A method for brain tumor detection and localization by means of deep learning and reliable prediction explainability
- 1Department for High Performance Computing and Networking (ICAR), National Research Council of Italy (CNR), Rende, Italy.
- 2Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, Campobasso, Italy.
- 3Department of Engineering, University of Sannio, Benevento, Italy.
Abstract
Brain tumors, which are abnormal growths in the brain or central spinal canal, represent a serious global health threat. In 2023, they were responsible for 94,390 cases and 18,990 deaths in the US. Early detection with Magnetic Resonance Imaging is critical for effective treatment and higher survival rates. In this paper, we propose a method for the classification and localization of brain tumors in magnetic resonance imaging. Our method is based on the application of convolutional neural networks and for this task, we introduce and design a new network called the CBP_Net. The experimental analysis includes the Standard_CNN, a network designed by the authors, and other state-of-the-art networks, i.e., MobileNet, DenseNet, InceptionV3, ResNet50 and EfficientNetB0. This study emphasizes both quantitative and qualitative evaluations. The results demonstrate that the networks achieve optimal quantitative metrics: from 0.993 to 1.0 in accuracy. Qualitatively, we focus on visual explanations using Class Activation Mapping algorithms, specifically Grad-CAM and Score-CAM, to generate heatmaps highlighting relevant regions in the images. The Structural Similarity Index Measure is then employed to quantitatively measure the similarity between the heatmaps generated by the two CAM algorithms. This approach improves the reliability and trustworthiness of AI-driven brain tumor detection, helping clinicians diagnose.
Related
- An optimized machine learning approach for reliable agronomic parameter prediction in precision farming systems
- A real-time deep learning method for detection and localization of non-emerged cabbage seedlings
- Representation-aware conformal prediction for reliable uncertainty quantification in drug-target affinity
- Key parameters for reliable biosensing using organic photoelectrochemical transistors: a case study on bilirubin detection
- Physical determinants of reliable RNA–ligand binding prediction revealed by P-RISE
BibTeX
@article{giammarco2026method,
title = {{A method for brain tumor detection and localization by means of deep learning and reliable prediction explainability}},
author = {Marcello Di Giammarco and Antonella Santone and Mario Cesarelli and Fabio Martinelli and Francesco Mercaldo},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0361135},
url = {https://doi.org/10.1371/journal.pone.0361135},
note = {CC BY},
}
RIS
TY - JOUR
TI - A method for brain tumor detection and localization by means of deep learning and reliable prediction explainability
AU - Marcello Di Giammarco
AU - Antonella Santone
AU - Mario Cesarelli
AU - Fabio Martinelli
AU - Francesco Mercaldo
PY - 2026
DA - 2026/10/29
JO - PLOS One
DO - 10.1371/journal.pone.0361135
UR - https://doi.org/10.1371/journal.pone.0361135
AB - Brain tumors, which are abnormal growths in the brain or central spinal canal, represent a serious global health threat. In 2023, they were responsible for 94,390 cases and 18,990 deaths in the US. Early detection with Magnetic Resonance Imaging is critical for effective treatment and higher survival rates. In this paper, we propose a method for the classification and localization of brain tumors in magnetic resonance imaging. Our method is based on the application of convolutional neural networks and for this task, we introduce and design a new network called the CBP_Net. The experimental analysis includes the Standard_CNN, a network designed by the authors, and other state-of-the-art networks, i.e., MobileNet, DenseNet, InceptionV3, ResNet50 and EfficientNetB0. This study emphasizes both quantitative and qualitative evaluations. The results demonstrate that the networks achieve optimal quantitative metrics: from 0.993 to 1.0 in accuracy. Qualitatively, we focus on visual explanations using Class Activation Mapping algorithms, specifically Grad-CAM and Score-CAM, to generate heatmaps highlighting relevant regions in the images. The Structural Similarity Index Measure is then employed to quantitatively measure the similarity between the heatmaps generated by the two CAM algorithms. This approach improves the reliability and trustworthiness of AI-driven brain tumor detection, helping clinicians diagnose.
SN - 1932-6203
ER -