Fovia Utopia

I've found over the years that the PACS field is rather mobile. A friend that worked for company A might now be found at company C having arrived there after doing time at firm B. You might remember back when Merge first bought out Amicas...there were some discussions about whom to keep and whom to let go, and I was rather vocal in urging (begging?) Merge to keep the folks who made Amicas Merge PACS what it is. That didn't work out, but one of my friends from that realm is now with an amazing little company called Fovia. I sought him out at RSNA, as I usually do, and he showed me some cool stuff. Due to some personal things, I've been too lazy to write postponed my brief but exciting RSNA report from Fovia, but here it is. Finally.

Fovia is in some ways the biggest PACS company you've never heard of. Although it isn't a PACS company, and you have heard of it here on these very pages.

Fovia is a "behind the scenes" company. Think Intel. They make the chips, but you can't buy an Intel-branded computer. Fovia makes rendering software used by many PACS companies, including Merge. In case you didn't know, Fovia:

• Founded in 2003 and inventor of High Definition Volume Rendering®

• Provides a highly scalable CPU-based, server-side rendering solution delivering images to clients applications anytime and anywhere

• Optimized for the CPU and delivers near perfect linear scalability as the # of cores increases. Does not require a GPU, or the headaches associated with OpenGL drivers.

• Scales well with dataset size. There is almost no visible difference in performance or quality when rendering 500 slices or 4000 slices (maybe 10% slowdown)

• Scales well and preserves the quality and performance when rendering to large displays. This is critical for larger medical monitors such as 4K or 6+ MP displays.

• Provides a “Fovia Inside” solution that is directly integrated into OEM customers’ solutions. The benefit is that OEM customers retain their own user interface and workflows, but gain HDVR inside their products. 

• Fovia products are integrated into products and PACS from quite a few names you know, including GE, Sectra, Merge/IBM, and Intelerad.

 At RSNA, Fovia introduced us to their two latest technologies: XStream® HDVR® WebSDK and F.A.S.T.® Interactive Segmentation.

XStream HDVR WebSDK

An SDK is a Software Development Kit, and this one delivers Fovia’s High Definition Volume Rendering from the enterprise or cloud over cellular and Wi-Fi networks directly to desktop or mobile devices with no compromise in performance or quality. This yields a zero-footprint application that will run on almost any platform, be it desktop, tablet, iOS, Android, what-have-you. But this is far from just another run-of-the-mill basic viewer. With HDVR, one has access to fully interactive 2D, MPR, and even 3D workflows. The software vendor can use these building blocks to create workflows within their own products.

Click below to experience, first-hand, the incredible rendering power available from the cloud:

http://rsna.fovia.com

F.A.S.T. Interactive Segmentation

Three-Dimensional images are pretty, and often useful on their own. But the real magic comes when you can pick some particular part of the rendering to play with, which we call segmentation. F.A.S.T. Interactive Segmentation (and I'm not sure what the acronym stands for, but the darn thing is indeed fast!) F.A.S.T. Interactive Segmentation provides real-time (yup, that fast) 3D interactive segmentation on 2D and 3D views.

Now we've all seen segmentation with the various advanced visualization programs out there. But F.A.S.T. Interactive Segmentation is different: it is intuitive and easy to use. One simply clicks and drags, be it with a finger or mouse, and voila! Your favorite body part is selected and highlighted in the color of your choice. This process can work independently or can be used to augment an automatic segmentation algorithm. F.A.S.T. Interactive Segmentation is ideal for the challenging or non-perfect scans where it is critical that the case can be segmented for analysis of the disease.

With F.A.S.T. Interactive Segmentation, segmentation workflows can be completed interactively in well under a minute on a variety of studies, and not the “perfect case.” I saw the following cases demonstrated live. The screen captures don't do the process justice, but you can easily see the quality of the end result.

Low-dose lung screening using MIP or Faded MIP, can quickly identify lung nodules, segment the nodules and determine volumetric measurements (this literally takes just a few seconds). Here, the trachea and the pulmonary vasculature are segmented to determine if this lesion could be accessed via transbronchial biopsy (it could NOT)...

Here, is an example of surgical planning for a partial nephrectomy. Typically, segmentation might take between 30 and 45 minutes per case, but using F.A.S.T. Interactive Segmentation (and no pre-processing), the Fovia folks were able to do this in under 3 minutes:

• segment the aorta and the renal arteries
• segment the lesions
• segment the kidneys
• segment the renal veins

The images are impressive, but actually watching this process take place is staggering, particularly to those of us who use advanced visualization products regularly. Frankly, I was so impressed, I declared, "Why aren’t others, like TeraRecon using this???" It seems that Fovia and TeraRecon have been unable to connect. So, believing myself to be far more important in this space than I really am, I grabbed my iPhone and called our TeraRecon rep...who happened NOT to be at RSNA. But he made some calls and we all sent texts...and nothing happened. At least not yet. As usual, my influence is less than I would like it to be, and far less than some of you out there might think.

But I still hope TeraRecon will get around to talking with Fovia about F.A.S.T. Interactive Segmentation. Trust me, it would significantly improve the TR segmentation interface.

Frankly, in my humble opinion, it wouldn't be such a bad idea for Fovia to offer its own PACS or advanced visualization product. Don't tell anyone I said so...