five

IWOAI Drift-Shift Challenge

收藏
DataCite Commons2022-06-20 更新2024-07-13 收录
下载链接:
https://erda.ku.dk/archives/1518a9c6b1db56269ef6ef62badd9d31/published-archive.html
下载链接
链接失效反馈
官方服务:
资源简介:
This is the repository containing segmentation masks for the teams contributing to the "Drift and Shift" follow-up to the 2019 IWOAI Knee Cartilage Segmentation Challenge. All six teams participating in the 2019 KCSC here submitted segmentations for a collection of knee MRI coming from the V00 and V01 visits in the Osteoarthritis Initiative (OAI). Two teams also submitted segmentations using updated versions of their methods from the 2019 challenge. All teams were blinded to subject and visit information. This resulted in the 10,064 segmentations that are available in this repository. From each segmentation, volumes for fives compartments can be extracted: medial and lateral tibial cartilages, medial and lateral femoral cartilages, and patellar cartilage. The jupyter notebook that extracts these volumes also includes a method for extracting the mask and volume for central, load-bearing sub-regions of the medial and lateral femoral cartilages. The extraction script is CollectSegmentationVolumes.ipynb. The volumes are saved in hpf5/matlab files directly by the script. In order to also save (selected) mask files, the script will need to be (easily) modified. The data in this repository can be freely used for research (not commercial) purposes. Please reference the following publication when doing so: Towards Automatic Cartilage Quantification in Clinical Trials – A Follow-up Challenge to the 2019 IWOAI Knee Segmentation Challenge Erik B Dam1*, Arjun D Desai2, Cem M Deniz3, Haresh R Rajamohan4, Ravinder Regatte3, Claudia Iriondo5, Valentina Pedoia5, Sharmila Majumdar5, Mathias Perslev1, Christian Igel1, Akshay Pai6, Sibaji Gaj7, Mingrui Yang7, Kunio Nakamura7, Xiaojuan Li7, Hasan Maqbool8, Ismail Irmakci9, Sang-Eun Song8, Ulas Bagci9, Brian Hargreaves2, Garry Gold2, Akshay Chaudhari2 1 University of Copenhagen, Copenhagen, Denmark 2 Stanford University, Stanford, CA USA 3 New York University, Langone Health, New York, NY USA 4 New York University, New York, NY USA 5 University of California, San Francisco, CA USA 6 Cerebriu A/S, Copenhagen, Denmark 7 Cleveland Clinic, Cleveland, OH USA 8 University of Central Florida, Orlando, FL USA 9 Northwestern University, Evanston, IL USA * Corresponding author: erikdam@di.ku.dk
提供机构:
University of Copenhagen
创建时间:
2022-06-20
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作