Medical CT image amplification and reconstruction system based on deep learning

Image processing is a widely concerned and challenging subject. Medical imaging is an important means and tool in modern medical observation, and has become one of the fastest developing technical fields, widely used in diagnosis and treatment. Medical image processing is a very important part of the medical image technology. It can effectively process medical images, realize the extraction of pathological features, and improve the utilization rate of medical image information. At the same time, it is helpful for doctors to observe the lesion site more directly and specifically in the diagnosis process, and improve the diagnosis rate of the disease. According to the actual application requirements, under the condition of the existing hardware equipment in the hospital, some practical and efficient algorithms are selected from the existing image processing algorithms for optimization, self-built database, and through deep learning. A set of medical CT image amplification and reconstruction system is designed. SRGAN (Super-Resolution Generative Adversarial Networks) algorithm is used in the system and the medical CT image super-resolution reconstruction is completed. SRGAN consists of a denerator and a discriminator. The generator is responsible for synthesizing the high-resolution images, and the discriminator is used to determine whether a given image is from the generator or a real sample. The generator can reconstruct a given low resolution image into a high resolution image through a game confrontation process. The super-resolution reconstruction of medical images can reduce the requirements on the imaging environment without increasing the cost of high-resolution imaging technology. Through the restored clear medical images, the precise detection of pathological parts can be realized. The system is helpful for doctors to make better diagnosis of patients' conditions.