The present disclosure discloses a three-dimensional automatic location system for an epileptogenic focus based on deep learning. The system includes: a PET image acquisition and labelling module; a registration module mapping PET image to standard symmetrical brain template; a PET image preprocessing module generating mirror image pairs of left and right brain image blocks; a network SiameseNet training module containing two deep residual convolutional neural networks which share weight parameters, an output layer connecting a multilayer perceptron and a softmax layer, and using a training set of an epileptogenic focus image and an normal image to train the network to obtain a network model; a classification module and epileptogenic focus location module, using the trained network model to generate a probabilistic heatmap for the newly input PET image, a classifier determining whether the image is normal or epileptogenic focus sample, and then predicting a position for the epileptogenic focus region.

Systems and methods to partially-gate PET data include acquisition of first data describing a plurality of coincidences detected during a scan of an object, each of the plurality of coincidences associated with a coincidence time and a line of response, acquisition of a motion signal associated with motion of the object during the scan, determination of lines of response which are associated with a region of the object, determination of time periods of region motion based on the motion signal, modification of the first data to remove coincidences which are associated with the determined lines of response and which are associated with a coincidence time during a time period of region motion, reconstruction of an image of the object based on the modified first data, and display of the image.

An information processing apparatus includes a display control unit. The display control unit is configured to perform control to display a signal source in a superimposed manner on a plurality of biological tomographic images sliced in a predetermined direction, the signal source corresponding to a part of biological data indicating a temporal change of a biological signal, and initially display, in a display region of a screen of a display unit, a biological tomographic image on which a predetermined signal source is superimposed among the plurality of sliced biological tomographic images.

A radiation image display apparatus that constitutes a radiation imaging system includes a displayer and a hardware processor that acquires image data of a dynamic image constituted of a plurality of frame images, image data of an analysis dynamic image obtained by applying predetermined image processing to the image data of the dynamic image and image data of a related dynamic image which is related to the dynamic image or the analysis dynamic image respectively, and causes the displayer to display the related dynamic image together with the dynamic image and the analysis dynamic image.

A method for tomographic imaging comprising acquiring [200] a set of one or more 2D projection images [202] and reconstructing [204] a 3D volumetric image [216] from the set of one or more 2D projection images [202] using a residual deep learning network comprising an encoder network, a transform module and a decoder network, wherein the reconstructing comprises: transforming [206] by the encoder network the set of one or more 2D projection images [202] to 2D features [208]; mapping [210] by the transform module the 2D features [208] to 3D features [212]; and generating [214] by the decoder network the 3D volumetric image from the 3D features [212]. Preferably, the encoder network comprises 2D convolution residual blocks and the decoder network comprises 3D blocks without residual shortcuts within each of the 3D blocks.

An apparatus is configured to receive input image data corresponding to output image data of a first radiology scanner device, translate the input image data into a format corresponding to output image data of a second radiology scanner device and generate an output image corresponding to the translated input image data on a post processing imaging device associated with the first radiology scanner device. Medical images from a new scanner can be translate to look as if they came from a scanner of another vendor.

According to one embodiment, a radiation image diagnostic apparatus includes a gantry and image reconstruction circuitry. The gantry images a subject with radiation over a plurality of phases and acquires a plurality of imaging data sets for the plurality of phases. The image reconstruction circuitry executes an iterative reconstruction for the plurality of imaging data set to generate a plurality of reconstruction images for the plurality of phases. The image reconstruction circuitry executes the iterative reconstruction using, as the initial image, the first reconstruction image obtained by executing the iterative reconstruction based on the imaging data set of the first phase, generating a second reconstruction image for the second phase different from the first phase.

A peer-review flagging system is operable to receive a medical scan and a medical report written by a medical professional in conjunction with review of the medical scan. Automated assessment data is generated by performing an inference function on the medical scan by utilizing a computer vision model trained on a plurality of medical scans. Human assessment data is generated by performing an extraction function on the medical report. Consensus data is generated by comparing the automated assessment data to the first human assessment data. A peer-review notification is transmitted to a client device for display. The peer-review notification indicates the medical scan is flagged for peer-review in response to determining the consensus data indicates the automated assessment data compares unfavorably to the human assessment data.

Systems and methods for multi-modal, multi-resolution deep learning neural networks for segmentation, outcomes prediction and longitudinal response monitoring to immunotherapy and radiotherapy are detailed herein. A structure-specific Generational Adversarial Network (SSGAN) is used to synthesize realistic and structure-preserving images not produced using state-of-the art GANs and simultaneously incorporate constraints to produce synthetic images. A deeply supervised, Multi-modality, Multi-Resolution Residual Networks (DeepMMRRN) for tumor and organs-at-risk (OAR) segmentation may be used for tumor and OAR segmentation. The DeepMMRRN may combine multiple modalities for tumor and OAR segmentation. Accurate segmentation is may be realized by maximizing network capacity by simultaneously using features at multiple scales and resolutions and feature selection through deep supervision. DeepMMRRN Radiomics may be used for predicting and longitudinal monitoring response to immunotherapy. Auto-segmentations may be combined with radiomics analysis for predicting response prior to treatment initiation. Quantification of entire tumor burden may be used for automatic response assessment.

A radiographic image processing device includes a radiographic image acquisition unit that acquires a plurality of radiographic images of a specific subject taken using radiations having energies different from each other, a structure recognition unit that recognizes structures, which is included in the subject, using the radiographic images, an attenuation coefficient calculation unit that calculates attenuation coefficients μ of the radiation for the structures, which are recognized by the structure recognition unit, using recognition results of the structure recognition unit and the plurality of radiographic images, and an image processing unit that performs image processing on the radiographic images using the attenuation coefficients.