95% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Neuroinform.
Volume 19 - 2025 | doi: 10.3389/fninf.2025.1550432
This article is part of the Research Topic Machine Learning Algorithms for Brain Imaging: New Frontiers in Neurodiagnostics and Treatment View all 9 articles
Radiomics-Driven Neuro-Fuzzy Framework for Rule Generation to Enhance Explainability in MRI-Based Brain Tumor Segmentation
Provisionally accepted
Leondry Mayeta 1,2,3,4*
Eduardo P. Cavieres 2,3,4 Matías Salinas 1,2,3 Diego Mellado 1,2,3,4 Sebastian Ponce 1,3,4,5 Francisco Torres Moyano 2,4,6,7
Steren Chabert 2,3,4 Marvin Querales 3,5
Julio Sotelo 8
Rodrigo Salas 2,3,4*- 1 PhD Program in Health Sciences and Engineering, UNIVERSIDAD DE VALPARAISO, Valparaiso, Chile
- 2 School of Biomedical Engineering, Faculty of Engineering, UNIVERSIDAD DE VALPARAISO, Valparaiso, Chile
- 3 Center of Interdisciplinary Biomedical and Engineering Research for Health (MEDING), UNIVERSIDAD DE VALPARAISO, Valparaiso, Chile
- 4 Millenium Institute for Intelligent Healthcare Engineering (iHealth), Santiago, Chile
- 5 School of Medical Technology, Faculty of Medicine, UNIVERSIDAD DE VALPARAISO, Viña del Mar, Chile
- 6 Servicio de Imagenología, Hospital Carlos van Buren, Valparaiso, Chile
- 7 Centro para la Investigación Traslacional en Neurofarmacología (CITNE), UNIVERSIDAD DE VALPARAISO, Valparaiso, Chile
- 8 Departamento de Informática, Universidad Técnica Federico Santa María, Santiago, Chile
Brain tumors (BT) are among the leading causes of mortality worldwide. Early detection and precise characterization are critical to improving patient outcomes. Magnetic Resonance Imaging (MRI), a gold standard for non-invasive brain imaging, plays a pivotal role in the analysis of BT.Deep Learning (DL) models have emerged as powerful tools for tumor applications, offering automated solutions for segmentation, classification, and characterization tasks. However, their lack of interpretability and reliance on black-box decision-making processes pose challenges for integration into clinical workflows, where trust and transparency are paramount.
Keywords: Radiomics-Driven Neuro-Fuzzy Framework for Brain Tumor Segmentation Radiomics, Neuro-fuzzy systems, Decision rules, BT segmentation, Explainable artificial intelligence, Magnetic Resonance Imaging, deep learning
Received: 23 Dec 2024; Accepted: 24 Mar 2025.
Copyright: © 2025 Mayeta, Cavieres, Salinas, Mellado, Ponce, Torres Moyano, Chabert, Querales, Sotelo and Salas. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Leondry Mayeta, PhD Program in Health Sciences and Engineering, UNIVERSIDAD DE VALPARAISO, Valparaiso, Chile
Rodrigo Salas, School of Biomedical Engineering, Faculty of Engineering, UNIVERSIDAD DE VALPARAISO, Valparaiso, Chile
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.