Medical and anatomical data is large, volumetric, and unforgiving. A CT or MRI study is hundreds of megabytes of scalar data that a clinician or researcher wants rotated, sliced, re-lit, and measured at interactive rates, on hardware that ranges from a workstation to a tablet. We build the rendering engines that make that work.
Real-time anatomy and volumetric rendering
We build high-performance 3D engines for anatomy, imaging, and surgical visualization: surface models with hundreds of labeled parts, direct volume rendering of CT and MRI scalar fields, cut planes, isosurfaces, and transfer functions, held at interactive frame rates. The hard part is not drawing one pretty frame. It is holding the frame rate while a user drags through a dataset that does not fit comfortably in memory.
Transparency, X-ray, and cutaway views
Some of the most useful medical views are the ones you cannot photograph. An X-ray-style render, a cutaway that peels tissue away to expose a structure, a semi-transparent implant seen inside bone: all of them depend on getting transparency right, and transparency is where naive renderers fall apart. We build specialized transparency rendering for medical and surgical work: order-independent transparency so overlapping translucent structures composite correctly no matter the draw order, clip planes and cutaway geometry that open a body up without throwing away its context, and X-ray and additive blending that reads the way a radiologist expects.
What we have built
BioDigital Human is the 3D human-anatomy platform used across medical education and healthcare. We built the visualization engine behind its iPad app from scratch, on OpenSceneGraph and OpenGL ES 2, rendering detailed whole-body anatomy on a tablet, work that also lives on our mobile pillar.
For MiRus we built the 3D visualization for an IMU sensor-based surgical alignment system, taking live orientation data from inertial sensors and turning it into real-time guidance a surgeon can align to in the operating room.
We have also built volumetric medical viewers and worked with MRI, CT, and CAD-derived datasets for research and forensic use, including the streaming and level-of-detail techniques that keep large scans responsive.
Where it connects
Biomedical visualization shares its core problems with the rest of our work: the same geospatial streaming and level-of-detail that moves terrain moves a volume, the 3D graphics engineering underneath both, and the mobile constraints when the target is a tablet at the bedside.
Who works on it
AlphaPixel is a US-owned small business, founded in 2004, with senior developers who have shipped medical 3D on desktop and mobile for years. DLA DD2345 / ITAR registered. We take closed-source work and open source alike, and we do not sell a medical product, so our advice is not a pitch for one.
Talk to us
Tell us what you’re building and where it’s stuck. We’ll tell you straight whether it’s something we can help with, and how we’d approach it.
Or see how we run consulting and software development engagements.
