Light

eigenvivek / drr.jl Goto Github PK

View Code? Open in Web Editor NEW

0.0 1.0 0.0 35.61 MB

Parallelized, GPU-accelerated, and differentiable digitally reconstructed radiographs in Julia.

Julia 100.00%

medical-imaging

drr.jl's Introduction

DRR.jl

Summary

Digitally reconstructed radiographs (DRR) are simulated projectional radiographs generated from volumetric CT imaging data. This package provides parallelized, GPU-accelerated, and differentiable DRR generators in Julia.

Examples

Read the CT volume data and define the camera/detector geometry:

# Read the DICOM file
volume, ΔX, ΔY, ΔZ = read_dicom("../data/cxr"; pad=true)
grid = volume2grid(volume, ΔX, ΔY, ΔZ)  # The bottom-left corner of the CT is placed at (0,0,0)

# Define the camera
center = Vec3(180., 180., -100)
camera = Camera(center)

# Define the detector plane
center = Vec3(180., 180., 500.)
normal = Vec3(0., 0., -1.)
height, width = 601, 601
Δx, Δy = 2., 2.
detector = Detector(center, normal, height, width, Δx, Δy)

To generate a DRR using this setup, run

julia> spacing = 0.5

julia> drr = make_drr(grid, volume, camera, detector, spacing)

julia> heatmap(drr, c=:grays)

which generates the following projection:

drr.jl's People

Contributors

Watchers

drr.jl's Issues

Figure out how to get the spacing of a CT from DICOM

DICOM PixelData gives the numerical values in a CT but it doesn't give us the spacing

To accurately compute a DRR, voxels need to be stretched to world coordinates

https://stackoverflow.com/questions/14930222/how-to-calculate-space-between-dicom-slices-for-mpr

Make plastimatch demo in Julia notebook

Add installation instructions to README

Implement Siddon's method for weighted ray tracing

Test if DICOM.jl can import a CT volume

https://github.com/JuliaHealth/DICOM.jl

Potential method for GPU acceleration

For each ray, turn the individual trilinear matrices into a big block diagonal and do it in one go on the GPU

A single trilinear matrix is only 8x8 so it's inefficient to do individually on the GPU

Replace GridInterpolations dependency

Just need a dictionary of spacings

volume, ΔX, ΔY, ΔZ = read_dicom("data/cxr"; pad=true)
nx, ny, nz = size(volume)
spacing = Dict(
    "xs" => 0:ΔX:(nx-1)*ΔX,
    "ys" => 0:ΔY:(ny-1)*ΔY,
    "zs" => 0:ΔZ:(nz-1)*ΔZ,
)

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.