The preoperative evaluation for spinal surgery is based on the experience of physicians. However, due to individual differences and the lack of an objective tool to assist in clinical analysis, successful surgery and good postoperative results are hard to achieve. ITRI has applied an AI model and a deep learning and measurement algorithm to develop measurement and analysis tools for spine X-ray images. By training the AI model with preoperative and postoperative clinical images, the developed system can provide measurements of 52 parameters and the detection of abnormal spondylolisthesis. It can also simulate the effect of implants to aid physicians in evaluating spinal deformity.
Applications & Benefits
Physicians from several hospitals have joined the development trial using the system, and their comments have shown the improved efficiency of clinical diagnosis and treatment.