 This paper reviews deep learning techniques for medical image recognition, focusing on its potential for improving diagnostic accuracy and efficiency. It begins by discussing the characteristics and challenges of medical imaging, particularly those associated with MRI and CT scans. Next, it explores direct image processing methods, such as image enhancement and multimodal medical image fusion. Following this, it examines intelligent image recognition approaches tailored to specific anatomical structures. These approaches utilize various deep learning models and techniques, including CNNs, transfer learning, attention mechanisms, and cascading strategies. Additionally, it emphasizes the importance of neural network design in medical imaging, focusing on the extraction of multi-level features from U-shaped structures, dense connections, 3D convolution, and multimodal feature fusion. Finally, it identifies and addresses the key challenges in medical image recognition, such as data quality, model interpretability, generalizability, and computational resource requirements. In conclusion, this paper provides an extensive review of deep learning techniques for medical image recognition, highlighting their potential for improving diagnostic accuracy and efficiency. This article was authored by Hang Choi, Lee An-Hoo, and Ling Chi. We are article.tv, links in the description below.