Shannon Entropy in the Automatic Identification of Microbleeds Using Image Processing
Year: 2025
Type: article
Abstract: The detection of microbleeds in Magnetic Resonance Imaging (MRI) studies through the Susceptibility Weighted Image (SWI) technique is presented. The SWI technique has shown to play a relevant role in the identification of microbleeds, unlike conventional MRI techniques, the sensitivity is higher for detecting microbleeds and iron deposits. This work presents a technique for the quantitative detection of microbleeds through the implementation of Shannon entropy. It is complemented with a statistical analysis of the results and establishes a specific range that allows for the early detection of these structures in future research. Preliminary results suggest that this method represents a significant advancement in the accurate and timely detection of cerebral microbleeds, offering an alternative to traditional Magnetic Resonance approaches, suggesting that artificial intelligence is a promising path for deeper investigations in this field.
Authors: Alina Villanueva, Rafael Guzman Cabrer, Aron Hernandez-Trinidad, José Soto, Teodoro Cordova-Fraga
Institution: Universidad de Guanajuato
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4408571929