Resolution Of Brain Magnetic Resonance Imaging Further Improved By Artificial Intelligence (AI)
Source: Thailand Medical News Jan 19, 2020 4 years, 11 months, 4 days, 9 hours, 20 minutes ago
AI and medical researchers of the ICAI Group–Computational Intelligence and Image Analysis–of the University of Malaga (UMA) have designed an unprecedented method that is capable of improving
brain images obtained through
magnetic resonance imaging (
MRI) using
artificial intelligence.
This novel model manages to increase image quality from low resolution to high resolution without distorting the patients'
brain structures, using a deep learning artificial neural network , a model that is based on the functioning of the human brain–that "learns" this process.
Credit: University Of Malaga
Researcher Karl Thurnhofer, main author of this study explained to
Thailand Medical News, "Deep learning is based on very large neural networks, and so is its capacity to learn, reaching the complexity and abstraction of a
brain."
He adds that, thanks to this technique, the activity of identification can be performed alone, without supervision; an identification effort that the human eye would not be capable of doing.
The new study published in the scientific journal "Neurocomputing," represents a scientific breakthrough, since the algorithm developed by the UMA yields more accurate results in less time, with clear benefits for patients. "So far, the acquisition of quality
brain images has depended on the time the patient remained immobilized in the scanner; with our method,
image processing is carried out later on the computer," explains Thurnhofer.
The results will enable specialists to identify
brain-related pathologies, like physical injuries, cancer or language disorders, among others, with increased accuracy and definition, because image details are thinner, thus avoiding the performance of additional tests when diagnoses are uncertain, according to the experts.
Currently, the ICAI Group of the UMA, led by Professor Ezequiel López, co-author of this study, is a benchmark for neurocomputing, computational learning and
artificial intelligence. The Professors of the Department of Computer Science and Programming Languages Enrique Domínguez and Rafael Luque, as well as researcher Núria Roé-Vellvé, have also participated in this study.
Reference : Karl Thurnhofer-Hemsi et al. Deep learning-based super-resolution of 3D magnetic resonance images by regularly spaced shifting, Neurocomputing (2019). DOI: 10.1016/j.neucom.2019.05.107