# A Localisation-Segmentation Approach for Multi-label Annotation of Lumbar Vertebrae using Deep Nets

arXiv: https://arxiv.org/abs/1703.04347 · HTML: https://mlsanity.com/paper/1703.04347/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2017.

## Built on by (most cited first, 6 of 6)

- [Lumbar spine segmentation in MR images: a dataset and a public benchmark](https://mlsanity.com/paper/2306.12217/) (2023)
- [A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data](https://mlsanity.com/paper/2103.06360/) (2021)
- [Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle](https://mlsanity.com/paper/2110.12177/) (2021)
- [SLoRD: Structural Low-Rank Descriptors for Shape Consistency in Vertebrae Segmentation](https://mlsanity.com/paper/2407.08555/) (2024)
- [Organ localisation using supervised and semi supervised approaches combining reinforcement learning with imitation learning](https://mlsanity.com/paper/2112.03276/) (2021)
- [DoubleU-Net++: Architecture with Exploit Multiscale Features for Vertebrae Segmentation](https://mlsanity.com/paper/2201.12389/) (2022)

## Abstract (arXiv)

Multi-class segmentation of vertebrae is a non-trivial task mainly due to the high correlation in the appearance of adjacent vertebrae. Hence, such a task calls for the consideration of both global and local context. Based on this motivation, we propose a two-staged approach that, given a computed tomography dataset of the spine, segments the five lumbar vertebrae and simultaneously labels them. The first stage employs a multi-layered perceptron performing non-linear regression for locating the lumbar region using the global context. The second stage, comprised of a fully-convolutional deep network, exploits the local context in the localised lumbar region to segment and label the lumbar vertebrae in one go. Aided with practical data augmentation for training, our approach is highly generalisable, capable of successfully segmenting both healthy and abnormal vertebrae (fractured and scoliotic spines). We consistently achieve an average Dice coefficient of over 90 percent on a publicly available dataset of the xVertSeg segmentation challenge of MICCAI 2016. This is particularly noteworthy because the xVertSeg dataset is beset with severe deformities in the form of vertebral fractures and scoliosis.