Estimasi Fraksi Ejeksi Jantung Berbasis Unet Menggunakan Dataset 4D

Haryono, Nuzulul (2024) Estimasi Fraksi Ejeksi Jantung Berbasis Unet Menggunakan Dataset 4D. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5024201041-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until October 2026. Download (7MB) | Request a copy

Abstract

Fraksi Ejeksi (EF) merupakan salah satu parameter penting dalam bidang kardiologi yang mengukur persentase darah yang dipompa keluar dari ventrikel kiri jantung saat terjadi kon- traksi. Pengukuran EF memberikan informasi penting dalam diagnosis dan penanganan penyakit kardiovaskular, terutama gagal jantung. Nilai EF dihitung dari rasio antara volume diasto- lik akhir (End-Diastolic Volume/EDV) dan volume sistolik akhir (End-Systolic Volume/ESV). Penggunaan teknologi Machine Learning dari citra medis seperti Magnetic Resonance Imaging (MRI) dan ekokardiografi memungkinkan dilakukannya segmentasi ventrikel kiri secara akurat untuk mendapatkan nilai EDV dan ESV. Dalam penelitian ini, teknologi AI yang dimanfaatkan adalah metode Deep Learning dengan arsitektur U-net sebagai basis model prediksinya. Model tersebut diimplementasikan untuk proses segmentasi otomatis ventrikel kiri dari dataset publik citra medis jantung 4D.
=======================================================================================================================================
Ejection Fraction (EF) is a crucial cardiological parameter that measures the percentage of blood pumped out of the left ventricle of the heart during contraction. EF measurement provides vital information in the diagnosis and management of cardiovascular diseases, partic- ularly heart failure. The EF value is calculated as the ratio between the end-diastolic volume (EDV) and end-systolic volume (ESV). Medical imaging technologies like MRI and echocardio- graphy allow accurate segmentation of the left ventricle to obtain EDV and ESV. In this study, predictive models based on deep learning, such as U-Net, are used for automatic segmentation of the left ventricle in medical images.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	EF, U-Net, Segmentasi, Prediksi; EF, U-Net, Segmentation, Prediction
Subjects:	R Medicine > R Medicine (General) > R858 Deep Learning T Technology > T Technology (General) 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:	Nuzulul Rahmat Fauzi Haryono
Date Deposited:	01 Aug 2024 01:38
Last Modified:	09 Sep 2024 08:32
URI:	http://repository.its.ac.id/id/eprint/108907

Actions (login required)

View Item