Through segmentation all pixels of an organ or anatomical structure are detected. It is the basis for quantitative measurement. Measurements that can be obtained from the automated segmentation are for example the volume of organs or the curvature of the spine. Further applications are prosthetic planning or 3D-printing.
We offer customized solutions as a service project for further information check out Deep Learning Services.
Anatomical structures with substructures
Quantitative Measurements like the volume, angle or length can directly be calculated
Possible applications where automated annotation could be applied to:
- 2D radiographic images
- 3D MR, CT, PET and SPECT
- Bones (spine,..)
- Dental (nerve canal, bones, teeth) : Prosthetic planning
- Organs (Liver, Kidney,...): Volumetry
- Cardiac: Ejection fraction
- 3D printing
- Multi-modal input data
- Single-click solutions
- No parameterizations necessary
- Tumor segmentation in PET and SPECT
- Support for all kinds of input data
- Heterogeneous objects
- Manual refinement of segmentation result
- Sparse set of seed points for full 3-D segmentation
- GPU hardware acceleration
In image analysis and medical diagnosis, segmentation techniques are used to separate the objects of interest from the surrounding context. Once a segmentation has been computed,several statistics can easily be derived from the object. In general, manual segmentation methods are very time-consuming. Therefore, our focus is on semi-automatic and fully automatic methods.
Automatic image segmentation and annotation can customized to specific applications, like organ segmentation or computer aided diagnosis.
Algorithms require some guidance by the user, but in exchange allow the segmentation of arbitrary structures in the images. They are well suited for the segmentation of heterogenous structures, such as tumors, and for research purposes.
Bone Segmentation in MR Images
The left MR image shows the segmentation of a human femur. The heterogenous bone tissue in the MR image has been segmented using our semi-automatic segmentation method that requires only few marker points inside and outside the structure. The computation of the 3-D segmentation result takes only a few seconds on current GPU hardware. The middle image shows a volume rendering of the MR scan with the 3-D surface of the femur segmentation. The image on the right shows the surfaces of the segmented patella and tibia in addition.