ICL implantation method, system and device based on machine learning and readable storage medium

• Main Authors: CHEN QIAN, TAN LUOLE, TAN WEINA
• Format: Patent
• Language: Chinese; English
• Published: 05.04.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention provides an ICL implantation method based on machine learning, and the method comprises the steps: selecting an ICL preoperative UBM image for point position labeling, generating a Gaussian thermodynamic diagram based on the point position labeling, converting a model prediction result into a key point, and calculating key parameters of anterior and posterior chambers and ciliary bodies in the preoperative UBM image; the method comprises the following steps: selecting an ICL post-operation UBM overall display foot loop position picture to carry out point position labeling, training a Unet model to predict a Gaussian thermodynamic diagram, converting a model prediction result into key points, calculating ICL foot loop position related parameters in the UBM picture based on key point use, and calculating the ICL foot loop position related parameters in the UBM picture. In combination with an ICL preoperative UBM image, parameters of a postoperative UBM overall display foot loop position image and