Deep learning has rapidly gained traction in medical imaging, particularly in computer-aided diagnosis (CAD), radiomics, and medical image analysis. The introduction of deep learning, especially convolutional neural networks (CNNs), has transformed the field. In 2012, a CNN-based deep learning approach achieved a significant victory in the ImageNet classification competition, marking the beginning of its widespread adoption. This has led to increased research and application in medical imaging, where deep learning directly uses images as input, bypassing traditional feature extraction and segmentation. Before deep learning, machine learning (ML) relied on feature-based approaches, where features were extracted from segmented images and used for classification. Deep learning, however, enables direct learning from images, making it more efficient and powerful. Two major deep learning models are the massive-training artificial neural network (MTANN) and CNN. Both have similarities and differences, with MTANNs often showing better performance and efficiency in medical imaging tasks. Deep learning in medical imaging is an emerging and promising field. It has applications in tasks such as lung nodule detection, polyp detection, and bone-soft tissue separation. The key advantage of deep learning is its ability to learn directly from images without prior feature extraction, making it more effective for complex medical imaging tasks. As deep learning continues to evolve, it is expected to become the mainstream approach in medical imaging over the next few decades.Deep learning has rapidly gained traction in medical imaging, particularly in computer-aided diagnosis (CAD), radiomics, and medical image analysis. The introduction of deep learning, especially convolutional neural networks (CNNs), has transformed the field. In 2012, a CNN-based deep learning approach achieved a significant victory in the ImageNet classification competition, marking the beginning of its widespread adoption. This has led to increased research and application in medical imaging, where deep learning directly uses images as input, bypassing traditional feature extraction and segmentation. Before deep learning, machine learning (ML) relied on feature-based approaches, where features were extracted from segmented images and used for classification. Deep learning, however, enables direct learning from images, making it more efficient and powerful. Two major deep learning models are the massive-training artificial neural network (MTANN) and CNN. Both have similarities and differences, with MTANNs often showing better performance and efficiency in medical imaging tasks. Deep learning in medical imaging is an emerging and promising field. It has applications in tasks such as lung nodule detection, polyp detection, and bone-soft tissue separation. The key advantage of deep learning is its ability to learn directly from images without prior feature extraction, making it more effective for complex medical imaging tasks. As deep learning continues to evolve, it is expected to become the mainstream approach in medical imaging over the next few decades.