DETEKSI LESI PRA-KANKER SERVIKS PADA CITRA KOLPOSKOPI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR YOLO

NURQOLBIAH, FATIHANI and Nurmaini, Siti (2024) DETEKSI LESI PRA-KANKER SERVIKS PADA CITRA KOLPOSKOPI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR YOLO. Masters thesis, Sriwijaya University.

	Text RAMA_55101_09012682226008.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (26MB) | Request a copy
	Text RAMA_55101_09012682226008_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy
	Text RAMA_55101_09012682226008_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (5MB)
	Text RAMA_55101_09012682226008_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55101_09012682226008_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55101_09012682226008_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55101_09012682226008_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (74kB) | Request a copy
	Text RAMA_55101_09012682226008_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (99kB) | Request a copy
	Text RAMA_55101_09012682226008_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12MB) | Request a copy

Abstract

Deteksi lesi pra-kanker serviks memegang peran krusial dalam menganalisis citra medis untuk diagnosa yang tepat. Keterbatasan pengamatan visual mendorong perlunya deteksi berbasis komputer. Penelitian ini mengusulkan model deteksi lesi pra-kanker serviks menggunakan Convolutional Neural Network (CNN) dengan arsitektur YOLO, memberikan akurasi yang tinggi. Dua dataset digunakan, pertama dari IARS Cervical Cancer Image Bank (Dataset 1) dengan 913 gambar dari 200 kasus, dan kedua dari Rumah Sakit Mohammad Hoesin Palembang (Dataset 2) dengan 160 gambar. Hasil evaluasi matriks menunjukkan bahwa YOLOv8 menjadi model terbaik dengan mAP50 sebesar 92% pada Dataset 1, 78,4% pada Dataset 2, dan 81,5% pada gabungan kedua dataset.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Detection; Cervical Pre-Cancer; Colposcopy; Convolutional Neural Network; YOLO
Subjects:	#2 Repository of Library Services > Documentation of Important Decrees (UU, PP, Permen etc)
Divisions:	09-Faculty of Computer Science > 55101-Informatics (S2)
Depositing User:	Fatihani Nurqolbiah
Date Deposited:	01 Feb 2024 08:22
Last Modified:	01 Feb 2024 08:22
URI:	http://repository.unsri.ac.id/id/eprint/140608

Actions (login required)

View Item