đ
24 April 2026
DOI: 10.26877/bioma.v15i1.3550
MORPHOLOGICAL CHARACTERIZATION OF BRAIN TUMOR TISSUE IN MRI IMAGES USING CNN AND TRANSFER LEARNING
Bioma : Jurnal Ilmiah Biologi
Universitas Persatuan Guru Republik Indonesia Semarang
đ 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.
đ Keywords
#Brain Tumor; Deep Learning; Magnetic resonance imaging; Neural tissue morphology; Pattern recognition
âšī¸ Informasi Publikasi
Tanggal Publikasi
24 April 2026
Volume / Nomor / Tahun
Tahun 2026
đ HOW TO CITE
Hilmi, Dafa Fadhilah; Wibawa, Aji Prasetya ; Agustavada, Ardha Ardhana Putra; Sholum, Abdullah; Dwiyanto, Felix Andika, "MORPHOLOGICAL CHARACTERIZATION OF BRAIN TUMOR TISSUE IN MRI IMAGES USING CNN AND TRANSFER LEARNING," Bioma : Jurnal Ilmiah Biologi, Apr. 2026.
ACM
ACS
APA
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
0
Sitasi
Cek Google Scholar