Microscope imaging mode migration method and system and storage medium

• Main Authors: OKAMOTO KEIICHIRO, LIU JIANG, HIGASHIDA RISA, ZHANG YINGLIN, XI RUILING
• Format: Patent
• Language: Chinese; English
• Published: 08.08.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention discloses a microscope imaging modal migration method and system and a storage medium, and the method comprises the steps: carrying out the model training through employing a generative network, enabling the corneal endothelium image data of a domain A and the confocal microscope image data of a domain B to carry out the mutual conversion, so as to learn the images of the domain, and improving the resolution of the corneal endothelium. And taking the generated domain B synthetic image data and domain A synthetic image data as input to continuously and circularly train the generated image data, and continuously discriminating the continuously updated domain B synthetic image data and domain A synthetic image data to gradually obtain that the generated image data is closer to real image data in an original domain. In the training process, the performance of the generative network is improved mainly by reducing the value of the obtained loss function. Therefore, the method relieves the limitation o