Embodiments include controlling a processor to access a radiological image of a region of lung tissue, where the radiological image includes a ground glass (GGO) nodule; define a tumoral region by segmenting the GGO nodule, where defining the tumoral region includes defining a tumoral boundary; define a peri-tumoral region based on the tumoral boundary; extract a set of radiomic features from the peri-tumoral region and the tumoral region; provide the set of radiomic features to a machine learning classifier trained to distinguish minimally invasive adenocarcinoma (MIA) and adenocarcinoma in situ (AIS) from invasive adenocarcinoma; receive, from the machine learning classifier, a probability that the GGO nodule is invasive adenocarcinoma, where the machine learning classifier computes the probability based on the set of radiomic features; generate a classification of the GGO nodule as MIA or AIS, or invasive adenocarcinoma, based, at least in part, on the probability; and display the classification.

Techniques for segmentation include determining an edge of voxels in a range associated with a target object. A center voxel is determined. Target size is determined based on the center voxel. In some embodiments, edges near the center are suppressed, markers are determined based on the center, and an initial boundary is determined using a watershed transform. Some embodiments include determining multiple rays originating at the center in 3D, and determining adjacent rays for each. In some embodiments, a 2D field of amplitudes is determined on a first dimension for distance along a ray and a second dimension for successive rays in order. An initial boundary is determined based on a path of minimum cost to connect each ray. In some embodiments, active contouring is performed using a novel term to refine the initial boundary. In some embodiments, boundaries of part-solid target objects are refined using Markov models.

The present disclosure relates to systems and methods for processing real-time video and detecting objects in the video. In one implementation, a system is provided that includes an input port for receiving real-time video obtained from a medical image device, a first bus for transferring the received real-time video, and at least one processor configured to receive the real-time video from the first bus, perform object detection by applying a trained neural network on frames of the received real-time video, and overlay a border indicating a location of at least one detected object in the frames. The system also includes a second bus for receiving the video with the overlaid border, an output port for outputting the video with the overlaid border from the second bus to an external display, and a third bus for directly transmitting the received real-time video to the output port.

Embodiments associated with classifying a region of tissue using features extracted from nodules and surrounding structures. One example apparatus includes a feature extraction circuit configured to automatically extract a first set of quantitative features from a nodule represented in at least one CT image, and automatically extract a second set of quantitative features from the lung parenchyma region immediately surrounding the nodule represented in the at least one CT image; a feature selection circuit configured to select an optimally predictive feature set from the first set of quantitative features and the second set of quantitative features; and a training circuit configured to train a classifier using the optimally predictive feature set to assign malignancy risk to a lung nodule represented in a CT image of a region of tissue demonstrating lung nodules. A prognosis or treatment plan may be provided based on the malignancy risk.

An X-ray imaging system using multiple pulsed X-ray sources to perform highly efficient and ultrafast 3D radiography is presented. There are multiple pulsed X-ray sources mounted on a structure in motion to form an array of sources. The multiple X-ray sources move simultaneously relative to an object on a pre-defined arc track at a constant speed as a group. Electron beam inside each individual X-ray tube is deflected by magnetic or electrical field to move focal spot a small distance. When focal spot of an X-ray tube beam has a speed that is equal to group speed but with opposite moving direction, the X-ray source and X-ray flat panel detector are activated through an external exposure control unit so that source tube stay momentarily standstill equivalently. 3D scan can cover much wider sweep angle in much shorter time and image analysis can also be done in real-time.

Provided are a disease label creation device, a disease label creation method, a disease label creation program, a learning device, and a disease detection model that can create a disease label for a simple X-ray image at a low annotation cost. An information acquisition unit of a first processor of a disease label creation device acquires a simple X-ray image, a three-dimensional CT image paired with the simple X-ray image, and a three-dimensional first disease label extracted from the CT image. A registration processing unit of the first processor performs registration between the simple X-ray image and the CT image. A disease label converter of the first processor converts the first disease label into a two-dimensional second disease label corresponding to the simple X-ray image on the basis of a result of the registration by the registration processing unit to create a disease label.

A method of generating a language feature extraction model that causes a computer to extract a feature from a text related to an image, includes that a system performs machine learning using training data including a first image, first position information related to a region of interest in the first image, and a first text that describes the region of interest to input the first text into a first model, which is the language feature extraction model, to cause the first model to output a first feature amount, input the first image and the first feature amount into a second model to cause the second model to estimate the region of interest, and train the first model and the second model such that an estimated region of interest output from the second model matches the region of interest of a correct answer indicated by the first position information.

A method includes positioning a patient at a first orientation relative to a radiation source. The method further includes using a 3D imaging technique to measure one or more positions of the patient's chest. The method further includes, while using the 3D imaging technique to measure the one or more positions of the patient's chest: generating a model of the patient's chest using the one or more positions of the patient's chest; updating the model of the patient's chest as the patient breathes; and exposing the patient to a dose of radiation using the radiation source, wherein the dose is based on the model of the patient's chest.

The present disclosure relates to a method for training a classifier. The method includes: acquiring an original image; determining a candidate target by segmenting the original image based on at least two segmentation models; determining a universal set of features by extracting features from the candidate target; determining a reference subset of features by selecting features from the universal set of features; and determining a classifier by performing classifier training based on the reference subset of features.

Methods, apparatus, and other embodiments predict response to pemetrexed based chemotherapy. One example apparatus includes an image acquisition circuit that acquires a radiological image of a region of tissue demonstrating NSCLC that includes a region of interest (ROI) defining a tumoral volume, a peritumoral volume definition circuit that defines a peritumoral volume based on the boundary of the ROI and a distance, a feature extraction circuit that extracts a set of discriminative tumoral features from the tumoral volume, and a set of discriminative peritumoral features from the peritumoral volume, and a classification circuit that classifies the ROI as a responder or a non-responder using a machine learning classifier based, at least in part, on the set of discriminative tumoral features and the set of discriminative peritumoral features.