Methods and systems for image analysis are provided, and in particular for identifying a set of base-calling locations in a flow cell for DNA sequencing. These include capturing flow cell images after each sequencing step performed on the flow cell, and identifying candidate cluster centers in at least one of the flow cell images. Intensities are determined for each candidate cluster center in a set of flow cell images. Purities are determined for each candidate cluster center based on the intensities. Each candidate cluster center with a purity greater than the purity of the surrounding candidate cluster centers within a distance threshold is added to a template set of base-calling locations.

An image-based nucleic acid detection method applied to a nucleic acid detector is provided. The method includes obtaining a plurality of images when detection liquid is performing electrophoresis. Once a target image is recognized from the plurality of images, a nucleic acid detection result is analyzed based on the target image.

An image processing method including identifying, using a machine learning system, an area of interest of a target image by analyzing microscopic features extracted from multiple image regions in the target image, the machine learning system being generated by processing a plurality of training images each comprising an image of human tissue and a diagnostic label characterizing at least one of a slide morphology, a diagnostic value, a pathologist review outcome, and an analytic difficulty; determining, using the machine learning system, a probability of a target feature being present in the area of interest of the target image based on an average probability; and determining, using the machine learning system, a prioritization value, of a plurality of prioritization values, of the target image based on the probability of the target feature being present in the target image.

The technology disclosed relates to equalizer-based intensity correction for base calling. In particular, the technology disclosed relates to accessing an image whose pixels depict intensity emissions from a target cluster and intensity emissions from additional adjacent clusters, selecting a lookup table that contains pixel coefficients that are configured to increase a signal-to-noise ratio, applying the pixel coefficients to intensity values of the pixels in the image to produce an output, and base calling the target cluster based on the output.

The technology disclosed attenuates spatial crosstalk from sequencing images for base calling. In particular, the technology disclosed accesses an image whose pixels depict intensity emissions from a target cluster and intensity emissions from additional adjacent clusters. The pixels include a center pixel that contains a center of the target cluster. Each pixel in the pixels is divisible into a plurality of subpixels. Depending upon a particular subpixel, in a plurality of subpixels of the center pixel, which contains the center of the target cluster, the technology disclosed selects, from a bank of subpixel lookup tables, a subpixel lookup table that corresponds to the particular subpixel. The selected subpixel lookup table contains pixel coefficients that are configured to maximizes a signal-to-noise ratio. The technology disclosed element-wise multiplies the pixel coefficients with the pixels and determines a weighted sum.

Systems and methods for test object classification are provided in which the test object is docked with a target object in a plurality of different poses to form voxel maps. The maps are vectorized and fed into a convolutional neural network comprising an input layer, a plurality of individually weighted convolutional layers, and an output scorer. The convolutional layers include initial and final layers. Responsive to vectorized input, the input layer feeds values into the initial convolutional layer. Each respective convolutional layer, other than the final convolutional layer, feeds intermediate values as a function of the weights and input values of the respective layer into another of the convolutional layers. The final convolutional layer feeds values into one or more fully connected layers as a function of the final layer weights and input values. The one or more full connected layers feed values into the scorer which scores each input vector to thereby classify the test object.

Embodiments of the disclosure include methods for implementing a predictive model that predicts pluripotency of cells through a cost efficient and non-destructive means. The predictive model analyzes contrast images captured from the cells and outputs predictions of cellular pluripotency at the cellular level. Thus, implementation of the predictive model guides the selection and isolation of cells that are predicted to be pluripotent. Furthermore, the predictive model facilitates retrospective analyses to correlate pluripotency metrics with differentiation success and further enables tracking of cellular pluripotency over time (e.g., to evaluate differentiation of cells).

Apparatus and methods are described including successively acquiring a plurality of microscopic images of a portion of a blood sample, and tracking motion of pixels within the successively acquired microscopic images. Trypomastigote parasite candidates within the blood sample are identified, by identifying pixel motion that is typical of trypomastigote parasites. It is determined that the blood sample is infected with trypomastigote parasites, at least partially in response thereto. An output is generated indicating that that the blood sample is infected with trypomastigote parasites. Other applications are also described.

Described are machine learning methods of identifying one or more records having a specific phenotype to enable proper correlation between genetic records and phenotypes. In an aspect, a method of identifying one or more records having a specific phenotype may comprise: (a) receiving a plurality of first records, each associated with one or more of a plurality of phenotypes; (b) receiving a plurality of second records, each associated with one or more of the phenotypes, wherein the first and second records are non-overlapping; (c) applying a machine learning algorithm to at least one first record and at least one second record to determine a classifier; (d) receiving a plurality of third records, distinct from the first and second records; and (e) applying the classifier to the third records to identify one or more third records associated with the specific phenotype.

Systems and methods are disclosed for processing images including, for example, receiving a target image of a slide corresponding to a target specimen comprising a tissue sample of a patient; determining a quality control metric for the target image via a first trained machine learning model having been trained to predict the quality control metric based on the target image, wherein the quality control metric signifies a quality control issue; and outputting, via a user interface, a sequence of a plurality of digitized pathology images, wherein a placement of the target image in the sequence is based on the quality control metric.