A system for monitoring organ health during treatment for cancer and the like makes use of physiological imaging of the kind used for treatment monitoring and organ-specific processing to provide a comprehensive assessment of treatment side-effects.

Methods and systems are provided for reconstructing images from measurement data using one or more deep neural networks according to a decimation strategy. In one embodiment, a method for reconstructing an image using measurement data comprises, receiving measurement data acquired by an imaging device, selecting a decimation strategy, producing a reconstructed image from the measurement data using the decimation strategy and one or more deep neural networks, and displaying the reconstructed image via a display device. By decimating measurement data to form one or more decimated measurement data arrays, a computational complexity of mapping the measurement data to image data may be reduced from O(N.sup.4), where N is the size of the measurement data, to O(M.sup.4), where M is the size of an individual decimated measurement data array, wherein M<N.

For partial volume correction, the partial volume effect is simulated using patient-specific segmentation. An organ or other object of the patient is segmented using anatomical imaging. For simulation, the locations of the patient-specific object or objects are sub-divided, creating artificial boundaries in the object. A test activity is assigned to each sub-division and forward projected. The difference of the forward projected activity to the test activity provides a location-by-location partial volume correction map. This correction map is used in reconstruction from the measured emissions, resulting in more accurate activity estimation with less partial volume effect.

Systems and methods for generating a synthesized medical image are provided. An input medical image is received. A synthesized segmentation mask is generated. The input medical image is masked based on the synthesized segmentation mask. The masked input medical image has an unmasked portion and a masked portion. An initial synthesized medical image is generated using a trained machine learning based generator network. The initial synthesized medical image includes a synthesized version of the unmasked portion of the masked input medical image and synthesized patterns in the masked portion of the masked input medical image. The synthesized patterns is fused with the input medical image to generate a final synthesized medical image.

A method for dental treatment may include receiving a plurality of images of a patient, the plurality of images including the patient's dentition and an orthodontic appliance while the patient is wearing the orthodontic appliance, determining whether each of the plurality of images satisfy a plurality of detection criteria, segmenting the teeth in the images, segmenting the images to classify each pixel as being of the orthodontic appliance and the teeth, classifying the pixels of the image as being pixels belonging to a space between an aligner and a tooth, assigning the pixels belonging to a space to one or more of the teeth, determining a conversion between image-based spatial measurements to real-world spatial measurements by projecting a tooth from the treatment plan into a plane that corresponds to a plane of a corresponding tooth in the image, and determining a size of each of the one or more spaces.

For partial volume correction, the partial volume effect is simulated using patient-specific segmentation. An organ or other object of the patient is segmented using anatomical imaging. For simulation, the locations of the patient-specific object or objects are sub-divided, creating artificial boundaries in the object. A test activity is assigned to each sub-division and forward projected. The difference of the forward projected activity to the test activity provides a location-by-location partial volume correction map. This correction map is used in reconstruction from the measured emissions, resulting in more accurate activity estimation with less partial volume effect.

The present disclosure relates to systems and methods for image processing. The system may obtain at least one image of an object. For each of the at least one image, the system may determine a recognition result of the image. The recognition result may include an image type of the image, a type of a lesion in the image, a region of the lesion in the image, and/or an image feature of the image. Further, the system may process the at least one image of the object based on at least one recognition result corresponding to the at least one image.

Methods and systems are provided for reconstructing images from measurement data using one or more deep neural networks according to a decimation strategy. In one embodiment, a method for reconstructing an image using measurement data comprises, receiving measurement data acquired by an imaging device, selecting a decimation strategy, producing a reconstructed image from the measurement data using the decimation strategy and one or more deep neural networks, and displaying the reconstructed image via a display device. By decimating measurement data to form one or more decimated measurement data arrays, a computational complexity of mapping the measurement data to image data may be reduced from O(N.sup.4), where N is the size of the measurement data, to O(M.sup.4), where M is the size of an individual decimated measurement data array, wherein M<N.

Systems and methods for generating a synthesized medical image are provided. An input medical image is received. A synthesized segmentation mask is generated. The input medical image is masked based on the synthesized segmentation mask. The masked input medical image has an unmasked portion and a masked portion. An initial synthesized medical image is generated using a trained machine learning based generator network. The initial synthesized medical image includes a synthesized version of the unmasked portion of the masked input medical image and synthesized patterns in the masked portion of the masked input medical image. The synthesized patterns is fused with the input medical image to generate a final synthesized medical image.

A method includes obtaining image data, selecting image datasets from the image data, creating three-dimensional (3D) matrices based on the selected image dataset, refining the 3D matrices, applying one or more matrix operations to the refined 3D matrices, selecting corresponding matrix columns from the 3D matrices, applying big data convolution algorithm to the selected corresponding matrix columns to create a two-dimensional (2D) matrix, and applying a reconstruction algorithm to create a super-resolution biomarker map image.