Automated image analysis of lateral lumber X-rays by a form model.

Purpose: Development of a software for fully automated image analysis of la teral lumbar spine X-rays. Material and method: Using the concept of active shape models, we developed a software that produces a form model of the lu mbar spine from lateral lumbar spine radiographs and runs an automated imag e segmentation. This model is able to detect lumbar vertebrae automatically after the filtering of digitized X-ray images. The model was trained with 20 lateral lumbar spine radiographs with no pathological findings before we evaluated the software with 30 further X-ray images which were sorted by i mage quality ranging from one (best) to three (worst). There were 10 images for each quality. Results: image recognition strongly depended on image qu ality. In group one 52 and in group two 51 out of 60 vertebral bodies inclu ding the sacrum were recognized, but in group three only 18 vertebral bodie s were properly identified. Conclusion: Fully automated and reliable recogn ition of vertebral bodies from lateral spine radiographs using the concept of active shape models is possible. The precision of this technique is limi ted by the superposition of different structures. Further improvements are necessary. Therefore standardized image quality and enlargement of the trai ning data set are required.