Abstract: Embodiments described herein provide for determining a probability distribution of a three-dimensional point in a template feature map matching a three-dimensional point in space. A dual-domain target structure tracking end-to-end system receives projection data in one dimension or two dimensions and a three-dimensional simulation image. The end-to-end system extracts a template feature map from the simulation image using segmentation. The end-to-end system extracts features from the projection data, transforms the features of the projection data into three-dimensional space, and sequences the three-dimensional space to generate a three-dimensional feature map. The end-to-end system compares the template feature map to the generated three-dimensional feature map, determining an instantaneous probability distribution of the template feature map occurring in the three-dimensional feature map.

Abstract: A computer-implemented method of performing a treatment fraction of radiation therapy comprises: determining a current position of a target volume of patient anatomy; based on the current position of the target volume, computing an accumulated dose for non-target tissue proximate the target volume; determining that the accumulated dose is less than a current value for a dose budget of the non-target tissue; and in response to the accumulated dose being less than the current value for the dose budget, applying a treatment beam to the target volume while the target volume is in the current position.

Abstract: A reconstructed volume of a region of patient anatomy is processed to reduce motion artifacts in the reconstructed volume. Autosegmentation of high-contrast structures present in an initial reconstructed volume is performed to generate a 3D representation of the high-contrast structures. 2D mask projections are generated by performing forward projection on the 3D representation, where each 2D mask projection includes location information indicating pixels that correspond to the high-contrast structures during the forward projection process. The acquired 2D projections are modified via in-painting to generate corrected 2D projections, where the acquired 2D projections are modified using information from the 2D mask projections. For example, pixels in the acquired 2D projections that are associated with high-contrast moving structures are replaced with low-contrast pixels.

Abstract: Embodiments described herein provide for determining a probability distribution of a three-dimensional point in a template feature map matching a three-dimensional point in space. A dual-domain target structure tracking end-to-end system receives projection data in one dimension or two dimensions and a three-dimensional simulation image. The end-to-end system extracts a template feature map from the simulation image using segmentation. The end-to-end system extracts features from the projection data, transforms the features of the projection data into three-dimensional space, and sequences the three-dimensional space to generate a three-dimensional feature map. The end-to-end system compares the template feature map to the generated three-dimensional feature map, determining an instantaneous probability distribution of the template feature map occurring in the three-dimensional feature map.

Abstract: Example methods and systems for tomographic data analysis are provided. One example method may comprise: obtaining first three-dimensional (3D) feature volume data and processing the first 3D feature volume data using an AI engine that includes multiple first processing layers, an interposing forward-projection module and multiple second processing layers. Example processing using the AI engine may involve: generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers, transforming the second 3D volume data into 2D feature data using the forward-projection module and generating analysis output data by processing the 2D feature data using the multiple second processing layers.

Abstract: A reconstructed volume of a region of patient anatomy is processed to reduce motion artifacts in the reconstructed volume. Autosegmentation of high-contrast structures present in an initial reconstructed volume is performed to generate a 3D representation of the high-contrast structures. 2D mask projections are generated by performing forward projection on the 3D representation, where each 2D mask projection includes location information indicating pixels that correspond to the high-contrast structures during the forward projection process. The acquired 2D projections are modified via in-painting to generate corrected 2D projections, where the acquired 2D projections are modified using information from the 2D mask projections. For example, pixels in the acquired 2D projections that are associated with high-contrast moving structures are replaced with low-contrast pixels.

Abstract: Provided herein are methods and systems to train and execute a motion model that uses artificial intelligence methodologies (e.g., deep-learning) to learn and predict location of a patient's internal structures. A method comprises receiving respiratory data of a patient from an electronic sensor in addition to a medical image, such as kV image; executing an artificial intelligence model using the respiratory data and predicting deformation data for at least one internal structure of the patient, wherein the artificial intelligence model is trained in accordance with a training dataset comprising a set of participants, their corresponding respiratory data, and their corresponding deformation data; and outputting the predicted deformation data.

Abstract: Systems and methods for augmenting a training data set with annotated pseudo images for training machine learning models. The pseudo images are generated from corresponding images of the training data set and provide a realistic model of the interaction of image generating signals with the patient, while also providing a realistic patient model. The pseudo images are of a target imaging modality, which is different than the imaging modality of the training data set, and are generated using algorithms that account for artifacts of the target imaging modality. The pseudo images may include therein the contours and/or features of the anatomical structures contained in corresponding medical images of the training data set. The trained models can be used to generate contours in medical images of a patient of the target imaging modality or to predict an anatomical condition that may be indicative of a disease.

Abstract: A computer-implemented method of segmenting a reconstructed volume of a region of patient anatomy includes: determining an anatomical region associated with the reconstructed volume; detecting one or more metal objects disposed in an initial 3D metal object mask associated with the reconstructed volume; for each of the one or more metal objects disposed in the initial 3D metal object mask, determining a volume associated with the metal object; determining a value for at least one segmentation parameter based on the anatomical region and on the volume associated with the one or more metal objects; and generating a final 3D metal object mask associated with the reconstructed digital volume using the value for the segmentation parameter.

Abstract: A computer-implemented method for modifying X-ray projection images of a subject region includes: generating a set of combined two-dimensional (2D) projections of a subject region, wherein each combined 2D projection includes one or more mask-bordering pixels and one or more mask-edge pixels; forming a three-dimensional (3D) matrix of the set of combined 2D projections; based on the 3D matrix, generating a linear algebraic system for determining pixel values for pixels indicated in a set of 2D projection metal masks, wherein a first change in slope of pixel value associated with a mask-edge pixel of a combined 2D projection is constrained to equal a second change in slope of pixel value associated with a mask-bordering pixel of a combined 2D projection; determining values for a variable vector of the linear algebraic system; and generating a set of inpainted 2D projections by modifying initial 2D projections with values for the variable vector.

Abstract: Systems and methods for augmenting a training data set with annotated pseudo images for training machine learning models. The pseudo images are generated from corresponding images of the training data set and provide a realistic model of the interaction of image generating signals with the patient, while also providing a realistic patient model. The pseudo images are of a target imaging modality, which is different than the imaging modality of the training data set, and are generated using algorithms that account for artifacts of the target imaging modality. The pseudo images may include therein the contours and/or features of the anatomical structures contained in corresponding medical images of the training data set. The trained models can be used to generate contours in medical images of a patient of the target imaging modality or to predict an anatomical condition that may be indicative of a disease.

Abstract: A computer-implemented method of performing a treatment fraction of radiation therapy comprises: determining a current position of a target volume of patient anatomy; based on the current position of the target volume, computing an accumulated dose for non-target tissue proximate the target volume; determining that the accumulated dose is less than a current value for a dose budget of the non-target tissue; and in response to the accumulated dose being less than the current value for the dose budget, applying a treatment beam to the target volume while the target volume is in the current position.

Abstract: A method of imaging a region of patient anatomy having a target volume includes performing an autosegmentation of a high-contrast portion of a first reconstructed volume of the region to generate a three-dimensional (3D) representation of the high-contrast portion disposed within the region and generating a set of two-dimensional (2D) mask projections of the region by performing a forward projection process on the 3D representation, wherein each 2D mask projection in the set of 2D mask projections includes location information indicating pixels that are blocked by the high-contrast portion during the forward projection process performed on the 3D representation.

Abstract: Embodiments described herein provide for determining a probability distribution of a three-dimensional point in a template feature map matching a three-dimensional point in space. A dual-domain target structure tracking end-to-end system receives projection data in one dimension or two dimensions and a three-dimensional simulation image. The end-to-end system extracts a template feature map from the simulation image using segmentation. The end-to-end system extracts features from the projection data, transforms the features of the projection data into three-dimensional space, and sequences the three-dimensional space to generate a three-dimensional feature map. The end-to-end system compares the template feature map to the generated three-dimensional feature map, determining an instantaneous probability distribution of the template feature map occurring in the three-dimensional feature map.

Abstract: Example methods and systems for tomographic image reconstruction are provided. One example method may comprise: obtaining two-dimensional (2D) projection data and processing the 2D projection data using the AI engine that includes multiple first processing layers, an interposing back-projection module and multiple second processing layers. Example processing using the AI engine may involve: generating 2D feature data by processing the 2D projection data using the multiple first processing layers, reconstructing first three-dimensional (3D) feature volume data from the 2D feature data using the back-projection module; and generating second 3D feature volume data by processing the first 3D feature volume data using the multiple second processing layers.

Abstract: A computer-implemented method of performing a treatment fraction of radiation therapy comprises: determining a current position of a target volume of patient anatomy; based on the current position of the target volume, computing an accumulated dose for non-target tissue proximate the target volume; determining that the accumulated dose is less than a current value for a dose budget of the non-target tissue; and in response to the accumulated dose being less than the current value for the dose budget, applying a treatment beam to the target volume while the target volume is in the current position.

Abstract: Example methods and systems for tomographic data analysis are provided. One example method may comprise: obtaining first three-dimensional (3D) feature volume data and processing the first 3D feature volume data using an AI engine that includes multiple first processing layers, an interposing forward-projection module and multiple second processing layers. Example processing using the AI engine may involve: generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers, transforming the second 3D volume data into 2D feature data using the forward-projection module and generating analysis output data by processing the 2D feature data using the multiple second processing layers.

Abstract: Example methods and systems for tomographic data analysis are provided. One example method may comprise: obtaining first three-dimensional (3D) feature volume data and processing the first 3D feature volume data using an AI engine that includes multiple first processing layers, an interposing forward-projection module and multiple second processing layers. Example processing using the AI engine may involve: generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers, transforming the second 3D volume data into 2D feature data using the forward-projection module and generating analysis output data by processing the 2D feature data using the multiple second processing layers.

Abstract: A computer-implemented method of performing a treatment fraction of radiation therapy comprises: determining a current position of a target volume of patient anatomy; based on the current position of the target volume, computing an accumulated dose for non-target tissue proximate the target volume; determining that the accumulated dose is less than a current value for a dose budget of the non-target tissue; and in response to the accumulated dose being less than the current value for the dose budget, applying a treatment beam to the target volume while the target volume is in the current position.

Abstract: Reconstruction of projection images of a CBCT scan is performed by generating simulated projection data, comparing the simulated projection data to the projection images of the CBCT scan, determining a residual volume based on the comparison, and using the residual volume to determine an accurate reconstructed volume. The reconstructed volume can be used to segment a tumor (and potentially one or more organs) and align the tumor to a planning volume (e.g., from a CT scan) to identify changes, such as shape of the tumor and proximity of the tumor to an organ. These changes can be used to update a radiation therapy procedure, such as by altering a radiation treatment plan and fine-tuning a patient position.