Abstract: Systems, computer-implemented methods, and computer readable media for generating a synthetic image of an anatomical portion based on an origin image of the anatomical portion acquired by an imaging device using a first imaging modality are disclosed. These systems may be configured to receive the origin image of the anatomical portion acquired by the imaging device using the first imaging modality, receive a convolutional neural network model trained for predicting the synthetic image based on the origin image, and convert the origin image to the synthetic image through the convolutional neural network model. The synthetic image may resemble an imaging of the anatomical portion using a second imaging modality differing from the first imaging modality.

Abstract: Systems and methods are provided for generating a pseudo-CT prediction model that can be used to generate pseudo-CT images. An exemplary system may include a processor configured to retrieve training data including at least one MR image and at least one CT image for each of a plurality of training subjects. For each training subject, the processor may extract a plurality of features from each image point of the at least one MR image, create a feature vector for each image point based on the extracted features, and extract a CT value from each image point of the at least one CT image. The processor may also generate the pseudo-CT prediction model based on the feature vectors and the CT values of the plurality of training subjects.

Abstract: Systems and methods are disclosed for generating radiotherapy treatment machine parameters based on projection images of a target anatomy. The systems and methods include operations including receiving a set of pairs of image data for each gantry angle of a radiotherapy treatment machine, wherein each pair of the set of pairs comprises a given projection image that represents a view of an anatomy of a subject from a given gantry angle and a given graphical aperture image of multi-leaf collimator (MLC) leaf positions at the given gantry angle based on the given projection image; training a generative adversarial network (GAN) model based on the set of pairs of image data for each gantry angle; and using the trained GAN model to predict an aperture image of MLC leaf positions for a desired gantry angle based on a projection image that represents a view of an anatomical region of interest.

Abstract: The present disclosure relates to systems and methods for developing radiotherapy treatment plans through the use of machine learning approaches and neural network components. A neural network is trained using one or more three-dimensional medical images, one or more three-dimensional anatomy maps, and one or more dose distributions to predict a fluence map or a dose map. During training the neural network receives a predicted dose distribution determined by the neural network that is compared to an expected dose distribution. Iteratively the comparison is performed until a predetermined threshold is achieved. The trained neural network is then utilized to provide a three-dimensional dose distribution.

Abstract: Techniques for enhancing image segmentation with the integration of deep learning are disclosed herein. An example method for atlas-based segmentation using deep learning includes: applying a deep learning model to a subject image to identify an anatomical feature, registering an atlas image to the subject image, using the deep learning segmentation data to improve a registration result, generating a mapped atlas, and identifying the feature in the subject image using the mapped atlas. Another example method for training and use of a trained machine learning classifier, in an atlas-based segmentation process using deep learning, includes: applying a deep learning model to an atlas image, training a machine learning model classifier using data from applying the deep learning model, estimating structure labels of areas of the subject image, and defining structure labels by combining the estimated structure labels with labels produced from atlas-based segmentation on the subject image.

Abstract: A statistical learning technique that does not rely upon paired imaging information is described herein. The technique may be computer-implemented and may be used in order to train a statistical learning model to perform image synthesis, such as in support of radiation therapy treatment planning. In an example, a trained statistical learning model may include a convolutional neural network established as a generator convolutional network, and the generator may be trained at least in part using a separate convolutional neural network established as a discriminator convolutional network. The generator convolutional network and the discriminator convolutional network may form an adversarial network architecture for use during training. After training, the generator convolutional network may be provided for use in synthesis of images, such as to receive imaging data corresponding to a first imaging modality type, and to synthesize imaging data corresponding to a different, second imaging modality type.

Abstract: Systems and methods are disclosed for monitoring anatomic position of a human subject and modifying a radiotherapy treatment based on anatomic position changes, as determined with a regression model trained to estimate movement of a region of interest. Example operations for movement monitoring and therapy control include: obtaining 3D image data for a subject, which provides a reference volume and at least one defined region of interest; obtaining real-time 2D image data corresponding to the subject, captured during the radiotherapy treatment session; extracting features from the 2D image data; producing a relative motion estimation of a region of interest with a machine learning regression model, the model trained to estimate a spatial transformation from the 2D image data based on training from the reference volume; and controlling a radiotherapy beam of a radiotherapy machine used in the radiotherapy session, based on the relative motion estimation.

Abstract: Techniques for generating radiotherapy treatment plans and establishing machine learning models for the generation and optimization of radiotherapy dose data are disclosed. An example method for generating a radiotherapy dose distribution using a generative model, trained in a generative adversarial network, includes: receiving anatomical data of a human subject that indicates a mapping of an anatomical area for radiotherapy treatment; generating radiotherapy dose data corresponding to the mapping with use of the trained generative model, as the generative model processes the anatomical data as an input and provides the dose data as output; and identifying the radiotherapy dose distribution for the radiotherapy treatment of the human subject based on the dose data.

Abstract: Systems and techniques may be used to estimate a patient state during a radiotherapy treatment. 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 an input image using the correspondence motion model.

Abstract: Systems and methods can include a method for training a deep convolutional neural network to provide a patient radiation treatment plan, the method comprising collecting patient data from a group of patients, the patient data including at least one image of patient anatomy and a prior treatment plan, wherein the treatment plan includes predetermined machine parameters, and training a deep convolution neural network for regression by using the prior treatment plans and the corresponding collected patient data to determine a new treatment plan.

Abstract: Techniques for generating an enhanced cone-beam computed tomography (CBCT) image using a trained model are provided. A CBCT image of a subject is received. a synthetic computed tomography (sCT) image corresponding to the CBCT image is generated, using a generative model. The generative model is trained in a generative adversarial network (GAN). The generative model is further trained to process the CBCT image as an input and provide the sCT image as an output. The sCT image is presented for medical analysis of the subject.

Abstract: 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.

Abstract: Techniques for generating cancer registry records are provided. The techniques include obtaining a plurality of rules that define cancer registry record generation as a function of patient health records; obtaining one or more electronic health records associated with a patient that include cancer related treatment information; processing the cancer related treatment information in the one or more electronic health records to generate a cancer registry record for the patient that represents a portion of the cancer related treatment information; determining that the cancer registry record includes insufficient cancer related treatment information; and updating the cancer registry record to address the insufficient cancer related treatment information by evaluating the cancer related treatment information against the plurality of rules.

Abstract: Embodiments disclose a method and system for segmenting medical images. In certain embodiments, the system comprises a database configured to store a plurality of medical images acquired by an image acquisition device. The plurality of images include at least one first medical image of an object, and a second medical image of the object, each first medical image associated with a first structure label map. The system further comprises a processor that is configured to register the at least one first medical image to the second medical image, determine a classifier model using the registered first medical image and the corresponding first structure label map, and determine a second structure label map associated with the second medical image using the classifier model.

Abstract: System and methods may be used for arc fluence optimization without iteration to arc sequence generation. A method may include defining a particle arc range for a radiotherapy treatment of a patient, and generating an arc sequence, including a set of parameters for delivering the radiotherapy treatment, without requiring a dose calculation. The method may include optimizing fluence of the arc sequence for the radiotherapy treatment without iterating back to arc sequence generation, and outputting the fluence optimized arc sequence for use in the radiotherapy treatment.

Abstract: Systems and techniques may be used to estimate a relative motion of patient anatomy using a deep learning network during a radiotherapy treatment. For example, a method may include using a first deep neural network to relate input real-time partial patient measurements and a patient model including a reference volume to output patient states. The method may include using a second deep neural network to relate the patient states and the reference volume to relative motion information between the patient states and the reference volume. The deep neural networks may be used in real time to estimate a relative motion corresponding to an input image.

Abstract: The present disclosure relates to a method for use in adaptive radiotherapy and a treatment planning device. The method may comprise accessing a first medical image and a second medical image that represent a region of interest of a patient at different times. Each medical image is segmented into a target region and at least one non-target region. The method may further comprise accessing a deformation vector field including a plurality of vectors, wherein each vector defines a geometric transformation to map a respective voxel in the first medical image to a corresponding voxel in the second medical image.

Abstract: Embodiments of the disclosure may be directed to an image processing system configured to receive a medical image of a region of a subject's body taken at a first time and to receive a surface image of an exterior portion of the region of the subject's body taken at the first time. The image processing may also be configured to receive a medical image of the region of the subject's body taken at a second time and to register the medical image taken at the first time, the surface image taken at the first time, and the medical image taken at the second time.

Abstract: Techniques are described herein for delivering a particle beam from a continuously rotating gantry towards a target according to a determined patient state. The determined patient state and an identified gantry angle of a gantry may be used to deliver a set of beamlets (e.g., a pattern of radiation dose) to the target. The particle beam may rotate through a range of gantry angles. The set of beamlets may be delivered continuously while the gantry rotates.

Abstract: Systems and methods are provided for generating a pseudo-CT prediction model that can be used to generate pseudo-CT images. An exemplary system may include a processor configured to retrieve training data including at least one MR image and at least one CT image for each of a plurality of training subjects. For each training subject, the processor may extract a plurality of features from each image point of the at least one MR image, create a feature vector for each image point based on the extracted features, and extract a CT value from each image point of the at least one CT image. The processor may also generate the pseudo-CT prediction model based on the feature vectors and the CT values of the plurality of training subjects.