Yapay Sinir Ağı Tabanlı Model ile X-ray Görüntülerinden Covid-19 Teşhisi

Pneumonia Detection from Pediatric Lung X-Ray Images Using Artificial Neural Networks ABSTRACT Studies on medical imaging have grown significantly in recent years. Doctors have a crucial convenience for diagnosis thanks to semi- or fully automatic region recognition in medical imaging. It is crucial to support treatment without a specialist doctor, particularly in those nations where there is a dearth of such medical professionals. The little air sacs known as alveoli are most impacted by pneumonia, a lung inflammation. A key component of providing the right therapy conditions to heal patients and reduce harm while eradicating inflammation is early detection and precise diagnosis. Noise and blurring in patient photos obtained from X-ray machines are cleaned using deep learning algorithms and image processing techniques, and they are very helpful in. In this study, we studied chest X-ray images of pediatric patients with pneumonia and healthy individuals. XGBoost (eXtreme gradient boosting) is an innovative machine learning algorithm based on decision tree and using gradient boosting in its computations. It achieved 97.01% success with high classification performance. Keywords: Medical imaging, Machine learning, Pediatric Chest X-ray

Section: Introductionmentioning

confidence: 99%

Pneumonia Detection from Pediatric Lung X-Ray Images Using Artificial Neural Networks

Dündar,

Koçer

2024

“…Nowadays, methods that provide early diagnosis of besides important cancer diseases [16] and infections caused by viruses and bacteria are gaining importance day by day. Ataş et al and Eren et al the diagnostic systems they developed also contributed to new methods used in the detection of viruses [17,18].Investigators are consistently looking forward to developing new biosensing mechanisms to detect bacteria. Regarding that, biosensing technologies are developing day by day as an alternative to conventional methods for the detection of MRSA.…”

Section: Introductionmentioning

confidence: 99%

Detection of Methicillin-Resistant Staphylococcus Aureus Bacteria Using Liquid Crystals

Kemiklioğlu¹,

Tuncgovde²

2023

Methicillin-resistant Staphylococcus aureus (MRSA) is an essential pathogen for public health and this bacteria commonly cause serious infectious in humans. In recent years, MRSA bacteria are detected by the bacterial culture and nucleic acid-based methods which are time-consuming and labor-intensive. In this study, a novel liquid crystal (LC)-based biosensing system was developed to overcome these limitations. The objective of this study was to detect the presence of MRSA bacteria which prepared within the isotonic water and phosphate buffer saline (PBS). In this system, the binding of MRSA bacteria to the dimethyloctadecyl [3-(trimethoxysilyl) propyl] ammonium chloride (DMOAP)-coated surface disrupted the orientation of LCs, triggering a transition from a homeotropic orientation to a random one. This transition in the orientation of the LCs was observed as a change from a dark optical LC image to a bright one under a polarized light microscope (POM) and the reflection values of LC molecules were determined by using a spectrometer. Through this sensing mechanism, MRSA bacteria prepared within the isotonic water was detected ranging from the 9.2x10 3 CFU/mL to 9.2x10 7 CFU/mL concentration. Furthermore, MRSA bacteria prepared in PBS was detected in the concentration range of 7.1x10 4 CFU/mL to 7.1x10 8 CFU/mL by using this system.

Glakom ve Katarakt Hastalığının Derin Öğrenme Modelleri ile Teşhisi

Tümay,

Civelek,

Teke

2024

Göz, insanoğlunun en önemli organlarından biri olmasına rağmen birçok hastalığa da maruz kalabilmektedir. Bu hastalıklardan bazılarına toplumda sıklıkla rastlanmaktadır. Bunlardan ikisi katarakt ve glakom olarak bilinen çok önemli göz hastalıklarıdır. Evrişimli Sinir Ağları (ESA), bu hastalıkların erken tanı ve uzman teşhisine yardımcı olmak için kullanılabilir. Bu çalışmada derin öğrenme yöntemlerinden biri olan Evrişimli Sinir Ağları kullanılarak katarakt, glakom ve normal göz dibi görüntüleri sınıflandırılmıştır. Eğitilmiş Ağlar kullanılarak Googlenet, Densenet-201, Xception ve Inception-V3 ağlarının performansları karşılaştırılmıştır. Her ağ için adam, rmsprop ve sgdm optimizasyon yöntemleri uygulanmıştır. Bu çalışma, datasetteki 262 Katarakt, 200 Glakom ve 2816 normal göz dibi görüntüsü kullanılarak yapılmıştır. Görüntüler, yeniden boyutlandırma, arka planı kaldırma, rastgele döndürme ve yeniden boyutlandırma ile önceden işlenmiştir. Matlab ortamında yapılan simülasyonlar sonucunda, diğer ağlara göre en iyi sonuçlar rmsprop optimizasyonlu Xception ağ mimarisi ile elde edilmiştir.