Fadhillah Al Ghifari
Universitas Muhammadiyah Prof. Dr Hamka, Jakarta

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

Found 1 Documents
Search

IMPLEMENTASI ALGORITHMA CONVOLUTIONAL NEURAL NETWORK (CNN) PADA SOFTWARE PENDETEKSI TUMOR OTAK BERDASARKAN MAGNETIC RESONANCE IMAGE (MRI) Akhmad Rizal Dzikrillah; Fadhlina Shifa Hanum; Fadhillah Al Ghifari; Pancatatva Hesti Gunawan
Infotech: Journal of Technology Information Vol 12, No 1 (2026): JUNI (In Progress)
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v12i1.594

Abstract

A brain tumor is an abnormal growth of brain cells that occurs in or around the brain and can be life-threatening. A common technique used to diagnose a brain tumor is through the analysis of MRI images of the patient's brain by a radiologist. Deep learning technology can be used to generate a classification model for the presence of a brain tumor based on a dataset of Magnetic Resonance Images (MRIs) of patients in a hospital. This study aims to create software that can diagnose the presence of a brain tumor based on a patient's MRI images. The software implements a classification model using a Convolutional Neural Network (CNN) algorithm. The CNN classification model has an accuracy of up to 0.96 with a precision of 1.00, a recall of 0.92, and an F1-Score of 0.96 for the MRI category diagnosed with a tumor and with a precision of 0.92, a recall of 1.00, and an F1-Score of 0.96 for the MRI category diagnosed with a non-tumor. The model also does not experience overfitting based on epoch evaluation. The results of the diagnosis of the presence of brain tumors by the software always showed agreement with the results of the radiology expert's diagnosis in all research samples.