nadeemlab/Physics-ArX
Physics-based data augmentation library for quantifying CT and CBCT images in radiotherapy [PMB'23, PMB'21, Medical Physics'21, AAPM'21]
This project helps radiation oncologists and medical physicists by generating realistic, paired synthetic CBCT and planning CT images for radiotherapy treatment planning. You provide high-quality planning CT images, baseline CBCT, and 4D CT data, and it produces a large dataset of varied, perfectly registered synthetic CBCTs. This dataset can then be used to train AI models that quantify daily/weekly CBCTs and improve organ-at-risk segmentation, leading to more robust treatment plans.
No commits in the last 6 months.
Use this if you need to create robust deep learning models for radiotherapy image quantification and segmentation, especially when working with varied cone-beam CT (CBCT) data and requiring perfectly paired training examples.
Not ideal if you are looking for a ready-to-use clinical tool for immediate patient treatment, as this is a data augmentation library for model development.
Stars
72
Forks
18
Language
Python
License
—
Category
Last pushed
May 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nadeemlab/Physics-ArX"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ProjectNeura/MIPCandy
Build a complete experiment pipeline for your PyTorch MIP model in 10 seconds.
canlab/CanlabCore
Core tools required for running Canlab Matlab toolboxes. The heart of this toolbox is...
tbepler/topaz
Pipeline for particle picking in cryo-electron microscopy images using convolutional neural...
MPI-Dortmund/tomotwin-cryoet
cryo-ET particle picking by representation and metric learning
bioimage-io/core-bioimage-io-python
Python libraries for loading, running and packaging bioimage.io models