A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography

Overview

Update 7/5/2021

Note that for VerSe dataset partially visible vertebrae at the top or bottom of the scan (or both) were not annotated, while CTSpine1K annotated them, which caused the situation that in our previous-version paper the reported dice value on VerSe dataset is much lower than on CTSpine1K dataset (0.619 VS 0.840). Therefore, we annotated all visible vertebrea (see figure below) and recalculated the metrics(0.766 VS 0.840).

We have updated our paper on arxiv and uploaded the completed annotations for VerSe dataset to Google drive Google drive and Baiduyun (password:send email to [email protected]). label

Besides, we updated a more specific biconcave fracture case on Figure 1(F).

Update 6/11/2021

We upload the Path.csv to clarify the CT positions we used for COLONOG dataset and HNSCC-3DCT-RT dataset, and delete the dicom2nii.py file. We also upload the original CT images to Baiduyun (password:send email to [email protected])

Introduction for the CTSpine1K dataset

To advance the research in spinal image analysis, we hereby present a large-scale and comprehensive dataset: CTSpine1K. To build a comprehensive spine dataset that replicates practical appearance variations, we curate CTSpine1K from the following four open sources, totalling 1,005 CT volumes (over 500,000 labeled slices and over 11,000 vertebrae) of diverse appearance variations.

*COLONOG. This sub-dataset comes from the CT COLONOGRAPHY dataset related to a CT colonography trial12. We randomly select one of the two positions (we open the code for selecting them, dicom2nii.py), which have similar information, of each patient for our dataset . There are 825 CT scans and are in Digital Imaging and Communication in Medicine (DICOM) format.

*HNSCC-3DCT-RT. This sub-dataset contains three dimensional (3D) high-resolution fan-beam CT scans collected during pre-treatment, mid-treatment, and post-treatment using a Siemens 16-slice CT scanner with the standard clinical protocol for head-and-neck squamous cell carcinoma (HNSCC) patients13. These images are in DICOM format.

*MSD T10. This sub-dataset comes from the 10th Medical Segmentation Decathlon14. To attain more slices containing the spine, we select the task03_liver dataset consisting of 201 cases. These images are in Neuroimaging Informatics Technology Initiative (NIfTI) format (https://nifti.nimh.nih.gov/nifti-1).

*COVID-19. This sub-dataset consists of non-enhanced chest CTs from 632 patients with COVID-19 infections. The images were acquired at the point of care in an outbreak setting from patients with Reverse Transcription Polymerase Chain Reaction(RT-PCR) confirmation for the presence of SARS-CoV-215. We pick 40 scans with the images stored in NIfTI format.

We reformat all DICOM images to NIfTI to simplify data processing and de-identify images, meeting the institutional review board (IRB) policies of contributing sites. More details for those sub-datasets could be found in12–15. All existing sub-datasets are under Creative Commons license CC-BY-NC-SA and we will keep the license unchanged. It should be noted that for sub-dataset task03_liver and sub-dataset COVID-19, we only choose a part of cases from them, and in all these data sources, we exclude those cases of very low quality. The overview of our dataset and the thorough comparison with the VerSe Challenge dataset (We only chose those samples which are not cropped) can be seen in Table 1.

spine1K situation

For more information about CTSpine1K dataset, please read the following paper. Please also cite this paper if you are using CTSpine1K dataset for your research.

Yang Deng, Ce Wang, Yuan Hui, et al. CtSpine1k: A large-scale dataset for spinal vertebrae segmentation in computed tomography. arXiv preprint arXiv:2105.14711 (2021). 

Downloading the CTSpine1K Dataset

The original images could be downloaded from correspongding URL above.

The segmentation masks and the pre-trained model are on Google drive or Baiduyun (password:send email to [email protected])

Annotation pipeline with nnUnet

Follow https://github.com/MIC-DKFZ/nnUNet/commit/058b695d61d34dda7f79cd36ab950a5d3e031653 to set and use nnUnet. The specific usage we here could be seen in ReadMe.md file. Our annotation pipeline is presented in figure 2 below. annotataion

Benchmarking results

The benchmarking results are shown in Table 2. table

Acknowledgement

Thank Febian's nnUnet and we appreciate the open-source sub-datasets we used.

Thank Jianji Wang and Guoxin Fan(MD) for their help in Fig.1(F)

Please feel free to email [email protected] if you have any question.

Owner
ICT.MIRACLE lab
The Medical Imaging, Robotics, Analytical Computing Laboratory & Engineering (MIRACLE) group
ICT.MIRACLE lab
Code for ICCV2021 paper SPEC: Seeing People in the Wild with an Estimated Camera

SPEC: Seeing People in the Wild with an Estimated Camera [ICCV 2021] SPEC: Seeing People in the Wild with an Estimated Camera, Muhammed Kocabas, Chun-

Muhammed Kocabas 187 Dec 26, 2022
Vehicle speed detection with python

Vehicle-speed-detection In the project simulate the tracker.py first then simulate the SpeedDetector.py. Finally, a new window pops up and the output

3 Dec 15, 2022
商品推荐系统

商品top50推荐系统 问题建模 本项目的数据集给出了15万左右的用户以及12万左右的商品, 以及对应的经过脱敏处理的用户特征和经过预处理的商品特征,旨在为用户推荐50个其可能购买的商品。 推荐系统架构方案 本项目采用传统的召回+排序的方案。

107 Dec 29, 2022
Reproduce ResNet-v2(Identity Mappings in Deep Residual Networks) with MXNet

Reproduce ResNet-v2 using MXNet Requirements Install MXNet on a machine with CUDA GPU, and it's better also installed with cuDNN v5 Please fix the ran

Wei Wu 531 Dec 04, 2022
Deep Semisupervised Multiview Learning With Increasing Views (IEEE TCYB 2021, PyTorch Code)

Deep Semisupervised Multiview Learning With Increasing Views (ISVN, IEEE TCYB) Peng Hu, Xi Peng, Hongyuan Zhu, Liangli Zhen, Jie Lin, Huaibai Yan, Dez

3 Nov 19, 2022
Python scripts for performing stereo depth estimation using the MobileStereoNet model in ONNX

ONNX-MobileStereoNet Python scripts for performing stereo depth estimation using the MobileStereoNet model in ONNX Stereo depth estimation on the cone

Ibai Gorordo 23 Nov 29, 2022
On-device speech-to-index engine powered by deep learning.

On-device speech-to-index engine powered by deep learning.

Picovoice 30 Nov 24, 2022
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

EfficientZero (NeurIPS 2021) Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021. Thank you for you

Weirui Ye 671 Jan 03, 2023
This is the replication package for paper submission: Towards Training Reproducible Deep Learning Models.

This is the replication package for paper submission: Towards Training Reproducible Deep Learning Models.

0 Feb 02, 2022
Localizing Visual Sounds the Hard Way

Localizing-Visual-Sounds-the-Hard-Way Code and Dataset for "Localizing Visual Sounds the Hard Way". The repo contains code and our pre-trained model.

Honglie Chen 58 Dec 07, 2022
Assessing syntactic abilities of BERT

BERT-Syntax Assesing the syntactic abilities of BERT. What Evaluate Google's BERT-Base and BERT-Large models on the syntactic agreement datasets from

Yoav Goldberg 147 Aug 02, 2022
An intelligent, flexible grammar of machine learning.

An english representation of machine learning. Modify what you want, let us handle the rest. Overview Nylon is a python library that lets you customiz

Palash Shah 79 Dec 02, 2022
Rapid experimentation and scaling of deep learning models on molecular and crystal graphs.

LitMatter A template for rapid experimentation and scaling deep learning models on molecular and crystal graphs. How to use Clone this repository and

Nathan Frey 32 Dec 06, 2022
High-fidelity 3D Model Compression based on Key Spheres

High-fidelity 3D Model Compression based on Key Spheres This repository contains the implementation of the paper: Yuanzhan Li, Yuqi Liu, Yujie Lu, Siy

5 Oct 11, 2022
Neural Scene Graphs for Dynamic Scene (CVPR 2021)

Implementation of Neural Scene Graphs, that optimizes multiple radiance fields to represent different objects and a static scene background. Learned representations can be rendered with novel object

151 Dec 26, 2022
An open-source Deep Learning Engine for Healthcare that aims to treat & prevent major diseases

AlphaCare Background AlphaCare is a work-in-progress, open-source Deep Learning Engine for Healthcare that aims to treat and prevent major diseases. T

Siraj Raval 44 Nov 05, 2022
[CVPRW 21] "BNN - BN = ? Training Binary Neural Networks without Batch Normalization", Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang

BNN - BN = ? Training Binary Neural Networks without Batch Normalization Codes for this paper BNN - BN = ? Training Binary Neural Networks without Bat

VITA 40 Dec 30, 2022
PoseViz – Multi-person, multi-camera 3D human pose visualization tool built using Mayavi.

PoseViz – 3D Human Pose Visualizer Multi-person, multi-camera 3D human pose visualization tool built using Mayavi. As used in MeTRAbs visualizations.

István Sárándi 79 Dec 30, 2022
NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-based Simulation (ACL-IJCNLP 2021)

NeuralWOZ This code is official implementation of "NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-based Simulation". Sungdong Kim, Mi

NAVER AI 31 Oct 25, 2022
In this project, we create and implement a deep learning library from scratch.

ARA In this project, we create and implement a deep learning library from scratch. Table of Contents Deep Leaning Library Table of Contents About The

22 Aug 23, 2022