Researchers from the Universitat Politècnica de València (UPV) and the French National Centre for Scientific Research (CNRS) have developed DeepCeres, the world’s most advanced software for studying the human cerebellum using high-resolution NMR images. Published in the journal NeuroImage, this groundbreaking tool promises to enhance research and diagnosis of diseases such as ALS, schizophrenia, autism, and Alzheimer’s by providing unprecedented accuracy in analyzing the cerebellum’s complex structures.
The cerebellum, though small in size, houses about 50% of the brain’s neurons and is crucial for cognitive, emotional, and motor functions. However, studying this vital brain region has been challenging due to its intricate anatomy and the limitations of conventional magnetic resonance imaging (MRI). DeepCeres overcomes these obstacles by leveraging artificial intelligence to segment and measure 27 distinct structures within the cerebellum with remarkable precision.
Sergio Morell-Ortega, a researcher at UPV’s ITACA Institute, highlights that DeepCeres is now the most accurate tool available for studying the cerebellum. The software uses deep neural networks to transform standard 1 cubic millimeter MRI images into ultra-high-resolution images of 0.125 mm³. This advancement allows researchers and healthcare professionals to obtain detailed insights into the cerebellum’s anatomy without requiring ultra-high-resolution initial images.
José Vicente Manjón, the project’s lead researcher, compares this improvement to moving from black-and-white to color images, emphasizing that DeepCeres is unparalleled in its capabilities and is accessible to the global scientific community.
“DeepCeres overcomes all these challenges and is, today, the most accurate tool in the world for measuring such an important structure of the central nervous system as the cerebellum,” said Sergio Morell-Ortega.
José Vicente Manjón added, “Using standard resonance images of 1 cubic millimeter, 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.”
DeepCeres represents a significant leap forward in neuroscience and clinical practice, offering new possibilities for understanding and diagnosing neurological and psychiatric conditions. By enabling precise volumetric quantification of the cerebellum, the software could lead to breakthroughs in the study of diseases like cerebellar ataxia, ALS, schizophrenia, autism, and
Alzheimer’s. The researchers anticipate that DeepCeres will become an indispensable tool for the scientific community, paving the way for future discoveries in brain research.
Add comment