Agilent Technologies, Inc.

Amir Ben-Dor

Elad Arbel

Zohar H Yakhini

Victor Lim

Richard K Workman

Itay Remer

Nicholas Michael Sampas

Robert Lloyd Kincaid

Leslie Anne Leonard

Paul S Meltzer

Edward R Dougherty

Yidong Chen

Michael L Bittner

Ron Shamir

Jeff Trent

Ashani Weeraratna

Yuan Jiang

Nick Sampas

Novel tools and techniques are provided for implementing augmented reality (AR)-based assistance within a work environment. In various embodiments, a computing system might receive, from a camera having a field of view of a work environment, first images of at least part of the work environment, the first images overlapping with a field of view of a user wearing an AR headset; might analyze the received first images to identify objects; might query a database(s) to determine a task associated with a first object(s) among the identified objects; might generate an image overlay providing at least one of graphical icon-based, text-based, image-based, and/or highlighting-based instruction(s) each indicative of instructions presented to the user to implement the task associated with the first object(s); and might display, to the user's eyes through the AR headset, the generated first image overlay that overlaps with the field of view of the user's eyes.

Method and system for implementing augmented reality (AR)-based assistance within work environment

Novel tools and techniques are provided for implementing digital microscopy imaging using deep learning-based segmentation and/or implementing instance segmentation based on partial annotations. In various embodiments, a computing system might receive first and second images, the first image comprising a field of view of a biological sample, while the second image comprises labeling of objects of interest in the biological sample. The computing system might encode, using an encoder, the second image to generate third and fourth encoded images (different from each other) that comprise proximity scores or maps. The computing system might train an AI system to predict objects of interest based at least in part on the third and fourth encoded images. The computing system might generate (using regression) and decode (using a decoder) two or more images based on a new image of a biological sample to predict labeling of objects in the new image.

Deep learning based instance segmentation via multiple regression layers

Novel tools and techniques are provided for implementing digital microscopy imaging using deep learning-based segmentation via multiple regression layers, implementing instance segmentation based on partial annotations, and/or implementing user interface configured to facilitate user annotation for instance segmentation. In various embodiments, a computing system might generate a user interface configured to collect training data for predicting instance segmentation within biological samples, and might display, within a display portion of the user interface, the first image comprising a field of view of a biological sample. The computing system might receive, from a user via the user interface, first user input indicating a centroid for each of a first plurality of objects of interest and second user input indicating a border around each of the first plurality of objects of interest. The computing system might train an AI system to predict instance segmentation of objects of interest in images of biological samples.

User interface configured to facilitate user annotation for instance segmentation within biological samples

A method of operating a data processing system to automatically process a color digital image of a specimen that has been stained with a first dye and a second different dye is disclosed. The method includes receiving a color image that includes a plurality of pixels, each pixel being characterized by a pixel vector having components determined by the intensity of light in each of a corresponding number of wavelength bands. A plurality of pixel vectors of the image are transformed to a hue space divided into a plurality of bins, each bin being characterized by a number of pixels that have been transformed into that bin. The data processing system automatically finds first and second color vectors characterizing the first and second dyes, respectively based on the number of pixels that were transformed into each of the bins.

Method for unsupervised stain separation in pathological whole slide images

Systems and methods for displaying gene- and/or protein-related data with respect to chromosome maps at locations identifying relevant positioning of the genes with which the gene- and/or protein related data are associated. Multiple experiments may be plotted onto the display adjacent one or more chromosome maps. Automatic extraction of genomic location, based on accession numbers or other unique identifiers and cross connection with expression data is provided. Statistical assessments of correlations between expression and genome localization may be performed. Zooming capabilities, thumbnail/fullview toggling, browsability and linked data may be included as features of the visualization systems described.

Visualizing expression data on chromosomal graphic schemes

The overexpression of certain marker genes including Wnt5a has been found useful in the identification of more aggressive forms of malignant melanoma. Therefore, the overexpression of these genes in tumor samples of malignant melanoma may be useful in the diagnosis, profiling, and treatment of patients suffering from this disease. Inhibitors of Wnt5a activity may be useful in the treatment of aggressive forms of malignant melanoma. Inhibition of Wnt5a activity may be effected by any method including anti-sense therapy, gene therapy, and pharmaceutical intervention.

Classifying cancers

A method and system for applying arbitrary similarity metrics to data entities in order to partition the entities into subsets of related entities. The method and system iteratively construct successive subsets, during construction of each subset adding candidate entities, not yet assigned to a subset, with high affinities toward the subset and removing entities previously assigned to the subset for which the affinities toward the subset have decreased. The method and system efficiently partition data with a high probability of finding an optimal or near-optimal partitioning.

Growing community of inventors

Kfar-Saba, Israel

Amir Ben-Dor