Brain tumor diagnosis in MRI scans images using Residual/Shuffle Network optimized by augmented Falcon Finch optimization DOI Creative Commons

Xiaohang Guo,

Tianyi Liu, Qinglong Chi

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 13, 2024

Brain tumor diagnosis is an important task in prognosing and treatment planning of the patients with brain cancer. meantime, using Magnetic Resonance Imaging (MRI) as a commonly used non-invasive imaging technique provide experts helpful view for detecting tumors. While deep learning methods have shown significant success analyzing medical images, they often require careful design architecture tuning hyperparameters to achieve optimal results. This study presents new approach diagnosing tumors MRI scans learning, focusing on Residual/Shuffle Networks. The designed network structures offer efficient results when compared traditional models. To enhance proposed classification, modified metaheuristic algorithm named Augmented Falcon Finch Optimization (AFFO) introduced. AFFO utilizes bio-inspired principles effectively search best hyperparameter configurations, thereby enhancing reliability accuracy model. performance method evaluated standard dataset existing techniques, including ResNet, AlexNet, VGG-16, Inception V3, U-Net illustrate effectiveness combining Networks diagnosis.

Язык: Английский

Integrating Metal–Phenolic Networks-Mediated Separation and Machine Learning-Aided Surface-Enhanced Raman Spectroscopy for Accurate Nanoplastics Quantification and Classification DOI
Haoxin Ye, Shiyu Jiang,

Yan Yan

и другие.

ACS Nano, Год журнала: 2024, Номер unknown

Опубликована: Сен. 16, 2024

Increasing accumulation of nanoplastics across ecosystems poses a significant threat to both terrestrial and aquatic life. Surface-enhanced Raman scattering (SERS) is an emerging technique used for detection. However, the identification classification using SERS faces challenges regarding sensitivity accuracy as are sparsely dispersed in environment. Metal-phenolic networks (MPNs) have potential rapidly concentrate separate various types sizes nanoplastics. combined with machine learning may improve prediction accuracy. Herein, we report integration MPNs-mediated separation learning-aided methods accurate high-precision quantification nanoplastics, which tailored include complete region characteristic peaks diverse contrast traditional manual analysis spectra on singular peak. Our customized system (e.g., outlier detection, classification, quantification) allows detectable (accuracy 81.84%), > 97%), sensitive (polystyrene (PS), poly(methyl methacrylate) (PMMA), polyethylene (PE), poly(lactic acid) (PLA)) down ultralow concentrations (0.1 ppm) well 92%) nanoplastic mixtures at subppm level. The effectiveness this approach substantiated by its ability discern between different detect samples natural water systems.

Язык: Английский

Процитировано

6
A hybrid multi-optimizer approach using CNN and GB for accurate prediction of citrus fruit diseases DOI Creative Commons

Lawrence Kujur,

V. B. Gupta, Abhinav Singhal

и другие.

Deleted Journal, Год журнала: 2025, Номер 7(3)

Опубликована: Фев. 18, 2025

Язык: Английский

Процитировано

0
VNLU-Net: Visual Network with Lightweight Union-net for Acute Myeloid Leukemia Detection on Heterogeneous Dataset DOI

Rabul Saikia,

Roopam Deka,

Anupam Sarma

и другие.

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 107, С. 107840 - 107840

Опубликована: Март 29, 2025

Язык: Английский

Процитировано

0
Addressing cross-population domain shift in chest X-ray classification through supervised adversarial domain adaptation DOI Creative Commons
Ramli Musa, Rajesh S. Prasad,

Monica Hernandez

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 3, 2025

Язык: Английский

Процитировано

0
Improving human detection in the presence of cartoon characters using retrained deep learning models DOI
Wei King Tiong, Yan Chai Hum, Ying Loong Lee

и другие.

Signal Image and Video Processing, Год журнала: 2025, Номер 19(6)

Опубликована: Апрель 2, 2025

Язык: Английский

Процитировано

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

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 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.

Язык: Английский

Процитировано

0
Transformer-inspired training principles based breast cancer prediction: combining EfficientNetB0 and ResNet50 DOI Creative Commons
Tariq Shahzad, Tehseen Mazhar, Sheikh Muhammad Saqib

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 18, 2025

Язык: Английский

Процитировано

0
Advancing Breast Cancer Diagnosis: Integrating Deep Transfer Learning and U-Net Segmentation for Precise Classification and Delineation of Ultrasound Images DOI Creative Commons
Divine Senanu Ametefe, Dah John,

Abdulmalik Adozuka Aliu

и другие.

Results in Engineering, Год журнала: 2025, Номер unknown, С. 105047 - 105047

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Renewable energy forecasting using optimized quantum temporal model based on Ninja optimization algorithm DOI Creative Commons

Mona Ahmed Yassen,

El-Sayed M. El-kenawy,

Mohamed S. Abdelfattah

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 27, 2025

Abstract Artificial intelligence allows improvements in renewable energy systems by increasing efficiency while enhancing reliability and reducing costs. Renewable forecasting receives substantial improvement applying deep learning methods as one of its promising approaches. The research utilizes QTM with NiOA optimization for achieving maximum performance. functions through critical processes when models high accuracy large complex datasets selecting the most appropriate features. Fundamental data preparation steps, including normalization scaling, gap handling, play a vital role before using input reliable operations. Using Ninja binary engine produces superior results than all tested algorithms, SBO, bSCA, bFA, bGA, bFEP, bGSA, bDE, bTSH bBA, resulting enhanced classification accuracy. capability bNinja to choose optimal features establishes usefulness applications. Experimental implementation revealed that incorporating Optimization Algorithm model delivered best R 2 performance at 95.15% an exceptional RMSE value 0.00003, thus establishing ability optimize

Язык: Английский

Процитировано

0
The Intersection of AI, Cloud Computing, and Healthcare DOI
Wael A. Awad, Amena Mahmoud

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 379 - 404

Опубликована: Март 28, 2025

The convergence of Artificial Intelligence (AI) and Cloud Computing has ushered in a new era innovation across various industries, including healthcare. AI, with its ability to analyze vast datasets, identify patterns, make intelligent decisions, offers transformative potential for improving patient outcomes enhancing healthcare efficiency. Computing, on the other hand, provides scalable flexible infrastructure storing, processing, accessing data, enabling seamless collaboration among professionals development innovative applications. This overview presents comprehensive intersection AI healthcare, exploring their applications, benefits, challenges, ethical considerations. survey will delve into aspects cloud computing adoption usage, challenges opportunities, future trends, expectations.

Язык: Английский

Процитировано

0