Implementasi Algoritma Convolutional Neural Network (CNN) pada Aplikasi Android untuk Mendeteksi Tumor Otak dari Citra MRI

Wibowo, Aimar (2024) Implementasi Algoritma Convolutional Neural Network (CNN) pada Aplikasi Android untuk Mendeteksi Tumor Otak dari Citra MRI. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05111940000034-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (1MB) | Request a copy

Abstract

Tumor otak adalah penyakit serius yang dapat berakibat fatal jika tidak terdeteksi dan diobati secara dini. Magnetic Resonance Imaging (MRI) adalah teknik pencitraan medis yang banyak digunakan untuk mendiagnosis tumor otak. Namun, interpretasi gambar MRI memerlukan pengetahuan ahli dan bisa memakan waktu. Untuk mengatasi masalah ini, tugas akhir ini mengusulkan implementasi algoritma Convolutional Neural Network (CNN) dalam aplikasi Android untuk deteksi tumor otak dari gambar MRI. Sistem yang diusulkan diharapkan dapat membantu profesional medis dalam mendiagnosis tumor otak dengan lebih akurat dan efisien. Evaluasi kinerja sistem yang diusulkan akan dilakukan menggunakan beberapa metrik seperti akurasi, presisi, recall, dan f1-score. Hasil confusion matrix tanpa menggunakan augmentasi data menghasilkan nilai akurasi sebesar 97.67%, presisi sebesar 96.55%, recall sebesar 98.05%, dan f1-score sebesar 97.3%. Sedangkan hasil confusion matrix menggunakan augmentasi data menghasilkan nilai akurasi sebesar 97.67%, presisi 98.38%, recall sebesar 97.12%, dan f1-score sebesar 97.75%.
=================================================================================================================================
Brain tumors are serious diseases that can be fatal if not detected and treated early. Magnetic Resonance Imaging (MRI) is a medical imaging technique that is widely used to diagnose brain tumors. However, interpretation of MRI images requires expert knowledge and can be time consuming. To overcome this problem, this undergraduate thesis proposes the implementation of the Convolutional Neural Network (CNN) algorithm in an Android application for brain tumor detection from MRI images. The proposed system is expected to help medical professionals in diagnosing brain tumors more accurately and efficiently. Performance evaluation of the proposed system will be carried out using several metrics such as accuracy, precision, recall, and f1-score. The results of the confusion matrix without using data augmentation produce an accuracy value of 98.17%, precision of 97.67%, recall of 98.05%, and f1-score of 97.86%. Meanwhile, the results of the confusion matrix using data augmentation produced an accuracy value of 97.67%, precision of 98.38%, recall of 97.75%, and f1-score of 97.75%.

Item Type:	Thesis (Other)
Additional Information:	RSIf 006.32 AIM i 2024
Uncontrolled Keywords:	android, citra mri, convolutional neural network, deep learning, tumor otak, brain tumor, mri image.
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Aimar Wibowo
Date Deposited:	08 Feb 2024 09:55
Last Modified:	01 Nov 2024 09:23
URI:	http://repository.its.ac.id/id/eprint/106456

Actions (login required)

View Item