Synopsys Cloud
Cloud native EDA tools & pre-optimized hardware platforms
Request a Free Trial →
Definition
With 3D image segmentation, data acquired from 3D imaging modalities such as Computed Tomography (CT), Micro-Computed Tomography (micro-CT or X-ray) or Magnetic Resonance Imaging (MRI) scanners is labelled to isolate regions of interest. These regions represent any subject or sub-region within the scan that will later be scrutinized. This could facilitate analysis of part of the human body, or a specific feature within an industrial component or assembly.
What Problems Does 3D Image Segmentation Solve?
Although direct measurement and analysis of 3D images is possible in some scenarios, segmented images are the basis for most 3D image analysis. Extraction of the geometry of a region of interest through 3D image segmentation allows for conversion into 3D models, which permits visualization and quantification of the scanned subject. Further virtual analysis of these models, for example through computer simulation, or even obtaining a physical representation of the subject through 3D printing, all require segmentation to be completed on the 3D images.
How Does 3D Image Segmentation Work?
A key concept in image segmentation is surface determination, where the boundary between one region and another is accurately captured. Greyscale information stored in the scan is used to determine the location of these boundaries. The exact procedure is highly variable depending image type and quality, as well as the subject type and other factors. The processes can also vary from highly manual to semi-automated or even fully automated segmentation that can incorporate elements of machine learning.
Segmentation is frequently made easier by image pre-processing steps, which involve filtering the images to remove noise and scanning artefacts, or to enhance contrast.
In Synopsys Simpleware software, a suite of image processing tools is available for efficient segmentation of 3D images. Pre-processing tools and intelligent time-saving options help to efficiently obtain accurate segmentation from even very challenging scans, for example:
- Using interpolation approaches to segment large volumes with greatly reduced manually labelled regions
- Automatically adjusting surface positions to correct for noise, artefacts or other segmentation inaccuracies
More recently, Simpleware software has introduced automated segmentation capabilities with Artificial Intelligence (AI) technology using Machine Learning (ML). These segmentation solutions learn, from examples of good segmentation, how to produce similarly high quality result in new cases. This strategy has already been applied to common anatomies of interest in the orthopaedic field like the knee and hip.
For high throughput applications, Machine Learning approaches are inarguably the future of segmentation, where an automated, robust, and fast segmentation process can replace those requiring more user interaction, making more time available for high-value tasks.
Where and When Does 3D Image Segmentation Fit in the Product Portfolio?
Comprehensive and intuitive 3D image segmentation is crucial to the process of generating models from scan data. High-quality segmentation ensures that models are suitable for analysis and able to be tailored to a particular application. Accurate segmentation of the human body, for example, is crucial to identifying anatomical regions of interest for a surgery, or for understanding the location of pathologies.
Synopsys Simpleware software includes 3D image segmentation as part of a comprehensive set of options for working with scans, for example, 3D image processing and 3D image visualization. By combining different approaches to 3D image data, users can comprehensively explore structures and set up further tasks such as simulation or 3D printing.
Go Beyond 3D Image Segmentation
Carrying out 3D image segmentation is often the crucial step before exporting a model based on the segmented data. Once the segmentation is complete, as well as any other image processing work, then uses can:
- Obtain measurements and statistics from segmented regions of interest
- Generate surface meshes for 3D printing and CAD processes
- Create volume meshes for Finite Element Analysis (FEA) or Computational Fluid Dynamics (CFD)
- Calculate effective material properties from material microstructure
- Use AI-enabled segmentation and landmarking tools to automate routine manual tasks
How is 3D Image Segmentation Being Applied to Real-World Cases?
Segmentation of the skull and brain in Simpleware software
A good example of 3D image segmentation being used involves work at Stanford University on simulating brain surgery. In this project, researchers looked at how to reduce risk during decompressive craniectomies, where pressure is relieved in the skull during invasive brain surgery. Carried out between Stanford, the Stevens Institute of Technology, Oxford University, and the University of Exeter, models were built using Simpleware software, including segmentation.
1. MRI scans were obtained from an adult female brain
2. Data is imported to Simpleware ScanIP for 3D image segmentation of the brain and skull, including tissue, cerebellum, skin, and skull areas.
3. FE meshes were generated using Simpleware software to convert the complex segmented image data into a volumetric mesh including tissues, features, and color mapping is used to quantify the battery.
4. Craniectomies were simulated using SIMULIA Abaqus to study different swelling scenarios, with the goal of identifying an optimal opening size to control pressure and minimize the risk of axonal damage.
5. Future work will focus on improving the simulation of these high-risk surgeries to inform pre-surgical planning and improve patient care.