Scoliosis screening method based on back image

• Main Authors: ZHAN WEIDA, HAO ZIQIANG, TANG YING, WANG XIUZHUO, HAN DENG, GE WEI
• Format: Patent
• Language: Chinese; English
• Published: 13.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The invention discloses a scoliosis screening method based on a back image, belongs to the technical field of medical image classification, and aims at solving the problem that an existing scoliosis screening method is low in accuracy and efficiency. Preparing data sets: preparing a scoliosis data set I and a scoliosis data set II; training a network model: inputting the prepared scoliosis data set I into the constructed network model for training; selecting a minimum loss function and an optimal evaluation index; the model is finely adjusted through the second scoliosis data set, and stable and available model parameters are obtained; and storing the model: solidifying the finally determined model parameters, and when scoliosis screening operation needs to be carried out, directly inputting the image into the network to obtain a final screening result. The scoliosis screening method has the advantages that the scoliosis screening is high in accuracy and screening efficiency, and the scoliosis screening metho