology platform for neurological tumor identification comprises providing a multilayer convolutional network for neurological tumor identification configured for segmenting data sets of full neurologic scans into resolution voxels; supervised learning and validation of the platform by classification of tissue within classification voxels of a specific given training and validation data sets by the multilayer convolutional network for neurological tumor identification with each classification voxel of the training and validation data sets having a predetermined ground truth; and implementing the platform by classification of tissue within classification voxels of a specific given patient data sets by the multilayer convolutional network for neurological tumor identification with each classification voxel of each data set assigned a label. The platform may be used for T-cell therapy initiation and tracking. An artificial intelligence based neuroradiology platform implemented according to the method is disclosed.

Apparatus and methods are described including placing at least a portion of a blood sample within a sample chamber (52), and acquiring microscopic images of the portion of the blood sample. Candidates of a given entity within the blood sample are identified, within the microscopic image. At least some of the candidates as being the given entity are validated, by performing further analysis of the candidates. A count of the candidates of the given entity is compared to a count of the validated candidates of the given entity, and at least the portion of the sample is invalidated from being used for performing at least some measurements upon the sample, at least partially based upon a relationship between the count of candidates and the count of validated candidates. Other applications are also described.

A method for processing microscope images in order to generate an image processing result comprises: implementing a convolutional neural network, wherein a first convolutional layer calculates an output tensor from an input tensor formed from a microscope image. The output tensor is input into one or more further layers of the convolutional neural network in order to calculate the image processing result. The first convolutional layer comprises a plurality of filter kernels. At least several of the filter kernels are respectively representable by at least one filter matrix with learning parameters and dependent filter matrices with implicit parameters, which are determined by means of the learning parameters and one or more weights to be learned, wherein the filter matrices with learning parameters of different filter kernels are different from one another and different layers of the output tensor are calculated by different filter kernels.

The invention relates to a method and to an apparatus for analyzing an image of a microlithographic microstructured component wherein in the image each of a multiplicity of pixels is assigned in each case an intensity value. A method according to the invention comprises the following steps: isolating a plurality of edge fragments in the image;

classifying each of the isolated edge fragments either as a relevant edge fragment or as an irrelevant edge fragment; and ascertaining contiguous segments in the image based on the relevant edge fragments.