Reference : Leveraging state-of-the-art architectures by enriching training information - a case study
Diverse speeches and writings : Speeches/Talks
Engineering, computing & technology : Multidisciplinary, general & others
Systems Biomedicine
http://hdl.handle.net/10993/48102
Leveraging state-of-the-art architectures by enriching training information - a case study
English
Sölter, Jan []
Proverbio, Daniele []
Baniasadi, Mehri []
Bossa, Matias Nicolas []
Vlasov, Vanja []
Garcia Santa Cruz, Beatriz []
Husch, Andreas mailto [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Interventional Neuroscience >]
11-Jan-2021
International
COVID 19-20 Lung CT Lesion Segmentation Grand Challenge Mini-symposium
2021-01-11
Children’s National Hospital
Nvidia
National Institutes of Health
USA
[en] Our working hypothesis is that key factors in COVID-19 imaging are the available
imaging data and their label noise and confounders, rather than network
architectures per se. Thus, we applied existing state-of-the-art convolution neural
network frameworks based on the U-Net architecture, namely nnU-Net [3],
and focused on leveraging the available training data. We did not apply any
pre-training nor modi ed the network architecture.
First, we enriched training information by generating two additional labels for
lung and body area. Lung labels were created with a public available lung segmentation
network and weak body labels were generated by thresholding. Subsequently,
we trained three di erent multi-class networks: 2-label (original background
and lesion labels), 3-label (additional lung label) and 4-label (additional
lung and body label). The 3-label obtained the best single network performance
in internal cross-validation (Dice-Score 0.756) and on the leaderboard (Dice-
Score 0.755, Haussdor 95-Score 57.5).
To improve robustness, we created a weighted ensemble of all three models, with
calibrated weights to optimise the ranking in Dice-Score. This ensemble achieved
a slight performance gain in internal cross-validation (Dice-Score 0.760). On the
validation set leaderboard, it improved our Dice-Score to 0.768 and Haussdor 95-
Score to 54.8. It ranked 3rd in phase I according to mean Dice-Score.
Adding unlabelled data from the public TCIA dataset in a student-teacher manner
signi cantly improved our internal validation score (Dice-Score of 0.770).
However, we noticed partial overlap between our additional training data (although
not human-labelled) and  nal test data and therefore submitted the
ensemble without additional data, to yield realistic assessments.
Researchers
http://hdl.handle.net/10993/48102
FnR ; FNR14702831 > Andreas Husch > AICovIX > Ai Based Diagnosis Of Covid-19 From Ct/X-ray Imaging > 01/06/2020 > 30/11/2020 > 2020

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Abstract_MICCAI_Covid_Lesion_Seg_Challenge_2020-2.pdfAuthor preprint100.7 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.