Abstract: A system may receive a radiology report including a finding of a radiologist with respect to a region of interest of a subject, and generate, using a first AI model, structured data including a set of predetermined fields and a set of corresponding values extracted from the radiology report. The system may determine, using the first AI model, a medical image dataset of the subject corresponding to the radiology report stored in a medical image database using the structured data. The system may segment and label, using a second AI model, a set of regions of each medical image of the medical image dataset. The system may determine, using the first AI model, a medical image of the medical image dataset that depicts the region of interest of the subject using the structured data, and perform an action based on determining the medical image that depicts the region of interest.

Abstract: A medical imaging system includes an image library comprising a plurality of library images depicting known objects and a memory device storing instructions thereon that, when executed, cause a processing circuit to: receive, via a camera of the medical imaging device, a patient image within an imaging space, detect, using a trained model, an object in the patient image, classify, using the trained model, the detected object as either one of a known object from the image library or an unknown object, display an indication of the detected object on a user interface, receive, via the user interface, a user input indicating whether the detected object has been correctly classified as a known object or an unknown object by the trained model, and at least one of obtain a medical image of the patient and the detected object or update the image library based on the user input.

Abstract: Described herein are systems and methods that enable generation and storage of an accessible privacy preserved image that includes camera image data, obscures privacy regions, and is accessible via a standard medical imaging format. A method may include acquiring camera image data via a camera and acquiring scanner image data via a scanner, identifying a privacy region and obscuring camera image data in the privacy region to generate a privacy preserved camera image, and registering the privacy preserved camera image with scanner image data using a camera-scanner coordinate transformation matrix to generate an accessible privacy preserved image.

Abstract: The current disclosure provides systems and methods for automatic image alignment of three-dimensional (3D) medical image volumes. The method includes pre-processing the 3D medical image volume by selecting a sub-volume of interest, detecting anatomical landmarks in the sub-volume using a deep neural network, estimating transformation parameters based on the anatomical landmarks to adjust rotation angles and translation of the sub-volume, adjusting the rotation angles and translation to produce a first aligned sub-volume, determining confidence in the transformation parameters based on the first aligned sub-volume, and iteratively refining the transformation parameters if the confidence is below a predetermined threshold. The disclosed approach for automated image alignment reduces the need for manual alignment and, increases a probability of the 3D image volume converging to a desired orientation compared to conventional approaches.

Abstract: A computer implemented method is provided. The method includes establishing, via multiple processors, a continuous federated learning framework including a global model at a global site and respective local models derived from the global model at respective local sites. The method also includes retraining or retuning, via the multiple processors, the global model and the respective local models without sharing actual datasets between the global site and the respective local sites but instead sharing synthetic datasets generated from the actual datasets.

Abstract: Various methods and ultrasound imaging systems are provided for segmenting an object. In one example, a method includes accessing a volumetric ultrasound dataset, receiving an identification of a seed point for an object in an image generated based on the volumetric ultrasound dataset, and implementing a two-dimensional segmentation model on a first plurality of parallel slices based on the seed point to generate a first plurality of segmented regions. The method includes implementing the two-dimensional segmentation model on a second plurality of parallel slices based on the seed point to generate a second plurality of segmented regions. The method includes generating a detected region by accumulating the first plurality of segmented regions and the second plurality of segmented regions. The method includes implementing a shape completion model to generate a three-dimensional shape model for the object, and displaying rendering of the object based on the three-dimensional shape model.

Abstract: Systems and methods for self-supervised representation learning as a means to generate context-specific pretrained models include selecting data from a set of available data sets; selecting a pretext task from domain specific pretext tasks; selecting a target problem specific network architecture based on a user selection from available choices or any customized model as per user preference; and generating a pretrained model for the selected network architecture using the selected data obtained from the set of available data sets and a pretext task as obtained from domain specific pretext tasks.

Abstract: Systems or techniques that facilitate camera-based deep learning prediction and guidance for medical imaging protocols are provided. In various embodiments, a system can infer, via execution of a first deep learning neural network, a prescribed imaging protocol that is to be performed by a medical imaging scanner on a medical patient. In various aspects, the system can infer, via execution of a second deep learning neural network on a preparation image or video of the medical patient that is captured by a camera associated with the medical imaging scanner, whether or not the medical patient is prepared for the prescribed imaging protocol. In various instances, the system can, in response to an inference that the medical patient is not prepared for the prescribed imaging protocol, initiate an electronic guidance action that explains or shows how to make the medical patient prepared for the prescribed imaging protocol.

Abstract: The current disclosure provides systems and methods for improving a visualization of an image volume of a uterus and/or endometrium of a subject acquired using a transvaginal ultrasound system (TVUS). In one example, a method for the TVUS comprises extracting a medial axis of an endometrium of a received two-dimensional (2D) ultrasound image of a uterus of a subject; generating a uterine trace line based on the extracted medial axis; acquiring a three-dimensional (3D) image volume of the uterus based on the uterine trace line; and displaying the 3D image volume on a display device of the TVUS.

Abstract: Systems/techniques that facilitate anatomy-driven augmentation of medical images are provided. In various embodiments, a system can access a medical image and a ground-truth segmentation mask corresponding to the medical image, wherein the ground-truth segmentation mask can indicate a location of a first anatomical structure depicted in the medical image. In various aspects, the system can create an augmented version of the medical image and an augmented version of the ground-truth segmentation mask, by applying a continuous deformation field to fewer than all pixels or voxels in the medical image and in the ground-truth segmentation mask. In various instances, the continuous deformation field can encompass: pixels or voxels that correspond to the first anatomical structure; and pixels or voxels that correspond to a surrounding periphery of the first anatomical structure.

Abstract: Systems and methods are provided for an image processing system. In an example, a method includes acquiring a pathology dataset, acquiring a reference dataset, generating a deformation field by mapping points of a reference case of the reference dataset to points of a patient image of the pathology dataset, manipulating the deformation field, applying the deformation field to the reference case to generate a simulated pathology image including a simulated deformation pathology, and outputting the simulated pathology image.

Abstract: A method includes obtaining a medical image and receiving a selection of both a template image and a region of interest within the template image. The method includes inputting both the medical image and the template image into a trained vision transformer model and outputting from the trained vision transformer model both pixel level feature vectors from the medical image and a reference pixel level feature vector from the region of interest of the template image. The method includes inputting both the pixel level feature vectors and the reference pixel level feature vector into a trained contrastive similarity metric learning model and outputting from the trained contrastive similarity metric learning model pixel that are similar to reference pixels. The method includes labeling the pixels in the medical image with a segmentation mask, wherein the pixels that are labeled in the medical image correspond to the region of interest.

Abstract: A computer implemented method is provided. The method includes establishing, via multiple processors, a continuous federated learning framework including a global model at a global site and respective local models derived from the global model at respective local sites. The method also includes retraining or retuning, via the multiple processors, the global model and the respective local models without sharing actual datasets between the global site and the respective local sites but instead sharing synthetic datasets generated from the actual datasets.

Abstract: Various systems and methods are presented regarding segmentation of medical images whereby a segmentation process comprises of channels configured to share labels. Accordingly, rather than each label in a series of images all requiring an individual channel in a segmentation model, the segmentation model can be configured such that a single channel (e.g., having a single group of labels) is shared by images having multiple labels. By sharing a channel, and label group, across multiple labels, the efficiency of the segmentation model is improved as fewer channels are required to segment a series of images. Matching between regions of interest across the series of images can be performed to determine a number of shared channels required for the segmentation model. The series of images can be further applied to the segmentation model to generate a set of labeled segmented images.

Abstract: Techniques are described for generating high quality training data collections for training artificial intelligence (AI) models in the medical imaging domain. A method embodiment comprises receiving, by a system comprising processor, input indicating a clinical context associated with usage of a medical image dataset, and selecting, by the system, one or more data scrutiny metrics for filtering the medical image dataset based on the clinical context. The method further comprises applying, by the system, one or more image processing functions to the medical image dataset to generate metric values of the one or more data scrutiny metrics for respective medical images included in the medical image dataset, filtering, by the system, the medical image dataset into one or more subsets based on one or more acceptability criteria for the metric values.

Abstract: One-shot medical image feature localization techniques are provided that employ pretrained foundation models and domain knowledge. In an example, a computer-implemented method can comprise determining positions of target features within a target medical image of an anatomical region of a subject based on reference spatial relationships between the target features as defined in reference spatial information, and based on matching reference pixel features respectively associated with the target features with corresponding subsets of pixel features of the target medical image, wherein the reference pixel features comprise template image pixel features extracted from labeled versions of the target features as included in a template medical image depicting the anatomical region of a reference subject. The method further comprises generating label information for the target features identifying the target features and their positions and associating the label information with the target medical image.

Abstract: Systems and methods for workflow management for labeling the subject anatomy are provided. The method comprises obtaining at least one localizer image of a subject anatomy using a low-resolution medical imaging device. The method further comprises labeling at least one anatomical point within the at least one localizer image. The method further comprises extracting using a machine learning module a mask of the at least one localizer image comprising the at least one anatomical point label. The method further comprises using the mask to label at least one anatomical point on a high-resolution image of the subject anatomy based on the at least one anatomical point within the localizer image.

Abstract: Systems and techniques that facilitate data diversity visualization and/or quantification for machine learning models are provided. In various embodiments, a processor can access a first dataset and a second dataset, where a machine learning (ML) model is trained on the first dataset. In various instances, the processor can obtain a first set of latent activations generated by the ML model based on the first dataset, and a second set of latent activations generated by the ML model based on the second dataset. In various aspects, the processor can generate a first set of compressed data points based on the first set of latent activations, and a second set of compressed data points based on the second set of latent activations, via dimensionality reduction. In various instances, a diversity component can compute a diversity score based on the first set of compressed data points and second set of compressed data points.

Abstract: Systems/techniques that facilitate deep learning multi-planar reformatting of medical images are provided. In various embodiments, a system can access a three-dimensional medical image. In various aspects, the system can localize, via execution of a machine learning model, a set of landmarks depicted in the three-dimensional medical image, a set of principal anatomical planes depicted in the three-dimensional medical image, and a set of organs depicted in the three-dimensional medical image. In various instances, the system can determine an anatomical orientation exhibited by the three-dimensional medical image, based on the set of landmarks, the set of principal anatomical planes, or the set of organs. In various cases, the system can rotate the three-dimensional medical image, such that the anatomical orientation now matches a predetermined anatomical orientation.

Abstract: Techniques are described for generating high quality training data collections for training artificial intelligence (AI) models in the medical imaging domain. A method embodiment comprises receiving, by a system comprising processor, input indicating a clinical context associated with usage of a medical image dataset, and selecting, by the system, one or more data scrutiny metrics for filtering the medical image dataset based on the clinical context. The method further comprises applying, by the system, one or more image processing functions to the medical image dataset to generate metric values of the one or more data scrutiny metrics for respective medical images included in the medical image dataset, filtering, by the system, the medical image dataset into one or more subsets based on one or more acceptability criteria for the metric values.