Segmentasi Atrium Kiri pada Citra MRI Jantung Menggunakan Arsitektur Unet2D. (Left Atrium Segmentation in Cardiac MRI Images Using Unet2D Architecture).

Subaktiar, Dion (2024) Segmentasi Atrium Kiri pada Citra MRI Jantung Menggunakan Arsitektur Unet2D. (Left Atrium Segmentation in Cardiac MRI Images Using Unet2D Architecture). Undergraduate thesis, Universitas 17 Agustus 1945 Surabaya.

	Text Abstrak.pdf Download (5MB)
	Text bab1.pdf Restricted to Repository staff only Download (172kB)
	Text bab2.pdf Restricted to Repository staff only Download (669kB)
	Text bab3.pdf Restricted to Repository staff only Download (322kB)
	Text bab4.pdf Restricted to Repository staff only Download (7MB)
	Text bab5.pdf Restricted to Repository staff only Download (84kB)
	Text Daftar Pustaka.pdf Restricted to Repository staff only Download (859kB)
	Text Surat Keterangan Pengalihan Publikasi.pdf Download (2MB)
	Text Jurnal Ilmiah.pdf Restricted to Repository staff only Download (316kB)
	Text Jurnal Turnitin.pdf Restricted to Repository staff only Download (754kB)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Download (0B)
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Restricted to Repository staff only Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B)
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B)

Abstract

The cardiovascular system is an important system for the human body which, if damaged and not checked, can cause disease complications. However, the use of Computed Tomography (CT) is considered inadequate in terms of displaying delicate organs in the cardiovascular system. MRI imaging has proven effective in displaying delicate organs, thereby facilitating the segmentation process of the cardiovascular system. With various classification methods such as Convolutional Neural Network (CNN), this research uses the -Net architecture for cardiac MRI image segmentation. Through careful pre-processing and training the model with a dataset enriched through data augmentation, this research succeeded in improving the accuracy in separating anatomical structures in CMR images of the heart. These findings could have a positive impact on diagnostics and medical research related to heart health, enabling more precise and efficient identification of cardiovascular conditions. This research also emphasizes that pre-processing and the amount of data greatly influence segmentation results. Both in terms of image size and number of epochs, these two factors play an important role in determining segmentation quality. Pre-processing steps such as normalization, noise reduction, edge detection, and contrast stretching can help in optimally preparing data for model training. The best results were obtained with a variable image size of 256px and through preprocessing and model training for 250 epochs, producing an average dice score of 0.8197. This shows that selecting the right preprocessing will be able to improve the performance of segmentation results.

Actions (login required)

View Item