Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Benchmarking Deep Convolutional Neural Networks for Brain Tumor Detection Using Magnetic Resonance Imaging Data

CommIT (Communication and Information Technology) Journal · Vol. 20 No. 2 (2026) · hlm. 415–432

DOI
10.21512/commit.v20i2.14392
ISSN
2460-7010, 1979-2484
Terbit
2026-09-08
Penerbit
Bina Nusantara University
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Brain tumors are associated with high mortality and severe neurological effects, making accurate and timely diagnosis essential. However, manual interpretation of Magnetic Resonance Imaging (MRI) remains subjective and time-consuming. Deep learning, particularly Convolutional Neural Networks (CNNs), offers a promising approach to improving diagnostic accuracy and efficiency. This research systematically benchmarks five CNN architectures (VGG19, DenseNet201, ResNet50, Inception-v3, and MobileNet) on balanced and naturally imbalanced MRI datasets. Its novelty lies in evaluating all models under a unified preprocessing and transferlearning framework across both dataset distributions, with Grad-CAM used to support interpretability. Preprocessing includes resizing, adaptive masking, Gaussian blur, Contrast Limited Adaptive Histogram Equalization (CLAHE), normalization, and augmentation, followed by transfer learning using ImageNet-pretrained models. Performance is evaluated using accuracy, precision, recall, specificity, F1-score, and Area Under the Curve (AUC). Results show that VGG19 achieves the highest accuracy (0.937 for balanced and 0.962 for imbalanced data), recall (0.991 and 0.984, respectively), and F1-score, demonstrating strong sensitivity and generalization. DenseNet201 achieves the highest AUC (0.992 and 0.996) and high specificity, indicating strong overall discriminative performance. These findings suggest that VGG19 is particularly suitable for sensitivity-oriented early screening, whereas DenseNet201 is advantageous when overall discrimination and specificity are prioritized. In conclusion, CNN-based models show substantial potential for brain tumor classification, with architecture selection depending on specific clinical priorities.

Kata kunci

Jaringan kolaborasi para penulis

40 penulis · 152 tautan kepenulisan bersama · 97 lintas organisasi · menampilkan 40 yang paling banyak terhubung

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Institut Teknologi Sepuluh Nopember
  • Rajamangala University of Technology
  • University of Indonesia
  • Universiti of Malaysia Sabah
  • Indonesian Institute of Sciences
  • Bandung Institute of Technology
  • Institut Teknologi Dan Bisnis STIKOM Bali
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Padma Nyoman CrisnapatiRajamangala University of Technology6
Myo Min AungRajamangala University of Technology6
Yuri PamungkasInstitut Teknologi Sepuluh Nopember4
Abdul KarimHallym University3
Evi TriandiniInstitut Teknologi Dan Bisnis STIKOM Bali3
Wawan YunantoNational Taiwan University of Science and Technology3
Nipat JongsawatRajamangala University of Technology2
Anucha TungkasthanRajamangala University of Technology2
Stralen PratasikInstitut Teknologi Sepuluh Nopember2
Rahmah Yasinta RangkutiInstitut Teknologi Sepuluh Nopember2
Dechrit ManeethamRajamangala University of Technology1
Muhammad Imam SuryaIndonesian Institute of Sciences1
Siti Fauziyah RahmanUniversity of Indonesia1
Irfan MartiansyahIndonesian Institute of Sciences1
Wiguna RahmanNational Research and Innovation Agency1
Yudan WhulanzaUniversity of Indonesia1
Adella JosephinUniversity of Indonesia1
Kenny LischerUniversity of Indonesia1
Irzaman IrzamanIPB University1
Z. JamalAfiliasi tidak diketahui1
Agus SubagioDiponegoro University1
Pepen ArifinBandung Institute of Technology1
Fitri Suryani ArsyadSriwijaya University1
Budi MulyantiIndonesia University of Education1
M. BarmawiBandung Institute of Technology1
Ratri Dwi IndrianiAfiliasi tidak diketahui1
Yuri PamungkasAfiliasi tidak diketahui1
Made KrisnandaUniversity of Newcastle Australia1
Diah Puspito WulandariInstitut Teknologi Sepuluh Nopember1
Adhi Dharma WibawaInstitut Teknologi Sepuluh Nopember1
Natan DerekNorwegian University of Science and Technology1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.binus.ac.id/index.php/commit/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Benchmarking Deep Convolutional Neural Networks for Brain Tumor Detection Using Magnetic Resonance Imaging Data</dc:title>
	<dc:creator>Firdaus, Tegar Anugrah</dc:creator>
	<dc:creator>Rais, Bryan</dc:creator>
	<dc:creator>Salim, Marcelinus Jonathan</dc:creator>
	<dc:creator>Negara, Andhika Rastra</dc:creator>
	<dc:creator>Zia, Muhammad Qaiser Zaydan</dc:creator>
	<dc:creator>Thwe, Yamin</dc:creator>
	<dc:creator>Uda, Muhammad Nur Afnan</dc:creator>
	<dc:creator>Hashim, Uda</dc:creator>
	<dc:creator>Pamungkas, Yuri</dc:creator>
	<dc:subject xml:lang="en-US">Deep Convolutional Neural Networks</dc:subject>
	<dc:subject xml:lang="en-US">Brain Tumor Classification</dc:subject>
	<dc:subject xml:lang="en-US">Magnetic Resonance Imaging (MRI)</dc:subject>
	<dc:subject xml:lang="en-US">Medical Image Analysis</dc:subject>
	<dc:description xml:lang="en-US">Brain tumors are associated with high mortality and severe neurological effects, making accurate and timely diagnosis essential. However, manual interpretation of Magnetic Resonance Imaging (MRI) remains subjective and time-consuming. Deep learning, particularly Convolutional Neural Networks (CNNs), offers a promising approach to improving diagnostic accuracy and efficiency. This research systematically benchmarks five CNN architectures (VGG19, DenseNet201, ResNet50, Inception-v3, and MobileNet) on balanced and naturally imbalanced MRI datasets. Its novelty lies in evaluating all models under a unified preprocessing and transferlearning framework across both dataset distributions, with Grad-CAM used to support interpretability. Preprocessing includes resizing, adaptive masking, Gaussian blur, Contrast Limited Adaptive Histogram Equalization (CLAHE), normalization, and augmentation, followed by transfer learning using ImageNet-pretrained models. Performance is evaluated using accuracy, precision, recall, specificity, F1-score, and Area Under the Curve (AUC). Results show that VGG19 achieves the highest accuracy (0.937 for balanced and 0.962 for imbalanced data), recall (0.991 and 0.984, respectively), and F1-score, demonstrating strong sensitivity and generalization. DenseNet201 achieves the highest AUC (0.992 and 0.996) and high specificity, indicating strong overall discriminative performance. These findings suggest that VGG19 is particularly suitable for sensitivity-oriented early screening, whereas DenseNet201 is advantageous when overall discrimination and specificity are prioritized. In conclusion, CNN-based models show substantial potential for brain tumor classification, with architecture selection depending on specific clinical priorities.
 
</dc:description>
	<dc:publisher xml:lang="en-US">Bina Nusantara University</dc:publisher>
	<dc:date>2026-09-08</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.binus.ac.id/index.php/commit/article/view/14392</dc:identifier>
	<dc:identifier>10.21512/commit.v20i2.14392</dc:identifier>
	<dc:source xml:lang="en-US">CommIT (Communication and Information Technology) Journal; Vol. 20 No. 2 (2026): CommIT Journal ; 415-432</dc:source>
	<dc:source>2460-7010</dc:source>
	<dc:source>1979-2484</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.binus.ac.id/index.php/commit/article/view/14392/5840</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 Tegar Anugrah Firdaus, Bryan Rais, Marcelinus Jonathan Salim, Andhika Rastra Negara, Muhammad Qaiser Zaydan Zia, Yamin Thwe, Muhammad Nur Afnan Uda, Uda Hashim, Yuri Pamungkas</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>