Ultrasound Image Enhancement challenge 2023 Banner
Join

News

  • [08.10] The 2nd-Testing phase has been updated. Please re-upload your results and other relevant documents. Sorry for the inconvenience.
  • The submission deadline of the 1st-validation phase has been updated.
  • The 1s-validation phase and 2nd-testing phase are opened.
  • In the first phase, participants could upload submissions via the phase "1st-Validation (Results Submission ONLY)". The short method introduction paper (at least 4 pages, PDF format) is optional in the phase.
  • In the 2nd-testing phase, participants should upload submissions via "2nd-Testing (Final)", with a short method introduction paper (at least 4 pages, PDF format). And the link to the code to achieve the designed algorithm is required.
  • The reconstructed images must be the same dimensions and resolution (256×256) as the testing data.

Two-Phase Submission

Participants should upload submissions via the grand-challenge.org submission system, with a short method introduction paper (at least 4 pages, PDF format). They could submit the algorithm in the form of a docker container (.tar file), or the results (the generated high-quality ultrasound images) of their algorithm in the form of a single .zip file. Low-quality ultrasound images of the testing dataset are available, please see the Datasets Page. If they submit .zip file, names of generated high-quality ultrasound images should be consistent with low-quality ones accordingly.

For the 1st phase (validation phase), each team will be allowed to create 5 submissions between July 10th (12:00 AM GMT), 2023, and August 7th (11:59 PM GMT), 2023 to this phase.
For the 2nd phase (testing phase), the submission deadline is August 31th (11:59 PM GMT), 2023. 

Evaluation

Metrics

Three widely used evaluation metrics are used: 

(locally-normalized-cross-correlation) LNCC

(structure similarity) SSIM

(peak signal-noise ratio) PSNR

Ranking methods

For each test case, respectively calculate their 1) LNCC, 2) SSIM, 3) PSNR.  Then, we will calculate the average rank of these three indicators to obtain the final ranking.