A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data
This work addresses the need for more reliable segmentation tools in medical imaging, particularly for handling anatomical variations, but is incremental as it builds on a previous challenge dataset.
The authors tackled the problem of automated vertebral segmentation in spine CT images by introducing the VerSe 2020 dataset, which includes 300 subjects with 4142 annotated vertebrae from multiple scanner vendors and anatomical variants, to improve algorithm robustness.
With the advent of deep learning algorithms, fully automated radiological image analysis is within reach. In spine imaging, several atlas- and shape-based as well as deep learning segmentation algorithms have been proposed, allowing for subsequent automated analysis of morphology and pathology. The first Large Scale Vertebrae Segmentation Challenge (VerSe 2019) showed that these perform well on normal anatomy, but fail in variants not frequently present in the training dataset. Building on that experience, we report on the largely increased VerSe 2020 dataset and results from the second iteration of the VerSe challenge (MICCAI 2020, Lima, Peru). VerSe 2020 comprises annotated spine computed tomography (CT) images from 300 subjects with 4142 fully visualized and annotated vertebrae, collected across multiple centres from four different scanner manufacturers, enriched with cases that exhibit anatomical variants such as enumeration abnormalities (n=77) and transitional vertebrae (n=161). Metadata includes vertebral labelling information, voxel-level segmentation masks obtained with a human-machine hybrid algorithm and anatomical ratings, to enable the development and benchmarking of robust and accurate segmentation algorithms.