VerSe: A Vertebrae Labelling and Segmentation Benchmark

This work is a technical report concerning the Large Scale Vertebrae Segmentation Challenge (VerSe) organised in conjunction with the MICCAI 2019. The challenge set-up consisting of two tasks, vertebrae labelling and vertebrae segmentation, is detailed. A total of 160 multidetector CT scans closely resembling a typical spine-centreed clinical setting were prepared and annotated at voxel-level by a human-machine hybrid algorithm. Both the annotation protocol and the algorithm that aided the medical experts in this annotation process are presented. More importantly, eleven fully automated algorithms of the participating teams were submitted to be benchmarked on the VerSe data. This work presents a detailed performance analysis of these algorithms with the best performing algorithm achieving a vertebrae identification rate of 95% and a Dice coefficient of 90%. VerSe'19 is an open-call challenge and its image data along with the annotations and evaluation tools will continue to be publicly accessible through its online portal.

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Jozsef Illes,et al.  Radiology reporting of osteoporotic vertebral fragility fractures on computed tomography studies: results of a UK national audit , 2020, European Radiology.

[4]  Hans-Christian Hege,et al.  Automatic Segmentation of the Pelvic Bones from CT Data Based on a Statistical Shape Model , 2008, VCBM.

[5]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[6]  Ronald M. Summers,et al.  A multi-center milestone study of clinical vertebral CT segmentation , 2016, Comput. Medical Imaging Graph..

[7]  R E Wigh,et al.  The Thoracolumbar and Lumbosacral Transitional Junctions , 1980, Spine.

[8]  Thomas R Oxland,et al.  Fundamental biomechanics of the spine--What we have learned in the past 25 years and future directions. , 2016, Journal of biomechanics.

[9]  Aaron Carass,et al.  Why rankings of biomedical image analysis competitions should be interpreted with care , 2018, Nature Communications.

[10]  Bostjan Likar,et al.  A Framework for Automated Spine and Vertebrae Interpolation-Based Detection and Model-Based Segmentation , 2015, IEEE Transactions on Medical Imaging.

[11]  Yingzhou Li,et al.  Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks , 2018, Communications in Computational Physics.

[12]  Ronald M. Summers,et al.  Detection of Vertebral Body Fractures Based on Cortical Shell Unwrapping , 2012, MICCAI.

[13]  Ernst J. Rummeny,et al.  Significance of sagittal reformations in routine thoracic and abdominal multislice CT studies for detecting osteoporotic fractures and other spine abnormalities , 2008, European Radiology.

[14]  Daguang Xu,et al.  C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[16]  Klaus H. Maier-Hein,et al.  Automated Design of Deep Learning Methods for Biomedical Image Segmentation , 2019 .

[17]  Jan S. Kirschke,et al.  Btrfly Net: Vertebrae Labelling with Energy-based Adversarial Learning of Local Spine Prior , 2018, MICCAI.

[18]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[19]  Bora Erden.  3 D Convolutional Neural Network for Brain Tumor Segmentation , 2017 .

[20]  Thomas Baum,et al.  A Vertebral Segmentation Dataset with Fracture Grading , 2020, Radiology. Artificial intelligence.

[21]  R. Whitehouse,et al.  Under-reporting of osteoporotic vertebral fractures on computed tomography. , 2009, European journal of radiology.

[22]  Markus Haltmeier,et al.  Projection-Based 2.5D U-net Architecture for Fast Volumetric Segmentation , 2019, 2019 13th International conference on Sampling Theory and Applications (SampTA).

[23]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[24]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[25]  J. Cauley,et al.  Risk of Mortality Following Clinical Fractures , 2000, Osteoporosis International.

[26]  Nassir Navab,et al.  Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks , 2018, MICCAI.

[27]  Stefan Zachow,et al.  Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative , 2019, Medical Image Anal..

[28]  Jan S. Kirschke,et al.  Labeling Vertebrae with Two-dimensional Reformations of Multidetector CT Images: An Adversarial Approach for Incorporating Prior Knowledge of Spine Anatomy. , 2020, Radiology. Artificial intelligence.

[29]  N. Sollmann,et al.  X-ray-based quantitative osteoporosis imaging at the spine , 2019, Osteoporosis International.