Klasifikasi Penyakit pada Citra Dermoscopic Kulit Menggunakan Convolutional Neural Network (CNN)

Kusuma, Arta (2019) Klasifikasi Penyakit pada Citra Dermoscopic Kulit Menggunakan Convolutional Neural Network (CNN). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07211540000004-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (8MB) | Request a copy

Abstract

Dengan kemajuan Teknologi Informasi dan Komunikasi, diagnosis penyakit kulit dapat dilakukan sedini mungkin agar pasien segera mendapatkan perawatan. Pada penelitian kali ini akan dikembangkan sebuah sistem klasifikasi penyakit kulit yang akan diterapkan pada teknologi Teledermatology. Sistem ini akan mengklasifikasi penyakit kulit pada citra dermoscopic menggunakan algoritma Deep Learning yaitu Convolutional Neural Network (CNN). Citra dermoscopic merupakan sebuah citra yang menampilkan lesi jaringan kulit yang digunakan dokter spesialis kulit dalam melakukan diagnosis penyakit. Data citra dermoscopic yang digunakan pada penelitian ini adalah Dataset MNIST HAM10000 yang berjumlah 10.015 citra dan dipublikasikan oleh International Skin Image Collaboration (ISIC). Dataset tersebut terbagi dalam tujuh jenis kelas penyakit kulit yang termasuk dalam kategori kanker kulit. Proses klasifikasi citra akan menggunakan dua pre-trained model CNN yaitu MobileNet v1 dan Inception V3. Model hasil proses training kemudian diterapkan pada sebuah web-classifier. Hasil perbandingan performa akurasi prediksi menunjukan bahwa web-classifier yang menggunakan model CNN Inception V3 memiliki nilai akurasi sebesar 72% sedangkan web-classifier yang menggunakan model MobileNet v1 memiliki nilai akurasi sebesar 58%.
============================================================================================================================================
The advancement of Information and Communication Technology can improve the process of diagnosis skin diseases so that patients can get treatment immediately. In this study a system of classification and detection of skin diseases will be developed that will be applied to the technology of Teledermatology.This system will classify skin diseases on dermoscopic images using the Deep Learning algorithm, Convolutional Neural Network (CNN). Dermoscopic image is an image that displays skin tissue lesions used by dermatologist in diagnosing diseases. The dermoscopic image data in this study from MNIST HAM10000 dataset which amounts to 10,015 images and published by International Skin Image Collaboration (ISIC). The dataset is divided into seven class of skin diseases which fall into the category of skin cancer. The image classification process will use two pre-trained CNN models, MobileNet v1 and Inception V3. The model results from the learning process will be applied to a web-classifier. The comparison of predictive accuracy shows that the web-classifier using the CNN Inception V3 model has an accuracy value of 72% while the web-classifier that uses the MobileNet v1 model has an accuracy value of 58%.

Item Type:	Thesis (Other)
Additional Information:	RSKom 006.32 Her k-1 2019
Uncontrolled Keywords:	Skin Disease, Dermoscopic Image, Deep Learning, Convolutional Neural Network.
Subjects:	Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) R Medicine > RL Dermatology
Divisions:	Faculty of Information Technology > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Arta Kusuma Hernanda
Date Deposited:	06 Aug 2026 01:16
Last Modified:	06 Aug 2026 01:16
URI:	http://repository.its.ac.id/id/eprint/70450

Actions (login required)

View Item