Advanced software improves cerebellar analysis for diagnosing the disease

Advanced software improves cerebellar analysis for diagnosing the disease

A team of researchers from the Universitat Politècnica de València (UPV) and the French National Center for Scientific Research (CNRS) have developed the world's most advanced software to study the human cerebellum with high-resolution NMR images. This software is called Deepceres and helps research and diagnose diseases such as ALS, schizophrenia, autism and Alzheimer's, among others. The work of the Spanish and French researchers was published in the prestigious journal Neuroimage.

Despite its small size compared to the rest of the brain, the cerebellum contains approximately 50% of all brain neurons and plays a fundamental role in cognitive, emotional and motor functions.

As Sergio Morell-Eorga, a project researcher at the ITACA Institute of the University Politècnica de València, explains, segmenting the cerebellum has so far been a major challenge due to the complexity of its anatomy and the difficulty of differentiating its structures through conventional magnetic resonance images.

“Deepceres overcomes all these challenges and is today the most accurate tool in the world to measure such an important structure of the central nervous system as the cerebellum,” emphasizes Morell.

High accuracy

The Deepceres software can measure 27 structures of the cerebellum. And it occurs to improve the precision of segmentation compared to the previously used methods, which is mainly due to the application of various artificial intelligence tools.

Using standard 1 cubic millimeter resonance images, these are converted into ultra-high resolution images of 0.125 mm3 using deep neural networks. This allows researchers and healthcare professionals to obtain detailed information about the anatomy of the cerebellum without the need for ultra-high resolution data in the initial image. It's like going from a black and white image to a color image. There is currently nothing similar and it is also open to the entire scientific community. “

Professor José Vicente Manjón, principal investigator of the project

Applications in neuroscience and clinical practice

According to the developers of Deepceres, the precision of volumetric quantification of the cerebellum helps in the study of neurological pathologies such as cerebellar ataxia, amyotrophic lateral sclerosis or psychiatric diseases such as schizophrenia and autism.

“In addition, several recently published studies have shown the incidence of the structure of the cerebellum in neurodegenerative diseases such as Alzheimer's,” adds Sergio Morell.

15,000 cerebellums in five months

To facilitate its use, the UPV and French CNRS teams have developed an online platform accessible to research and medical personnel. Since its launch five months ago, Deepceres has processed images from nearly 15,000 cerebellums. So far, it has been used by experts from many countries, with the greatest impact being in the United States and China.

Researchers from the Research Institute of Industrial Control Systems and Computing and the Department of Applied Mathematics at the University Politècnica de València, the Department of Psychobiology at the University of Valencia, the Medical Imaging Department at the University of La Fe and Polytechnic Hospital and the Fisabio mixture have also been involved in the development of the Felipe-Biomedical-Imagebiokentum is involved in the development of the Felipe development.

Sources: