XDMD provides two solutions:
- Image Analysis as Software
- Image Analysis as Service
For both solutions we develop the algorithms for analysis (details in our approach). The difference is what is being transferred to your environment: the software or the functionality.
Image Analysis
as Software
Tailored software solutions for organizations needing to integrate image analysis into their own systems
Basically, we provide the firmware for your medical device. The training algorithms enable continued development on-site. All software products have test routines, comprehensive documentation, and direct support. In addition, we can ensure compliance with applicable regulatory standards. The advantages of this approach are its direct integration and meeting the system constraints (e.g. available GPUs) which may be desirable for medical devices that should operate fully independently.
Image Analysis
as Service
Tailored software solutions delivered via our cloud-based platform for scalabe image analysis
As with our first solution, algorithms are tailored to your application, complete with test routines and comprehensive documentation. Images can be uploaded manually, or a secure connection can be established between our platform and your system for automated processing. We handle updates and ensure uptime. The advantages of this approach are that no in-house technical expertise is required to analyze your images and that computational resources can easily be scaled.
Analysis tasks
The most common tasks are registration, segmentation, and detection. Of these, segmentation is arguably the most important, because it involves interpretation, typically follows the other tasks, and enables quantifications. Segmentation is the contouring of objects or labeling of pixels in the image and is at the heart of almost all workflows and products.
Segmentation enables: quantification, visualization, characterization of anatomy, characterization of pathology, surgical planning and navigation, surgical scene understanding, treatment response monitoring, hemodynamic simulation, morpho-dynamic simulation, etcetera.
Details
These images are segmentation examples in the field of neuroradiology, the field of origin of XDMD. They show the segmentation of blood vessels in the brain in a CT scan of a stroke patient with a ventricular shunt (Scientific Reports). Based on this result, smaller vessels can be more easily inspected for the presence of occlusions, detailed measurements of the vessels in 3D can be carried out, or the blood flow can be simulated.
Details
More neuro segmentation examples of the cranial cavity, the hemispheres, the cerebral vasculature, the white and gray matter, and the cerebrospinal fluid, all from different patients. The vessel segmentation has been overlaid with a color map based on the flow arrival times to enhance the visualization of potential flow abnormalities (American Journal of Neuroradiology). The white and gray matter is an example of soft tissue segmentation in CT which normally is the domain of MR imaging. The method was the world’s first (Scientific Reports).
Details
An example of abdominal fat segmentation in CT, with the top-left image showing the delineation of the abdominal region, and the remaining images showing subcutaneous fat in brown and visceral fat in green (MICCAI). These types play different roles in the pathophysiology of various diseases.