faebstn96 / helix2fan Goto Github PK
View Code? Open in Web Editor NEWHelical to fan-beam CT geometry rebinning and differentiable FBP of DICOM-CT-PD projections
License: Apache License 2.0
Helical to fan-beam CT geometry rebinning and differentiable FBP of DICOM-CT-PD projections
License: Apache License 2.0
Hi, do you have any experience with rebinning scans that contain multiple rotations? As far as I understood, rebinning works only for 2pi, which is also something I experienced in action. Could you give a hint on the parameters that could potentially control the behavior of the algorithm in this case?
I got this error when I tried to run the codes
Traceback (most recent call last):
File "/home/wangzhe/wangzhe2/SV_Algorithms/helix2fan-master/main.py", line 67, in
run(parser)
File "/home/wangzhe/wangzhe2/SV_Algorithms/helix2fan-master/main.py", line 18, in run
raw_projections, parser = read_dicom(parser)
File "/home/wangzhe/wangzhe2/SV_Algorithms/helix2fan-master/read_data.py", line 82, in read_dicom
nu = data_headers[0].Rows
Hi!I wonder if this work support flying focal spot now?
I had all necessary packages installed, and tried running this on AAPM-Myo LDCT dataset (concretely on a single subject L109, containing multiple .dcm
files), only to get the following error:
Processing scan scan_001.
Loading projection data: 100%|█████████████████████████████████████████████████| 4000/4000 [00:05<00:00, 750.04it/s]
Traceback (most recent call last):
File "main.py", line 67, in <module>
run(parser)
File "main.py", line 18, in run
raw_projections, parser = read_dicom(parser)
File "/home/clma/projects/helix2fan-master/read_data.py", line 96, in read_dicom
hu_factor = float(data_headers[0][0x70411001].value) # WaterAttenuationCoefficient (see manual for HU conversion)
File "/home/clma/miniconda3/envs/recon38/lib/python3.8/site-packages/pydicom/dataset.py", line 987, in __getitem__
elem = self._dict[tag]
KeyError: (7041, 1001)
Any advice on that?
Hello, thx for your greate job!
I adopt the 2016Mayo challenge data, it has 40 thousands+ view of every patient.
I have tried to rebin it for four hours, is there any methods to accelerate the operation?
Many thx again
Hi, I get below error when trying to generate fan_beam projections from LDCT data.
I will try to investigate the problem further. I wonder if it you already know how to resolve it quickly?
python main.py --path_dicom /mnt/new/datasets/lowDoseCT/manifest-1648648375084/LDCT-and-Projection-data/N001/01-31-2022-NA-NA-63397/1.000000-Full\ Dose\ Projections-25858 --idx_proj_start 0 --idx_proj_stop 100
proj_rebinned = np.zeros((args.rotview, args.nu, args.nz_rebinned), dtype=np.float32) ValueError: negative dimensions are not allowed
Thanks,
I want to download the data from the TCIA library, but I don't have permission to download. What do I need to do to get the data?
Thank you for sharing this repository!
I have two questions about the above-mentioned variables:
Thanks,
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.