Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Enhancing imbalanced dataset diagnosis using class-based input image composition

IAES International Journal of Artificial Intelligence · Vol. 15 No. 2 (2026) · hlm. 1613–1622

DOI
10.11591/ijai.v15.i2.pp1613-1622
ISSN
2252-8938, 2089-4872
Terbit
2026-04-01
Penerbit
Institute of Advanced Engineering and Science
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Deep learning models often falter when faced with small, imbalanced datasets or degraded image quality, leading to unacceptably high false prediction rates. To bridge this gap, we introduce class-based image composition. This technique reformulates training inputs by fusing multiple intra-class images into unique composite input images (CoImg). By concentrating information density and amplifying intra-class variance, CoImg forces the model to discern subtle, nuanced disease patterns that might otherwise be lost. We validated this approach using the optical coherence tomography dataset for image-based deep learning methods (OCTDL), a collection of seven imbalanced retinal disease scan categories. From this, we engineered Co-OCTDL: a perfectly balanced variant where each training sample exists as a 3×1 layout composite. To measure the impact of this new representation, we benchmarked the original dataset against its composite counterpart using a VGG16 architecture. Precision was paramount. We maintained identical hyperparameters and model structures across all experiments to ensure a rigorous, fair comparison. The results were transformative. While baseline datasets struggled, the enhanced Co OCTDL achieved a near-perfect F1-score of 0.995 and an AUC of 0.9996. The method effectively neutralized the risks of class imbalance. It didn't just improve the numbers; it refined the diagnostic reliability of the model.

Kata kunci

Jaringan kolaborasi para penulis

7 penulis · 9 tautan kepenulisan bersama

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

  • Sidi Mohamed Ben Abdellah University
  • 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
Ali AbarkanSidi Mohamed Ben Abdellah University1
Abderrahim SaaidiSidi Mohamed Ben Abdellah University1
El Bachir TaziSidi Mohamed Ben Abdellah University1
Siham MencouSidi Mohamed Ben Abdellah University1

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) http://ijai.iaescore.com/index.php/IJAI/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 16 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">Enhancing imbalanced dataset diagnosis using class-based input  image composition</dc:title>
	<dc:creator>Hlali, Azzeddine</dc:creator>
	<dc:creator>Ben Yakhlef, Majid</dc:creator>
	<dc:creator>El Hazzat, Soulaiman</dc:creator>
	<dc:subject xml:lang="en-US"></dc:subject>
	<dc:subject xml:lang="en-US">Class imbalance; False diagnostic metrics; Low-quality features; Medical image analysis; Retinal disease classification</dc:subject>
	<dc:description xml:lang="en-US">Deep learning models often falter when faced with small, imbalanced datasets or degraded image quality, leading to unacceptably high false prediction rates. To bridge this gap, we introduce class-based image composition. This technique reformulates training inputs by fusing multiple intra-class images into unique composite input images (CoImg). By concentrating information density and amplifying intra-class variance, CoImg forces the model to discern subtle, nuanced disease patterns that might otherwise be lost. We validated this approach using the optical coherence tomography dataset for image-based deep learning methods (OCTDL), a collection of seven imbalanced retinal disease scan categories. From this, we engineered Co-OCTDL: a perfectly balanced variant where each training sample exists as a 3×1 layout composite. To measure the impact of this new representation, we benchmarked the original dataset against its composite counterpart using a VGG16 architecture. Precision was paramount. We maintained identical hyperparameters and model structures across all experiments to ensure a rigorous, fair comparison. The results were transformative. While baseline datasets struggled, the enhanced Co OCTDL achieved a near-perfect F1-score of 0.995 and an AUC of 0.9996. The method effectively neutralized the risks of class imbalance. It didn't just improve the numbers; it refined the diagnostic reliability of the model.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US"></dc:contributor>
	<dc:date>2026-04-01</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"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijai.iaescore.com/index.php/IJAI/article/view/31111</dc:identifier>
	<dc:identifier>10.11591/ijai.v15.i2.pp1613-1622</dc:identifier>
	<dc:source xml:lang="en-US">IAES International Journal of Artificial Intelligence (IJ-AI); Vol 15, No 2: April 2026; 1613-1622</dc:source>
	<dc:source>2252-8938</dc:source>
	<dc:source>2089-4872</dc:source>
	<dc:source>10.11591/ijai.v15.i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijai.iaescore.com/index.php/IJAI/article/view/31111/15142</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 Azzeddine Hlali, Majid Ben Yakhlef, Soulaiman El Hazzat</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>