Abstract: Cell identification and classification is a well-known problem in the pathology domain that help identify microenvironments. In addition to the characteristic of each cell, its interactions with the neighboring regions or other cells is also important. This involves correct identification of neighboring elements and analytically representing the interactions between them. This disclosure presents a system that combines many such features, some hand engineered and some machine derived through training of Deep Learning algorithms that can be used to study the microenvironments.

Abstract: Histopathological scoring can be based on the areas of certain types of cells or the expression of genotypic or phenotypic characteristics of those cells, as identified by a biological assay. Automating a scoring process with an image analysis algorithm includes correctly delineating the areas of interest, a process known as segmentation. The present systems and methods accomplish this segmentation using a generative adversarial network trained to generate masks covering each area of interest. The invention can perform both segmentation and classification by using a separate image band for each class. A scoring algorithm may utilize the classifications of, for example, a tumor area and an area of immune cell staining by interpreting the separate image bands of each area. Classification problems with more bands would use images with the equivalent number of bands. There is no limit to the number of bands an image can encode for each pixel.

Abstract: Histopathological scoring can be based on ratios of different types of cells, and in particular, cells which exhibit a particular genotypic or phenotypic characteristic, as identified by a biological assay. Automating the scoring process with an image analysis algorithm requires both correctly delineating cells, a process known as segmentation, and classifying each cell according to its morphology and reactivity to the assay. Successful classification thus depends on both successful segmentation and successful classification, resulting in the error rates of the two steps being compounded. Systems and methods of the present disclosure reduce error by performing the cell counting and classification task in a single step using a generative adversarial network (or GAN). The present disclosure similarly employs a GAN for counting cells by representing the training data as a Gaussian at the center of each cell nucleus.

Abstract: Histopathological scoring can be based on the areas of certain types of cells or the expression of genotypic or phenotypic characteristics of those cells, as identified by a biological assay. Automating a scoring process with an image analysis algorithm includes correctly delineating the areas of interest, a process known as segmentation. The present systems and methods accomplish this segmentation using a generative adversarial network trained to generate masks covering each area of interest. The invention can perform both segmentation and classification by using a separate image band for each class. A scoring algorithm may utilize the classifications of, for example, a tumor area and an area of immune cell staining by interpreting the separate image bands of each area. Classification problems with more bands would use images with the equivalent number of bands. There is no limit to the number of bands an image can encode for each pixel.

Abstract: Systems and methods of the present disclosure enable ground truth dataset creation using processing devices configured to receive at least one user profile of at least one user and user-generated labels for each sample of at least one sample, where the user-generated labels are associated with the at least one user profile. A most likely label for each sample is produced using a weighting of each user-generated label according to user attributes in each user profile associated with each user-generated label. Each most likely label is recorded for each sample in a ground-truth dataset associated with each sample to identify a ground truth of the at least one sample, and each most likely label and each sample is provided to a machine learning model to train the machine learning model according to a difference between a predicted label for each sample and each most likely label.

Abstract: As users browse web pages online they may come across a recipe in which they are interested, included in a web page. The user may then interact with a web browser tool, thereby expressing interest in the recipe. A recipe book server extracts the recipe from the web page including the recipe. The recipe book server may provide the user with an interface, via a web page for example, for editing or modifying the recipe. The recipe book server, on receiving a selection of recipes from the user to include in a cookbook may generate one or more candidate cookbooks using cookbook templates by populating the cookbook templates with the selected recipes. The user may select and modify a cookbook from the candidate cookbooks. The recipe book server then prepares the selected cookbook for printing, and may send the prepared cookbook to be printed by a professional printer.