INSTANCE SEGMENTATION SAMBUNGAN SKUAMO KOLUMNAR DAN LESI PADA DATA INSPEKSI VISUAL ASAM ASETAT MENGGUNAKAN MASK REGION CONVOLUTIONAL NEURAL

FLORINA, GAVIRA OLIPA and Nurmaini, Siti (2022) INSTANCE SEGMENTATION SAMBUNGAN SKUAMO KOLUMNAR DAN LESI PADA DATA INSPEKSI VISUAL ASAM ASETAT MENGGUNAKAN MASK REGION CONVOLUTIONAL NEURAL. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181823017.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011181823017_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
Preview	Text RAMA_56201_09011181823017_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (948kB) | Preview
	Text RAMA_56201_09011181823017_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (347kB) | Request a copy
	Text RAMA_56201_09011181823017_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (741kB) | Request a copy
	Text RAMA_56201_09011181823017_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_56201_09011181823017_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5kB) | Request a copy
	Text RAMA_56201_09011181823017_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (233kB) | Request a copy
	Text RAMA_56201_09011181823017_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (240kB) | Request a copy

Abstract

In Indonesia, cervical cancer is still a disease with the second largest number of sufferers after breast cancer. Cervical cancer occurs due to infection with the Human Papilloma Virus (HPV), which is found in the cervix. One of the screening methods that is often used for cervical pre-cancer detection is the Acetic Acid Visual Inspection (IVA) method. This method has a level of efficiency and convenience. After applying acetic acid to the cervix, the lesions will be visible. Lesions are conditions in which abnormal cell growth occurs, this occurs due to changes in the cervix that may be precancerous. For examination of the most significant areas, a Squamous Columnar junction (SSK) is used, which is the boundary between two different cell types. The image analysis process can be done to determine the area of SSK and Lesions by segmenting, detecting, and classifying. Mask-RCNN for Instance Segmentation or also called the segmentation process, detection andclassification are carried out simultaneously. Thus, in this study, the Mask-RCNN method was used to segment SSK and Lesion instances using cervical precancer medical images. The results for the SSK area that has the best performance evaluation get 70.57% Intersection over Union (IoU), 68.51% Dice Score Similarity (DSC), and 98.10% mean Average Precision (mAP). The results of the study for the targeted lesion area were obtained from the best performance model and obtained the results of 60.44% Intersection over Union (IoU), 68.51% Dice Score Similarity (DSC), and 98.85% mean Average Precision (mAP).

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pre-Cancer, VIA Screening, SSK, Lesions, Mask-RCNN
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:	GAVIRA OLIPA FLORINA
Date Deposited:	18 Apr 2022 03:59
Last Modified:	18 Apr 2022 04:00
URI:	http://repository.unsri.ac.id/id/eprint/69072

Actions (login required)

View Item