Analysis of Acute Lymphoblastic Leukemia Detection Methods Using Deep Learning DOI
Pranavesh Kumar Talupuri,

Beebi Naseeba,

Nagendra Panini Challa

и другие.

Опубликована: Окт. 18, 2023

This research work puts forward a comparative study of four prominent deep learning models - ResNet, InceptionNet, MobileNet and EfficientNet — for the classification detection Acute Lymphoblastic Leukemia (ALL) from microscopic single blood cell images. Leukemia, critical hematological malignancy, demands accurate swift diagnosis to facilitate effective treatment. The advent has revolutionized medical image analysis, enabling automated efficient disease detection. In this work, we evaluate performance MobileNet, EfficientNet, all which have demonstrated exceptional capabilities in various computer vision tasks. proposed involves construction dataset containing diverse images, then undergoes preprocessing augmentation ensure model robustness generalization. Subsequently, architectures are implemented, pretrained on large-scale datasets, fine-tuned leukemia dataset. Training, validation, testing phases conducted under controlled experimental conditions. results reveal nuanced differences classification. evaluation metrics provide insights into their strengths limitations, helping guide selection based specific application requirements. clarifies how impact context analysis.

Язык: Английский

Comparative Analysis of Deep Learning Models for Multiclass Alzheimer’s Disease Classification DOI Creative Commons
Raghav Agarwal,

Abbaraju Sai Sathwik,

Deepthi Godavarthi

и другие.

EAI Endorsed Transactions on Pervasive Health and Technology, Год журнала: 2023, Номер 9

Опубликована: Ноя. 8, 2023

INTRODUCTION: The terrible neurological condition is known Worldwide; millions of individuals are affected with Alzheimer's disease (AD). Effective treatment and management AD depend on early detection a precise diagnosis. An effective method for identifying anatomical functional abnormalities in the brain linked to magnetic resonance imaging (MRI). OBJECTIVES: However, manual MRI scan interpretation requires lot time inconsistent between observers. automated analysis images identification diagnosis using deep learning techniques has shown promise. METHODS: In this paper, we present convolutional neural network (CNN)-based model automatically classifying (AD) healthy control group. A huge dataset scans was used train CNN, which distinguished groups excellent accuracy. RESULTS: Additionally, looked into how transfer may be enhance pre-trained models boost CNN performance. We discovered that considerably increased model's accuracy decreased overfitting. Our findings show precisely detect diagnose utilizing approaches machine learning. CONCLUSION: These improve efficiency enable identification, resulting better therapy.

Язык: Английский

Процитировано

5
Diabetic Retinopathy Classification Using Deep Learning DOI Creative Commons

Abbaraju Sai Sathwik,

Raghav Agarwal,

Ajith Jubilson E

и другие.

EAI Endorsed Transactions on Pervasive Health and Technology, Год журнала: 2023, Номер 9

Опубликована: Ноя. 8, 2023

One of the main causes adult blindness and a frequent consequence diabetes is diabetic retinopathy (DR). To avoid visual loss, DR must be promptly identified classified. In this article, we suggest an automated detection classification method based on deep learning applied to fundus pictures. The suggested technique uses transfer for classification. On dataset 3,662 images with real-world severity labels, trained validated our model. According findings, successfully detected classified overall accuracy 78.14%. Our model fared better than other recent cutting-edge techniques, illuminating promise learning-based strategies management. research indicates that may employed as screening tool in clinical environment, enabling early illness diagnosis prompt treatment.

Язык: Английский

Процитировано

4
White Blood Cells Classification using CNN DOI Creative Commons

Jinka Chandra Kiran,

Beebi Naseeba,

Abbaraju Sai Sathwik

и другие.

EAI Endorsed Transactions on Pervasive Health and Technology, Год журнала: 2024, Номер 9

Опубликована: Янв. 15, 2024

One kind of cancer that arises from an overabundance white blood cells produced by the patient's bone marrow and lymph nodes is leukaemia. Since are primary source immunity, or body's defence, it imperative to determine type leukocyte cell patient has leukaemia as soon possible. Failure do so could result in a more serious condition. Haematologists typically use light microscope examine necessary traces order classify identify features cytoplasm nucleus diagnose patient. form leukaemia, which develops when produce excessive amount cells. It vital possible because postponing diagnosis can worsen situation. Our corpuscles defence. In define found nucleus, hematopathologists patients.

Язык: Английский

Процитировано

0
Cardiovascular Disease Prediction Using Deep Learning DOI

Vaneet Khanna

2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Год журнала: 2024, Номер 17, С. 1 - 6

Опубликована: Март 14, 2024

Cardiovascular disease (CVD), ahead of all other causes death worldwide in this era. There is an immediate need for accurate, reliable, and practically applicable ways early detection treatment diseases, it connects a number hazards cardiovascular disease. One common method analyzing massive amounts historical information healthcare data extraction. To assist physicians with CVD prediction, they employ mining deep learning (DL) techniques to navigate complex medical data. This review paper critically examines the application predicting emphasizing collection, preprocessing, model selection, performance metrics, challenges. The data-driven nature DL models allows analysis diverse patient information, contributing more accurate risk assessments. achieves by discussing challenges limitations, importance collaborative efforts connect DL's potential enhancing prediction improving outcomes.

Язык: Английский

Процитировано

0
Edge-based Heart Disease Prediction using Federated Learning DOI

Ancy Jenifer. J,

Getzi Jeba Leelipushpam Paulraj,

Gladston Rosario M

и другие.

Опубликована: Апрель 17, 2024

Cardiovascular diseases are one of major causes for death globally. Prediction these becomes a bit complex in the fields like clinical analysis. It is observed that over many millions deaths recorded because heart disease. And it ratio four five cardiovascular due to failure. In recent times making decisions and predictions from large amount medical data produced healthcare industries, machine learning being effectively used. Despite hype, still existing based disease detection methods need their be present centralized place. Since hospital, there various privacy security concerns needed considered hence impossible collect all store place centrally. So, with this problem statement, research work aims implement federated approach train model. A shared model makes its averaging algorithm perform aggregates local updates clients along edge device ensures security. The results indicate proposed has achieved 93.4% accuracy levels by integrating LASSO feature selection algorithm.

Язык: Английский

Процитировано

0
Myocardial Infarction Diagnosis: Pattern Analysis of ECG Report Images Using Machine Learning Techniques DOI

B S Raghukumar,

B Naveen

Опубликована: Апрель 26, 2024

The ECG machine data is utilized to diagnose cardiac conditions, specifically focusing on identifying myocardial infarction rates by analyzing pattern variations within report images. Variations in the output of electrodes 2 and 3 are noted as indicative a heart attack. authors employ various image processing techniques like thresholding, contrast enhancement learning methods SVM, GBC, k-neighbors process these patterns, aiming enhance accuracy. After extracting four features, most effective classifiers employed, with Gradient Boosting Classifier (GBC) set features exhibiting highest accuracy at 76.60%. This paper emphasizes preprocessing crucial for obtaining structured refined data, facilitating better feature selection extraction from graph It underscores distinctive aid rate prediction. evaluates several machines classifiers, highlighting their efficiency simplifying expediting diagnosis process. Furthermore, research suggests that incorporating additional could potentially improve

Язык: Английский

Процитировано

0
Forecasting the Risk of Heart Disease Using Recurrent Neural Network DOI

Althaph Bollapalli,

Nagendra Panini Challa

Опубликована: Май 2, 2024

Язык: Английский

Процитировано

0
Revolutionizing Cardiovascular Attack Prediction: A Comprehensive Machine Learning Approach for Accurate and Timely Detection DOI

S. Durai,

D. Jaganathan,

Vittaldas V. Prabhu

и другие.

Опубликована: Апрель 18, 2024

Язык: Английский

Процитировано

0
Analysis of Acute Lymphoblastic Leukemia Detection Methods Using Deep Learning DOI
Pranavesh Kumar Talupuri,

Beebi Naseeba,

Nagendra Panini Challa

и другие.

Опубликована: Окт. 18, 2023

This research work puts forward a comparative study of four prominent deep learning models - ResNet, InceptionNet, MobileNet and EfficientNet — for the classification detection Acute Lymphoblastic Leukemia (ALL) from microscopic single blood cell images. Leukemia, critical hematological malignancy, demands accurate swift diagnosis to facilitate effective treatment. The advent has revolutionized medical image analysis, enabling automated efficient disease detection. In this work, we evaluate performance MobileNet, EfficientNet, all which have demonstrated exceptional capabilities in various computer vision tasks. proposed involves construction dataset containing diverse images, then undergoes preprocessing augmentation ensure model robustness generalization. Subsequently, architectures are implemented, pretrained on large-scale datasets, fine-tuned leukemia dataset. Training, validation, testing phases conducted under controlled experimental conditions. results reveal nuanced differences classification. evaluation metrics provide insights into their strengths limitations, helping guide selection based specific application requirements. clarifies how impact context analysis.

Язык: Английский

Процитировано

1