PERBANDINGAN METODE PENINGKATAN KUALITAS CITRA MEDIS HISTOPATOLOGI UNTUK KLASIFIKASI KANKER PARU

RAMADHAN, MUHAMMAD RIFQI and Fachrurrozi, Muhammad and Rachmatullah, Muhammad Naufal (2024) PERBANDINGAN METODE PENINGKATAN KUALITAS CITRA MEDIS HISTOPATOLOGI UNTUK KLASIFIKASI KANKER PARU. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021182025028.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182025028_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_01_front_ref.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (388kB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (244kB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (481kB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (485kB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (109kB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (78kB) | Request a copy
	Text RAMA_55201_09021182025028_0222058001_0001129204_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9kB) | Request a copy

Abstract

This study aims to enhance the dataset of lung cancer histopathological images. There is already exist CNN architecture for lung cancer classification, but only have accuracy of 71%. The dataset of lung cancer histopathological images suffers from poor color constancy and contrast due to variability in image capture, management, analysis, and data collection processes. To address these issues, this study implements image enhancement techniques, including Weighted Contrast-Limited Adaptive Histogram Equalization (WCLAHE), Reinhard’s Method, and Color Deconvolution Vectors (CDV) Multi Modal. These methods will be applied to the dataset to improve color constancy and contrast. The effectiveness of each method will be evaluated by comparing each Histogram Correlation, Entropy, PSNR, PCC, dan SSIM scores for each image enhancement method and the classification accuracy of the CNN architecture that has been developed using the enhanced images as the training dataset After the evaluation, the image dataset that has been enhanced achieved a high score and The CNN Models has 80%, 83%, and 83% accuracy respectively for WCLAHE, Reinhard’s Method, dan CDV Multi Modal image enhancement method.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Histopathological Images, Image Enhancement, Classification, CNN
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Rifqi Ramadhan
Date Deposited:	19 Aug 2024 02:58
Last Modified:	19 Aug 2024 02:58
URI:	http://repository.unsri.ac.id/id/eprint/155646

Actions (login required)

View Item