PENINGKATAN KINERJA SISTEM DETEKSI BATU GINJAL PADA CITRA CT SCAN MENGGUNAKAN ALGORITMA YOLOv8 DENGAN MODIFIKASI BACKBONE LAYER

DAMAYANTI, MUTIARA and Sutarno, Sutarno (2025) PENINGKATAN KINERJA SISTEM DETEKSI BATU GINJAL PADA CITRA CT SCAN MENGGUNAKAN ALGORITMA YOLOv8 DENGAN MODIFIKASI BACKBONE LAYER. Undergraduate thesis, Sriwijaya University.

	Image RAMA_56201_09011282126089_cover.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011282126089.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011282126089_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011282126089_0201117802_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011282126089_0201117802_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (964kB) | Request a copy
	Text RAMA_56201_09011282126089_0201117802_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (415kB) | Request a copy
	Text RAMA_56201_09011282126089_0201117802_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011282126089_0201117802_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (159kB) | Request a copy
	Text RAMA_56201_09011282126089_0201117802_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (290kB) | Request a copy
	Text RAMA_56201_09011282126089_0201117802_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Kidney stones are a condition that can interfere with kidney function and if left untreated can increase the risk of various health problems, such as chronic kidney disease, end-stage renal failure, cardiovascular disease, diabetes, and hypertension. Therefore, it is important for sufferers to take early prevention by detecting kidney stones in order to prevent serious complications in the future. In this study, kidney stone detection was carried out on CT Scan images using the YOLOv8 (You Only Look Once) algorithm. To obtain the best accuracy results, this study will compare the results of the model using the default YOLOv8 architecture with the modified architecture. Modification of the YOLOv8 backbone architecture was carried out by dividing it into three separate models, where each model only has four layers with a different number of channels depending on the model used. Based on the evaluation of the testing dataset, it was found that model 3 with batch 64 was the best model with a precision value of 0.994, recall of 0.965, mAP50 of 0.987, and mAP50-95 of 0.771

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Deteksi Batu Ginjal, Citra CT Scan, YOLOv8, Backbone Layer
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Mutiara Damayanti
Date Deposited:	15 Aug 2025 05:32
Last Modified:	15 Aug 2025 05:32
URI:	http://repository.unsri.ac.id/id/eprint/182778

Actions (login required)

View Item