Skripsi

SEGMENTASI TUMOR OTAK PADA CITRA HASIL MAGNETIC RESONANCE IMAGING (MRI) OTAK MENGGUNAKAN PERBAIKAN ARSITEKTUR 3D V-NET

---

Penilaian

---

Detection of abnormalities in brain MRI images as an effort to detect brain tumors early can be implemented with image segmentation using Convolutional Neural Network (CNN). An architecture frequently used in 3D image segmentation is the 3D U-Net architecture. In this study, a modification was made to the 3D U-Net architecture by removing the bridge part to produce a new architecture is 3D V-Net for brain tumor segmentation in magnetic resonance imaging (MRI)images of the brain. Results of this study using Brain Tumor Segmentation dataset is score of accuracy, Intersection over Union (IoU), F1-Score, sensitivity, and specificity 97.95%, 73,84%, 80,30%, 89,42 %, and 98,16% respectively. Based on the results, it can be shown that 3D V-Net architecture is capable of segmenting brain tumors on brain MRI images, but still has a fairly low IoU value.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307000938	T90036	T900362023	Central Library (Referens)	Available

Detail Information

Series Title

-

Call Number

T900362023

Publisher

Indralaya : Jurusan Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam, Universitas Sriwijaya., 2023

Collation

xii, 60 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

510.285 07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Matematika
Pengolahan dan Analisa Data di Bidang Matematika

Specific Detail Info

-

Statement of Responsibility

PITRIA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment