WO2014174461A2

WO2014174461A2 - Image visualization

Info

Publication number: WO2014174461A2
Application number: PCT/IB2014/060940
Authority: WO
Inventors: Shlomo Gotman; Eran RUBENS
Original assignee: Koninklijke Philips N.V.
Priority date: 2013-04-24
Filing date: 2014-04-23
Publication date: 2014-10-30
Also published as: WO2014174461A3; CN113096777A; EP2989575B1; US20160062956A1; EP2989575A2; CN105144175A; JP2016522705A; US11830605B2; JP6433983B2

Abstract

A system and/or method that facilitates sharing image viewing context between vendor visualization applications without integration of different software application from different vendors packages is describe herein. In one instance, a visualization computing system (102) includes a processor (116) that executes computer readable instructions that capture a visual context of an imaging study displayed via a basic visualization application running on a vendor computing system, identify the study based on the captured visual context, load the study on the visualization computing system, and launch an advanced visualization application, which allows viewing and manipulation of the loaded study using advanced visualization tools unavailable by the basic visualization application.

Description

Image Visualization

The following generally relates to viewing images such as computed tomography (CT) images, X-ray images, magnetic resonance (MR) images, positron emission tomography (PET) images, single photon emission computer tomography

(SPECT) images, and/or other images.

Images generated in electronic format by systems such as CT, X-ray, MR,

PET, SPECT, and/or other imaging systems have been viewed through visualization software executing on a computing system such as a computer. For example, such images have been viewed via a PACS (Picture Archiving and Communication System) and/or the like. Such systems have been provided by different vendors with basic common viewing capabilities, allowing for similar viewing across systems. Where a particular vendor includes advanced visualization tools with their software and/or customized information in the images, such tools and/or information may not be available and/or accessible via application software of another vendor.

An approach to mitigating such unavailability and/or inaccessibility of the advanced visualization tools and/or customized information is for the vendor to provide an add-on application or the like to the other vendors to run on the other vendors' systems. However, this requires running two different applications from two different vendors in the same software environment without sharing any information. As such, the user has to select and load the imaging data twice, one for each application/system, and possibly go back and forth between applications to view and/or manipulate the imaging data, rendering image viewing and/or manipulation tedious and consuming clinician time.

The CCOW (Clinical Context Object Workgroup) context sharing standard provides a limited solution to the above. With respect to Health informatics, the CCOW standard is an HL7 standard protocol that allows vendor independent disparate applications to synchronize in real time, at the user-interface level, and present information at the desktop and/or portal level in a unified manner. This standard requires that both vendors' applications adhere to the same standard. Unfortunately, the CCOW standard has not been implemented by majority of the vendors. In addition, this will likely not change in the future, partially due to conflicting business goals between vendors. Aspects described herein address the above-referenced problems and others. The following describes a system and/or method that facilitates sharing image viewing context between vendor visualization applications without integration of different software application from different vendors packages, neither by software integration, nor by compliance with a standard. However, the partial or full integration of the different software applications from the different vendors is also contemplated herein.

In one aspect, a visualization computing system includes a processor that executes computer readable instructions that capture a visual context of an imaging study displayed via a basic visualization application running on a vendor computing system, identify the study based on the captured visual context, load the study on the visualization computing system, and launch an advanced visualization application, which allows viewing and manipulation of the loaded study using advanced visualization tools unavailable by the basic visualization application.

In another aspect, a method includes capturing a screen layout of a study loaded in connection with a basic visualization application executing on a first computing system, identifying, based on the captured screen layout, an identification of the loaded study, and loading the identified study in connection with an advanced visualization application, which includes visualization tools in addition to those of the basic visualization, of a second different computing system.

In another aspect, a computer readable storage medium is encoded with one or more computer executable instructions, which, when executed by a processor of a computing system, causes the processor to: determine an identification of a study loaded in a basic visualization application executing on a first computing system based on a screen capture of the loaded study and a layout template of the basic visualization application, and load the identified study in connection with an advanced visualization application, which includes visualization tools in addition to those of the basic visualization, of a second different computing system.

The invention may take form in various components and arrangements of components, and in various steps and arrangements of steps. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.

FIGURE 1 schematically illustrates an example visualization computing system that includes an advanced visualization application(s) and a context identifier.

FIGURE 2 illustrates an example of the context identifier. FIGURE 3 illustrates an example of data displayed in a GUI for a basic visualization application running on a vendor computing system.

FIGURE 4 illustrates an example of the visualization computing system in connection with an external imaging device.

FIGURE 5 illustrates an example screen layout template generator.

FIGURE 6 illustrates an example method for identifying and using a visualization context of a vendor computing system with a visualization computing system with advanced visualization tools.

FIGURE 7 illustrates an example method for generating screen layout templates.

FIGURE 8 illustrates textual information for a first screen shot with first textual information and an image of an object

FIGURE 9 illustrates textual information for a second screen shot with second textual information, which is different from the first textual information, and the image of the object.

FIGURE 10 illustrates a difference image generated by subtracting the screen layouts of FIGURES 8 and 9.

Initially referring to FIGURE 1, a visualization computing system 102 is schematically illustrated in connection with a vendor computing system 104, imaging systems 106, 108, 110 and 112, and a data repository 114. In this example, the vendor computing system 104 includes basic visualization tools whereas the visualization computing system 102 includes the basic visualization tools and additional visualization tools such as vendor custom tools.

The visualization computing system 102 includes a processor(s) 116 such as a microprocessor, a central processing unit, a controller, or the like. The visualization computing system 102 further includes input/output (I/O) 118 that facilitates communication with an output device(s) 120 such as a display monitor, filmer, etc., with an input device (s) 122 such as a mouse, keyboard, etc., with a network 124, etc.

The visualization computing system 102 further includes a computer readable storage medium 126, which includes physical memory or other non-transitory memory. The processor(s) 116 executes computer readable instructions 128 encoded or embedded in the computer readable storage medium 126. The processor(s) 116 can also execute computer readable instructions carried by a signal, carrier wave, and other transitory (non-computer readable storage) medium. In the illustrated example, the instructions 128 include a basic visualization application(s) 130, which, for this example, include instructions for basic viewing capabilities likely to be common across most vendor computing systems. The illustrated vendor computing system 104 also includes the basic visualization application(s)130, as well as a processor(s), computer readable storage medium, I/O, input and output devices, which are not shown for sake of clarity and brevity.

The instructions 128 further include an advanced visualization application(s) 132, which, for this example, include additional instructions for image viewing and/or manipulating capabilities that are not common to the vendor computing system 104 and/or part of the basic visualization application(s) 130. The instructions 128 further include a context identifier 134. As described in greater detail below, the context identifier 134 identifies a visualization context (or screen layout) of the vendor computing system 104, and employs this context with the visualization computing system 102 to present the same study in connection with the advanced visualization application(s) 132.

In one instance, this allows a user to seamlessly move from the vendor computing system 104 to the visualization computing system 102 when the user desires to use advanced visualization tools that are not available via the vendor computing system 104. Seamlessly means that the same study and the same image presented by the vendor computing system 104 is automatically identified, loaded and presented by the visualization computing system 102. In one instance, this mitigates having to integrate visualization applications of different vendors and/or comply with a standard screen layout utilized by multiple different vendors.

The illustrated visualization computing system 102 and/or the vendor computing system 104 obtain imaging data from one or more of the imaging systems 106, 108, 110 and 112, the data repository 114, and/or other device and/or storage. The imaging systems include a CT imaging system 106, an MR imaging system 108, a SPECT imaging system 110, and a PET imaging system 112. Other imaging systems are also contemplated herein. The data repository 114 may include one or more of a radiology information system (RIS), a hospital information system (HIS), an electronic medical record (EMR), a sever, a database, and/or the like.

The visualization computing system 102 can be activated to determine the visualization context of the vendor computing system 104 in response to a user activating the visualization computing system 102 to do so, for example, when the user determines they want to use the advanced visualization application(s) 132. In another instance, the visualization computing system 102 determines the context when the basic visualization application is employed and stores the context information and/or pre-loads the study on the visualization computing system 102.

The vendor computing system 104 and/or the visualization computing system 102 can be PACS and/or other computing systems.

Turning to FIGURE 2, an example of the context identifier 134 is illustrated. A screen capture component 202 captures the current context or content displayed, in a display monitor or the like, by the vendor computing system 104. An example of such content is depicted in FIGURE 3 which shows a monitor 302 with a display region 304 in which a basic visualization graphical user interface (GUI) 306 corresponding to the basic visualization application 105 is displayed. In FIGURE 3, a study has already been loaded and is visually presented in the GUI 306. The loaded data includes an image of a two dimensional axial slice of a scanned object and various information corresponding to the patient, the scan, the axil slice, etc. In this example, the screen capture component 202 visually captures the GUI 306.

In one instance, the screen capture component 202 includes a software module that is conveyed to and executed by the vendor computing system 104. The executing software module captures the screen in an electronic data format and conveys the electronic data to the visualization computing system 102. In another instance, the software module is otherwise conveyed to and executed by the vendor computing system 104, for example, over the network 124 via a server, from portable memory (e.g., CD/DVD, etc.), etc. In yet another instance, the screen capture component 202 is employed in connection with an external imaging device such as an optical sensor, such as a camera, a video recorder, or the like. This is shown in FIGURE 4, which includes an external imaging device 402. In this case, the picture or video of the GUI 306 is sent to the visualization computing system 102.

Returning to FIGURE 2, a region identifier 204 employs a pre-determined screen layout template(s) 206 from a template bank 208 to identify one or more regions in the captured screen shot. The particular template(s) 206 corresponds to the layout of information in the captured screen shot and can be identified, for example, from a plurality of different templates 206, based on a name and/or unique identification of the vendor of the vendor computing system 104, a name of the basic visualization software the vendor computing system 104, a user selected template, an identification of a viewing facility at which the images are being viewed, and/or other information. Turning briefly to FIGURE 3, in this example, the template 206 identifies regions 310, 312, 314 and 316, e.g., by screen coordinates or otherwise. The template 206 also identifies what information is displayed in each of the one or more regions.

Returning to FIGURE 2, an information extractor 210 extracts the information from the identified one or more regions of the captured screen shot. For example, in the example in FIGURE 3, the template 206 identifies the region 310 as displaying a string and/or value corresponding to a unique identification of the study ("Study ID"), the region 412 as displaying a string and/or value corresponding to a series number ("Series #"), the region 314 as displaying a string and/or value corresponding to an image slice number ("Image #"), and the region 316 as displaying a string and/or value corresponding to a slice location ("Slice location"). The information extractor 210 extracts this information such that it extracts the "Study ID", the "Series #", the "Image #", and the "Slice location".

A character recognizer 212 interprets the extracted information to determine the meaning of the extracted information. For example, in FIGURE3, the character recognizer 212 interprets the extracted information corresponding to the "Series #" 312 as "#2", the "image #" as "#107", etc. A study retriever 214 retrieves the study, e.g., based on the interpreted extracted information corresponding to the unique identification of the study. The study can be retrieved from the CT imaging system 106, the MR imaging system 108, the SPECT imaging system 110, the PET imaging system 112 and/or other imaging system, the data repository 114, and/or other device.

An advanced application launcher 216 launches an advanced visualization application(s) 132. The particular application launched can be identified based on the interpreted extracted information. For example, where the interpreted extracted information includes information indicating the particular scan protocol, for example, a cardiac scan, the advanced application launcher 216 can select an advanced cardiac application from the advanced visualization application(s) 132 (FIGURE 1). In another example, a user selects an advanced visualization application(s) 132 of interest, for example, via a GUI selection from a menu of available advanced applications. The menu may be presented in either or both of the vendor computing system 104 or the visualization computing system 102. In yet another example, a default advanced application is selected. The default application can be identified via a default file.

FIGURE 5 illustrates an example template generator 502 that generates at least one of the templates 206.

The template generator 502 obtains (e.g., retrieves, receives, etc.) at least two screen shots of images of the same object (e.g., a calibration phantom) but with different but known textual information such as different "Study ID," "Series #," "Image #," "Slice location," and/or other displayed information. The screen shots can be obtained via the screen capture component 202 and/or otherwise. This may include loading two studies and capturing the screen layouts and/or receiving the screen layouts.

An image difference generator 504 subtracts the at least two screen shots, generating a difference image. Since the object is the same in the at least two screen shots, the object therein cancels out. However, the information in the textual information is different and thus the difference image will include regions with difference information. This is shown in FIGURES 8, 9 and 10. FIGURE 8 shows textual information for a first screen shot, FIGURE 9 shows different textual information for a second screen shot, and FIGURE 10 shows the difference between the textual information in FIGURES 8 and 9.

A region locator 506 records coordinates to these regions. In this example, three regions are located, a first region 1002 corresponding to examination identification, a second region 1004 corresponding to series identification, and a third region 1006

corresponding to image identification. In this example, the three regions are adjacent to each other. In other instances, the regions may be located in different regions of the images, for example, as shown in FIGURE 3 in connection with 310, 312, 314 and 316. In other examples, more or less regions are identified.

A string matcher 508 matches the known meaning of the textual information in the original at least two images using the coordinate information to locate the textual information. For example, in connection with FIGURE 10, the string matcher 508 matches the location corresponding with 1002 with the string corresponding to the examination identification, the location corresponding with 1004 with the string corresponding to the series identification, and the location corresponding with 1006 with the string corresponding to the image identification.

A mapper 510 maps the identified strings to corresponding locations, generating a screen layout template identifying the regions of interest in the screen layout that includes textual information of interest. The above can be repeated for a plurality of different vendors such that a screen layout template is generated for the screen layout of each one of the plurality of different vendors. In another instance, a vendor provides the screen layout template for their screen layout. The templates can be stored in the visualization computing system 102 (as shown) or external thereto, for example, at a server.

FIGURES 6 and 7 illustrate methods in accordance with the description herein. It is to be appreciated that the ordering of the acts in the methods is not limiting. As such, other orderings are contemplated herein. In addition, one or more acts may be omitted and/or one or more additional acts may be included.

FIGURE 6 illustrate an example method for employing the visualization computing system 102.

At 602, a study is loaded into a basic visualization application executing on a vendor computing system.

At 604, an image displayed by the vendor computing system is captured.

At 606, textual information in regions of interest identified from a template is extracted from the captured image.

At 608, the extracted textual information in is interpreted to identify the study loaded in the basic visualization application.

At 610, the identified study is retrieved.

At 612, an advanced visualization application is launched on a visualization computing system, which is different from the vendor computing system.

At 614, the identified study is loaded in the advanced visualization

application.

At 616, an operator of the visualization computing system view and/or manipulates the loaded study via the advanced visualization application.

FIGURE 7 illustrate an example method for generating templates.

At 702, at least two screen shots of images of the same object but with different but known textual information are obtained for a basic visualization application running on a vendor computing system. This can be achieved by loading the studies side by side and performing a screen capture or by receiving already capture screen layouts.

At 704, the at least two screen shots are subtracted, generating a difference image.

At 706, regions of the difference image with the different known textual information are identified. Generally, regions in the at least two images with the same information will cancel out such that the only regions in the difference image with textual information are those regions that include different textual information.

At 708, the textual information in the identified regions is extracted.

At 710, the extracted textual information is matched with the known meaning. At 712, the meaning of extracted textual information and the corresponding location is mapped, generating a screen layout template for the screen layout of the basic visualization application running on the vendor computing system.

At 714, the mapping is stored.

At 716, the mapping is utilized by the visualization computing system 102 to present a study loaded in the basic visualization application running on the vendor computing system via an advanced visualization application running on the visualization computing system 102 in the same visual context as it is presented in the basic visualization application running on the vendor computing system.

The above methods may be implemented by way of computer readable instructions, encoded or embedded on computer readable storage medium, which, when executed by a computer processor(s), cause the processor(s) to carry out the described acts. Additionally or alternatively, at least one of the computer readable instructions is carried by a signal, carrier wave or other transitory medium.

In a variation, context identification is performed through the use of accessibility application programming interfaces (APIs) of an operating system of Microsoft, Apple, etc. Accessibility APIs allow an external application to introspect the user interface of another application in a non-intrusive fashion. These APIs are meant to enable

accessibility tools such as screen readers to work with any application.

Furthermore, a screen context recognition (SCR) profile could be created based on a user interface (UI) hierarchical structure of the application and then used to retrieve the information from various UI elements. Profile creation can follow a very similar technique to the one above where images with known data are displayed. It is then possible to "search" the UI and look for the known markers to identify their matching UI elements.

The SCR system would need to be deployed on the target environment (PC) and can be very lightweight. It would have to include a resident agent that runs to capture and extract the context continuously.

To further ease the integration of dedicated applications that make use of the context information (which is often complex on PACS workstations), the SCR system could communicate context captures and changes to a server. This server would then be used by either a thin-client application such as the IntelliSpace Portal client or a web-based zero- footprint application which can then react to context changes appropriately.

The invention has been described with reference to the preferred embodiments. Modifications and alterations may occur to others upon reading and understanding the preceding detailed description. It is intended that the invention be constructed as including all such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

CLAIMS:

1. A visualization computing system (102), comprising:

a processor (116) that executes computer readable instructions that capture a visual context of an imaging study displayed via a basic visualization application running on a vendor computing system, identify the study based on the captured visual context, load the study on the visualization computing system, and launch an advanced visualization application, which allows viewing and manipulation of the loaded study using advanced visualization tools unavailable by the basic visualization application.

2. The visualization computing system of claim 1, wherein the study is identified based on a screen layout template corresponding to a particular vendor of the vendor computing system.

3. The visualization computing system of claim 2, wherein the template identifies a location of textual information identifying the study in the captured visual context via screen coordinates.

4. The visualization computing system of claim 3, wherein the executing computer readable instructions further extract the textual information from the location identified in the captured visual context.

5. The visualization computing system of claim 4, wherein the executing computer readable instructions employ a character recognition algorithm that interprets the extracted textual information.

6. The visualization computing system of any of claims 1 to 5, wherein the executing computer readable instructions identify a study protocol that indicates a type of scan based on the captured visual context and launches the advanced visualization application that corresponds to a same type of scan.

7. The visualization computing system of any of claims 1 to 6, wherein the executing computer readable instructions generates the template from at least two calibration images of the vendor in which the calibration images include different textual information.

8. The visualization computing system of claim 7, wherein the executing computer readable instructions subtract the at least two calibration images, generating a difference image indicating locations of different text.

9. The visualization computing system of claim 8, wherein the executing computer readable instructions map the locations to a type of data at the locations, thereby creating the template.

10. The visualization computing system of any of claims 1 to 9, wherein the vendor computing system and the visualization computing system are separate and distinct computing system.

11. A method, comprising:

capturing a screen layout of a study loaded in connection with a basic visualization application executing on a first computing system;

identifying, based on the captured screen layout, an identification of the loaded study;

loading the identified study in connection with an advanced visualization application, which includes visualization tools in additions to those of the basic visualization, of a second different computing system.

12. The method of claim 11, further comprising:

identifying the identification of the loaded study based on a screen layout template corresponding to a vendor of the vendor computing system.

13. The method of claim 12, wherein the template identifies a location of textual information in the captured visual context that identifies the study.

14. The method of claim 13, further comprising:

extracting the textual information from the location identified in the captured visual context;

interpreting the extracted textual information; and

identifying a study protocol that indicates a type of scan based on the captured visual context.

15. The method of claim 14, further comprising:

launching the advanced visualization application, which corresponds to a same type of scan.

16. The method of any of claims 11 to 15, further comprising:

generating the template from at least two calibration images of the vendor in which the calibration images include different textual information.

17. The method of claim 16, further comprising:

subtract the at least two calibration images, thereby generating a difference image indicating locations of different text.

18. The method of claim 17, further comprising:

mapping the locations to a known type of data at the locations, thereby creating the template.

19. The method of any of claims 11 to 18, wherein the vendor computing system and the visualization computing system are separate and distinct computing system.

20. A computer readable storage medium encoded with one or more computer executable instructions, which, when executed by a processor of a computing system, causes the processor to:

determine an identification of a study loaded in a basic visualization application executing on a first computing system based on a screen capture of the loaded study and a layout template of the basic visualization application;

load the identified study in connection with an advanced visualization application, which includes visualization tools in addition to those of the basic visualization, of a second different computing system.