SISTEM PENDETEKSIAN PENYAKIT PNEUMONIA PADA CITRA RONTGEN DADA MENGGUNAKAN METODE CNN DENGAN ARSITEKTUR RETINANET

SATRIO, BAGUS and Fachrurrozi, Muhammad and Darmawahyuni, Annisa (2024) SISTEM PENDETEKSIAN PENYAKIT PNEUMONIA PADA CITRA RONTGEN DADA MENGGUNAKAN METODE CNN DENGAN ARSITEKTUR RETINANET. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021182025025.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_55201_09021182025025_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021182025025_0222058001_8968340022_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021182025025_0222058001_8968340022_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182025025_0222058001_8968340022_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182025025_0222058001_8968340022_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182025025_0222058001_8968340022_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021182025025_0222058001_8968340022_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (127kB) | Request a copy
	Text RAMA_55201_09021182025025_0222058001_8968340022_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (128kB) | Request a copy
	Text RAMA_55201_09021182025025_0222058001_8968340022_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Pneumonia is one of the lung diseases that is often identified through chest X-ray images, but manual diagnosis requires high time and skill. Therefore, this study aims to improve the efficiency and accuracy of pneumonia diagnosis through the application of deep learning technology. The CNN method was chosen due to its ability to automatically extract features from medical images. RetinaNet, as an object detection model architecture, was chosen to improve the accuracy of disease localization in X-ray images. The training data used comes from a set of chest X-ray image data that has been annotated with a pneumonia label. The experimental results show that the developed system is able to detect pneumonia disease in chest X-ray images with mAP scores of 0.95 with IoU Threshold 0.3 and 0.83 with IoU Threshold 0.5. The application of RetinaNet architecture to CNN contributes significantly in improving the accuracy of disease detection. Thus, this system is expected to be a tool for medical personnel in supporting the rapid and accurate diagnosis of pneumonia based on chest X-ray images.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pneumonia, Pembelajaran Mendalam, Deteksi Objek, RetinaNet, Gambar Rontgen Dada
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General) T Technology > T Technology (General) > T58.5-58.64 Information technology > T58.5 General works Management information systems Cf. HD30.213 Industrial management Cf. HF5549.5.C6+ Communication in personnel management Cf. TS158.6 Automatic data collection systems (Production control)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Bagus Satrio
Date Deposited:	19 Mar 2024 05:43
Last Modified:	19 Mar 2024 05:43
URI:	http://repository.unsri.ac.id/id/eprint/141774

Actions (login required)

View Item