Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Why choose -175 and 250 as a_min and a_max? #78

Open
qimaqi opened this issue Jun 25, 2024 · 1 comment
Open

Why choose -175 and 250 as a_min and a_max? #78

qimaqi opened this issue Jun 25, 2024 · 1 comment

Comments

@qimaqi
Copy link

qimaqi commented Jun 25, 2024

Hi there
I am wondering why the a_min and a_max values for ScaleIntensityRanged in train.py are set to -175 and 250. The normal range for intensity is typically -1000 to 1000. Is there a specific reason for this setup? It seems that using these parameters clips out many values?

@ljwztc
Copy link
Owner

ljwztc commented Jul 26, 2024

The range is specifically designed for the abdominal area.
The answer from gpt may help you understand this: In CT imaging, different tissues and substances have characteristic HU values. For example:
- Air: around -1000 HU
- Lung: around -500 HU
- Fat: around -100 to -50 HU
- Soft tissues (e.g., muscle, liver): around 0 to 100 HU
- Bone: 700 HU and above
By focusing on the range from -175 to 250 HU, we can enhance the visualization and analysis of soft tissues, which are often the primary areas of interest in many diagnostic scenarios.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants