Intelligent dynamic preloading and processing
View Patent ↗Provided herein are various systems and methods of adjusting images of an image series that are preloaded (and/or otherwise processed) in view of behavior data associated with viewing of other previous exams having similar characteristics (e.g., same modality) and/or by the same user.
1. A method for processing images, the method comprising:
by one or more computer processors configured to execute software instructions:
receiving a request for display of a first image series comprising a plurality of images;
determining a characteristic of the first image series;
monitoring behavior of a user in displaying images of the first image series, including recording behavior data indicating an order in which images of the first image series are accessed by the user;
analyzing the behavior data in order to determine a model usable to predict respective probabilities of images of the first image series at various adjacency offsets from a particular image of the first image series being needed next after selection or display of the particular image;
associating the model with the characteristic of the first image series;
determining that a characteristic of a second image series matches the characteristic of the first image series, the second image series including a sequence of a first image and a second image;
determining, based on the model, a set of probabilities related to the second image series, wherein the set of probabilities indicates, for each particular image of at least some images of the second image series, probabilities of images of the second image series at various adjacency offsets from the particular image being needed next after selection or display of the particular image; and
based at least in part on the set of probabilities related to the second image series, processing the first image of the second image series and the second image of the second image series out of sequence.
2. The method of claim 1 , wherein more than one of the images of the first image series has a same respective probability of being needed next after selection or display of the particular image.
3. The method of claim 1 , wherein the model indicates that a first image of the first image series having a higher adjacency offset than a second image of the first image series is more likely to be needed within the predetermined time period.
4. The method of claim 1 , wherein the characteristic of the first image series comprises at least one of: exam type, modality, clinical information, clinical history of a patient, region of body depicted in the first image series, technical parameter of the first image series, or an indication of whether the plurality of images were obtained with or without intravenous contrast.
5. The method of claim 1 , wherein the characteristic of the first image series comprises a technical parameter of the first image series, and wherein the technical parameter comprises at least one of: series type, an indication of whether the first image series is a 2D or a volumetric acquisition, slice thickness, resolution, image size, or image type.
6. The method of claim 1 , wherein the characteristic of the first image series comprises a series type of the first image series, and wherein the series type comprises at least one of: primary acquisition, MPR (multiplanar reconstruction), MIP (maximum intensity projection), or 3D volume rendering.
7. The method of claim 1 , wherein the model is further associated with a characteristic of the user including at least one of: a user identity, a user group of the user, or a user role of the user.
8. The method of claim 1 further comprising:
by the one or more computer processors configured to execute the software instructions:
determining, based on the set of probabilities, one or more images of the second image series to preload into a local memory of a display device.
9. The method of claim 8 further comprising:
by the one or more computer processors configured to execute the software instructions:
determining which of the one or more images to preload are already stored in the local memory; and
initiating preloading of any of the one or more images to preload that are not already stored in the local memory.
10. The method of claim 1 further comprising:
by the one or more computer processors configured to execute the software instructions:
preprocessing, based on the set of probabilities, images of the second image series.
11. The method of claim 10 , wherein preprocessing images of the second image series comprises:
based on the set of probabilities, preloading images of the second image series that have been processed into a local memory of a display device.
12. The method of claim 10 , wherein preprocessing images of the second image series comprises at least one of: decompressing, performing computer aided diagnosis, or reconstructing images of the second image series.
13. The method of claim 10 , wherein preprocessing images of the second image series comprises reconstructing images, and wherein reconstructing images comprises at least one of: MPR (multiplanar reconstruction), MIP (maximum intensity projection), or 3D volume rendering.
14. A method for processing images, the method comprising:
by one or more computer processors configured to execute software instructions:
receiving a request for display of a first image series comprising a plurality of images;
determining a characteristic of a first display device upon which images of the first image series are displayed;
monitoring behavior of a user in displaying images of the first image series, including recording behavior data indicating an order in which images of the first image series are accessed by the user;
analyzing the behavior data in order to determine a model usable to predict respective probabilities of images of the first image series at various adjacency offsets from a particular image of the first image series being needed next after selection or display of the particular image;
associating the model with the characteristic of the first display device;
determining that a characteristic of a second display device upon which images of a second image series are to be displayed matches the characteristic of the first display device, the second image series including a sequence of a first image and a second image;
determining, based on the model, probabilities of images of the second image series at various adjacency offsets from a particular image of the second image series being needed next after selection or display of the particular image of the second image series; and
based at least in part on the set of probabilities related to the second image series, processing the first image of the second image series and the second image of the second image series out of sequence.
15. The method of claim 14 , wherein the characteristic of the first display device comprises at least one of: a type of the first display device, a size of the first display device, a number of displays associated with the first display device, an amount of memory of the first display device, or a speed of transmission to the first display device.
16. The method of claim 14 further comprising:
by the one or more computer processors configured to execute the software instructions:
determining, based on the model, one or more images of the second image series to preload into a local memory of a display device.
17. The method of claim 16 further comprising:
by the one or more computer processors configured to execute the software instructions:
determining which of the one or more images to preload are already stored in the local memory; and
initiating preloading of any of the one or more images to preload that are not already stored in the local memory.
18. The method of claim 14 further comprising:
by the one or more computer processors configured to execute the software instructions:
preprocessing, based on the model, images of the second image series.
19. The method of claim 18 , wherein preprocessing images of the second image series comprises:
based on the model, preloading images of the second image series that have been processed into a local memory of a display device.
20. The method of claim 18 , wherein preprocessing images of the second image series comprises at least one of: decompressing, performing computer aided diagnosis, or reconstructing images of the second image series.