![]() |
Segmentation Image Processing Seg3D is a volume segmentation and processing tool developed by the NIH Center for Integrative Biomedical Computing. It combines a flexible manual segmentation interface with powerful higher-dimensional image processing and segmentation algorithms from the Insight Toolkit. Previous Releases |
Seg3D is a free volume segmentation and processing tool developed by the NIH Center for Integrative Biomedical Computing at the University of Utah Scientific Computing and Imaging (SCI) Institute. Seg3D combines a flexible manual segmentation interface with powerful higher-dimensional image processing and segmentation algorithms from the Insight Toolkit. Users can explore and label image volumes using volume rendering and orthogonal slice view windows.
Seg3D at a glance:
Please see the GitHub documentation pages for up-to-date installation and build documentation.
Acknowledgement: Seg3D is an Open Source software project that is principally funded through the SCI Institute's NIH/NIGMS CIBC Center. Please use the following acknowledgment and send us references to any publications, presentations, or successful funding applications that make use of NIH/NIGMS CIBC software or data sets.
"This project was supported by the National Institute of General Medical Sciences of the National Institutes of Health under grant number P41 GM103545-18."
• Seg3D Citation: [bibtex citation] [Endnote citation]
Seg3D is available for free and open source under the MIT License
NIH/NIGMS Center for Integrative Biomedical Computing Acknowledgment
CIBC software and the data sets provided on this web site are Open Source software projects that are principally funded through the SCI Institute's NIH/NCRR CIBC. For us to secure the funding that allows us to continue providing this software, we must have evidence of its utility. Thus we ask users of our software and data to acknowledge us in their publications and inform us of these publications. Please use the following acknowledgment and send us references to any publications, presentations, or successful funding applications that make use of the NIH/NCRR CIBC software or data sets we provide.
"This project was supported by the National Institute of General Medical Sciences of the National Institutes of Health under grant number P41 GM103545-18."
Seg3D is a relatively simple-to-use segmentation program that can be used for cases where automatic segmenting programs fail. It has a strong emphasis on manual and semi-manual segmentation, where filtered data guides the user in making decent segmentations of the data. The program is mainly intended for, but is not strictly limited to, segmentation of biological/medical data.
Seg3D also serves as the start of the modeling pipeline, where BioMesh3D can be used to turn segmentations into quality meshes and SCIRun can be used to simulate biological process on the segmented images.
Seg3D Basic Functionality![]() |
Seg3D Tutorial![]() |
Seg3D Python examples![]() |
Part 1: Create Project |
Part 2: Opening Images |
Part 3: Layout |
Part 4: Layer Manager |
Part 4.5: Navigation |
Part 5: Active Layer |
Part 6: Threshold Mask |
Part 7: |
Part 8: Save Project |
Seg3D for Users 2011 (Full Seminar)
|
Seg3D for Users 2011 (Individual Clips)
|
|

A: If you are running Seg3D on Windows or Mac OX, you can find system requirements under the Specifications tab. If you are running Seg3D on Linux, you’ll need to build it from source. You can check the Specifications tab for platform requirements, as well as the Developer Documentation tab for build instructions.
Seg3D 1.x session files are gzipped tar archives. The session file will typically contain a data volume (NRRD), a label file (NRRD), and an XML session descriptor file.
Just extract the all files, and then load the data volume and label files in Seg3D 2. After extracting the files, load the data volume in Seg3D 2 first, and afterward, the label file
For Linux, OS X, extract the files using tar. For example if the Seg3D 1.x session file is test_tooth.ses:
rideau:tmp aylakhan$ tar xzvf test_tooth.ses
x session.xml
x label1.nrrd
x data1.nrrd
For Windows: Seg3D sessions must be opened with tools that can open gzip files, such as the 7-zip utility, which can unpack gzipped tar archives.
A: From the original launch screen, choose the "Quick Open File" option, which allows you to open a file without creating a new project
A: We support a number of file formats, including DICOM. There is limited support for exporting to Matlab because spacing and axis information is hardcoded into the file header. Supported file types can be seen in the Segmentation Export Wizard, which is located in the file type drop-down list.
A: Try reducing or eliminating the amount of memory assigned to the Undo buffer. You can find this option in the “Preferences” window under “General/Project”.
A: Seg3D 2.x can read 3D Matlab structs, and also has backward compatibility for 4D Matlab structs formatted for Seg3D 1.x.
Seg3D 1.x can read 3D structs, as well as 4D Matlab structs with the first dimension as a dummy dimension (size == 1). In the case of 4D structs, the first dimension is simply ignored, and the information from the remaining axes is read in as a 3D struct.
A: pan: shift + left mouse button
scroll: shift + middle mouse button
zoom: shift + right mouse button