Lung cancer lifetime prediction model training and prediction method, system and device and medium

• Main Authors: REN YONG, HAN LANQING
• Format: Patent
• Language: Chinese; English
• Published: 10.05.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; 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; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a lung cancer lifetime prediction model training and prediction method, system and device and a medium, and relates to the technical field of computer-aided medicine. The lung cancer lifetime prediction model training method comprises the following steps that lung cancer data of a plurality of patients are obtained, and the lung cancer data comprise lung CT images of the patients before treatment, clinical treatment information and prognosis lifetime labels of the patients; screening and preprocessing the plurality of lung cancer data according to conditions of a green treatment method to obtain a plurality of initialized lung cancer data; storing the multiple pieces of initialized lung cancer data to obtain a training data set; initializing parameters of the lung cancer lifetime prediction model; and inputting the training data set into the initialized lung cancer lifetime prediction model for training to obtain a trained lung cancer lifetime prediction model. The prognosis lifetime o