Implementasi algoritma CNN dalam klasifikasi citra medis MRI penyakit alzheimer

Saputra, Dadan Firmansyah (2023) Implementasi algoritma CNN dalam klasifikasi citra medis MRI penyakit alzheimer. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text
1_cover.pdf

Download (93kB) | Preview
[img]
Preview
Text
2_abstrak.pdf

Download (24kB) | Preview
[img]
Preview
Text
Surat Pernyataan Karya Sendiri (14).pdf

Download (1MB) | Preview
[img]
Preview
Text
4_daftarisi.pdf

Download (69kB) | Preview
[img]
Preview
Text
5_bab1.pdf

Download (259kB) | Preview
[img] Text
6_bab2.pdf
Restricted to Registered users only

Download (202kB) | Request a copy
[img] Text
7_bab3.pdf
Restricted to Registered users only

Download (481kB) | Request a copy
[img] Text
8_bab4.pdf
Restricted to Registered users only

Download (1MB) | Request a copy
[img] Text
9_bab5.pdf
Restricted to Registered users only

Download (103kB) | Request a copy
[img] Text
10_daftarpustaka.pdf
Restricted to Registered users only

Download (160kB) | Request a copy
[img] Text
Lampiran (95).pdf
Restricted to Repository staff only

Download (2MB) | Request a copy

Abstract

Alzheimer's disease is a neurodegenerative condition that affects brain function, cognition and individual behavior, most commonly occurring in the elderly over 65 years. The importance of early diagnosis of Alzheimer's disease by analyzing brain MRI (Magnetic Resonance Imaging) medical images. One of the methods used for processing MRI medical images is the Convolutional Neural Network (CNN) algorithm. Therefore, research was conducted on how to apply the Convolutional Neural Network (CNN) algorithm to classify Magnetic Resonance Imaging (MRI) medical images of Alzheimer's disease and how well the algorithm performs utilizing Augmented Alzheimer MRI public dataset published by Sarvesh Dubey with format of images .JPG. Based on the research results, the Convolutional Neural Network (CNN) algorithm used to classify Alzheimer's disease is NonDemented, MildDemented, and ModerateDemented. Where, the application of the VGG-16 model to Alzheimer's MRI produces a high accuracy validation value with an image resolution of 64×64 pixels, the number of epochs is 70 using the adam optimizer which has a validation accuracy of 92%. Penyakit alzheimer merupakan kondisi neurodegeneratif yang mempengaruhi fungsi otak, kognisi, dan perilaku individu paling umum terjadi pada lansia di atas 65 tahun. Pentingnya diagnosis dini penyakit alzheimer dengan melakukan analisis citra medis MRI (Magnetic Resonance Imaging) otak. Salah satu metode yang digunakan untuk pengolahan citra medis MRI yakni algoritma Convolutional Neural Network (CNN). Maka dari itu, dilakukan penelitian bagaimana cara menerapkan algoritma CNN untuk klasifikasi citra medis MRI penyakit alzheimer dan sejauh mana kinerja algoritma tersebut dengan menggunakan public data Augmented Alzheimer MRI yang dipublikasikan oleh Sarvesh Dubey dengan tipe data gambar .JPG. Berdasarkan hasil penelitian, algoritma CNN yang digunakan untuk mengklasifikasikan penyakit alzheimer berupa NonDemented, MildDemented, dan ModerateDemented. Dimana, penerapan model VGG-16 pada MRI alzheimer menghasilkan nilai validation akurasi tinggi dengan resolusi gambar 64×64 pixel, jumlah epoch sebesar 70 dengan menggunakan optimizer adam yang memiliki validasi akurasi 92%.

Item Type: Thesis (Sarjana)
Uncontrolled Keywords: Penyakit alzheimer; MRI (Magnetic Resonance Imaging); Convolutional Neural Network (CNN); VGG-16; NonDemented; MildDemented; ModerateDemented
Subjects: Technology, Applied Sciences
Medicine and Health > General Publications of Medical Science
Divisions: Fakultas Sains dan Teknologi > Program Studi Teknik Informatika
Depositing User: Dadan Firmansyah Saputra
Date Deposited: 23 Jul 2025 03:15
Last Modified: 23 Jul 2025 03:15
URI: https://digilib.uinsgd.ac.id/id/eprint/113164

Actions (login required)

View Item View Item