Segmentasi Jantung Pada Citra Short-Axis View Magnetic Resonance Imaging Menggunakan 2D U-Net

Nindita, Nabil Virio Akhsan (2024) Segmentasi Jantung Pada Citra Short-Axis View Magnetic Resonance Imaging Menggunakan 2D U-Net. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5024201060-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (23MB) | Request a copy

Abstract

Penyakit kardiovaskular merupakan masalah kesehatan yang signifikan secara global, menyebabkan banyak kematian, terutama disebabkan oleh penyakit jantung. Diagnosis penyakit jantung yang akurat dan tepat waktu sangat penting untuk pengobatan yang efektif. Adanya kemajuan teknologi medis telah meningkatkan pemahaman dan pengambilan tindakan terhadap penyakit tersebut. Penelitian ini berfokus pada segmentasi struktur jantung pada citra Short Axis Magnetic Resonance Imaging ( SAX MRI) menggunakan model deep learning dengan arsitektur U-Net 2D. Tujuan utama dari penelitian ini adalah untuk mengembangkan model deep learning yang dapat mensegmentasi struktur jantung, yaitu ventrikel kiri (LV), ventrikel kanan (RV), dan miokardium. Penelitian ini menggunakan dataset Automated Cardiac Diagnosis Challenge (ACDC) 2017, yang mencakup pemindaian MRI dari 150 pasien dengan berbagai kondisi jantung. Model segmentasi berbasis U-Net 2D yang diusulkan diharapkan menghasilkan akurasi tinggi, sehingga berpotensi untuk memberi manfaat bagi penanganan penyakit jantung. Berdasarkan pengujian yang telah dilakukan dari skenario-skenario penelitian didapatkan hasil Dice dan IoU Score oleh model sebesar 0,8806 dan 0,7663.
=================================================================================================================================
Segmentasi Cardiovascular disease is a significant health problem globally, causing many deaths , mainly caused by heart disease. Accurate and timely diagnosis of heart disease is essential for effective treatment. Advances in medical technology have improved the understanding and treatment of these diseases. This research focuses on segmenting cardiac structures in Short Axis Magnetic Resonance Imaging (SAX MRI) images using deep learning model with 2D U-Net architecture. The main objective of this research is to develop a deep learning model that can segment the heart structures, namely the left ventricle (LV), right ventricle (RV), and myocardium. This study uses the Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset, which includes MRI scans of 150 patients with various heart conditions. The proposed 2D U-Net-based segmentation model is expected to yield high accuracy, potentially benefiting the treatment of heart disease. Based on the tests that have been carried out from the scenarios of this research the Dice and IoU Score results obtained by the model are 0,8806 and 0,7663.Jantung Pada Citra Short-Axis View Magnetic Resonance Imaging Menggunakan 2d U-Net

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Segmentasi, Jantung, MRI, 2D U-Net,Segmentation,Cardiac
Subjects:	R Medicine > R Medicine (General) > R858 Deep Learning R Medicine > RC Internal medicine > RC78.7.N83 Magnetic resonance imaging. T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Nabil Virio Akhsan Nindita
Date Deposited:	25 Jul 2024 01:43
Last Modified:	25 Jul 2024 01:43
URI:	http://repository.its.ac.id/id/eprint/108687

Actions (login required)

View Item