A method for characterizing cancer organoid response to an immune cell based therapy, includes providing a panel of different combinations of cancer organoid cells and immune cells to culturing wells and culturing the different combination under conditions that support organoid growth. Brightfield and corresponding fluorescence images of the culturing wells are captured and provided to one or more trained machine learning algorithms that identify and distinguish cancer organoid cells from immune cells and characterize cancer organoid morphology changes caused by an immune cell based therapies, from which an analytical report including a characterization of cancer organoid cell death caused by the immune cell based therapy is provided.

In various examples, high beam control for vehicles may be automated using a deep neural network (DNN) that processes sensor data received from vehicle sensors. The DNN may process the sensor data to output pixel-level semantic segmentation masks in order to differentiate actionable objects (e.g., vehicles with front or back lights lit, bicyclists, or pedestrians) from other objects (e.g., parked vehicles). Resulting segmentation masks output by the DNN(s), when combined with one or more post processing steps, may be used to generate masks for automated high beam on/off activation and/or dimming or shading—thereby providing additional illumination of an environment for the driver while controlling downstream effects of high beam glare for active vehicles.

The method of the present invention classifies the nuclei in prostate tissue images with a trained deep learning network and uses said nuclear classification to classify regions, such as glandular regions, according to their malignancy grade. The method according to the present disclosure also trains a deep learning network to identify the category of each nucleus in prostate tissue image data, said category representing the malignancy grade of the tissue surrounding the nuclei. The method of the present disclosure automatically segments the glands and identifies the nuclei in a prostate tissue data set. Said segmented glands are assigned a category by at least one domain expert, and said category is then used to automatically assign a category to each nucleus corresponding to the category of said nucleus' surrounding tissue. A multitude of windows, each said window surrounding a nucleus, comprises the training data for the deep learning network.

Disclosed is a method for diagnosing a neurodegenerative disease in a subject. The method comprises obtaining from the subject a sample comprising at least one live blood cell, and optionally isolating at least one live blood cell from the sample. The method further comprises generating one or more multispectral or hyperspectral images of the at least one cell, and analysing spectral characteristics of autofluorescence from the at least one cell. Also disclosed is a system configured to aid in the detection or diagnosis of a neurodegenerative disease. Also disclosed is a method for selecting a subject for treatment for a neurodegenerative disease. Also disclosed is a method for monitoring the response of a subject to a therapeutic treatment for a neurodegenerative disease. Also disclosed is a protocol for monitoring the efficacy of a therapeutic treatment for a neurodegenerative disease.

A reference image and at least one object image and at least one analysis image are used in a method for analyzing a structure within a fluidic system. A reference image section with the structure to be analyzed, which is isolated from a reference image, is provided, the reference image having been recorded with a first camera setting. An object image which has the same fluidic state as the reference image and which was recorded with the first or a second camera setting is selected. Using the object image and using the reference image section, an image registration is performed and an edge recognition is applied for the purposes of creating a mask. At least one analysis image is selected beforehand or afterwards, the at least one analysis image and the object image having been recorded with the same camera setting. The mask is applied to the analysis image for the purposes of isolating the image section of the analysis image to be analyzed. Subsequently, the image section to be analyzed can be examined using an image-analytical evaluation.

A method, computer program, and computer system is provided for predicting data from an image. An image is divided into one or more patch images. Spatial features corresponding to the one or more patch images are compressed. Output data corresponding to the compressed spatial features is predicted. The output data is predicted based on minimizing one or more loss functions corresponding to the compressed spatial features.

A blood smear full-view intelligent analysis method, and a blood cell segmentation model and recognition model construction method. The analysis method comprises: collecting a plurality of original blood smear single-view images, establishing an original blood smear single-view image group, and establishing a blood smear full-view image on the basis of the plurality of original blood smear single-view images; constructing an image restoration model on the basis of a first training set and a first verification set; constructing an image segmentation model on the basis of a second training set and a second verification set, obtaining a third training set and a third verification set on the basis of a plurality of segmented individual blood cell images, and constructing an image recognition model; and finally obtaining a blood cell classification result. According to the method, full-view blood cells are analyzed on the basis of an artificial intelligence algorithm, thereby greatly reducing interference of human factors, improving objectivity of an inspection result, and improving blood cell analysis and classification accuracy; recognition and analysis can be realized for picture input meeting requirements, the algorithm robustness and accuracy are higher than those of conventional image recognition algorithms, and the overall time is greatly shortened.

A microscope system is provided with a microscope that acquires images at least at a first magnification and a second magnification higher than the first magnification, and a processor. The processor is configured to specify a type of a container in which a specimen is placed, and when starting observation of the specimen placed in the container at the second magnification, the processor is configured to specify a map region corresponding to a map image constructed by stitching together a plurality of second images acquired by the microscope at a higher magnification than the first magnification by performing object detection according to the type of the container on a first image that includes the container acquired by the microscope at the first magnification, and cause a display unit to display the first image and a range of the map region on the first image.

The invention is related to a method for measuring the variability of the red blood cells deformability of an individual by determining the amount of red blood cells having a tank-treading motion in a population of red blood cells from a tested blood sample of said individual, and comparing the amount to a reference amount. The determination of the amount of red blood cells having a tank-treading motion is carried out using a visualisation means such as a brightfield microscope.

Systems and methods for machine learning tissue classification are provided herein. Datasets for a plurality of biological samples are first generated. The dataset of each biological sample includes image data of the biological sample and molecular measurement data of the biological sample captured at a plurality of capture areas of the biological sample. The capture areas of the biological sample are registered to corresponding locations in the image data of the biological sample. Then, a machine learning module is trained with the datasets. Another dataset for another biological sample is generated (e.g., in the same or similar manner as the other datasets). And, the other dataset of the other biological sample is processed through the trained machine learning module to predict features in the other biological sample.