VertXNet: Automatic Segmentation and Identification of Lumbar and Cervical Vertebrae from Spinal X-ray Images
This work addresses the bottleneck of lacking annotated vertebrae in computational imaging projects for clinical research, particularly in ankylosing spondylitis, though it is incremental as it builds on existing segmentation models.
The study tackled the problem of costly manual annotation of vertebrae in spinal X-ray images by proposing VertXNet, an ensemble method combining U-Net and Mask R-CNN, which achieved a mean Dice score of 0.9 for accurate segmentation and labeling on an in-house dataset of cervical and lumbar X-rays for ankylosing spondylitis patients.
Manual annotation of vertebrae on spinal X-ray imaging is costly and time-consuming due to bone shape complexity and image quality variations. In this study, we address this challenge by proposing an ensemble method called VertXNet, to automatically segment and label vertebrae in X-ray spinal images. VertXNet combines two state-of-the-art segmentation models, namely U-Net and Mask R-CNN to improve vertebrae segmentation. A main feature of VertXNet is to also infer vertebrae labels thanks to its Mask R-CNN component (trained to detect 'reference' vertebrae) on a given spinal X-ray image. VertXNet was evaluated on an in-house dataset of lateral cervical and lumbar X-ray imaging for ankylosing spondylitis (AS) patients. Our results show that VertXNet can accurately label spinal X-rays (mean Dice of 0.9). It can be used to circumvent the lack of annotated vertebrae without requiring human expert review. This step is crucial to investigate clinical associations by solving the lack of segmentation, a common bottleneck for most computational imaging projects.