Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Bioma : Jurnal Ilmiah Biologi
Agustavada, Ardha Ardhana Putra
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Education Immunology & microbiology

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
MORPHOLOGICAL CHARACTERIZATION OF BRAIN TUMOR TISSUE IN MRI IMAGES USING CNN AND TRANSFER LEARNING Hilmi, Dafa Fadhilah; Wibawa, Aji Prasetya; Agustavada, Ardha Ardhana Putra; Sholum, Abdullah; Dwiyanto, Felix Andika
BIOMA : Jurnal Ilmiah Biologi Vol. 15 No. 1 (2026): April 2026
Publisher : Prodi Pendidikan Biologi, FPMIPATI, Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/bioma.v15i1.3550

Abstract

This study evaluates the role of computational pattern recognition as an observational method for analyzing morphological characteristics of brain tumor tissue in MRI data. A total of 6,056 labeled MRI images, including glioma, meningioma, and pituitary tumor cases, were examined. The images were standardized to maintain uniform structural representation and processed using three convolutional-based architectures: a baseline CNN, MobileNetV2, and EfficientNet-B0. Model performance was assessed using accuracy, precision, recall, F1-score, AUC-ROC, and a confusion matrix. The findings show variation in identification performance across tumor categories, with pituitary tumors consistently recognized, while misclassification predominantly occurred between glioma and meningioma. Models based on transfer learning achieved stronger agreement with the reference labels than the baseline CNN, with MobileNetV2 demonstrating the most stable performance. The recurrence of similar misclassification patterns across models suggests the presence of shared morphological characteristics in MRI representations of certain tumor types. Overall, the results support the use of computational image analysis as a structured observational framework that enables consistent evaluation of brain tumor tissue morphology in MRI, providing complementary insights for biological interpretation.
Co-Authors Aji Prasetya Wibawa Dwiyanto, Felix Andika Hilmi, Dafa Fadhilah Sholum, Abdullah