VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images

Abstract

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision-support systems for diagnosis, surgery planning, and population-based analysis on spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms towards labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The content and code concerning VerSe can be accessed at: https://github.com/anjany/verse.

arXiv commentChallenge report for the VerSe 2019 and 2020. Published in Medical Image Analysis (DOI: https://doi.org/10.1016/j.media.2021.102166)

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Direct visualization of current induced spin accumulation in topological insulators
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• Why rankings of biomedical image analysis competitions should be interpreted with care
• Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization
• Iterative fully convolutional neural networks for automatic vertebra segmentation and identification
• Joint Vertebrae Identification and Localization in Spinal CT Images by Combining Short- and Long-Range Contextual Information
• A Localisation-Segmentation Approach for Multi-label Annotation of Lumbar Vertebrae using Deep Nets
• Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks

Cited by in corpus (15)

• TotalSegmentator: robust segmentation of 104 anatomical structures in CT images
• Segment Anything Model for Medical Images?
• Recent Progress in Transformer-based Medical Image Analysis
• Lumbar spine segmentation in MR images: a dataset and a public benchmark
• Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation
• CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography
• SPINEPS -- Automatic Whole Spine Segmentation of T2-weighted MR images using a Two-Phase Approach to Multi-class Semantic and Instance Segmentation
• A Robust Ensemble Algorithm for Ischemic Stroke Lesion Segmentation: Generalizability and Clinical Utility Beyond the ISLES Challenge
• 3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation
• Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?
• Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder
• Terabyte-scale supervised 3D training and benchmarking dataset of the mouse kidney
• A Systematic Collection of Medical Image Datasets for Deep Learning
• Unified Medical Image Segmentation with State Space Modeling Snake
• Body Part Regression for CT Images