KLASIFIKASI KANKER SEL DARAH PUTIH (ACUTE LYMPHOBLASTIC LEUKEMIA) DENGAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

Alfataniah, Nur Fajrina (2024) KLASIFIKASI KANKER SEL DARAH PUTIH (ACUTE LYMPHOBLASTIC LEUKEMIA) DENGAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN). Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text [1] Cover.pdf Download (910kB)
	Text [2] ABSTRAK INDONESIA.pdf Download (7kB)
	Text [3] ABSTRACT INGGRIS.pdf Download (6kB)
	Text [4] BAB 1.pdf Download (127kB)
	Text [5] BAB 2.pdf Download (396kB)
	Text [6] BAB 3.pdf Download (331kB)
	Text [7] BAB 4.pdf Restricted to Registered users only Download (337kB)
	Text [8] BAB 5.pdf Download (10kB)
	Text [10] DAFTAR PUSTAKA.pdf Download (80kB)
	Text [11] LAMPIRAN.pdf Restricted to Registered users only Download (713kB)

Abstract

Leukemia is a type of cancer that begins in human blood cells. Its aggressiveness can lead to rapid growth, and without proper treatment, it can be fatal within a few months. To aid in diagnosis, there is a system that utilizes image analysis to quickly diagnose diseases. In this study, a system was designed for the classification of Acute Lymphoblastic Leukemia (ALL) into 4 classes: Benign, Early, (Pre) Precursor, and Pro (Progenitor) using Convolutional Neural Network (CNN) methods with 2 architectures: MobileNetV3-Large and EfficientNet-B0. The data used consisted of 3,256 images divided into 4 classes: Benign, Early, precursor, and Progenitor. The classification results of Acute Lymphoblastic Leukemia using the EfficientNet-B0 architecture performed better than the MobileNetV3-Large architecture. The validation accuracy of the EfficientNet-B0 architecture reached 97.84%, while when tested with test data, it reached 98.48%. Meanwhile, for the MobileNet-V3-Large architecture, the validation accuracy reached 96.60%, and when tested with test data, it reached 96.32%. It is hoped that this system can assist medical professionals in detecting ALL more efficiently and accurately. Keywords: Acute Lymphoblastic Leukemia, Convolutional Neural Network, Efficientnetb0, Hyperparameter, Mobilenetv3large

Actions (login required)

View Item