Abstract: Systems and methods for identifying and presenting prior findings data in a radiology review workflow, based on natural language processing (NLP) of unstructured radiology report text, are disclosed. In an example, prior findings are generated with operations including: receiving text from a prior radiology report prepared for a patient in a prior radiology study; processing the text with a trained NLP engine to classify discrete prior findings in the prior radiology study that identify observed condition(s) and characteristics of the observed condition(s); and outputting or presenting the prior findings, such as in a radiology review user interface. In an example, the radiology review user interface displays the observed condition(s) and the characteristic(s) of the observed condition(s) to a user (e.g., a radiologist), and can apply sorting, filtering, or grouping based on pathology phrases or attribute words associated with the observed conditions or the characteristics of such observed conditions.

Abstract: Systems and methods for processing electronic imaging data obtained from medical imaging procedures, with use of trained artificial intelligence (AI) models, are disclosed herein. In an example, a use of a medical evaluation workflow involving an AI model includes: obtaining image data and non-image data associated with a medical imaging study; using at least one AI model to analyze the image data, with the trained AI model being validated with a defined governance standard to identify a characteristic or particular type of characteristic; identifying the characteristic with the AI model; and communicating the identified characteristic to a location associated with evaluation of the medical imaging study.

Abstract: Systems and methods for processing electronic imaging data obtained from medical imaging procedures are disclosed herein. Some embodiments relate to data processing mechanisms for medical imaging and diagnostic workflows involving the use of machine learning techniques such as deep learning, artificial neural networks, and related algorithms that perform machine recognition of specific features and conditions in imaging data. In an example, a deep learning model is selected for automated image recognition of a particular medical condition on image data, and applied to the image data to recognize characteristics of the particular medical condition. Based on the characteristics recognized by the automated image recognition on the image data, an electronic workflow for performing a diagnostic evaluation of the medical imaging study may be modified, updated, or prioritized.

Abstract: A teleradiology image processing system configured to receive, process, and transmit radiology read requests and digital radiology image data is disclosed herein. In one embodiment, a radiology processing system includes a series of processing components configured to receive digital radiology data from a medical provider, extract relevant information and radiology scan images from the digital radiology data, and initiate and control a workflow with a qualified remote radiologist who ultimately performs a read of the radiology scan images.

Abstract: Enhanced techniques for the extraction and use of metadata from medical images are disclosed herein. Based on the information in the metadata, specific processing may be performed within an image order management system, radiology information system (RIS), or like system. A radiology read order may be created, pre-populated, and transmitted via a processing system (e.g., a teleradiology image order management system) based on the metadata within the radiology image. For example, this metadata may exist within the header of a DICOM-formatted image data file or a DICOM communication protocol transmission. The processing system may then provide the prepopulated read order back to the source of the medical images for verification and submission. Other processing actions may also occur based on information extracted from the image metadata, such as custom workflows and handling based on an originating facility, or transferring the images to a particular radiologist or location.

Abstract: A system for managing remote doctor medical request workflow may include a workflow module that optimizes assignments of medical requests to remote doctors based on parameterized doctor and scheduling information and may further include a forecasting module that predicts the hospital credentials, state licenses or doctors needed to fulfill a projected volume of future medical requests. In one embodiment, radiologists are parameterized and then matched with requests for radiological readings based on information extracted from DICOM image headers and merged with associated information contained in a medical work order. In this embodiment, the radiologists are parameterized based on their locations, schedules, hospital credentials, state licensing, compensation metrics, and performance metrics and incoming requests for review of CT scans and the like are filtered based on the parameterized radiologist information to identify one or more radiologists who are to fulfill the medical request.

Abstract: Systems and methods for processing electronic imaging data obtained from medical imaging procedures are disclosed herein. Some embodiments relate to data processing mechanisms for medical imaging and diagnostic workflows involving the use of machine learning techniques such as deep learning, artificial neural networks, and related algorithms that perform machine recognition of specific features and conditions in imaging data. In an example, a deep learning model is selected for automated image recognition of a particular medical condition on image data, and applied to the image data to recognize characteristics of the particular medical condition. Based on the characteristics recognized by the automated image recognition on the image data, an electronic workflow for performing a diagnostic evaluation of the medical imaging study may be modified, updated, or prioritized.

Abstract: Systems and methods for processing electronic imaging data obtained from medical imaging procedures are disclosed herein. Some embodiments relate to data processing mechanisms for medical imaging and diagnostic workflows involving the use of machine learning techniques such as deep learning, artificial neural networks, and related algorithms that perform machine recognition of specific features and conditions in imaging data. In an example, a deep learning model is selected for automated image recognition of a particular medical condition on image data, and applied to the image data to recognize characteristics of the particular medical condition. Based on the characteristics recognized by the automated image recognition on the image data, an electronic workflow for performing a diagnostic evaluation of the medical imaging study may be modified, updated, or prioritized.

Abstract: Systems and methods for establishing standardization of radiology imaging procedure types and data related to such radiology imaging procedure types are disclosed herein. Radiology imaging data produced from radiology procedures at plurality of different systems and locations may produce different data formats and data values, even for the same radiology procedure. In one example, a radiology imaging order system is configured to standardize these different data formats and data values to a standardized format and identification that can be used for radiology study assignment, categorization, analytics, and related data federation activities. In further examples, multiple radiology procedures from respective facilities are normalized to a radiology procedure type schema, with each normalized radiology procedure type identifiable with a human-readable procedure identifier. Other examples of processing activities and use of the procedure identifier and standardized data are also disclosed herein.

Abstract: Systems and methods for coordinating a medical imaging workflow with the use of preparation and coordination actions, and similar pre-processing protocols are disclosed herein. Imaging procedure data from a medical imaging study, such as image data and order data produced from imaging procedures (e.g., radiological imaging procedures) at medical facilities is processed and presented for review to a preparing user. The preparing user is offered the ability to change the display characteristics of image presentation, supplement erroneous or incomplete data and information of the study, open a support request for the study, or associate prior or comparison images with the study. The changes provided by the preparing user within these or other portions of a preparation protocol may be used to affect a subsequent display of the medical imaging study, and in some examples, to affect the assignment of the study in the workflow to particular imaging users.

Abstract: A system configuration and techniques for optimizing schedules and associated use predictions of a multiple resource planning workflow are disclosed herein, applicable to environments such as radiologist scheduling in a teleradiology workflow. In one embodiment, a series of computing engines and components are provided to allow detailed forecasting and the generation of customized recommendations for scheduling and other resource usage scenarios. This forecasting can factor resource efficiencies, changes in resource demand volume, resource specialties, resource usage preferences, expected future events such as the removal or addition of resources at future times, and other resource availability or usage changes. The forecasts may be further enhanced through the use of historical data models and estimated future data models. Additionally, a calendar and other tools may be presented through a user interface to allow forecast and scenario customization based on selection of a series of future dates.

Abstract: A system for managing remote doctor medical request workflow may include a workflow module that optimizes assignments of medical requests to remote doctors based on parameterized doctor and scheduling information and may further include a forecasting module that predicts the hospital credentials, state licenses or doctors needed to fulfill a projected volume of future medical requests. In one embodiment, radiologists are parameterized and then matched with requests for radiological readings based on information extracted from DICOM image headers and merged with associated information contained in a medical work order. In this embodiment, the radiologists are parameterized based on their locations, schedules, hospital credentials, state licensing, compensation metrics, and performance metrics and incoming requests for review of CT scans and the like are filtered based on the parameterized radiologist information to identify one or more radiologists who are to fulfill the medical request.

Abstract: Enhanced techniques for the extraction and use of metadata from medical images are disclosed herein. Based on the information in the metadata, specific processing may be performed within an image order management system, radiology information system (RIS), or like system. A radiology read order may be created, pre-populated, and transmitted via a processing system (e.g., a teleradiology image order management system) based on the metadata within the radiology image. For example, this metadata may exist within the header of a DICOM-formatted image data file or a DICOM communication protocol transmission. The processing system may then provide the prepopulated read order back to the source of the medical images for verification and submission. Other processing actions may also occur based on information extracted from the image metadata, such as custom workflows and handling based on an originating facility, or transferring the images to a particular radiologist or location.

Abstract: A teleradiology image processing system configured to receive, process, and transmit radiology read requests and digital radiology image data is disclosed herein. In one embodiment, a radiology processing system includes a series of processing components configured to receive digital radiology data from a medical provider, extract relevant information and radiology scan images from the digital radiology data, and initiate and control a workflow with a qualified remote radiologist who ultimately performs a read of the radiology scan images.

Abstract: The subject matter of this specification can be implemented in, among other things, a system for interfacing with multiple medical imaging modalities that includes a manifest generator for generating a manifest of medical images. The manifest can be used to determine an ordering or a layout of the medical images generated by the modalities, optionally as a function of the modality type, anatomical area, and other variables. In some embodiments, the various medical images and metadata may be received at an image order management system that parses the metadata and assembles the metadata into the manifest files that may be transmitted independently to remote interpretation sites, which in turn may be equipped with image viewer applications that analyze the manifest files and determine a rearranged ordering and/or grouping of the medical images, wherein the rearrangement is executed as a function of modality, anatomy, orientation and other variables.

Abstract: Enhanced techniques for the extraction and use of metadata from medical images are disclosed herein. Based on the information in the metadata, specific processing may be performed within an image order management system, radiology information system (RIS), or like system. A radiology read order may be created, pre-populated, and transmitted via a processing system (e.g., a teleradiology image order management system) based on the metadata within the radiology image. For example, this metadata may exist within the header of a DICOM-formatted image data file or a DICOM communication protocol transmission. The processing system may then provide the pre-populated read order back to the source of the medical images for verification and submission. Other processing actions may also occur based on information extracted from the image metadata, such as custom workflows and handling based on an originating facility, or transferring the images to a particular radiologist or location.

Abstract: A system for managing remote doctor medical request workflow may include a workflow module that optimizes assignments of medical requests to remote doctors based on parameterized doctor and scheduling information and may further include a forecasting module that predicts the hospital credentials, state licenses or doctors needed to fulfill a projected volume of future medical requests. In one embodiment, radiologists are parameterized and then matched with requests for radiological readings based on information extracted from DICOM image headers and merged with associated information contained in a medical work order. In this embodiment, the radiologists are parameterized based on their locations, schedules, hospital credentials, state licensing, compensation metrics, and performance metrics and incoming requests for review of CT scans and the like are filtered based on the parameterized radiologist information to identify one or more radiologists who are to fulfill the medical request.

Abstract: A teleradiology image processing system configured to process radiology read requests and digital radiology image data is disclosed. In one embodiment, a radiology processing system includes a series of processing components configured to receive digital radiology data from a medical provider, extract relevant information and radiology scan images from the digital radiology data, and initiate and control a workflow with a qualified remote radiologist who ultimately performs a read of the radiology scan images.

Abstract: A system configuration and techniques for optimizing schedules and associated use predictions of a multiple resource planning workflow are disclosed herein, applicable to environments such as radiologist scheduling in a teleradiology workflow. In one embodiment, a series of computing engines and components are provided to allow detailed forecasting and the generation of customized recommendations for scheduling and other resource usage scenarios. This forecasting can factor resource efficiencies, changes in resource demand volume, resource specialties, resource usage preferences, expected future events such as the removal or addition of resources at future times, and other resource availability or usage changes. The forecasts may be further enhanced through the use of historical data models and estimated future data models. Additionally, a calendar and other tools may be presented through a user interface to allow forecast and scenario customization based on selection of a series of future dates.

Abstract: A teleradiology image processing system configured to process radiology read requests and digital radiology image data is disclosed. In one embodiment, a radiology processing system includes a series of processing components configured to receive digital radiology data from a medical provider, extract relevant information and radiology scan images from the digital radiology data, and initiate and control a workflow with a qualified remote radiologist who ultimately performs a read of the radiology scan images.