Convolutional Neural Networks based automated segmentation and labelling of the lumbar spine X-ray
This work addresses automated medical image analysis for clinical decision support in diagnosing spinal conditions, but it is incremental as it compares existing segmentation methods on a specific dataset.
The study compared instance and semantic segmentation networks for automated segmentation and labeling of lumbar spine X-rays, finding that the best instance segmentation model achieved up to 3% better mean accuracy and IoU, while semantic segmentation had slightly better pixel accuracy and weighted IoU.
The aim of this study is to investigate the segmentation accuracies of different segmentation networks trained on 730 manually annotated lateral lumbar spine X-rays. Instance segmentation networks were compared to semantic segmentation networks. The study cohort comprised diseased spines and postoperative images with metallic implants. The average mean accuracy and mean intersection over union (IoU) was up to 3 percent better for the best performing instance segmentation model, the average pixel accuracy and weighted IoU were slightly better for the best performing semantic segmentation model. Moreover, the inferences of the instance segmentation models are easier to implement for further processing pipelines in clinical decision support.