Text

PENGGUNAAN CONVOLUTION NEURAL NETWORK (CNN) DENGAN ARSITEKTUR UNET DAN FASTER RCNN DALAM MENDETEKSI TRANSCEREBELLAR PADA KEPALA JANIN DARI CITRA ULTRASONOGRAFI 2 DIMENSI

---

Penilaian

---

The head of the fetus is an important part to determine the condition of the fetus in pregnant women. Detection of the fetal head requires a long process and also takes a lot of time. This detection process also requires expertise and experience that must be carried out by a specialist in the field of obstetrics. This is a challenge to determine the condition of the fetus, especially detecting objects that are in the transcerebellar part. Objects that become markers on the transcerebellar are Cerebellar Hemi and Cisterna Magna. Therefore, in this study, the process of designing an algorithm with a deep learning method will be carried out to detect objects that are in trancerebellar in medical images to get accurate object results. This study performs segmentation using the U-Net architecture and will continue with the detection process using the Faster R-CNN architecture. The best results obtained are in the 3rd model using epoch 1000 and batch size 64 in segmentation and getting an mAP of 87.3% at the time of detection

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207003634	T78722	T787222022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T787222022

Publisher

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

Collation

xv, 855 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.650 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Sistem Komputer
, Jaringan komunikasih komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment