Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.

Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.

The present disclosure provides a method and a system for modelling a poor texture tunnel based on a vision-lidar coupling. The method includes: obtaining point cloud information collected by a depth camera, laser information collected by a lidar, and motion information of an unmanned aerial vehicle (UAV); generating a raster map based on the laser information, and obtaining pose information of the UAV based on the motion information; obtaining a map model through fusing the point cloud information, the raster map, and the pose information by a Bayesian fusion method; and correcting a latest map model by feature matching based on a previous map model.

Provided are systems and methods for registration and carrying out fine image adjustments of aerial or satellite images to obtain super registered images. Also provided are systems and methods for registration where resampling is minimized or avoided to reduce, minimize, or prevent spectral degradation.

Provided are systems and methods for registration and carrying out fine image adjustments of aerial or satellite images to obtain super registered images. Also provided are systems and methods for registration where resampling is minimized or avoided to reduce, minimize, or prevent spectral degradation.

A geospatial modeling system may include a memory and a processor cooperating therewith to generate a three-dimensional (3D) geospatial model including geospatial voxels based upon a plurality of geospatial images, obtain a newly collected geospatial image, and determine a reference geospatial image from the 3D geospatial model using Artificial Intelligence (AI) and based upon the newly collected geospatial image. The processor may further align the newly collected geospatial image and the reference geospatial image to generate a predictively registered image, and update the 3D geospatial model based upon the predictively registered image.

A geospatial modeling system may include a memory and a processor cooperating therewith to generate a three-dimensional (3D) geospatial model including geospatial voxels based upon a plurality of geospatial images, obtain a newly collected geospatial image, and determine a reference geospatial image from the 3D geospatial model using Artificial Intelligence (AI) and based upon the newly collected geospatial image. The processor may further align the newly collected geospatial image and the reference geospatial image to generate a predictively registered image, and update the 3D geospatial model based upon the predictively registered image.

A method for predicting the morphological changes of liver tumor after ablation based on deep learning includes: obtaining a medical image of liver tumor before ablation and a medical image of liver tumor after ablation; preprocessing the medical image of liver tumor before ablation and the medical image of liver tumor after ablation; obtaining a preoperative liver region map, postoperative liver region map, and postoperative liver tumor residual image map; obtaining a transformation matrix by a Coherent Point Drift (CPD) algorithm and obtaining a registration result map according to the transformation matrix; training the network by a random gradient descent method to obtain a liver tumor prediction model; using the liver tumor prediction model to predict the morphological changes of liver tumor after ablation. The method provides the basis for quantitatively evaluating whether the ablation area completely covers the tumor and facilitates the postoperative treatment plan for the patient.

A pulmonary function identifying method includes: obtaining a first image, having first image elements, and a second image, having second image elements, respectively corresponding to a first state and a second state of a lung; extracting first feature points of the first image and second feature points of the second image; registering the first image with the second image using a boundary point set registeration method and an inner tissue registeration method according to the first feature points and the second feature points, so that the first image elements correspond to the second image elements and tissue units of the lung; and determining functional index values representative of the tissue units of the lung using a ventilation function quantification method according to the first image elements and the second image elements corresponding to the first image elements.

Patient misidentification errors in medical imaging can result in serious consequences, such as the misdiagnosis of a disease state or the application of an inappropriate treatment regimen. Systems, methods, and apparatuses disclosed herein can properly and consistently identify, adjust, and/or correlate radiologic images with the correct patient. Systems and methods for automated and robust image capture are also provided. Methods for identifying a disease state in a patient and/or for treating a patient having the identified disease state are disclosed and can be based on characteristics identified through deep learning convolutional neural networks and that are associated with photographic and radiologic patient images.