Text

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

---

Penilaian

---

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).

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207000952	T69072	T690722022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T690722022

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xiii, 48 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.707

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Sistem Komputer
, Data dalam sistem-sistem komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment