Discover IXIQ.Ai | IXICO’s AI-Based Brain Segmentation Platform

What is IXIQ.Ai? Ask our scientific director Robin Wolz

This month, we are launching its first clinical trials into production. IXIQ.Ai is the next generation of our technology platform that we have been developing for over a decade.

With new deep learning AI tools and the growing number of curated datasets at our disposal, we can now automate the precise measurement of some of the most complex brain structures that play a key role in understanding neurodegenerative diseases such as Alzheimer’s disease and Huntington’s disease.

Our Scientific Director, Dr. Robin Wolz, has led the development of IXIQ.Ai with our scientific team for the past two years. We spoke to him about the evolution of the new platform, the process his team went through, and the exciting potential for clinical and healthcare applications now and in the future.

Robin, what is IXIQ.Ai?

First of all, many people don’t realize that IXICO means Extracting information from Imaging. And the “Q” in IXIQ.Ai means Quantitative.

In summary, IXIQ.Ai is an AI-based platform for brain segmentation. It provides our development engineers with an agile infrastructure that allows us to efficiently and quickly deploy imagery analysis solutions.

IXIQ.Ai can be trained on a specific problem by feeding the platform with training data for a specific brain region in a specific therapeutic indication. We call the resulting algorithm a “plugin” that can be deployed on our data management system, TrialTracker, to perform analysis of clinical trial data.

Taking Alzheimer’s disease (AD) and Huntington’s disease (HD) as examples, there are different brain regions relevant in both indications, and we need to train the platform on the specific population data. Taking young, healthy subjects would not work as well because it would not be able to learn the patterns of neurodegeneration seen in different patient populations.

Currently, the platform is pre-trained on our extensive database of clinical trials and natural history datasets in multiple CNS indications. Thanks to the pre-trained models of the IXIQ.Ai platform framework, plugins can be trained with a reduced number of highly organized datasets to obtain an optimized solution for a specific segmentation problem.

The validation we have performed over the past few years in developing plugins for HD and AD has demonstrated that IXIQ.Ai offers lower QC failure rates and reduced volume error compared to manual raters compared to tools widely used. This means that more data can be analyzed in a clinical trial with increased precision.

How long has IXIQ.Ai been in development?

We have been working on this specific project for about two years with a team of dedicated engineers – although it draws on the expertise, know-how and data we have collected at IXICO over more than a decade.

What was the development process for IXIQ.Ai like?

Because we are so tightly integrated into the central nervous system (CNS) clinical research ecosystem, we are all too aware of the shortcomings of more traditional analytical techniques, especially when it comes to segmenting more complex brain structures.

Particularly in HD, the striated regions of the brain are very difficult to segment because there is very little contrast between these regions and the surrounding brain tissue. Even for a manual appraiser, it’s not straightforward, and that’s where traditional techniques fail.

Our development process for IXIQ.Ai involved three key steps:

  1. Development of the hardware and software infrastructure to perform image segmentation based on convolutional neural networks (CNN) At scale. In this phase, our technology team set up the server infrastructure, specifically the graphics processing units (GPUs) which are the computer processors used to solve the neural networks. We then built the software infrastructure (the neural network architecture) which forms the core of the IXIQ.Ai platform and which can take data to form specific plugins.
  2. Curation of datasets in our main indications to train the platform on specific instances. Over the past 5-10 years, we have built a database of clinical trials and natural history datasets for the major indications in which we work. Leveraging this data to train IXIQ.Ai plug-ins requires data curation and annotation. As part of the development process, we have now completed this for our AD and HD datasets.
  3. Validation of instances developed with our academic and pharmaceutical partners. After development of the AD and HD plugins was completed, significant effort was put into validating the new technology with our academic and pharmaceutical partners to show how IXIQ.Ai increases performance over currently available tools. We have jointly presented these results at numerous conferences with our collaborators.

We look forward to presenting further discoveries with our academic and pharmaceutical partners at CHDI 17.and Annual Conference on HD Therapeuticsin Palm Springs, California, as well as the 15and ADPD Conferencein Barcelona, ​​Spain.

How is IXIQ.Ai an evolution of LEAP?

IXIQ.Ai allows us to measure things we couldn’t measure before. It sets a new standard compared to LEAP and other widely used platforms such as FreeSurfer. We set new standards with LEAP 10 years ago, and now we’re raising that standard again.

The main advantages of IXIQ.Ai over traditional machine learning techniques are:

  1. CNN-based approaches provide an increased ability to “learn” more subtle or difficult data patterns. Concretely, this makes the platform applicable to brain structures that are more difficult to measure, such as the putamen in HD.
  2. A significant reduction in computation time to analyze a scan (seconds vs hours). Traditional tools like FreeSurfer and LEAP work for several hours to segment the brain. IXIQ.Ai takes seconds to minutes to perform the same task, which is an amazing difference. This dramatically shortens our development cycles, as the reduction in time to analyze hundreds of datasets is huge, while allowing for more efficient deployment in production. This opens up a wealth of potential opportunities for clinical applications where real-time processing is a requirement.

How is IXIQ.Ai different from what already exists?

The concept of a neural network-based approach is not new or exclusive to IXIQ.Ai. Beyond optimizing such a 3D brain segmentation approach, a key value lies in combining this approach with the data we have collected that is essential to train the platform.

You may have heard people say, “Data is the new oil” or “Data is the new source code” and that’s absolutely true. When you have the data, you can develop a proprietary algorithm that becomes your “secret sauce.”

Our team has spent the past decade collecting and curating a large number of unique datasets from clinical trials and natural history studies that we are entitled to use in our R&D efforts. . It is this highly curated and contextualized data that allows us to unlock the full potential of the underlying AI architecture.

What are the clinical applications of IXIQ.Ai in your key therapeutic areas?

IXIQ.Ai provides volumetric segmentation in different brain regions affected in different therapeutic indications, such as the hippocampus and ventricles in AD and the putamen and caudate in HD.

The fact that we can measure volumes in these brain regions allows us to determine patient eligibility criteria for clinical trials. For example, in studies where the drug is delivered directly to the brain, we need to understand the size of the brain structure prior to drug delivery.

The platform can also map changes in brain volumes over time, allowing us to more accurately measure the long-term effectiveness of treatments. For example, with AD, the hippocampus – which is responsible for short-term memory – shrinks, so an effective drug would be expected to slow this progression and lead to less shrinkage. Such changes can be tracked with IXIQ.Ai.

What is the key impact you hope for IXIQ.Aiwill do in clinical research, and for patients?

With IXIQ.Ai, we are more likely to identify a treatment effect in a clinical trial. As we can analyze more data, we gain statistical power and more precise measurement. The platform is sensitive to small changes and we can examine regions of the brain that we couldn’t before because we couldn’t accurately measure them in an automated way. We also expect this to give us additional biomarkers to analyze.

We hope that improved imaging measurement will help speed up the drug development process and therefore play an important role in bringing new effective treatments to patients with neurodegenerative diseases more quickly.

Would you like more information about IXIQ.Ai?

To request further information or to arrange a demo, please contact Chris Hamilton (SVP Commercial) at [email protected]

Dated: 02/18/2022Category:

Previous

Egypt's GUPCO signs $41m deal to launch offshore oil rig

Next

Genki Forest fintech platform pockets $140m in Russia – SupChina

Check Also