Skip to content

Commit

Permalink
Add IA
Browse files Browse the repository at this point in the history
  • Loading branch information
nroduit committed Mar 26, 2024
1 parent ad7a883 commit 7eb1120
Show file tree
Hide file tree
Showing 7 changed files with 142 additions and 5 deletions.
80 changes: 80 additions & 0 deletions content/tutorials/dicom-artificial-intelligence.en.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,80 @@
---
title: AI DICOM Objects
weight: 339
description: How to display DICOM files generated by artificial intelligence (AI) frameworks
keywords: [ "dicom AI", "artificial intelligence", "AI", "dicom viewer", "free dicom viewer", "open source dicom viewer" ]
---

## <center>DICOM objects generated by artificial intelligence</center>

Artificial intelligence (AI) frameworks can produce various DICOM objects for different purposes. Here are some common DICOM object types produced by AI frameworks and how they are handled in Weasis (see Info window).

### DICOM Secondary Capture (SC)

This type of object represents secondary images where the AI has embedded information in the image pixels. These images may include annotations, measurements, or other enhancements to the original image data.

{{% notice info %}}
DICOM Secondary Capture can be displayed by Weasis like any other image data, see [DICOM 2D Viewer](../dicom-2d-viewer/).
{{% /notice %}}

### DICOM Segmentation (SEG)

These objects represent the results of segmentation algorithms applied to medical images. Segmentation involves partitioning an image into multiple segments to simplify its representation for analysis or display. AI frameworks can produce SEG objects containing segmentations of anatomical structures, lesions, or other regions of interest.

{{% notice info %}}
See [DICOM SEG](../dicom-segmentation) for displaying DICOM SEG objects in Weasis.
{{% /notice %}}

### DICOM RTSTRUCT

This type of DICOM object is originally used to represent structures delineated on CT images for radiotherapy treatment planning. Some AI frameworks may produce DICOM RTSTRUCT objects (geometric shapes) instead of DICOM Segmentation (pixel-based).

{{% notice info %}}
See [DICOM RT](../dicom-rt) for displaying DICOM RTSTRUCT objects in Weasis.
{{% /notice %}}

Displaying TotalSegmentator segmentation results in Weasis:
{{< youtube id="W6MHc3hEqfk" >}}

### DICOM Structured Report (SR)

AI frameworks can generate structured report containing the results of their analysis. These reports typically include structured information about findings, measurements, observations, and interpretations derived from medical images or other data.

{{% notice info %}}
See [DICOM SR Viewer](../dicom-sr)
{{% /notice %}}


### DICOM Encapsulated Documents
AI frameworks may produce DICOM objects containing encapsulated documents such as PDF reports, text documents, or other non-image data related to medical imaging studies.

{{% notice info %}}
This type of object can be displayed by the default system application associated with the document mime type. The DICOM attributes can be viewed from the thumbnail context menu (see image below).

![Open DICOM PDF tags](/tuto/dicom-attributes-pdf.png?classes=shadow)
<br>
{{% /notice %}}


### DICOM Presentation States
Presentation states define how images should be displayed, including display parameters such as window width, window center, and image orientation. A Grayscale Softcopy Presentation State (GSPS) object is used to display annotations and graphics that overlay on a displayed image. AI frameworks might generate presentation states to specify how images should be displayed based on their analysis results or to display graphics overlays on images.

{{% notice info %}}
See [DICOM PR](../build-ko-pr/#presentation-state-pr-or-gsps) for displaying DICOM Presentation States in Weasis.
{{% /notice %}}


### DICOM Enhanced Objects

Enhanced DICOM objects contain additional information. AI frameworks might produce enhanced DICOM objects to include additional annotations or other enhancements to the image data.

{{% notice info %}}
DICOM Enhanced (e.g. reduce noise or improve visualization of anatomical structures) can be displayed by Weasis like any other image data. Some other additional information (overlay, shutter and pixel padding) can be added to the image rendering, see [2D Viewer Display](../dicom-2d-viewer/#image).
{{% /notice %}}







25 changes: 25 additions & 0 deletions content/tutorials/dicom-audio.en.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
---
title: DICOM Audio Player
weight: 90
description: How to listen to DICOM audio data
keywords: [ "dicom au", "au", "audio", "dicom viewer", "open source dicom viewer" ]
---

## <center>Playing DICOM AU data {{< svg "static/tuto/icon/audio.svg" >}}</center>

This player is used to play audio data defined by the DICOM AU standard.

![Audio Player](/tuto/dicom-audio.png?classes=shadow&width=780px)
<br>
### Toolbar {{< badge "A" >}}
Actions in the toolbar are:
* {{< svg "static/tuto/icon/metadata.svg" >}} Show the DICOM metadata of the DICOM AU

### Play {{< badge "B" >}}
The _Play_ button allows you to play and pause. The slicer allows you to navigate through the audio file and display the position in seconds.

### Volume {{< badge "C" >}}
This slider allows you to adjust the volume of the audio file.

### Export Audio File {{< badge "D" >}}
The _Export Audio File_ button allows you to save the audio file in the format AU or WAVE.
4 changes: 3 additions & 1 deletion content/tutorials/dicom-segmentation.en.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ keywords: [ "dicom seg", "segmentation", "SEG", "dicom viewer", "free dicom view

Since Weasis {{< badge "v4.3.0" >}}, this panel lets you display the contents of a DICOM SEG file superimposed on the image. It also lets you modify the transparency of specific regions (label defined by a color).

DICOM SEG can be generated by [AI frameworks](../dicom-artificial-intelligence) to represent the results of segmentation algorithms applied to medical images.

### How to display DICOM SEG
In order to display the DICOM SEG regions in overlay on the image, follow these steps (see in the image below):

Expand All @@ -18,7 +20,7 @@ In order to display the DICOM SEG regions in overlay on the image, follow these
4. Select one or several regions to display for the selected DICOM SEG (3). Several regions are grouped together when they share the same first name. Note: the parent node must be selected to display the child regions.
5. Adjust global graphic opacity (border and interior)

![DICOM SEG](/tuto/dicom-seg.jpg?classes=shadow)
![DICOM SEG](/tuto/dicom-seg.jpg?classes=shadow&width=780px)
<br>

{{% notice note %}}
Expand Down
30 changes: 30 additions & 0 deletions content/tutorials/dicom-sr.en.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
---
title: DICOM SR Viewer
weight: 80
description: How to display DICOM Structured Report
keywords: [ "dicom sr", "sr", " structured report", "dicom viewer", "open source dicom viewer" ]
---

## <center>Displaying DICOM Structured Report {{< svg "static/tuto/icon/text.svg" >}} </center>

The DICOM Structured Report (SR) viewer is used to display and analyze DICOM SR data. The SR object is a structured collection of content items that represent a report of a diagnostic or therapeutic procedure. The content items are organized in a tree structure, and each item has a relationship with other items.

The viewer displays the content of the SR object in a structured way, allowing the user to navigate through the tree and visualize the content of each item.

![SR Viewer](/tuto/dicom-sr.png?classes=shadow&width=780px)
<br>

### Toolbar {{< badge "A" >}}
Actions in the toolbar are:
* {{< svg "static/tuto/icon/print.svg" >}} Allows you to print the rendering of the SR
* {{< svg "static/tuto/icon/metadata.svg" >}} Show the DICOM metadata of the SR

### Display SR Header {{< badge "B" >}}
The header of the SR object is displayed in a table format with 3 columns containing information about the patient, the study, and the report status.

### DICOM SR Tree {{< badge "C" >}}
The content of the SR object is displayed in a tree structure. Each node in the tree represents a content item with hierarchical numbering, and the tree structure reflects the relationships between the items.

Some items can have a link to other content items, and the viewer provides a way to navigate through the tree by clicking on the links.

This link can also open a related image which can contain measurements defined in the SR object (e.g. in the image above, clicking on _POLYLINE_ will open the image and display the polyline).
8 changes: 4 additions & 4 deletions content/tutorials/gui.en.md
Original file line number Diff line number Diff line change
Expand Up @@ -32,10 +32,10 @@ In the View menu at the top, toolbars and tools related to the selected viewer c
* [Maximum Intensity Projection (MIP) viewer](../mip)
* [DICOM 3D viewer](../dicom-3d-viewer)
* [DICOM ECG viewer](../dicom-ecg)
* DICOM Structured Report (SR) viewer
* DICOM Audio player
* DICOM PDF viewer (external)
* DICOM Video player (external)
* [DICOM Structured Report (SR) viewer](../dicom-sr)
* [DICOM Audio player](../dicom-audio)
* DICOM PDF viewer (default system application associated with pdf files). Same for other encapsulated documents.
* DICOM Video player (default system player associated with mpg files)

### List of other workspaces
* Dicomizer
Expand Down
Binary file added static/tuto/dicom-audio.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/tuto/dicom-sr.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 7eb1120

Please sign in to comment.