Segmentasi Fissura Paru pada Gambar CT-SCAN 2D Menggunakan Arsitektur U-Net. (Lung Fissure Segmentation On 2D CT-SCAN Images Using U-NET Architecture).

Lutvianata, Yuan (2024) Segmentasi Fissura Paru pada Gambar CT-SCAN 2D Menggunakan Arsitektur U-Net. (Lung Fissure Segmentation On 2D CT-SCAN Images Using U-NET Architecture). Undergraduate thesis, Universitas 17 Agustus 1945 Surabaya.

	Text ABSTRAK.pdf Download (876kB)
	Text BAB I.pdf Restricted to Repository staff only Download (214kB) | Request a copy
	Text BAB II.pdf Restricted to Repository staff only Download (514kB) | Request a copy
	Text BAB III.pdf Restricted to Repository staff only Download (360kB) | Request a copy
	Text BAB IV.pdf Restricted to Repository staff only Download (1MB) | Request a copy
	Text BAB V.pdf Restricted to Repository staff only Download (214kB) | Request a copy
	Text Surat ahli publikasi.pdf Download (256kB)
	Text JURNAL.pdf Restricted to Repository staff only Download (1MB) | Request a copy
	Text JURNAL_TURNITIN.pdf Restricted to Repository staff only Download (3MB) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_lightbox) lightbox.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_preview) preview.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_medium) medium.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Thumbnails conversion from text to thumbnail_small) small.jpg Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy
	Other (Generate index codes conversion from text to indexcodes) indexcodes.txt Restricted to Repository staff only Download (0B) | Request a copy

Abstract

Pulmonary fissures are the boundaries between lobes in the lungs, playing an important role in respiratory anatomy and function. Segmentation of pulmonary fissures in computed tomography (CT) images is critical for the assessment of pulmonary diseases such as chronic obstructive pulmonary disease (COPD) and COVID-19. In this research, we processed the dataset from a 3D dataset, then selected slices that only showed the lung fissures and then labeled them using an image labeler. In this study, five segmentation experiments were also carried out using the Unet model and using Hessian, with various methods: the first experiment used all images, the second experiment converted into two classes, the third experiment without lung limits, and the fourth experiment used preprocessing. The results show that preprocessing provides the highest Intersection over Union (IOU) value of 0.55884, while using all images produces an IOU of 0.54255. Removal of lung boundaries reduces the IOU to 0.40996, indicating the importance of lung boundary information. Converting to two classes results in an IOU of 0.53887. These results show that preprocessing improve model performance, providing promise in helping diagnose lung diseases more accurately and efficiently. This fifth experiment compares segmentation without deep learning, namely the Hessian method, producing clearly visible fissure output, producing an IOU of 0.0589 or 5.89%.

Actions (login required)

View Item