A gamma-ray spectrum classification apparatus, comprising circuitry configured: to provide a denoising autoencoder to receive gamma-ray spectrum data representing a gamma-ray spectrum of a material to be classified and to determine feature data indicative of one or more features representative of the gamma-ray spectrum data; and to provide a classification neural network to receive the feature data and to classify the material to be classified as one of a plurality of predetermined classifications using the feature data.

A tomographic imaging system comprises a support carrying an image data acquisition system and defining a reference coordinate frame. A scan plan control sets the image-data acquisition system to acquire image-data from a selected imaging zone in the reference coordinate system. A motion detection system to detect movement and includes (i) a dynamic camera system to receive dynamic image information registered in the image coordinate frame of the dynamic camera system, (ii) an arithmetic unit configured to transform the selected imaging zone from the reference coordinate frame to the image coordinate-frame and a (iii) motion analyser to derive motion information from the registered dynamic image information in the transformed selected imaging zone. In the event of motion detected by the motion analyser in or near the imaging zone, the detected motion may be employed for motion correction.

Techniques are described for generating reformatted views of a three-dimensional (3D) anatomy scan using deep-learning estimated scan prescription masks. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise a mask generation component that employs a pre-trained neural network model to generate masks for different anatomical landmarks depicted in one or more calibration images captured of an anatomical region of a patient. The computer executable components further comprise a reformatting component that reformats 3D image data captured of the anatomical region of the patient using the masks to generate different representations of the 3D image data that correspond to the different anatomical landmarks.

There are provided machine learning device and method which can prepare divided data suitable for machine learning from volume data for learning. A machine learning unit (15) calculates detection accuracy of each organ O(j,i) in a predicted mask Pj using a loss function Loss. However, the detection accuracy of the organ O(k,i) with a volume ratio A(k,i)<Th is not calculated. That is, in the predicted mask Pk, the detection accuracy of the organ O(k,i) with a volume ratio that is small to some extent is ignored. The machine learning unit (15) changes each connection load of a neural network (16) from an output layer side to an input layer side according to the loss function Loss.

Systems and techniques may be used to estimate a real-time patient state during a radiotherapy treatment using a magnetic resonance linear accelerator (MR-Linac). For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to a 2D MR image using the correspondence motion model. The method may include directing radiation therapy, using the MR-Linac, to a target according to the patient state.

A method and imaging system for contouring medical images is described. The method comprising: receiving at least one input 2D image slice, from a set of two-dimensional (2D) image slices constituting the 3D image, and at least one set of data representing an input contour identifying one or more structures of interest in the 3D image within the at least one input 2D image slice; receiving at least one selected target image slice, from the set of the 2D image slices; and predicting target contour data for the selected target image slice that identifies at least one of the same one or more structures of interest within the target image slice, based on one or more of the received input 2D image slices and the data representing an input contours.

In inspection information display device, method, and program includes a display controller displays data related to a patient, for example, an analysis result obtained by analyzing a medical image and inspection information related to the data on a display, a decision unit decides at least one of a necessary inspection or a necessary treatment for confirming the analysis result, a resource information acquisition unit acquires resource availability information for executing at least one of the necessary inspection or the necessary treatment for confirming the analysis result, and a display controller 31 further displays the resource availability information on the display.

A computer-implemented method for evaluating an image data set of an imaged region comprises: determining, from the image data set, at least two processed data sets having different image data content; applying a first sub-algorithm, of an evaluation algorithm, to a first of at least two processed data sets to determine a first intermediate result relating to image data content of the first of the at least two processed data sets; applying a second sub-algorithm, of the evaluation algorithm, to a second of the at least two processed data sets to determine a second intermediate result relating to image data content of the second of the at least two processed data sets; determining quantitative evaluation result data by a third sub-algorithm of the evaluation algorithm, wherein the third sub-algorithm uses both the first intermediate result and the second intermediate result as input data.

A method of reading a medical image by a computing device operated by at least one processor is provided. The method includes obtaining an abnormality score of the input image using an abnormality prediction model, filtering the input image so as not to be subsequently analyzed when the abnormality score is less than or equal to a cut-off score based on the cut-off score which makes a specific reading sensitivity; and obtaining an analysis result of the input image using a classification model that distinguishes the input image into classification classes when the abnormality score is greater than the cut-off score.

A method includes, receiving multiple measurements, which are acquired using a registration tool including an ultrasound (US) transducer and a position sensor of a position-tracking system. The measurements are acquired by positioning the registration tool, while maintaining a gap from skin tissue, at multiple respective locations on a patient head and acquiring respective position measurements of the position sensor and respective US measurements of the skin tissue at the locations. First positions, of the skin tissue at the multiple locations, are calculated based on the position measurement and the US measurements obtained using the registration tool. Second positions, of the skin tissue at the multiple locations, are identified in an anatomical image of the patient head. The anatomical image is registered with a coordinate system of the position tracking system, by correlating the first positions and the second positions, so as to enable tracking a medical instrument, which is inserted into the patient head and includes another position sensor of the position-tracking system, using the anatomical image registered with the position-tracking system.