Volume Graphics CT-analysis software now branded under Hexagon following merger
April 8, 2025
Volume Graphics GmbH, Heidelberg, Germany, has announced the release of version 2025.1 of its suite of CT analysis software, including a new VGTRAINER application. The application is intended to enable manufacturers to utilise the latest developments in automation and deep learning to design, develop and inspect high-quality products faster without requiring expertise in AI.
In parallel with the 2025.1 release, Volume Graphics will now complete its merger with Hexagon, a change five years in the making. Operating under Hexagon’s VG software, the logo and product icons will be refreshed, though the product names – VGSTUDIO MAX, VGSTUDIO, VGMETROLOGY, VGinLINE, and myVGL – will remain. All VG software works to provide clear, reliable insights across all data sources, from CT scans to optical and tactile measurements.
FutureVG software releases intend to increasingly integrate data processing capabilities for other NDT-source data to support customers across Hexagon’s Manufacturing Intelligence division, offering broader end-to-end digital solutions for quality inspection and advanced product development to support the future of non-destructive evaluation (NDE).
“This complete integration of VG software into Hexagon’s metrology software portfolio gives engineers and inspection personnel the ability to use computed tomography (CT) to see deeply and non-destructively into their materials – and then benefit from additional product-development tools that support further quality insights and assessment,” says Dr Daniela Handl, General Manager, VG, Hexagon Manufacturing Intelligence.
“The inclusion of Volume Graphics’ legacy capabilities into the Hexagon eco-system delivers a complete suite of product-development capabilities,” continued Handl. “These span design, simulation, testing, material selection, manufacturing-design planning, production, and inspection, through the complete value chain to end-of-life assessments of final product performance.”
VGSTUDIO MAX 2025.1
Hexagon’s VGSTUDIO MAX 2025.1 is called its first step towards training a model. To accurately label and prepare the training data sets, this application can be used to set up ideal segmentation scenarios, labelling only the most important inclusions or regions of interest.
VGTRAINER also offers AI-assisted segmentation models whereby – using a number (exact amount depending on application/data set complexity) of pre-segmented and labelled training data sets – the software produces a machine-learning model that can be imported into VGSTUDIO MAX for subsequent use in accurately segmenting complex or noisy data sets quickly and accurately. This is said to be ideal for cases in which there are hundreds of parts to inspect, or in- and at-line quality assurance scenarios
The software also features non-expert model training. Using this capability, once a set of labelled data has been prepared by experts, other customer-based engineers can import the training data into VGTRAINE R and generate a model automatically, without in-depth AI or machine learning experience, thus increasing accuracy over time and continuously improving quality inspection models
In addition to these is a reported increase in the speed of R&D and in-line inspection. Hexagon illustrated this through the experience of the independent manufacturing laboratory ELEMCA, Ramonville-Saint-Agne, France.
ELEMCA fed eight ideally segmented datasets of four materials (carbon, aluminium, glue and porosity) into Hexagon’s VGTRAINER to ‘learn’ the skills needed to generate a segmentation model. The manual segmentation – particularly of carbon vs glue – is time-consuming as the grey values of both components are very similar.
With ten datasets, VGTRAINER was able to create a machine-learning model that accurately segments these materials into two separate ROIs, allowing for the subsequent standard porosity detection within VGSTUDIO MAX. This full workflow (VGTRAINER model creation—AI-segmentation in VGSM + standard porosity detection) enabled ELEMCA to reduce the time needed from one hour to ten minutes.
“We anticipate that the time savings of more than 80% that AI is delivering will help us improve customer satisfaction across a broader range of industries as we leverage our evolving capabilities,” says Julien Uzanu, NDT Expert, ELEMCA.
In addition to VGTRAINER, version 2025.1 provides users with other enhanced features such as automatic beam hardening, object-specific views, and 3D reporting.
Hexagon customer Dr Peter Mikitisin, founder and owner of accredited materials testing laboratory iWP, added, “Hexagon’s VGTRAINER offers enhanced AI and machine learning capabilities that enable users to custom-train inspection models of proprietary parts, leading to much faster final inspection processes. There is an up-front time investment in labelling quality data sets and training models to spot failure modes, but that automation step radically saves manufacturers time on the production line.
“The AI approach quickly and automatically finds designated Regions of Interest (ROIs), segments them correctly, and visualises results. If normal manual inspection analysis takes one or two minutes, for example, a VG analysis of ROIs will take just three or four seconds. That is a major advancement for concurrently producing and inspecting parts on the production line in real-time.”
