MEDICAL IMAGING ENHANCEMENT WITH AI MODELS FOR AUTOMATIC DISEASE DETECTION AND CLASSIFICATION BASED ON MEDICAL IMAGES

Abstract

The development of artificial intelligence (AI) in the healthcare industry has recently been of utmost importance. Early discovery, diagnosis, categorization, analysis, and treatment options are always positive medical breakthroughs. In making diagnoses and strategic decisions for healthcare, precise and consistent picture classification is essential. The semantic gap has emerged as the main problem with picture sorting. To bridge the gap, traditional machine learning techniques for classification mainly depend on low-level features rather than high-level ones, use some hand-crafted features, but compel intensive feature extraction and classification procedures. Deep convolution neural networks (CNNs), a potent technique that has significantly advanced in recent years, are successful in classifying images. A thorough assessment of pertinent studies is required to further assist readers in understanding the research and its main concepts captured. This study highlights the various AI models for automatic disease detection and classification based on medical images. This can include identifying tumors, lesions, fractures, or other abnormalities. The models discussed in this article include Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), One-Class Learning Models, Recurrent Neural Networks (RNNs), and 3D and Multimodal Models. Since these models work with various modalities, there are numerous instances where computed tomography (CT), positron emission computed tomography (PET), X-ray, magnetic resonance imaging (MRI), and ultrasound (US). Are mentioned to help complement the research.