Image space-based particle generation modeling

1. A method comprising: obtaining original volume data, wherein the original volume data comprises a plurality of voxels;

transforming each voxel of the plurality of voxels of the original volume data, based on a distance from a viewpoint to a cross-sectional plane of the original volume data and a second distance from an image plane to the center of the original volume data, to generate a transformed volume data, wherein the cross-sectional plane is parallel to the image plane, wherein the distance between the surface face of the original volume data furthest from the viewer and the surface face of the original volume data closest to the viewer when the original volume data is projected on to the image plane is equal to the length of the transformed volume data along a gaze direction of the viewer;

for each voxel of the plurality of voxels, generating a particle from the transformed volume data with a probability corresponding to: −log(1−an opacity of each voxel), wherein the original volume data includes the opacity for each voxel;

projecting the particles on an image plane to generate a 2D image corresponding to the original volume data, wherein:

a normal vector of the image plane is parallel to a direction of the projecting the particles,

the 2D image includes a plurality of pixels, and

wherein a size and shape of each pixel of the 2D image is identical to a size and shape of each particle projected on the image plane;

generating a plurality of the 2D images corresponding to the original volume data; and

averaging the plurality of the 2D images to generate an ensemble 2D image.