Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Optimization of Multi-Section and Partially Augmented Magnetic Resonance Imaging (MRI) Images for Brain Tumor Classification Using ResNet-50

CommIT (Communication and Information Technology) Journal · Vol. 19 No. 1 (2025) · hlm. 115–128

DOI
10.21512/commit.v19i1.12467
ISSN
2460-7010, 1979-2484
Terbit
2025-05-05
Penerbit
Bina Nusantara University
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Brain tumor diagnosis is challenging due to complex brain anatomy and tumor variability across imaging views. Traditional methods are manual and error-prone, making deep learning, particularly ResNetbased Convolutional Neural Network (CNN), essential for improving accuracy. The research investigates the enhancement of brain tumor classification using Magnetic Resonance Imaging (MRI) images through a novel modification of the ResNet50 model. It specifically addresses data imbalance challenges in medical image analysis. By proposing a targeted approach to partial data augmentation, the researchers aim to overcome limitations in traditional deep-learning classification methodologies, particularly the performance bottlenecks encountered in differentiating complex brain tumor subtypes. The research uses MRI dataset containing 5,249 labeled images (glioma, meningioma, pituitary, no tumor) across axial, coronal, and sagittal planes, highlighting class and view-based imbalances addressed through targeted augmentation. The research employs transfer learning to analyze three scenarios: non-augmented, partially augmented, and rounding-down data. Results reveal that the partially augmented scenario achieves the highest classification accuracy at 85%, significantly surpassing the non-augmented scenario, which peaks at 79%. In contrast, the rounding-down scenario yields only 60.16% accuracy during validation, highlighting the negative impact of drastically reducing data quantities. The unique contribution lies in demonstrating how strategic partial augmentation can enhance pattern recognition and mitigate overfitting risks, particularly in medical imaging where precise differentiation is crucial. The findings highlight the critical role of nuanced data distribution in enhancing model robustness, as evidenced by improved pattern recognition and reduced overfitting risks in the augmented scenario.

Kata kunci

Jaringan kolaborasi para penulis

40 penulis · 123 tautan kepenulisan bersama · 71 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.

  • University of Pembangunan Nasional Veteran Jawa Timur
  • Universiti Malaysia Pahang Al-Sultan Abdullah
  • Universitas Nahdlatul Ulama Surabaya
  • Universitas Handayani Makassar
  • INTI International University
  • Hasanuddin University
  • Sunan Kalijaga State Islamic University Yogyakarta
  • 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
Sayyidah HumairahUniversity of Pembangunan Nasional Veteran Jawa Timur5
Deshinta Arrova DewiINTI International University4
Teguh HerlambangUniversitas Nahdlatul Ulama Surabaya2
Pangestu Sandya Etniko SiagianRedeemer University2
Wan Suryani Wan AwangSultan Zainal Abidin University2
Fara Disa DurryUniversity of Pembangunan Nasional Veteran Jawa Timur2
Abdul Latief ArdaUniversitas Handayani Makassar1
Muh. Fauzan SaidUniversitas Handayani Makassar1
Syamsu AlamHasanuddin University1
Anindo Saka FitriUniversity of Pembangunan Nasional Veteran Jawa Timur1
Abdul Rezha Efrat NajafUniversity of Pembangunan Nasional Veteran Jawa Timur1
Eko WahyudiSunan Kalijaga State Islamic University Yogyakarta1
Adelia Azizatul HaqUniversity of Pembangunan Nasional Veteran Jawa Timur1
Sugiarto SugiartoPoliteknik Statistika STIS1
Shofiya SyidadaUniversitas Wijaya Kusuma Surabaya1
Noor Fitria AzzahraAfiliasi tidak diketahui1
Budi Sulistiyo NugrohoUniversity of Pembangunan Nasional Veteran Jawa Timur1
Nyoman JuniartaUniversité de Lorraine1
Aji Akbar FirdausUniversitas Airlangga1
Ragil Puji RahayuUniversitas Nahdlatul Ulama Surabaya1
Dina NovitaUniversitas Muhammadiyah Surabaya1
Arasy AlimudinUniversitas Narotama1
Hamzah ArofUniversity of Malaya1
Zulhaidi Mohd JawiInstitut Penyelidikan Keselamatan Jalan Raya Malaysia1
Mohamad Heerwan Bin PeeieUniversiti Malaysia Pahang Al-Sultan Abdullah1
Ericsson YongUniversiti Malaysia Pahang Al-Sultan Abdullah1
Abdullah ZulkifliUniversiti Malaysia Pahang Al-Sultan Abdullah1
Muhammad Izhar IshakUniversiti Malaysia Pahang Al-Sultan Abdullah1
Muhammad Aizzat ZakariaUniversiti Malaysia Pahang Al-Sultan Abdullah1
Intan Suhana Mohd RazelanUniversiti Malaysia Pahang Al-Sultan Abdullah1
Ahmad Fakhri Ab. NasirUniversiti Malaysia Pahang Al-Sultan Abdullah1
Anak Agung Ngurah GunawanUdayana University1
Dheasy HerawatiUniversitas Maarif Hasyim Latif1
Wahyu S.J. SaputraUniversity of Pembangunan Nasional Veteran Jawa Timur1
Sahrul MunirNational Taipei University of 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">Optimization of Multi-Section and Partially Augmented Magnetic Resonance Imaging (MRI) Images for Brain Tumor Classification Using ResNet-50</dc:title>
	<dc:creator>Diyasa, I Gede Susrama Mas</dc:creator>
	<dc:creator>Sunarko, Victor Immanuel</dc:creator>
	<dc:creator>Puspaningrum, Eva Yulia</dc:creator>
	<dc:creator>Asy'ari, Vaizal</dc:creator>
	<dc:creator>Ibrahim, Mohd Zamri</dc:creator>
	<dc:subject xml:lang="en-US">Magnetic Resonance Imaging (MRI)</dc:subject>
	<dc:subject xml:lang="en-US">Brain Tumor</dc:subject>
	<dc:subject xml:lang="en-US">ResNet-50</dc:subject>
	<dc:description xml:lang="en-US">Brain tumor diagnosis is challenging due to complex brain anatomy and tumor variability across imaging views. Traditional methods are manual and error-prone, making deep learning, particularly ResNetbased Convolutional Neural Network (CNN), essential for improving accuracy. The research investigates the enhancement of brain tumor classification using Magnetic Resonance Imaging (MRI) images through a novel modification of the ResNet50 model. It specifically addresses data imbalance challenges in medical image analysis. By proposing a targeted approach to partial data augmentation, the researchers aim to overcome limitations in traditional deep-learning classification methodologies, particularly the performance bottlenecks encountered in differentiating complex brain tumor subtypes. The research uses MRI dataset containing 5,249 labeled images (glioma, meningioma, pituitary, no tumor) across axial, coronal, and sagittal planes, highlighting class and view-based imbalances addressed through targeted augmentation. The research employs transfer learning to analyze three scenarios: non-augmented, partially augmented, and rounding-down data. Results reveal that the partially augmented scenario achieves the highest classification accuracy at 85%, significantly surpassing the non-augmented scenario, which peaks at 79%. In contrast, the rounding-down scenario yields only 60.16% accuracy during validation, highlighting the negative impact of drastically reducing data quantities. The unique contribution lies in demonstrating how strategic partial augmentation can enhance pattern recognition and mitigate overfitting risks, particularly in medical imaging where precise differentiation is crucial. The findings highlight the critical role of nuanced data distribution in enhancing model robustness, as evidenced by improved pattern recognition and reduced overfitting risks in the augmented scenario.</dc:description>
	<dc:publisher xml:lang="en-US">Bina Nusantara University</dc:publisher>
	<dc:date>2025-05-05</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/12467</dc:identifier>
	<dc:identifier>10.21512/commit.v19i1.12467</dc:identifier>
	<dc:source xml:lang="en-US">CommIT (Communication and Information Technology) Journal; Vol. 19 No. 1 (2025): CommIT Journal ; 115-128</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/12467/5408</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 I Gede Susrama Mas Diyasa, Victor Immanuel Sunarko, Eva Yulia Puspaningrum, Vaizal Asy'ari, Mohd Zamri Ibrahim</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>