Multi-branch CNNFormer: a novel framework for predicting prostate cancer response to hormonal therapy DOI Creative Commons

Ibrahim Abdelhalim,

Mohamed Badawy, Mohamed Abou El‐Ghar

et al.

BioMedical Engineering OnLine, Journal Year: 2024, Volume and Issue: 23(1)

Published: Dec. 23, 2024

This study aims to accurately predict the effects of hormonal therapy on prostate cancer (PC) lesions by integrating multi-modality magnetic resonance imaging (MRI) and clinical marker prostate-specific antigen (PSA). It addresses limitations Convolutional Neural Networks (CNNs) in capturing long-range spatial relations Vision Transformer (ViT)'s deficiency localization information due consecutive downsampling. The research question focuses improving PC response prediction accuracy combining both approaches. We propose a 3D multi-branch CNN (CNNFormer) model, ViT. Each branch model utilizes encode volumetric images into high-level feature representations, preserving detailed localization, while ViT extracts global salient features. framework was evaluated 39-individual patient cohort, stratified PSA biomarker status. Our achieved remarkable performance differentiating responders non-responders therapy, with an 97.50%, sensitivity 100%, specificity 95.83%. These results demonstrate effectiveness CNNFormer despite cohort's small size. findings emphasize framework's potential enhancing personalized treatment planning monitoring. By strengths ViT, proposed approach offers robust, accurate implications for decision-making.

Language: Английский

An innovative approach to advanced voice classification of sacred Quranic recitations through multimodal fusion DOI
Esraa Hassan, Abeer Saber, Omar Alqahtani

et al.

Egyptian Informatics Journal, Journal Year: 2025, Volume and Issue: 30, P. 100640 - 100640

Published: March 18, 2025

Language: Английский

Citations

0
Leveraging ensemble convolutional neural networks and metaheuristic strategies for advanced kidney disease screening and classification DOI Creative Commons
Abeer Saber,

Esraa Hassan,

Samar Elbedwehy

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 11, 2025

Abstract To address the public health issue of renal failure and global shortage nephrologists, an AI-based system has been developed to automatically identify kidney diseases. Recent advancements in machine learning, deep learning (DL), artificial intelligence (AI) have unlocked new possibilities healthcare. By harnessing these technologies, we can analyze data gain insights into symptoms patterns, ultimately facilitating remote patient care. create diagnosis for disease, this paper focused on three major categories diseases: stones, cysts, tumors, which were collected annotated 12,446 computed tomography (CT) whole abdomen urogram images. effectively aid automatic identification diseases, a novel DL model built transfer-learning (TL) technology is implemented work. models are designed focus problems, whereas TL uses knowledge acquired while resolving one another pertinent issue. The proposed combines multiple improve overall performance by leveraging strengths different architectures, ensembles enhance accuracy, robustness, generalization. It enhances features extracted from MobileNet-V2, ResNet50, EfficientNet-B0 networks using metaheuristic algorithms bidirectional long-short-term memory (Bi-LSTM) CT image. MobileNetV2, hyperparameters optimized modified grey wolf optimization (GWO) approach better performance. suggested model’s measured five assessment metrics: sensitivity, specificity, precision, area under ROC curve (AUC) achieved 99.85% 99.8% 99.3% 98.1% 1.0 AUC.

Language: Английский

Citations

0
Comparison of Classical EEG Source Analysis with Deep Learning DOI
Joab R. Winkler, Christian Uhl, Stefan Geißelsöder

et al.

Lecture notes in electrical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 258 - 267

Published: Jan. 1, 2025

Language: Английский

Citations

0
Enhanced Monkeypox Skin Lesion Classification Using Pooling-Based Vision Transformer Architecture DOI

Esraa Hassan,

Abeer Saber, Tamer Z. Emara

et al.

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 291 - 306

Published: March 28, 2025

Monkeypox is viral disease transmitted from animals to man and presents symptoms of smallpox especially rashes lesions on the skin. The recent mutation that has led human-to-human transmission caused international concern therefore enhanced method diagnosing required proved. In this part work, we bring forward a powerful approach for monkeypox classification with pooled-based vision transformer mode called as Pooling-based Vision Transformer (PiT) architecture merged MobileNetV3 trained Adam optimizer. By merging strengths both architectures can enhance representation power by integrating local global feature extraction. This hybrid significantly reduces computational load through techniques like token pooling, leading higher accuracy without proportional increase in costs. Lion optimizer employed model convergence response performance contrast other optimizers. For task, proposed was 94.23, 91, 93.5 90.75 % occupancy accuracy, precision, recall, F1 score.

Language: Английский

Citations

0
Optimized ensemble deep learning approach for accurate breast cancer diagnosis using transfer learning and grey wolf optimization DOI
Esraa Hassan, Abeer Saber, Shaker El–Sappagh

et al.

Evolving Systems, Journal Year: 2025, Volume and Issue: 16(2)

Published: April 29, 2025

Language: Английский

Citations

0
Toward precision cardiology: a transformer-based system for adaptive prediction of heart disease DOI
Fatma M. Talaat, W Aly

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: May 2, 2025

Language: Английский

Citations

0
Domain knowledge-infused pre-trained deep learning models for efficient white blood cell classification DOI Creative Commons

P Jeneessha,

B. Vinoth Kumar

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 4, 2025

Language: Английский

Citations

0
Adaptive Mish activation and ranger optimizer-based SEA-ResNet50 model with explainable AI for multiclass classification of COVID-19 chest X-ray images DOI Creative Commons

S. R. Sannasi Chakravarthy,

N. Bharanidharan,

C. Vinothini

et al.

BMC Medical Imaging, Journal Year: 2024, Volume and Issue: 24(1)

Published: Aug. 9, 2024

A recent global health crisis, COVID-19 is a significant crisis that has profoundly affected lifestyles. The detection of such diseases from similar thoracic anomalies using medical images challenging task. Thus, the requirement an end-to-end automated system vastly necessary in clinical treatments. In this way, work proposes Squeeze-and-Excitation Attention-based ResNet50 (SEA-ResNet50) model for detecting utilizing chest X-ray data. Here, idea lies improving residual units squeeze-and-excitation attention mechanism. For further enhancement, Ranger optimizer and adaptive Mish activation function are employed to improve feature learning SEA-ResNet50 model. evaluation, two publicly available radiographic datasets utilized. input augmented during experimentation robust evaluation against four output classes namely normal, pneumonia, lung opacity, COVID-19. Then comparative study done VGG-16, Xception, ResNet18, ResNet50, DenseNet121 architectures. proposed framework together with provided maximum classification accuracies 98.38% (multiclass) 99.29% (binary classification) as compared existing CNN method achieved highest Kappa validation scores 0.975 0.98 over others. Furthermore, visualization saliency maps abnormal regions represented explainable artificial intelligence (XAI) model, thereby enhancing interpretability disease diagnosis.

Language: Английский

Citations

2
Prostate cancer classification using adaptive swarm Intelligence based deep attention neural network DOI

D Sowmya,

Siriki Atchuta Bhavani,

V. V. S. Sasank

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 96, P. 106654 - 106654

Published: July 19, 2024

Language: Английский

Citations

1
Deep attention for enhanced OCT image analysis in clinical retinal diagnosis DOI Creative Commons
Fatma M. Talaat,

Ahmed Abd Al-Rahman Ali,

Raghda Shawky El-Gendy

et al.

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 19, 2024

Abstract Retinal illnesses such as age-related macular degeneration (AMD) and diabetic maculopathy pose serious risks to vision in the developed world. The diagnosis assessment of these disorders have undergone revolutionary change with development optical coherence tomography (OCT). This study proposes a novel method for improving clinical precision retinal disease by utilizing strength Attention-Based DenseNet, deep learning architecture attention processes. For model building evaluation, dataset 84495 high-resolution OCT images divided into NORMAL, CNV, DME, DRUSEN classes was used. Data augmentation techniques were employed enhance model's robustness. DenseNet achieved validation accuracy 0.9167 batch size 32 50 training epochs. discovery presents promising route more precise speedy identification illnesses, ultimately enhancing patient care outcomes settings integrating cutting-edge technology powerful neural network architectures.

Language: Английский

Citations

1