Wahyuningtyas (2020) Identifikasi Noise MRI Brain Image Dengan Metode Radial Basis Function (RBF). Skripsi thesis, UNIVERSITAS AIRLANGGA.

	Text (HALAMAN JUDUL) 1. HALAMAN JUDUL.pdf Download (352kB)
	Text (ABSTRAK) 2. ABSTRAK.pdf Download (118kB)
	Text (DAFTAR ISI) 3. DAFTAR ISI.pdf Download (229kB)
	Text (BAB I) 4. BAB I PENDAHULUAN.pdf Download (334kB)
	Text (BAB II) 5. BAB II TINJAUAN PUSTAKA.pdf Restricted to Registered users only until 8 January 2024. Download (917kB) | Request a copy
	Text (BAB III) 6. BAB III METODOLOGI PENELITIAN.pdf Restricted to Registered users only until 8 January 2024. Download (601kB) | Request a copy
	Text (BAB IV) 7. BAB IV HASIL DAN PEMBAHASAN.pdf Restricted to Registered users only until 8 January 2024. Download (477kB) | Request a copy
	Text (BAB V) 8. BAB V KESIMPULAN DAN SARAN.pdf Restricted to Registered users only until 8 January 2024. Download (198kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9. DAFTAR PUSTAKA.pdf Download (258kB)
	Text (LAMPIRAN) 10. LAMPIRAN.pdf Restricted to Registered users only until 8 January 2024. Download (726kB) | Request a copy
	Text (PERNYATAAN KESEDIAAN PUBLIKASI) 11. PERNYATAAN KESEDIAAN PUBLIKASI.pdf Restricted to Registered users only Download (205kB) | Request a copy

Abstract

Noise is an unwanted component because it disturbs an image. In the medical field, the image of an MRI can also be exposed to noise as in the MRI image of the Brain. Noise causes the image quality to deteriorate and disrupt important parts of the body which will be translated by medical images. Therefore this study aims to develop computational methods to identify noise in MRI brain images according to its type, namely Gaussian Noise, Salt & Pepper Noise, and noise speckle. The first order histogram feature extraction method is used to get the mean, entropy, variance, skewness, and kurtosis feature values from MRI Brain images. These five features are used as input for the classification system using the Radial Base Function method. The training data used consisted of 180 images and 40 T2 FLAIR sequences and T2 FFE sequences for the test data. The highest accuracy results on hidden layer 9 and the 5th k-fold cross-validation at the training stage were 89.4%. Test Results for FLAIR T2 sequences 15% Gaussian noise and 85% salt & Pepper noise images, whereas for T2 FFE sequences the percentage produced by the Radial Basis network testing is 15% Gaussian noise images, 25% of images have Speckle noise and 60% of imagery brunoise Salt & Pepper.

Item Type:	Thesis (Skripsi)
Additional Information:	KKC KK MPF. 33-20 Wah i
Uncontrolled Keywords:	Noise Identification, Radial Basis Function, MRI Brain Image
Subjects:	Q Science > QD Chemistry > QD450-801 Physical and theoretical chemistry
Divisions:	08. Fakultas Sains dan Teknologi > Fisika
Creators:	Creators NIM Wahyuningtyas NIM081611333087
Contributors:	Contribution Name NIDN / NIDK Thesis advisor Endah Purwanti NIDN0031107705 Thesis advisor Khusnul Ain NIDN0005077203
Depositing User:	Tatik Poedjijarti
Date Deposited:	08 Jan 2021 00:41
Last Modified:	08 Jan 2021 00:41
URI:	http://repository.unair.ac.id/id/eprint/102709
Sosial Share:

Actions (login required)

View Item