SEGMENTASI DAN DETEKSI KELAINAN JANTUNG ANAK DENGAN PANDANGAN 4 CHAMBER VIEW

UTAMA, M. RIZKY ADITYA and Nurmaini, Siti (2022) SEGMENTASI DAN DETEKSI KELAINAN JANTUNG ANAK DENGAN PANDANGAN 4 CHAMBER VIEW. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281722030.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011281722030_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
Preview	Text RAMA_56201_09011281722030_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB) | Preview
	Text RAMA_56201_09011281722030_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (441kB) | Request a copy
	Text RAMA_56201_09011281722030_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (540kB) | Request a copy
	Text RAMA_56201_09011281722030_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281722030_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (89kB) | Request a copy
	Text RAMA_56201_09011281722030_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (161kB) | Request a copy
	Text RAMA_56201_09011281722030_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy

Abstract

Recently, Deep Learning-based approaches in the medical field have brought excellent performance in segmentation and object detection. In computer-based methods, image segmentation is a fundamental way to extract useful information from medical images. Object detection, as the core of the computer vision research problem, has attracted much attention from researchers. Research related to infant heart defects has not been commonly conducted because the data of infant heart medical images are very few to be accessed by many people. The data used is a infant heart ultrasonography video with a four chamber view. The data is converted into frames, annotations, and data augmentation before use. Convolutional Neural Network has been partially applied with promising results on various biomedical imaging problems. In medical image segmentation in recent years most of the credit goes to Unet. As for the case of object detection, Faster R-CNN is one of the best ways to detect objects. In the case of segmentation research conducted, the best model gets an IoU of 97.76 and DSC of 97.89. In the case of object detection, the feature extraction used is VGG16 and ResNet50. In the first detection case performed, the model using Resnet50 was better than VGG16. The model obtained a mAP of 95.67%. However, in the second detection case, the model using VGG16 was the best model with an mAP of 82.38%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Citra Medis, Ultrasonografi, Jantung Anak
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	M. Rizky Aditya Utama
Date Deposited:	23 Nov 2022 05:25
Last Modified:	23 Nov 2022 05:25
URI:	http://repository.unsri.ac.id/id/eprint/82555

Actions (login required)

View Item