Lightweight deep learning for medical imaging using MobileNetV2-based brain pathology classification with Grad-CAM interpretability.
Overview
- Department of Computing, University of Derby, Derby, United Kingdom
- Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
- Department of Management Information Systems, College of Business and Economics, Qassim University, Saudi Arabia
- Faculty of Computing and Information, Al-Baha University, Al-Baha, Saudi Arabia
- Redcad Laboratory, University of Sfax, Sfax, Tunisia
Abstract
Introduction: Computed Tomography (CT) brain scans are crucial for diagnosing various neurological conditions, including tumors, cancer, and aneurysms. CT brain scans are essential for guiding treatment decisions and monitoring disease progression. In this study, we propose a novel framework for brain CT image classification that leverages convolutional neural networks (CNNs), Digital Imaging and Communications in Medicine (DICOM) pre-processing, transfer learning with multiple deep models, and ensemble prediction techniques. The primary objective is to enhance the accuracy and interpretability of brain abnormality detection.
Methods: Our approach uses a comprehensive dataset of CT brain scans that undergo meticulous pre-processing to ensure data integrity and uniformity, and employs Grad-CAM for interpretability. We employ four state-of-the-art pre-trained models: MobileNetV2, ResNet-50, EfficientNet-B0, and VGG-16, each serving as a feature extractor, followed by a classification head tailored to our specific task.
Results: The experimental results demonstrate that MobileNetV2 and the Ensemble model achieved the highest classification accuracy of 97.44% with macro-AUC scores of 0.9895 and 0.9914, respectively, followed by VGG16 with 92.31% accuracy and the highest macro-AUC of 0.9962. In contrast, ResNet50 and EfficientNetB0 achieved accuracies of 61.54% and 33.33%, respectively, indicating fundamental limitations in learning discriminative features for this medical imaging task. MobileNetV2 proved to be the most efficient model, achieving superior accuracy with training and test times of 89 s and 38.16 s, respectively.
Discussion: MobileNetV2 is highly suitable for clinical deployment where both accuracy and computational efficiency are critical.
Reproduced under the paper's license (CC BY), from the paper cited above.
Code
The paper links to its data and to no code of its authors: see the Data section.
Tracing map
A tracing map links a paper to the code its authors published: this paper has none, so it has no map.
Data
Datasets cited
- kaggle.com/
datasets/ , at Kaggle; found in the end of the papertrainingdatapro
Data availability statement
The original contributions presented in the study are included in the article/
Reproduced under the paper's license (CC BY), from the paper cited above.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 1, 28 September 2026: the first record
Recorded: type, language, journal, volume, pages, dates, 5 authors, 5 keywords, 41 references.
Cite
This paper
Sattar, M. U., Alamro, M. A., Mihoub, A., Aljarboa, S., & Krichen, M. (2026). Lightweight deep learning for medical imaging using MobileNetV2-based brain pathology classification with Grad-CAM interpretability. Frontiers in medicine, 13, 1810860. https://
BibTeX
@article{sattar2026light
author = {Sattar, Mian Usman and Alamro, Meznah A. and Mihoub, Alaeddine and Aljarboa, Soliman and Krichen, Moez},
title = {{Lightweight deep learning for medical imaging using MobileNetV2-based brain pathology classification with Grad-CAM interpretability}},
journal = {Frontiers in medicine},
year = {2026},
month = may,
volume = {13},
pages = {1810860},
publisher = {Frontiers Media SA},
issn = {2296-858X},
doi = {10.3389/
url = {https://
pmid = {42338932},
pmcid = {PMC13284855}
}
RIS
TY - JOUR
AU - Sattar, Mian Usman
AU - Alamro, Meznah A.
AU - Mihoub, Alaeddine
AU - Aljarboa, Soliman
AU - Krichen, Moez
TI - Lightweight deep learning for medical imaging using MobileNetV2-based brain pathology classification with Grad-CAM interpretability
T2 - Frontiers in medicine
J2 - Front Med (Lausanne)
PY - 2026
DA - 2026/
VL - 13
SP - 1810860
SN - 2296-858X
PB - Frontiers Media SA
DO - 10.3389/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.3389/
"type": "article-journal",
"title": "Lightweight deep learning for medical imaging using MobileNetV2-based brain pathology classification with Grad-CAM interpretability",
"container-title": "Frontiers in medicine",
"author": [
{
"family": "Sattar",
"given": "Mian Usman"
},
{
"family": "Alamro",
"given": "Meznah A."
},
{
"family": "Mihoub",
"given": "Alaeddine"
},
{
"family": "Aljarboa",
"given": "Soliman"
},
{
"family": "Krichen",
"given": "Moez"
}
],
"container-title-short":
"volume": "13",
"page": "1810860",
"DOI": "10.3389/
"PMID": "42338932",
"PMCID": "PMC13284855",
"ISSN": "2296-858X",
"publisher": "Frontiers Media SA",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
29
]
]
}
}
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1038/s41598-026-50158-1 [code]
- NeXtSwin-X: dual-branch cross-attention fusion of ConvNeXt and swin transformer for accurate brain tumor classification from MRI and CT.Journal: Scientific reportsIn common: kaggle.com/datasets/trainingdatapro, other
- [2] doi:10.3390/cancers17010121
- Advanced Brain Tumor Classification in MR Images Using Transfer Learning and Pre-Trained Deep CNN Models.Journal: CancersIn common: 3 references
- [3] doi:10.3390/diagnostics15151863
- Role of Feature Diversity in the Performance of Hybrid Models-An Investigation of Brain Tumor Classification from Brain MRI Scans.Journal: Diagnostics (Basel, Switzerland)In common: 3 references
- [4] doi:10.1038/s41598-025-29768-8
- Interpretable multi-model deep learning framework for automated four-class diagnosis of ocular toxoplasmosis using fundus imaging.Journal: Scientific reportsIn common: other, 2 references
- [5] doi:10.1371/journal.pone.0350637 [code]
- Deep learning-based arterial waveform analysis for predicting postoperative cerebrovascular events in pediatric patients with Moyamoya disease.Journal: PloS oneIn common: 3 references
- [6] doi:10.1155/2022/9541115
- Jellyfish Search-Optimized Deep Learning for Compressive Strength Prediction in Images of Ready-Mixed Concrete.Journal: Computational intelligence and neuroscienceIn common: 3 references
- [7] doi:10.3390/bioengineering13020157 [code]
- A Robust ConvNeXt-Based Framework for Efficient, Generalizable, and Explainable Brain Tumor Classification on MRI.Journal: Bioengineering (Basel, Switzerland)In common: 2 references
- [8] doi:10.3390/life15030327
- Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks.Journal: Life (Basel, Switzerland)In common: 2 references
- [9] doi:10.3390/bioengineering11030266
- Brain Tumor Detection and Categorization with Segmentation of Improved Unsupervised Clustering Approach and Machine Learning Classifier.Journal: Bioengineering (Basel, Switzerland)In common: 2 references
- [10] doi:10.1371/journal.pone.0292768
- PRCnet: An efficient model for automatic detection of brain tumor in MRI images.Journal: PloS oneIn common: 2 references
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
