

<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet type='text/xsl' href='/oai.xsl' ?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/"
	xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/
	http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
<responseDate>2026-07-22T08:20:38Z</responseDate>
<request verb="ListRecords" metadataPrefix="oai_dc" identifier="oai:publications.copernicus.org:acp30709">http:///OAfile/jner-1596271.</request>
	<ListRecords>
	<record>
	<header>
		<identifier>/OAfile/jner-1596271xsd</identifier>

		<datestamp>2026-01-01 </datestamp>
		<setSpec>acp</setSpec>
		</header>
		<metadata>
		<oai_dc:dc
			xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"
			xmlns:dc="http://purl.org/dc/elements/1.1/"
			xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
			xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/
			http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
			<dc:title><![CDATA[The Effect of Image Preprocessing Techniques on Pneumonia Detection from  Lung X-ray Images]]></dc:title>
			<dc:creator>YİĞİTBAŞ*,Enver</dc:creator>
			<dc:description><![CDATA[Early and accurate detection of pneumonia is of great importance, particularly in accelerating diagnostic processes and improving treatment success in the healthcare field. In this study, a pretrained MobileNetV2 deep learning model was used for the automatic classification of pneumonia using chest X-ray images. The model was configured using the transfer learning approach, and only the final classification layers were retrained. The training process was carried out for 20 epochs, allowing the model to benefit from the strong feature extraction capabilities of the pretrained architecture.
In order to improve model performance, image preprocessing techniques including CLAHE (Contrast Limited Adaptive Histogram Equalization), Histogram Equalization, and Image Sharpening were applied. These methods enhanced the contrast levels of chest X-ray images, made low-contrast regions more distinguishable, and enabled the model to learn more discriminative features.
The performances of the developed models were evaluated using accuracy, precision, recall, and F1-score metrics. In addition, confusion matrix analyses were performed to examine the classification results in detail. Experimental results showed that the highest performance was achieved using the Histogram Equalization preprocessing method, with an accuracy of 87.02% and an F1-score of 90.37%. In particular, the high recall values demonstrated that the developed system was highly successful in detecting pneumonia cases.
The chest X-ray dataset used in this study was obtained from the Kaggle platform, and the effects of transfer learning and image preprocessing techniques on medical image classification were comparatively analyzed. The obtained results indicate that image preprocessing methods can significantly improve the performance of deep learning-based pneumonia detection systems.
]]></dc:description>
			<dc:date>2026-01-01</dc:date>
			<dc:type>Text</dc:type>
			<dc:format>application/pdf</dc:format>
			<dc:identifier>-</dc:identifier>
			<dc:identifier>-</dc:identifier>
			<dc:source>-</dc:source>
			<dc:language>eng</dc:language>
		</oai_dc:dc>
	</metadata>
	</record>
</ListRecords>
</OAI-PMH>

