Validation of Neuroimaging Technology Platform

IXICO plc

26 February 2026

 

IXICO plc

("IXICO", the "Company" or the "Group")

IXICO further validates the automation capabilities of

its IXI™ neuroimaging technology platform  

26 February 2026, IXICO plc (AIM: IXI) - London, UK. IXICO, a global leader in neuroscience imaging and biomarker analytics, using its AI-driven platform to help advance drug development in neurological disorders, announced it has presented new data demonstrating that automated capabilities to measure brain volume loss on magnetic resonance imaging (MRI) within its IXI™ Platform are at a minimum matching, and in some measures exceeding, the performance of semi-manual methods which require manual analysis by (human) experts.

The accurate measurement of brain volume shrinkage (brain atrophy), caused by the loss of brain cells and the breakdown of connections between them, is fundamental to developing new treatments for a number of neurodegenerative diseases, including Huntington's Disease (HD).  Traditionally, researchers have relied on a semi-manual approach to measure brain volume loss, known as  the Boundary Shift Integral (BSI) which is currently considered to be the 'gold standard' method of analysis.

In a recent study conducted by IXICO and a large US pharmaceutical partner, the results show that automated capabilities to measure brain atrophy on MRI  within its IXI™ Platform match or exceed the performance of the semi-manual BSI method, providing an advanced, cost-effective and scalable solution to support clinical trials in HD.  Of the three approaches evaluated to measure brain atrophy, IXI™ demonstrated it was the most sensitive method for detecting whole brain and caudate (a small region deep in the brain impacted early in HD) volume loss.    

A full summary of the study and more detail on the data presented is available on IXICO's website by following this link.   The data is being presented in a scientific poster at the 21^st Annual Huntington's Disease Therapeutics Conference in California, USA this week (23-26 February 2026).   

Robin Wolz, Chief Scientific Officer of IXICO, commented: "By using a scalable, sensitive AI imaging analysis approach such as on our IXI^TM Platform, researchers can reduce the operational burden of semi-manually analysed images and increase sensitivity to detecting changes in the brain. It is my belief that this has huge potential to impact how biomarker analyses inform the next generation of drug development programs in neurodegenerative disease". 

Ends

For further information please contact:

IXICO plc	[phone]
Grant Nash, Chief Financial Officer James Chandler, Chief Business Officer
Cavendish Capital Markets Limited (Nominated Adviser and Sole Broker)	[phone]
Giles Balleny, Isaac Hooper (Corporate Finance) Nigel Birks (Healthcare Specialist Sales) Harriet Ward (Corporate Broking) Michael F Johnson (Sales)

About IXICO www.IXICO.com

IXICO is a global leader in neuroscience imaging and biomarker analytics, using its proprietary AI-driven platform to help advance the treatment of neurological disorders and reduce the uncertainties associated with drug discovery, development and monitoring.   As a key part of the global neurological disease research community, the Company has built a global reputation and 20-year track record as an end-to-end Imaging Contract Research Organisation (iCRO) working with leading pharma companies, innovative biotech's, disease consortia and non-profit organisations. IXICO has supported hundreds of neurological clinical trials, analysed hundreds of thousands scans and built an expansive network of expert imaging centres around the world.  

The IXICO Platform is tailor-made for neurological disease, reliably processing data from global trials, precisely measuring key imaging biomarkers associated with the identification, progression and treatment of diseases such as Alzheimer's, Huntington's and Parkinson's.  Image data is interrogated by the Platform and IXICO's expert scientists translating complex data into clinically meaningful while minimizing data variability and increasing reproducibility.

 

END