SEGMENTASI LESI PRA-KANKER SERVIKS MENGGUNAKAN YOLO DAN SEGMENT ANYTHING MODEL

ROLIS, MUHAMMAD ALPIM ALFA and Nurmaini, Siti (2025) SEGMENTASI LESI PRA-KANKER SERVIKS MENGGUNAKAN YOLO DAN SEGMENT ANYTHING MODEL. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_56201_09011282126072_cover.jpg]
Preview
Image
RAMA_56201_09011282126072_cover.jpg - Cover Image
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_56201_09011282126072.pdf] Text
RAMA_56201_09011282126072.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_56201_09011282126072_TURNITIN.pdf] Text
RAMA_56201_09011282126072_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (7MB) | Request a copy
[thumbnail of RAMA_56201_09011282126072_0002085908_01_front_ref.pdf] Text
RAMA_56201_09011282126072_0002085908_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB)
[thumbnail of RAMA_56201_09011282126072_0002085908_02.pdf] Text
RAMA_56201_09011282126072_0002085908_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (860kB) | Request a copy
[thumbnail of RAMA_56201_09011282126072_0002085908_03.pdf] Text
RAMA_56201_09011282126072_0002085908_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (684kB) | Request a copy
[thumbnail of RAMA_56201_09011282126072_0002085908_04.pdf] Text
RAMA_56201_09011282126072_0002085908_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[thumbnail of RAMA_56201_09011282126072_0002085908_05.pdf] Text
RAMA_56201_09011282126072_0002085908_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (219kB) | Request a copy
[thumbnail of RAMA_56201_09011282126072_0002085908_06_ref.pdf] Text
RAMA_56201_09011282126072_0002085908_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (336kB) | Request a copy
[thumbnail of RAMA_56201_09011282126072_0002085908_07_lamp.pdf] Text
RAMA_56201_09011282126072_0002085908_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (966kB) | Request a copy

Abstract

With the advancement of technology, deep learning models are increasingly being used in the medical field, particularly in image segmentation. This study aims to develop and evaluate methods for segmenting pre-cancerous cervical lesions using the YOLO (You Only Look Once) architecture, specifically YOLOv8 and YOLOv11, as well as the Segment Anything Model (SAM and SAM 2). The YOLO model is used to detect the cervical area, columnar area (CA), and lesions in medical images obtained from Mohammad Hoesin General Hospital and the International Agency for Research on Cancer (IARC). The bounding box detection results from YOLO are used as prompts for the segmentation process using SAM, forming a modular pipeline that enables optimization. The research results indicate that the YOLO+SAM approach provides competitive segmentation performance and modular flexibility, supporting an automated segmentation system for pre-cancerous cervical lesions for early diagnosis processes.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Image Segementation, Deep Learning, Segment Anything Model, YOLO
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: Muhammad Alpim Alfa Rolis
Date Deposited: 14 Jul 2025 06:55
Last Modified: 14 Jul 2025 06:55
URI: http://repository.unsri.ac.id/id/eprint/178370

Actions (login required)

View Item View Item