The present disclosure describes a computer-implemented method for processing clinical three-dimensional image. The method includes training a fully supervised segmentation model using a labelled image dataset containing images for a disease at a predefined set of contrast phases or modalities, allow the segmentation model to segment images at the predefined set of contrast phases or modalities; finetuning the fully supervised segmentation model through co-heterogenous training and adversarial domain adaptation (ADA) using an unlabelled image dataset containing clinical multi-phase or multi-modality image data, to allow the segmentation model to segment images at contrast phases or modalities other than the predefined set of contrast phases or modalities; and further finetuning the fully supervised segmentation model using domain-specific pseudo labelling to identify pathological regions missed by the segmentation model.

A dynamic anatomic atlas is disclosed, comprising static atlas data describing atlas segments and dynamic atlas data comprising information on a dynamic property which information is respectively linked to the atlas segments.

Detections in video frames of a video signal, which are output from a machine learning model, are associated to generate a detection chain. Display of a detection in the video signal is caused based on a position of the detection in the detection chain, the confidence value of the detection and the location of the detection.

A method and system for automated deformable registration of an organ from medical images includes generating segmentations of the organ by processing a first and second series of images corresponding to different organ states using a first trained CNN. A second trained CNN processes the first and second series of images and the segmentations to deformably register the second series of images to the first series of images. The second trained CNN predicts a displacement field by minimizing a registration loss function, where the displacement field maximizes colocalization of the organ between the different states.

A diagnosis method includes: (a) checking tear film break-up time point and location by photographing cornea of the subject's eye and checking in time series at least one or more times of the tear film break-up time point; (b) checking corneal surface temperature by measuring the surface temperature of the cornea of the subject to be evaluated using a thermal imaging camera performed simultaneously with the photographing of the tear film of the eye; (c) mapping the tear film break-up time point and the change in the surface temperature of the cornea based on time; and (d) diagnosing type of dry eye syndrome based on any one of the tear film break-up time point and a location of surface temperature change time point of the corneal corresponding thereto, in mapping result in step (c).

An image processing apparatus includes at least one processor, and the processor derives three-dimensional coordinate information that defines a position of a structure in a tomographic plane from a tomographic image including the structure, and that defines a position of an end part of the structure outside the tomographic plane in a direction intersecting the tomographic image.

Risk prediction models are trained and deployed to analyze images, such as computed tomography scans, for predicting risk of lung cancer (e.g., current or future risk of lung cancer) for one or more subjects. Individual risk prediction models are trained on nodule-specific and non-nodule specific features, including longitudinal nodule specific and longitudinal non-nodule specific features, such that each risk prediction model can predict risk of lung cancer across different time horizons. Such risk prediction models are useful for developing preventive therapies for lung cancer by enabling clinical trial enrichment.

A method for imaging expected results of a medical cosmetic treatment includes converting an input image of an anatomical feature into an input image vector. A direction vector corresponding to the medical cosmetic treatment is determined. An amplitude of the direction vector is determined. The direction vector is multiplied by the determined amplitude to obtain a product vector. The product vector is vector added to the input image vector. An output image corresponding to the expected visual appearance of the human anatomical feature is generated from the vector added product vector and input image vector. A computer program stored in a non-transitory computer readable medium causes a computer to perform the imaging method.

Detecting single bacterial cells in a sample includes collecting, from a sample provided to an imaging apparatus, a multiplicity of images of the sample over a length of time; assessing a trajectory of each bacterial cell in the sample; and assessing, based on the trajectory of each bacterial cell in the sample, a number of bacterial cell divisions that occur in the sample during the length of time.

A processor searches for a first similar case from among a plurality of reference cases, each of the plurality of reference cases including at least one diagnosed image and a diagnosis log, the diagnosis log describing a treatment method performed on a diagnosed patient for whom the diagnosed image is acquired and a treatment result obtained by the treatment method, the first similar case having a similar feature to a target image obtained by imaging a treatment target patient who is to be treated, the first similar case including, as the diagnosed image, a post-treatment image obtained through imaging after treatment. The processor further searches for a second similar case from among the plurality of reference cases, the second similar case having a similar feature to the post-treatment image included in the first similar case. Further, the processor presents the treatment method and the treatment result described in a search diagnosis log that is the diagnosis log included in each of the first similar case and the second similar case.