Skip to content

Commit

Permalink
Add publications of Stan and Daan
Browse files Browse the repository at this point in the history
  • Loading branch information
@drepeeters
drepeeters committed Dec 7, 2023
1 parent 3b2e99d commit a8a4a30
Showing 1 changed file with 66 additions and 39 deletions.
105 changes: 66 additions & 39 deletions diag.bib
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22449,41 +22449,33 @@ @article{Nill11
all_ss_ids = {['1b2583976cd39108af8f0b7d9f1900b4e61e4c95']},
}

@article{Noor19,
author = {Noordman, C.R. and Vreeswijk, G.A.W.},
title = {Evolving novelty strategies for the Iterated Prisoner's Dilemma in deceptive tournaments},
doi = {10.1016/j.tcs.2018.10.026},
year = {2019},
abstract = {Abstract unavailable},
url = {http://dx.doi.org/10.1016/j.tcs.2018.10.026},
file = {Noor19.pdf:pdf\\Noor19.pdf:PDF},
optnote = {DIAG, RADIOLOGY},
journal = {Theoretical Computer Science},
automatic = {yes},
citation-count = {2},
pages = {1-16},
volume = {785},
all_ss_ids = {[fde118f6324d87e79811f01522e106e64237bec2]},
gscites = {0},
}

@article{Noor23,
author = {Noordman, Constant Richard and Yakar, Derya and Bosma, Joeran and Simonis, Frank Frederikus Jacobus and Huisman, Henkjan},
title = {Complexities of deep learning-based undersampled MR image reconstruction},
doi = {10.1186/s41747-023-00372-7},
year = {2023},
abstract = {AbstractArtificial intelligence has opened a new path of innovation in magnetic resonance (MR) image reconstruction of undersampled k-space acquisitions. This review offers readers an analysis of the current deep learning-based MR image reconstruction methods. The literature in this field shows exponential growth, both in volume and complexity, as the capabilities of machine learning in solving inverse problems such as image reconstruction are explored. We review the latest developments, aiming to assist researchers and radiologists who are developing new methods or seeking to provide valuable feedback. We shed light on key concepts by exploring the technical intricacies of MR image reconstruction, highlighting the importance of raw datasets and the difficulty of evaluating diagnostic value using standard metrics.Relevance statement Increasingly complex algorithms output reconstructed images that are difficult to assess for robustness and diagnostic quality, necessitating high-quality datasets and collaboration with radiologists.Key points* Deep learning-based image reconstruction algorithms are increasing both in complexity and performance.* The evaluation of reconstructed images may mistake perceived image quality for diagnostic value.* Collaboration with radiologists is crucial for advancing deep learning technology.
@Conference{Noor22,
author = {van Rijssel, Michael and van den Berg, Cornelis and Noordman, Stan and van Lier, Astrid.},
title = {Accelerating phase-cycled bSSFP using sparsity across the phase-cycling dimension},
url = {https://archive.ismrm.org/2022/4801.html},
abstract = {Banding artifacts in balanced steady state free precession images can be resolved by applying radiofrequency phase cycling. Unfortunately, the scan time increases linearly with the amount of phase cycles acquired, hindering clinical adoption of this sequence. We aimed to reduce the amount of phase cycles that need to be acquired by employing a signal model in an iterative reconstruction. Preliminary validation of this algorithm was performed in-silico and in a phantom. Results show excellent agreement in-silico (relative mean absolute error, RMAE, 0.0045%) and in phantom tubes with T1 and T2 values in the physiological range (RMAE 3-4%).},
journal = {ISMRM-ESMRMB},
optnote = {DIAG, RADIOLOGY},
year = {2022},
}

@Article{Noor23,
author = {Noordman, Stan and Yakar, Derya and Bosma, Joeran and Simonis, Frank Frederikus Jacobus and Huisman, Henkjan},
title = {Complexities of deep learning-based undersampled MR image reconstruction},
doi = {10.1186/s41747-023-00372-7},
url = {http://dx.doi.org/10.1186/s41747-023-00372-7},
volume = {7},
abstract = {AbstractArtificial intelligence has opened a new path of innovation in magnetic resonance (MR) image reconstruction of undersampled k-space acquisitions. This review offers readers an analysis of the current deep learning-based MR image reconstruction methods. The literature in this field shows exponential growth, both in volume and complexity, as the capabilities of machine learning in solving inverse problems such as image reconstruction are explored. We review the latest developments, aiming to assist researchers and radiologists who are developing new methods or seeking to provide valuable feedback. We shed light on key concepts by exploring the technical intricacies of MR image reconstruction, highlighting the importance of raw datasets and the difficulty of evaluating diagnostic value using standard metrics.Relevance statement Increasingly complex algorithms output reconstructed images that are difficult to assess for robustness and diagnostic quality, necessitating high-quality datasets and collaboration with radiologists.Key points* Deep learning-based image reconstruction algorithms are increasing both in complexity and performance.* The evaluation of reconstructed images may mistake perceived image quality for diagnostic value.* Collaboration with radiologists is crucial for advancing deep learning technology.
Graphical Abstract},
url = {http://dx.doi.org/10.1186/s41747-023-00372-7},
file = {Noor23.pdf:pdf\\Noor23.pdf:PDF},
optnote = {DIAG, RADIOLOGY},
journal = {European Radiology Experimental},
automatic = {yes},
all_ss_ids = {[03a7b0c8377b4cfd5bd37215d644d31033b7ae23]},
automatic = {yes},
citation-count = {0},
volume = {7},
all_ss_ids = {[03a7b0c8377b4cfd5bd37215d644d31033b7ae23]},
pmid = {37789241},
gscites = {0},
file = {Noor23.pdf:pdf\\Noor23.pdf:PDF},
gscites = {0},
journal = {European Radiology Experimental},
optnote = {DIAG, RADIOLOGY},
pmid = {37789241},
year = {2023},
}

@article{Noot22,
Expand Down Expand Up @@ -23087,17 +23079,17 @@ @inproceedings{Peem13
month = {10},
}

@conference{Peet23,
author = {Peeters, Dr\'{e} and Alves, Nat\'{a}lia and Venkadesh, K and Dinnessen, R and Saghir, Z and Scholten, E and Huisman, H and Schaefer-Prokop, C and Vliegenthart, R and Prokop, M and Jacobs, C},
@Conference{Peet23,
author = {Peeters, Dr\'{e} and Alves, Nat\'{a}lia and Venkadesh, K and Dinnessen, R and Saghir, Z and Scholten, E and Huisman, H and Schaefer-Prokop, C and Vliegenthart, R and Prokop, M and Jacobs, C},
booktitle = ECR,
title = {The effect of applying an uncertainty estimation method on the performance of a deep learning model for nodule malignancy risk estimation},
abstract = {Purpose: Artificial Intelligence (AI) algorithms often lack uncertainty estimation for classification tasks. Uncertainty estimation may however be an important requirement for clinical adoption of AI algorithms. In this study, we integrate a method for uncertainty estimation into a previously developed AI algorithm and investigate the performance when applying different uncertainty thresholds.
title = {The effect of applying an uncertainty estimation method on the performance of a deep learning model for nodule malignancy risk estimation},
abstract = {Purpose: Artificial Intelligence (AI) algorithms often lack uncertainty estimation for classification tasks. Uncertainty estimation may however be an important requirement for clinical adoption of AI algorithms. In this study, we integrate a method for uncertainty estimation into a previously developed AI algorithm and investigate the performance when applying different uncertainty thresholds.
Methods and materials: We used a retrospective external validation dataset from the Danish Lung Cancer Screening Trial, containing 818 benign and 65 malignant nodules. Our previously developed AI algorithm for nodule malignancy risk estimation was extended with a method for measuring the prediction uncertainty. The uncertainty score (UnS) was calculated by measuring the standard deviation over 20 different predictions of an ensemble of AI models. Two UnS thresholds at the 90th and 95th percentile were applied to retain 90% and 95% of all cases as certain, respectively. For these scenarios, we calculated the area under the ROC curve (AUC) for certain and uncertain cases, and for the full set of nodules.
Results: On the full set of 883 nodules, the AUC of the AI risk score was 0.932. For the 90th and 95th percentile, the AUC of the AI risk score for certain cases was 0.934 and 0.935, respectively, and for the uncertain cases was 0.710 and 0.688, respectively.
Conclusion: In this retrospective data set, we demonstrate that integrating an uncertainty estimation method into a deep learning-based nodule malignancy risk estimation algorithm slightly increased the performance on certain cases. The AI performance is substantially worse on uncertain cases and therefore in need of human visual review.
Limitations: This study is a retrospective analysis on data from one single lung cancer screening trial. More external validation is needed.},
optnote = {DIAG, RADIOLOGY},
year = {2023},
optnote = {DIAG, RADIOLOGY},
year = {2023},
}

@conference{Pegg17a,
Expand Down Expand Up @@ -34007,4 +33999,39 @@ @conference{deVos2017
optnote = {DIAG},
}

@Article{Noor22,
author = {Noordman, Stan and Vreeswijk, G.A.W},
title = {Evolving novelty strategies for the Iterated Prisoner's Dilemma in deceptive tournaments},
doi = {10.1016/j.tcs.2018.10.026},
pages = {1-16},
url = {http://dx.doi.org/10.1016/j.tcs.2018.10.026},
volume = {785},
abstract = {Abstract unavailable},
all_ss_ids = {[fde118f6324d87e79811f01522e106e64237bec2]},
automatic = {yes},
citation-count = {2},
file = {Noor19.pdf:pdf\\Noor19.pdf:PDF},
gscites = {0},
journal = {Theoretical Computer Science},
optnote = {DIAG, RADIOLOGY},
year = {2019},
}

@Book{Witt15,
author = {Wittenberg, Rianne and Rossi, Santiago and Schaefer-Prokop, Cornelia},
title = {Drug-Induced Interstitial Lung Disease in Oncology Patients},
doi = {10.1007/174_2015_1080},
pages = {129-145},
url = {http://dx.doi.org/10.1007/174_2015_1080},
abstract = {Abstract unavailable},
all_ss_ids = {[a9d7609639015a49b03167508b66d055e30c51c9]},
automatic = {yes},
citation-count = {0},
file = {Witt15.pdf:pdf\\Witt15.pdf:PDF},
gscites = {1},
journal = {Imaging of Complications and Toxicity following Tumor Therapy},
optnote = {DIAG, RADIOLOGY},
year = {2015},
}

@Comment{jabref-meta: databaseType:biblatex;}

0 comments on commit a8a4a30

Please sign in to comment.