Artificial Intelligence in Biomedical Engineering: A Comprehensive Study

AbstractThis study investigates the application of artificial intelligence (AI) in biomedical engineering, focusing on deep learning techniques to improve diagnostic accuracy in medical imaging. Assumptions include the superiority of convolutional neural networks (CNNs) over traditional machine learning methods in classifying biomedical images. Materials consist of multiple publicly available medical imaging datasets, including mammography, brain MRI, and chest X-rays. Methods involve implementing and comparing various CNN architectures (VGG۱۶, ResNet۵۰, InceptionV۳) with classical classifiers (SVM, Random Forest, k-NN). Transfer learning and data augmentation techniques were employed to enhance model generalization. Results show CNN models outperform traditional methods significantly, achieving up to ۹۲.۵% accuracy in breast cancer detection and comparable improvements in brain tumor and chest disease classification. These findings highlight the potential of AI to assist clinical diagnostics effectively.

کلیدواژه ها:

Artificial Intelligence ، Biomedical Engineering ، Deep Learning ، Medical Imaging ، Convolutional Neural Networks