Systems and methods for automated rendering
Systems and methods for determining rendering parameters based on authored snapshots or templates. In one aspect, clinically relevant snapshots of patient medical data are created by experts to support educational or clinical workflows. Alternatively, the snapshots are created by automation processes from AI-based organ and disease segmentations. In another aspect, clinically relevant templates are generated. Rendering parameters are derived from the snapshots or templates, stored, and then applied for either rendering new data or interactive viewing of existing data.
1. A method for automated rendering from templates, the method comprising:
acquiring, by a medical imaging device, medical image data of a patient;
segmenting the medical image data into one or more segmentation masks;
retrieving one or more templates corresponding to the one or more segmentation masks, the one or more templates comprising at least a reference image and viewing parameters;
computing, using a differentiable renderer, one or more rendering parameters based on a style of the reference image, the rendering parameters comprising at least lighting parameters, material properties, and transfer functions; and
generating an image for the medical image data using the one or more rendering parameters.
2. The method of claim 1 , wherein retrieving the one or more templates comprises registering the one or more segmentation masks against a body atlas configured to store a plurality of different masks of different regions and organs.
3. The method of claim 1 , wherein the one or more templates are generated from a traditional anatomical illustration or a photograph.
4. The method of claim 1 , wherein the one or more rendering parameters define a color and a texture of the generated image.
5. The method of claim 1 , wherein the one or more templates comprise at least reference images for different organs.