Shared Task on Radiology Report Summarization (RadSum@BioNLP23)

Event Notification Type: 
Call for Participation
Abbreviated Title: 
RadSum@BioNLP23
Contact Email: 
Contact: 
Jean-Benoit Delbrouck
Submission Deadline: 
Monday, 1 May 2023

[LAST CALL FOR PARTICIPATION] We are excited to announce the new edition of the Shared Task on Radiology Report Summarization (RadSum) at BioNLP 2023, co-located with ACL 2023.

*OVERVIEW*

The research area of radiology report summarization currently faces an important limitation: most research is carried out on chest X-rays. To palliate these limitations, we propose two datasets:

- A shared summarization task that includes six different modalities and anatomies, totalling 79,779 samples, based on the MIMIC-III database.
- A shared summarization task on chest x-ray radiology reports with images and a brand new out-of-domain test-set from Stanford University.

The emphasis of the workshop is on 1) the use multimodal input (for mimic-cxr) 2) the evaluation of the submissions on the factual correctness of the summary using new metrics.

All participants will be invited to write a paper describing their solution that will be included in the Proceedings of the 22st Workshop on Biomedical Language Processing.

*IMPORTANT DATES*

* Releasing of hidden test-sets: April 6th, 2023
* System submission deadline: April 26th, 2023
* System papers due date: May 1st, 2023
* Notification of acceptance: June 1st, 2023
* Camera-ready system papers due: June 13th, 2023
* BioNLP Workshop Date: July 13th or 14th, 2023

*ORGANIZERS*

JB Delbrouck, Stanford University
Maya Varma, Stanford University
Pierre Chambon, Stanford University
Curtis Langlotz, Stanford University

*MORE INFORMATION*
For more information, please visit our website: https://vilmedic.app/misc/bionlp23/sharedtask/
Please also join our google-group: https://groups.google.com/g/bionlp23-radiology-summ/
For any questions, please contact me at jbdel [at] stanford.edu