A novel transfer learning-based model for diagnosing malaria from parasitized and uninfected red blood cell images

Decision Analytics Journal, Journal Year: 2023, Volume and Issue: 9, P. 100352 - 100352

Published: Nov. 4, 2023

Malaria represents a potentially fatal communicable illness triggered by the Plasmodium parasite. This disease is transmitted to humans through bites of Anopheles mosquitoes that carry infection. has significant and devastating consequences on health systems fragile countries, particularly in sub-Saharan Africa. affects red blood cells invading replicating within them, destroying releasing toxic byproducts into bloodstream. The parasite's ability stick modify surface can cause them become sticky, obstructing flow vital organs such as brain spleen. Therefore, efficient approaches for early detection malaria are critical saving patients' lives. main aim this study develop an model diagnosis. We used images based parasitized uninfected experiments. applied neural network-based Neural Search Architecture Network (NASNet) compared its performance with machine learning techniques. Moreover, we proposed novel NNR (NASNet Random forest) method feature engineering. approach first extracts spatial features from input images, then class prediction probability extracted these features. set obtained data extraction trains models. Our comprehensive experiments show support vector outperformed state-of-the-art models, achieving high-performance score 99% having inference time near 0.025 s. validated using k-fold cross-validation optimized hyperparameters tuning. research improved diagnosis assist medical specialists reducing mortality rate.

Language: Английский

---

INTEGRATING AI INTO HEALTH INFORMATICS FOR ENHANCED PUBLIC HEALTH IN AFRICA: A COMPREHENSIVE REVIEW

International Medical Science Research Journal, Journal Year: 2023, Volume and Issue: 3(3), P. 127 - 144

Published: Dec. 13, 2023

This study delves into the integration of Artificial Intelligence (AI) within field health informatics and its transformative effect on public outcomes in Africa. It will cover how AI-driven solutions are being implemented to overcome challenges disease surveillance, healthcare delivery, policy. The paper aims provide an in-depth analysis current innovations, effectiveness these technological interventions, their broader implications for policy management across African continent. holds potential enhancing comprehensive review explores multifaceted applications, challenges, opportunities associated with convergence AI encompasses various domains, including diagnostics, treatment optimization, management. Key themes addressed include adoption technologies healthcare, impact detection monitoring, improving accessibility resource-constrained settings. Moreover, ethical considerations, regulatory disparities technology diverse regions examined, providing insights complexities implementing landscape. Through initiatives, case studies, emerging trends, this contribute a understanding integrating advancement Ultimately, exploration seeks inform policymakers, professionals, researchers critical role can play addressing continent fostering sustainable solutions. Keywords: Intelligence, Health Informatics, Management, Africa, Review, Disease Surveillance.

Language: Английский

---

VL-M2C: Leveraging deep learning approach for stage detection of malaria parasites

Journal of Integrated Science and Technology, Journal Year: 2025, Volume and Issue: 13(3)

Published: Jan. 7, 2025

Malaria is a parasitic infection that can be caused by the bite of infected anopheles' mosquito and progress from mild symptoms to severe forms which make it crucial understand its potential consequences. This study majorly focusses on multiclass classification provides an ensemble framework for detection stages malaria parasite in thin blood smears. In this we used publicly accessible dataset comprising 1320 images together with training test json file. Initially pre-processing applied improve image quality, then key regions are extracted retain important information during feature extraction phase. During compared different techniques find best model stages. Several metrics, including accuracy, recall, precision, loss, analyze performance model. study, method VL-M2C ie VGG LSTM Multiclass Classification has been proposed raises overall accuracy robustness considering advantages individual classifiers. It VGG16, CNN RCNN. Our (98.56%) lowest loss (0.1240), thus proves promising diagnosis system.

Language: Английский

---

Optimized deep transfer learning techniques for spine fracture detection using CT scan images

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 8, 2025

Language: Английский

---

Deep learning method for malaria parasite evaluation from microscopic blood smear

Artificial Intelligence in Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 103114 - 103114

Published: March 1, 2025

Language: Английский

---

Evrişimli Sinir Ağı (ESA) Mimarileri ile Hücre Görüntülerinden Sıtmanın Tespit Edilmesi

Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, Journal Year: 2024, Volume and Issue: 39(1), P. 197 - 210

Published: March 28, 2024

Sıtma, dünyanın birçok bölgesinde yaygın olarak görülen enfekte sivrisineklerin ısırıkları yoluyla insanlara bulaşan parazitlerin neden olduğu hayatı tehdit eden bir hastalıktır. Plasmodium adlı kan paraziti bu hastalığına sebep olmaktadır. Sıtmanın erken teşhisi ve tedavisi, özellikle hastalığın gelişmekte olan ülkelerde, hastalık ölüm oranlarının azaltılması açısından çok önemlidir. Sıtma teşhisinde kullanılan klasik yöntem, uzmanlar tarafından kırmızı hücrelerinin mikroskop yardımıyla incelenmesiyle tespitidir. Bu sadece uzmanın bilgi deneyimine dayandığı için verimsizdir. Günümüzde yüksek oranda doğru şekilde tespiti makine öğrenmesi yöntemleri kullanılmaktadır. çalışmada, hücreyi parazitli veya parazitsiz tespit Evrişimli Sinir Ağı (ESA) mimarisi önerilmiştir. Önerilen ESA mimarisine ek VGG-19, InceptionResNetV2, DenseNet121 EfficientNetB3 gibi önceden eğitilmiş mimarilerinin performansları ile önerdiğimiz modelin performansı karşılaştırılmıştır. Önerdiğimiz mimarisinde National Institute of Health (NIH) yayınlanan Veri Kümesi kullanılarak deneyler gerçekleştirilmiştir. Mimarimiz %98,9 doğruluk çalışmaktadır. Çalışmanın sonuçları, içeren hücre görüntülerinin doğruluğunu artırmada etkili olduğunu göstermektedir.

---

Deep-HPI-pred: An R-Shiny applet for network-based classification and prediction of Host-Pathogen protein-protein interactions

Computational and Structural Biotechnology Journal, Journal Year: 2023, Volume and Issue: 23, P. 316 - 329

Published: Dec. 15, 2023

Host-pathogen interactions (HPIs) are vital in numerous biological activities and intrinsically linked to the onset progression of infectious diseases. HPIs pivotal entire lifecycle diseases: from pathogen introduction, navigating through mechanisms that bypass host cellular defenses, its subsequent proliferation inside host. At heart these stages lies synergy proteins both pathogen. By understanding interlinking protein dynamics, we can gain crucial insights into how diseases progress pave way for stronger plant defenses swift formulation countermeasures. In framework current study, developed a web-based R/Shiny app, Deep-HPI-pred, uses network-driven feature learning method predict yet unmapped between proteins. Leveraging citrus

Language: Английский

---

The design of an efficient bioinspired CNN model for automated malaria detection in blood smear images

AIP conference proceedings, Journal Year: 2024, Volume and Issue: 3167, P. 030020 - 030020

Published: Jan. 1, 2024

Language: Английский

---

Implementation of Convolutional Neural Network Malarial Cells Detection

2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), Journal Year: 2024, Volume and Issue: 14, P. 1 - 6

Published: April 17, 2024

This paper proposes a Convolutional Neural Network (CNN) approach to analyze and detect the malarial parasite-infected blood smear cells. Malaria is fatal illness solely transmits through bites of infected female mosquitoes Anopheles.. Recent studies show that in 2020, there were 241 million cases malaria worldwide, which resulted death nearly 6,27,000 people. The diagnostic process must be automated avoid human participation during diagnosis because delayed or inaccurate causes most these deaths. To enhance reliability, deep-learning technologies CNN, such as medical image processing techniques, are employed assess parasitemia microscopic slides. In this research, we propose supervised learning-based Visual Geometry Group (VGG-19) performs accurate classification malaria-infected dataset comprises 27,560 images segmented cells, equally divided into parasitized (infected) uninfected utilized for VGG-19 architecture. first step define methods can used training model. next stage discusses techniques deep neural networks data augmentation increase size model's performance. Finally, accuracy outcomes compared from CNN using same datasets testing, validating phases. Our trained model uses samples predict presence malarial-infected cells achieves 97% rate.

Language: Английский

---

Malaria and Molecular Diagnosis

Published: July 4, 2024

It is an endemic vector-borne parasitic disease caused by protozoan parasites of the genus Plasmodium in tropical and subtropical regions worldwide. In each area, malaria transmitted a specific set Anopheles species. consists over 200 species, infecting mammals, birds, reptiles, generally tend to be host-specific. falciparum, vivax, malariae, ovale, knowlesi are five known species that causes humans. Of cause humans, P. falciparum severe malaria. vivax most widespread parasite globally. malariae least frequent pathogenic, causing mainly asymptomatic infections with submicroscopic parasitemia, leading low morbidity mortality, although it can occasionally evolve chronic renal disease. Different require distinct treatment regimens. Early accurate diagnosis specifically identify agent among all malarial thus crucial for correct control. Prompt key averting relies on access effective therapeutics. Several methods, such as microscopy-based analysis, rapid diagnostic test (RDT), serological molecular methods available diagnose Nucleic acid amplification tests (NAATs), which have advantages, high sensitivity processivity capacity drug-resistant strains, despite being more time consuming expensive than microscopy RDTs. PCR-based also ideal diagnosing mixed infections. However, PCR reliance electricity, costly reagents laboratory facilities sample preparation limited reference laboratories. To eliminate malaria, control prevention efforts necessary reduce prevalence limit development drug resistance parasite. This requires robust monitoring surveillance system. Vector surveillance, larvae vector important. Vaccines recently, use monoclonal antibodies needed Enhanced investigation spp. genetic variations will contribute successful future.

Language: Английский

---