Jeroen Bertels

Jeroen Bertels

Auto-generated profile, based on publicly available information

Jeroen Bertels

Department of Electrical Engineering KU Leuven Processing Speech and Images Belgium

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 June 2020 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
TETom Eelbode
Tom Eelbode
JBJeroen Bertels
Jeroen Bertels
MBMaxim Berman
Maxim Berman
DVDirk Vandermeulen
Dirk Vandermeulen
FMFrederik Maes
Frederik Maes
MBMatthew B. Blaschko
Matthew B. Blaschko
In many medical imaging and classical computer vision tasks, the Dice score and Jaccard index are used to evaluate the segmentation performance. Despite the existence and great empirical success of metric-sensitive losses, i.e. relaxations of these metrics such as soft Dice, soft Jaccard and Lovász-Softmax, many researchers still use per-pixel losses, such as (weighted) cross-entropy to train CNNs for segmentation. Therefore, the target metric is in many cases not directly optimized. We investigate from a theoretical perspective, the relation within the group of metric-sensitive loss functions and question the existence of an optimal weighting scheme for weighted cross-entropy to optimize the Dice score and Jaccard index at test time. We find that the Dice score and Jaccard index approximate each other relatively and absolutely, but we find no such approximation for a weighted Hamming similarity. For the Tversky loss, the approximation gets monotonically worse when deviating from the trivial weight setting where soft Tversky equals soft Dice. We verify these results empirically in an extensive validation on six medical segmentation tasks and can confirm that metric-sensitive losses are superior to cross-entropy based loss functions in case of evaluation with Dice Score or Jaccard Index. This further holds in a multi-class setting, and across different object sizes and foreground/background ratios. These results encourage a wider adoption of metric-sensitive loss functions for medical segmentation tasks where the performance measure of interest is the Dice score or Jaccard index.

1 April 2020 in International journal of legal medicine
Verified
Journal Article
Closed access
PDF file
NBNikolay Banar
Nikolay Banar
JBJeroen Bertels
Jeroen Bertels
FLFrançois Laurent
François Laurent
RBRizky Merdietio Boedi
Rizky Merdietio Boedi
JTJannick De Tobel
Jannick De Tobel
DVDirk Vandermeulen
Dirk Vandermeulen

5 September 2019 in Journal of Forensic Sciences
Verified
Journal Article
Closed access
PDF file
RBRizky Merdietio Boedi
Rizky Merdietio Boedi
NBNikolay Banar
Nikolay Banar
JTJannick De Tobel
Jannick De Tobel
JBJeroen Bertels
Jeroen Bertels
DVDirk Vandermeulen
Dirk Vandermeulen
PTPatrick Werner Thevissen
Patrick Werner Thevissen

23 December 2021 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
MRMasoomeh Rahimpour
Masoomeh Rahimpour
JBJeroen Bertels
Jeroen Bertels
ARAhmed Radwan
Ahmed Radwan
HVHenri Vandermeulen
Henri Vandermeulen
SSStefan Sunaert
Stefan Sunaert
MKMichel Koole
Michel Koole
Convolutional neural networks (CNNs) for brain tumor segmentation are generally developed using complete sets of magnetic resonance imaging (MRI) sequences for both training and inference. As such, these algorithms are not trained for realistic, clinical scenarios where parts of the MRI sequences which were used for training, are missing during inference. To increase clinical applicability, we proposed a cross-modal distillation approach to leverage the availability of multi-sequence MRI data for training and generate an enriched CNN model which uses only single-sequence MRI data for inference but outperforms a single-sequence CNN model. We assessed the performance of the proposed method for whole tumor and tumor core segmentation with multi-sequence MRI data available for training but only $T_{1}$ -weighted ( $T_{\text{1}w}$ ) sequence data available for inference, using BraTS 2018, and in-house datasets. Results showed that cross-modal distillation significantly improved the Dice score for both whole tumor and tumor core segmentation when only $T_{\text{1}w}$ sequence data were available for inference. For the evaluation using the in-house dataset, cross-modal distillation achieved an average Dice score of 79.04% and 69.39% for whole tumor and tumor core segmentation, respectively, while a single-sequence U-Net model using $T_{\text{1}w}$ sequence data for both training and inference achieved an average Dice score of 73.60% and 62.62%, respectively. These findings confirmed cross-modal distillation as an effective method to increase the potential of single-sequence CNN models such that segmentation performance is less compromised by missing MRI sequences or having only one MRI sequence available for segmentation.

10 August 2023 in Medical Image Analysis
Verified
Journal Article
Closed access
SOSophie Ostmeier
Sophie Ostmeier
BABrian Axelrod
Brian Axelrod
FIFabian Isensee
Fabian Isensee
JBJeroen Bertels
Jeroen Bertels
MMMichael Mlynash
Michael Mlynash
JHJeremy J. Heit
Jeremy J. Heit

1 January 2021 in Medical Image Analysis
Verified
Journal Article
Closed access
JBJeroen Bertels
Jeroen Bertels
DRDavid Robben
David Robben
DVDirk Vandermeulen
Dirk Vandermeulen
PSPaul Suetens
Paul Suetens