PASSA, RAHMA SATILA and Nurmaini, Siti and Rini, Dian Palupi (2023) INSTANCE SEGMENTATION PADA MAGNETIC RESONANCE IMAGING TUMOR OTAK MENGGUNAKAN YOLOv7 DAN YOLOv8. Masters thesis, Sriwijaya University.
Text
RAMA_55101_09012682125009.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy |
|
Text
RAMA_55101_09012682125009_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy |
|
Text
RAMA_55101_09012682125009_0002085908_0023027804_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (779kB) |
|
Text
RAMA_55101_09012682125009_0002085908_0023027804_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_09012682125009_0002085908_0023027804_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy |
|
Text
RAMA_55101_09012682125009_0002085908_0023027804_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy |
|
Text
RAMA_55101_09012682125009_0002085908_0023027804_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (139kB) | Request a copy |
|
Text
RAMA_55101_09012682125009_0002085908_0023027804_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (151kB) | Request a copy |
|
Text
RAMA_55101_09012682125009_0002085908_0023027804_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (65MB) | Request a copy |
Abstract
Pencitraan medis, seperti MRI, berperan penting dalam mensegmentasi tumor otak, tetapi banyak tugas yang masih bergantung pada penilaian manual yang memakan waktu. Oleh karena itu, dibutuhkan segmentasi otomatis yang akurat untuk mempercepat diagnosis dan penanganan. Dengan menggunakan model-model terkini, YOLOv7 dan YOLOv8 yang didukung oleh dasar kerja CNN, penelitian dilakukan untuk mensegmentasi tumor otak. YOLOv8 mencapai hasil yang terbaik. Pada box, YOLOv8 mencapai precision sebesar 0,92, recall 0,923, F1 score 0,921, mAP50 0,957, dan mAP50-95 0,78. Pada mask, YOLOv8 juga menunjukkan performa yang sangat baik dengan precision 0,928, recall 0,925, F1 score 0,926, mAP50 0,962, dan mAP50-95 0,77. Penelitian berhasil mensegmentasi tumor otak pada citra MRI mengunakan YOLOv7 dan YOLOv8 dengan hasil yang baik.
Item Type: | Thesis (Masters) |
---|---|
Uncontrolled Keywords: | deep learning, segmentation, brain tumor, YOLOv7, YOLOv8 |
Subjects: | Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. |
Divisions: | 09-Faculty of Computer Science > 55101-Informatics (S2) |
Depositing User: | Rahma Satila Passa |
Date Deposited: | 12 Jan 2024 07:37 |
Last Modified: | 12 Jan 2024 07:37 |
URI: | http://repository.unsri.ac.id/id/eprint/138061 |
Actions (login required)
View Item |