CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays Call for Papers
ICCV 2023 CVAMD Shared Task: CXR-LT
Call for Participation
----------------------
We invite you to participate in our competition,
CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays.
This is the shared task of
the ICCV 2023 (https://iccv2023.thecvf.com/)
workshop on Computer Vision for Automated Medical Diagnosis (CVAMD)
(https://cvamd2023.github.io/). This competition will be conducted through CodaLab.
Competition website: https://bionlplab.github.io/2023_ICCV_CVAMD/
CodaLab website: https://codalab.lisn.upsaclay.fr/competitions/12599
Important dates
--------------
05/01/2023: Development Phase begins.
Participants can begin making submissions and tracking
results on the public leaderboard.
07/14/2023: Testing Phase begins.
Unlabeled test data will be released to registered
participants. The leaderboard will be kept private for this
phase.
07/17/2023: Competition ends. Participants are invited to
submit their solutions as 8-page papers to ICCV CVAMD 2023!
07/28/2023: ICCV CVAMD 2023 submission deadline.
(Competition participants may receive an extension if needed.)
08/11/2023: ICCV CVAMD 2023 acceptance notification.
10/06/2023: ICCV CVAMD 2023 workshop.
Background: Many real-world problems, including diagnostic medical
imaging exams, are "long-tailed" - there are a few common
findings followed by more relatively rare conditions. In chest
radiography, diagnosis is both a long-tailed and multi-label problem,
as patients often present with multiple disease findings
simultaneously. This is distinct from most large-scale image
classification benchmarks, where each image only belongs to one label
and the distribution of labels is relatively balanced. This
competition will provide a challenging large-scale multi-label
long-tailed learning task on chest X-rays, (CXRs) encouraging
community engagement with this emerging interdisciplinary topic.
Task: Given a CXR, detect all clinical findings. If no findings are
present, predict "No Finding" (with the exception that "No Finding"
can co-occur with "Support Devices"). To do this, you will train
multi-label thorax disease classifiers on the provided labeled
training data.
Dataset: This challenge will use an expanded version of MIMIC-CXR-JPG,
a large benchmark dataset for automated thorax disease classification
(https://physionet.org/content/mimic-cxr-jpg/2.0.0/). Each CXR study
in the dataset was labeled with 12 newly added disease findings
extracted from the associated radiology reports. The resulting
long-tailed (LT) dataset contains 377,110 CXRs, each labeled with at
least one of 26 clinical findings (including a "No Finding" class).
Workshop: This competition is hosted in conjunction with the ICCV
CVAMD 2023. Upon completion of the competition, we will invite
participants to submit their solutions for potential presentation at
CVAMD 2023 and publication in the ICCV 2023 workshop proceedings. We
intend to accept 5-6 papers for publication and select 3 of the
accepted papers for oral presentation at CVAMD in Paris.
Steering Committee
-----------------
Leo Anthony Celi, MD, MPH, MSc | MIT/Harvard
Zhiyong Lu, PhD, FACMI | NIH
George Shih, MD | Weill Cornell Medicine
Ronald M. Summers, MD, PhD | NIH
Organizing Committee
-------------------
Atlas Wang (chair) | The University of Texas at Austin
Yifan Peng (chair) | Weill Cornell Medicine
Gregory Holste | The University of Texas at Austin
Ajay Jaiswal | The University of Texas at Austin
Mingquan Lin | Weill Cornell Medicine
Song Wang | The University of Texas at Austin
Yuzhe Yang | MIT
This competition is supported in part by the Artificial Intelligence
Journal (AIJ). For any questions, please contact
cxr.lt.competition.2023@gmail.com.
Best,
CXR-LT Organizers