OSCR

Hyperparameter Optimization of Convolutional Neural Networks for Robust Tumor Image Classification.

Overview

Authors: Syed Muddusir Hussain1, Jawwad Sami Ur Rahman1, Faraz Akram1, Muhammad Adeel Asghar2, Raja Majid Mehmood3,4
  1. Biomedical Engineering Department, Riphah International University, I-14 Campus, Islamabad 45210, Pakistan; (S.M.H.); (J.S.U.R.); (F.A.)
  2. Electrical and Computer Engineering Department, Riphah International University, I-14 Campus, Islamabad 45210, Pakistan
  3. Centre for Advanced Analytics, COE for Artificial Intelligence, Multimedia University, Persiaran Multimedia, Cyberjaya 63100, Selangor, Malaysia
  4. Faculty of Computing and Informatics, Multimedia University, Persiaran Multimedia, Cyberjaya 63100, Selangor, Malaysia
Institutions: Riphah International University (Pakistan); Multimedia University (Malaysia)
Journal: Diagnostics (Basel, Switzerland), volume 16, issue 8, article 1215
Dates: received 14 March 2026; accepted 15 April 2026; published online 18 April 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/diagnostics16081215 · PMID 42072840 · PMCID PMC13114896 · OpenAlex W7155003576
Open access: gold, a free copy (OpenAlex)
Categories: structural MRI / diffusion (modality), other condition (population)
Methods: Machine learning, Statistics
Keywords: brain tumor, convolutional neural network, hyperparameter, MRI images, precise tumor detection, tumor detection
Topic: Brain Tumor Detection and Classification (Computer Vision and Pattern Recognition, Computer Science), according to OpenAlex
Citations: not cited yet (Europe PMC); 39 references in the paper

Abstract

Background/Objectives: The human brain is responsible for controlling various physiological functions, and hence, the presence of tumors in the brain is a major concern in the medical field. The correct identification and categorization of tumors in the brain using Magnetic Resonance Imaging (MRI) is a major requirement for the diagnosis and treatment of a tumor. The proposed research will focus on designing a CNN model that is optimized for tumor image classification. Methods: This research proposes an optimized CNN model featuring strategically placed dropout layers and hyperparameter optimization. This study uses a dataset of 640 MRI scans (320 tumor and 320 non-tumor) collected from a private hospital in Saudi Arabia. The proposed method utilizes a learning rate of 0.001 in combination with the Adam optimizer to ensure stable and efficient convergence. Its performance was benchmarked against established architectures, including VGG-19, Inception V3, ResNet-10, and ResNet-50, with evaluation based on classification accuracy and computational cost. Results: The experimental results show that the optimized CNN proposed in this work performs much better than the deeper architectures. The network reached a maximum training accuracy of 97.77% and a final test accuracy of 95.35% with a small test loss of 0.2223. The test accuracy of the optimized VGG-19 and Inception V3 networks was much lower, with a training time per epoch that was several orders of magnitude higher. The validation stability of the proposed network was high (92.25% to 95.35%) during the final stages of training. Conclusions: The conclusion drawn from this study is that hyperparameter optimization and strategic regularization are more advantageous for tumor classification using MRI images than the mere depth of the model. The accuracy of 95.35% with low computational complexity makes this lightweight CNN model a feasible solution for real-time applications.

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

Data Availability Statement

The dataset analyzed in this study was obtained from a private hospital in Saudi Arabia. In accordance with patient privacy regulations and ethical guidelines, the dataset is not publicly available. Even though the given study is constrained by a single-source dataset, future research will be dedicated to testing the suggested model with the help of publicly available and multi-institutional datasets, i.e., the Brain Tumor Segmentation (BraTS) dataset and other benchmark repositories. This validation will also test the generalizability and strength of the proposed methodology in a variety of clinical imaging conditions. Those researchers who are interested in accessing such datasets are advised to use publicly available repositories of MRI images or even partner with clinical institutions with the necessary ethical approvals.

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, 29 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 6 keywords, 1 funder, 31 references.

Cite

This paper

Hussain, S. M., Rahman, J. S. U., Akram, F., Asghar, M. A., & Majid Mehmood, R. (2026). Hyperparameter Optimization of Convolutional Neural Networks for Robust Tumor Image Classification. Diagnostics (Basel, Switzerland), 16(8), 1215. https://doi.org/10.3390/diagnostics16081215

BibTeX

@article{hussain2026hyperparameter,
author = {Hussain, Syed Muddusir and Rahman, Jawwad Sami Ur and Akram, Faraz and Asghar, Muhammad Adeel and Majid Mehmood, Raja},
title = {{Hyperparameter Optimization of Convolutional Neural Networks for Robust Tumor Image Classification}},
journal = {Diagnostics (Basel, Switzerland)},
year = {2026},
month = apr,
volume = {16},
number = {8},
pages = {1215},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2075-4418},
doi = {10.3390/diagnostics16081215},
url = {https://doi.org/10.3390/diagnostics16081215},
pmid = {42072840},
pmcid = {PMC13114896}
}

RIS

TY - JOUR
AU - Hussain, Syed Muddusir
AU - Rahman, Jawwad Sami Ur
AU - Akram, Faraz
AU - Asghar, Muhammad Adeel
AU - Majid Mehmood, Raja
TI - Hyperparameter Optimization of Convolutional Neural Networks for Robust Tumor Image Classification
T2 - Diagnostics (Basel, Switzerland)
J2 - Diagnostics (Basel)
PY - 2026
DA - 2026/04/18
VL - 16
IS - 8
SP - 1215
SN - 2075-4418
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/diagnostics16081215
UR - https://doi.org/10.3390/diagnostics16081215
LA - en
ER -

CSL-JSON

{
"id": "10.3390/diagnostics16081215",
"type": "article-journal",
"title": "Hyperparameter Optimization of Convolutional Neural Networks for Robust Tumor Image Classification",
"container-title": "Diagnostics (Basel, Switzerland)",
"author": [
{
"family": "Hussain",
"given": "Syed Muddusir"
},
{
"family": "Rahman",
"given": "Jawwad Sami Ur"
},
{
"family": "Akram",
"given": "Faraz"
},
{
"family": "Asghar",
"given": "Muhammad Adeel"
},
{
"family": "Majid Mehmood",
"given": "Raja"
}
],
"container-title-short": "Diagnostics (Basel)",
"volume": "16",
"issue": "8",
"page": "1215",
"DOI": "10.3390/diagnostics16081215",
"PMID": "42072840",
"PMCID": "PMC13114896",
"ISSN": "2075-4418",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/diagnostics16081215",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
18
]
]
}
}

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:10.3390/tomography12040044 [code]
HAAU-Net: Hybrid Adaptive Attention U-Net Integrated with Context-Aware Morphologically Stable Features for Real-Time MRI Brain Tumor Detection and Segmentation.
Journal: Tomography (Ann Arbor, Mich.)
In common: structural MRI / diffusion, other condition, author Muhammad Adeel Asghar
[2] doi:10.1186/s13059-025-03847-5 [code]
Cell type-specific inference from bulk RNA-sequencing data by integrating single-cell reference profiles via EPIC-unmix.
Journal: Genome biology
In common: DOI 10.7303/syn2580853, 1 reference
[3] doi:10.1186/s13195-025-01865-w
Protein fingerprints of brain-derived extracellular vesicles predict types of tau pathology.
Journal: Alzheimer's research & therapy
In common: DOI 10.7303/syn2580853, 1 reference
[4] doi:10.1038/s41597-023-02507-2 [code]
Multi-omic atlas of the parahippocampal gyrus in Alzheimer's disease.
Journal: Scientific data
In common: DOI 10.7303/syn2580853, 1 reference
[5] doi:10.1038/s41598-025-99576-7 [code]
Brain tumor detection empowered with ensemble deep learning approaches from MRI scan images.
Journal: Scientific reports
In common: structural MRI / diffusion, other condition, 3 references
[6] doi:10.3390/cancers15164172
Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging.
Journal: Cancers
In common: structural MRI / diffusion, other condition, 3 references
[7] doi:10.1186/s40708-025-00279-6
Boosting brain tumor detection with an optimized ResNet and explainability via Grad-CAM and LIME.
Journal: Brain informatics
In common: other condition, 3 references
[8] doi:10.1002/alz.70060
Metabolic stress and age drive inflammation and cognitive decline in mice and humans.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: DOI 10.7303/syn2580853, other condition
[9] doi:10.1093/braincomms/fcag326 [code]
Brain multiomic profiling identifies tau-related transcriptomic dysregulation in Alzheimer's disease.
Journal: Brain communications
In common: DOI 10.7303/syn2580853
[10] doi:10.1038/s41467-026-70243-3 [code]
TYK2 mediates neuroinflammation in Alzheimer's disease brains with TDP-43 pathology.
Journal: Nature communications
In common: DOI 10.7303/syn2580853

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.

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.