Systems and methods to deliver point of care alerts for radiological findings
Apparatus, systems, and methods to deliver point of care alerts for radiological findings are disclosed. An example imaging apparatus includes an image data store, an image quality checker, and a training learning network. The example image data store is to store image data acquired using the imaging apparatus. The example image quality checker is to evaluate image data from the image data store in comparison to an image quality measure. The example trained learning network is to process the image data to identify a clinical finding in the image data, the identification of a clinical finding to trigger a notification at the imaging apparatus to notify a healthcare practitioner regarding the clinical finding and prompt a responsive action with respect to a patient associated with the image data.
1. A mobile imaging apparatus comprising:
wheels;
a source;
a detector; and
a housing including:
an image data storage to storage image data acquired at a current location using the source of the mobile imaging apparatus; and
a processor to implement:
an image quality checker to evaluate the image data from the image data storage in comparison to an image quality measure using an artificial intelligence model operating on the mobile imaging apparatus at the current location; and
a trained learning network to, when the evaluation satisfies the image quality measure, process the image data at the current location to identify a clinical finding in the image data, the identification of a clinical finding to trigger a notification at the mobile imaging apparatus to notify a healthcare practitioner regarding the clinical finding and prompt a responsive action with respect to a patient associated with the image data.
2. The apparatus of claim 1 , wherein the mobile imaging apparatus is a mobile x-ray imaging apparatus.
3. The apparatus of claim 1 , further including a display, wherein the notification is output via a graphical user interface displayed via the display at the mobile imaging apparatus.
4. The apparatus of claim 3 , wherein presentation of the notification corresponds to a criticality of the clinical finding.
5. The apparatus of claim 1 , wherein the trained learning network includes a deep learning network trained on reference image data and associated findings and deployed to the mobile imaging apparatus.
6. The apparatus of claim 1 , further including a pre-processor to prepare the image data for processing by the trained learning network after evaluation by the image quality checker.
7. The apparatus of claim 1 , further including an image enhancer to process the image data to enhance the clinical finding in a displayed image resulting from the image data.
8. A non-transitory computer-readable storage medium in a mobile imaging apparatus including wheels, a source, a detector, and a housing including the computer-readable storage medium and a processor, the computer-readable storage medium including instructions which, when executed, cause the processor in the mobile imaging apparatus to implement at least:
an image data storage to storage image data acquired at a current location using the source of the mobile imaging apparatus;
an image quality checker to evaluate the image data from the image data storage in comparison to an image quality measure using an artificial intelligence model operating on the mobile imaging apparatus at the current location; and
a trained learning network to, when the evaluation satisfies the image quality measure, process the image data at the current location to identify a clinical finding in the image data, the identification of a clinical finding to trigger a notification at the mobile imaging apparatus to notify a healthcare practitioner regarding the clinical finding and prompt a responsive action with respect to a patient associated with the image data.
9. The computer-readable storage medium of claim 8 , wherein the mobile imaging apparatus is a mobile x-ray imaging apparatus.
10. The computer-readable storage medium of claim 8 , wherein the instructions, when executed, cause the processor to output the notification via a graphical user interface displayed at the mobile imaging apparatus.
11. The computer-readable storage medium of claim 10 , wherein presentation of the notification corresponds to a criticality of the clinical finding.
12. The computer-readable storage medium of claim 8 , wherein the trained learning network includes a deep learning network trained on reference image data and associated findings and deployed to the imaging apparatus.
13. The computer-readable storage medium of claim 8 , wherein the instructions, when executed, cause the processor to further implement a pre-processor to prepare the image data for processing by the trained learning network after evaluation by the image quality checker.
14. The computer-readable storage medium of claim 8 , wherein the instructions, when executed, cause the processor to further implement an image enhancer to process the image data to enhance the clinical finding in a displayed image resulting from the image data.
15. A computer-implemented method comprising:
evaluating, at a mobile imaging apparatus, image data acquired at a current location using a source of the mobile imaging apparatus in comparison to an image quality measure using an artificial intelligence model operating on the mobile imaging apparatus at the current location, the mobile imaging apparatus including wheels, the source, a detector, and a housing including a processor;
when the image data satisfies the image quality measure, processing the image data via a trained learning network at the current location to identify a clinical finding in the image data; and
triggering, at the current location based on identification of a clinical finding, a notification at the mobile imaging apparatus to notify a healthcare practitioner regarding the clinical finding and prompt a responsive action with respect to a patient associated with the image data.
16. The method of claim 15 , wherein the notification is presented via a graphical user interface in proportion to a criticality of the clinical finding.
17. The method of claim 15 , further including preparing the image data for processing by the trained learning network after evaluation with respect to the image quality measure.
18. The method of claim 15 , further including processing the image data to enhance the clinical finding in a displayed image resulting from the image data.
19. The method of claim 15 , further including accepting input to proceed with processing the image data via the trained learning network to identify a clinical finding in the image data when the image data does not satisfy the image quality measure.
20. The method of claim 15 , wherein the trained learning network is located on at least one of a cloud-based server or an edge device.
21. The method of claim 15 , further including sending at least one of a Digital Imaging and Communications in Medicine (DICOM) tag or a Health Level 7 (HL7) message to create a worklist prioritization rule for a picture archiving and communication system (PACS) in response to the identification of clinical finding.
22. The apparatus of claim 1 , wherein the trained learning network is configured to connect the imaging apparatus with at least one of a cloud-based server or an edge device to identify the clinical finding in the image data and output the notification at the imaging apparatus.