Computer vision systems and methods for optimizing correlation clustering for image segmentation are provided. The system receives input data and generates a correlation clustering formulation for Benders Decomposition for optimized correlation clustering of the input data. The system optimizes the Benders Decomposition for the generated correlation clustering formulation and performs image segmentation using the optimized Benders Decomposition.

Computer vision systems and methods for optimizing correlation clustering for image segmentation are provided. The system receives input data and generates a correlation clustering formulation for Benders Decomposition for optimized correlation clustering of the input data. The system optimizes the Benders Decomposition for the generated correlation clustering formulation and performs image segmentation using the optimized Benders Decomposition.

A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry is configured to obtain a medical image related to the pancreas. The processing circuitry is configured to extract a pancreas region included in the medical image. The processing circuitry is configured to extract at least one tubular structure region from the inside of the pancreas region. The processing circuitry is configured to identify a first end part and a second end part related to the pancreas on the basis of the pancreas region. The processing circuitry is configured to estimate a primary pancreatic duct centerline of the pancreas on the basis of the tubular structure region, the first end part, and the second end part.

Certain aspects and features of this disclosure relate to graph-based video instance segmentation. In one example, a reference instance of an object in a reference frame and features in a target frame are identified and used to produce a graph of nodes and edges. Each node represents a feature in the target frame or the reference instance of the object in the reference frame. Each edge of the graph represents a spatiotemporal relationship between the feature in the target frame and the reference instance of the object. Embeddings of the nodes and edges of the graph are iteratively updated based on the spatiotemporal relationship between a feature in the target frame and the reference instance of the object in the reference frame, resulting in a fused node embedding that can be used for detecting the target instance of the object.

Retinal layer segmentation in optical coherence tomography (OCT) data is improved by using OCT angiography (OCTA) data to enhance a target retinal layer within the OCT data that may lack sufficient definition for segmentation. The OCT data is enhanced based on a mixture of the OCT data and OCTA data, such that contrast in the OCT data is enhanced in areas where OCT and OCTA data are dissimilar, and is reduced in areas where the OCT and OCTA data are similar. The target retinal layer in the OCT data is segmented based on the enhanced data. Two en face images of the OCTA data that include the target retinal layer are used to check for errors in the segmentation of the target retinal layer in the OCT data. Identified errors are replaced with an approximation based on the locations of top and bottom retinal layers of one of the en face images.

Provided are methods for object detection using radar and lidar fusion, which can include generating clusters combining clusters of point clouds for radar and lidar, respectively, from which fused features are determined using a deep learning model. Systems and computer program products are also provided.

Provided are methods for object detection using radar and lidar fusion, which can include generating clusters combining clusters of point clouds for radar and lidar, respectively, from which fused features are determined using a deep learning model. Systems and computer program products are also provided.

Segmentation of multi-energy CT data, including data in three or more energy bands. A user is enabled to input one or more region indicators in displayed CT data. Probability maps are generated and may be refined using distance metrics, which may include geodesic and Euclidean distance metrics. Segmentation may be based on the probability maps and/or refined probability maps. Segmentation of medical image data is also disclosed.

The invention relates to a method for automatic segmentation of a dental arch that comprises acquiring a three-dimensional surface of the dental arch, in order to obtain a three-dimensional representation comprising a set of vertices, generating virtual views from the three-dimensional representation, projecting the three-dimensional representation onto each two-dimensional virtual view, in order to obtain an image representing each vertex on the virtual view, processing each image by means of a deep learning network, carrying out inverse projection of each image in order to assign, to each vertex of the three-dimensional representation, one or more pixels of the images in which the vertex appears and to which it corresponds, and assigning one or more probability vectors to each vertex, determining the class of dental tissue to which each vertex most probably belongs based on the probability vector or vectors.

A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, using a model, a learned image representation of a target image. The operations further include generating, using a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image based on the convolving of the learned image representation of the target image with the text embedding.