Guidelines
Submission guidance for results and papers
-- Evaluation during validation phase:
For convenience and fairness, an evaluation platform has been released to evaluate the prediction of submitted algorithm. You can directly upload your predictions on the validation data (in nifty format) via the website.
The evaluation channel will start on 7th May 2022 and end on 22nd July 2022.
After you register in this challenge, we will assign you of a account and provide the guidebook for the evaluation via email.
Note that evaluation on validation data will be allowed up to 10 times for each task per team.
-- Evaluation during test phase:
For final evaluation on the test data, you need to wrap your algorithm in a docker. Please send us the link to access your docker file via our e-mail address LAScarQS2022@outlook.com or LAScarQS2022@163.com, and specify the docker commands that should be called when running the container, with the subject line such as "[ Team ID ] + test evaluation".
Note that evaluation on the test data will be allowed ONCE for each task per team.
-- Registration of abstract:
Please submit the abstract for registration via our paper submission system CMT-LAScarQS. You can click the "+Create new submission" icon to submit your abstract and fill in your information.
Participants who submit abstracts in the CMT system can contact the organizers after 22nd July 2022, to obtain the ground truth of the validation set.
-- Submission of paper:
Please visit our paper submission system CMT-LAScarQS and upload the full text of your manuscript. Note that the author's names and institute should be anonymous, otherwise you will be disqualified for the final rank.
Publish papers using the data or evaluation results
Please cite the following papers when you use the data for publications:
[1] Lei Li, Veronika A Zimmer, Julia A Schnabel, Xiahai Zhuang*: AtrialJSQnet: A New Framework for Joint Segmentation and Quantification of Left Atrium and Scars Incorporating Spatial and Shape Information, Medical Image Analysis, vol. 76, 102303, 2022.
link.
[2] Lei Li, Veronika A Zimmer, Julia A Schnabel, Xiahai Zhuang*: Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review, Medical Image Analysis, vol. 77, 102360, 2022.
link.
[3] Lei Li, Veronika A Zimmer, Julia A Schnabel, Xiahai Zhuang*: AtrialGeneral: Domain Generalization for Left Atrial Segmentation of Multi-Center LGE MRIs, MICCAI, 557–566, 2021. link
Feiyan Li; Weisheng Li 2. Two Stage of Histogram Matching Augmentation for Domain Generalization : Application to Left Atrial Segmentation
Xuru Zhang; Xinye Yang ; Liqin Huang; Lihua Huang
3. Automatically Segmenting the Left Atrium and Scars from LGE-MRIs Using a boundary-focused nnU-Net
Yuchen Zhang; Yanda Meng; Yalin Zheng*
4. Automated segmentation of the left atrium and scar using deep convolutional neural networks
Kumaradevan Punithakumar; Michelle Noga
5. TESSLA: Two-Stage Ensemble Scar Segmentation for the Left Atrium
Shaheim N Ogbomo-Harmitt; Jakub Grzelak; Ahmed Qureshi; Andrew King; Oleg Aslanidi
6. Using Polynomial Loss and Uncertainty Information for Robust Left Atrial and Scar Quantification and Segmentation
Tewodros W Arega; Stéphanie Bricq; Fabrice MERIAUDEAU
7. Deep U-Net architecture with curriculum learning for left atrial segmentation
Lei Jiang; Yan Li; Yifan Wang; Hengfei Cui; Yong Xia; Yanning Zhang
8. Sequential segmentation of the left atrium and atrial scars using a multi-scale weight sharing network and boundary-based processing
Abbas Khan; Omnia Alwazzan; Martin Benning; Greg Slabaugh
9. UGformer for Robust Left Atrium and Scar Segmentation Across Scanners
Tianyi Liu; Size Hou; Jiayuan Zhu; Zilong Zhao; Haochuan Jiang *
10. LASSNet: A 4 steps DNN for LA Segmentation and Scar Quantification
Arthur Lefebvre; Carolyna A. P. Yamamoto; Julie K. Shade; Ryan P. Bradley; Rebecca A. Yu; Rheeda L. Ali; Dan Popescu; Adityo Prakosa; Eugene G. Kholmovski; Natalia A. Trayanova
11. LA-HRNet: High-resolution network for automatic left atrial segmentation in multi-center LEG MRI
Tongtong Xie, Hongshan Yu, Zhengeng Yang
12. Multi-Depth Boundary-Aware Left Atrial Scar Segmentation Network
Mengjun Wu; Wangbin Ding; Liqin Huang; Mingjing Yang
13. Edge-enhanced Features Guided Joint Segmentation and Quantification of Left Atrium and Scars in LGE MRI Images
Siping Zhou, Guangquan Zhou
14. Self Pre-training with Single-scale Adapter for Left Atrial Segmentation
Can Tu; Ziyan Huang; Junjun He; Zhongying Deng; Jin Ye ; Haoyu Wang; Yuncheng Yang; Chenglong Ma; xiaowei ding
15. Automatic Semi-supervised Left atrial segmentation using deep-supervision 3DResUnet with Pseudo Labeling Approach for LAScarQS 2022 Challenge
Abdul Qayyum; Moona Mazher
16. Automatic Atrial Segmentation from LGE-MRIs Using Attentional 3D V-Net
Shoubo Xiang, Kang Li, Mao Chen
How to participate
Please refer to page of Data. Read carefully the Terms and Conditions and return the signed Data Use agreement document to the organizers. We’ll then get in touch and send you the data link.
For the evaluation, all submitted segmentation results should have exactly the same image information as the original images (including spacing, size, orientation info and short int data type etc).
Review process
For the submitted manuscripts, they will be firstly reviewed by the organizers who will ensure the quality of the paper reached the publication standard. Then, each paper will be reviewed by our reviewers. The review procedure will be double-blinded, similar to the MICCAI submissions. Review comments will be sent to the authors for their further consideration of modifications and preparation for the final camera ready copy that will be included in the workshop proceedings.
Paper Format
The format should follow the LNCS style according to the main MICCAI conference guidelines, anonymous.
The main body of the manuscript should be 8 or 12 pages, and there is no restriction on the pages of reference.
There are some suggestions for the paper.
1. Please ensure that you cite the above papers in your manuscript.
2. Please provide the running time of your model as well as your device information in your manuscript.
3. Open source code is encouraged.
4. Supplementary materials are acceptable.