Over ons

Consortium

Team

AI Vlaanderen

Contact

<h5>Description:</h5>
<p>We provide software to measure per-image expected calibration error (ECE), per-image volume bias (defined as difference between true volume and prediction based on a segmentation system) and the correlation between them.&nbsp;</p>

<h5>More Information:</h5>
<ul>
<li><strong>Grand Challenge/Workpackage(s):</strong> GC1 - WP6</li>
<li><strong>Responsible Research Lead:</strong> <a href="mailto:matthew.blaschko@esat.kuleuven.be" target="_blank" rel="noopener">Matthew B. Blaschko</a></li>
<li><strong>Authors:</strong> <a href="mailto:teodora.popordanoska@kuleuven.be" target="_blank" rel="noopener">Teodora Popordanoska</a>, <a href="mailto:jeroen.bertels@kuleuven.be" target="_blank" rel="noopener">Jeroen Bertels</a>, <a href="mailto:matthew.blaschko@esat.kuleuven.be" target="_blank" rel="noopener">Matthew B. Blaschko</a></li>
<li><strong>Programming Language: </strong>Python</li>
<li><a href="https://github.com/tpopordanoska/calibration_and_bias" target="_blank" rel="noopener">Link to the repository</a></li>
<li><strong>Categories:</strong> Supervised Learning, Images</li>
</ul>

<h5>Publications:</h5>
<ul>
<li>T. Popordanoska, J. Bertels, D. Vandermeulen, F. Maes,&nbsp; M. Blaschko, "<a href="https://limo.libis.be/primo-explore/fulldisplay?docid=LIRIAS3480230&amp;context=L&amp;vid=Lirias&amp;search_scope=Lirias&amp;tab=default_tab&amp;lang=en_US&amp;fromSitemap=1" target="_blank" rel="noopener">On the relationship between calibrated predictors and unbiased volume estimation</a>", 24th international conference on medical image computing and computer assisted intervention (MICCAI 2021), 2021.</li>
</ul>
<p>&nbsp;</p>

<p>A software for evaluating model calibration, volume bias and a correlation between the two</p>