dc.contributor.author
Büttner, Martha
dc.contributor.author
Schneider, Lisa
dc.contributor.author
Krasowski, Aleksander
dc.contributor.author
Krois, Joachim
dc.contributor.author
Feldberg, Ben
dc.contributor.author
Schwendicke, Falk
dc.date.accessioned
2023-09-25T11:15:38Z
dc.date.available
2023-09-25T11:15:38Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/40967
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-40688
dc.description.abstract
Supervised deep learning requires labelled data. On medical images, data is often labelled inconsistently (e.g., too large) with varying accuracies. We aimed to assess the impact of such label noise on dental calculus detection on bitewing radiographs. On 2584 bitewings calculus was accurately labeled using bounding boxes (BBs) and artificially increased and decreased stepwise, resulting in 30 consistently and 9 inconsistently noisy datasets. An object detection network (YOLOv5) was trained on each dataset and evaluated on noisy and accurate test data. Training on accurately labeled data yielded an mAP50: 0.77 (SD: 0.01). When trained on consistently too small BBs model performance significantly decreased on accurate and noisy test data. Model performance trained on consistently too large BBs decreased immediately on accurate test data (e.g., 200% BBs: mAP50: 0.24; SD: 0.05; p < 0.05), but only after drastically increasing BBs on noisy test data (e.g., 70,000%: mAP50: 0.75; SD: 0.01; p < 0.05). Models trained on inconsistent BB sizes showed a significant decrease of performance when deviating 20% or more from the original when tested on noisy data (mAP50: 0.74; SD: 0.02; p < 0.05), or 30% or more when tested on accurate data (mAP50: 0.76; SD: 0.01; p < 0.05). In conclusion, accurate predictions need accurate labeled data in the training process. Testing on noisy data may disguise the effects of noisy training data. Researchers should be aware of the relevance of accurately annotated data, especially when testing model performances.
en
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
dc.subject
artificial intelligence
en
dc.subject
machine learning
en
dc.subject
deep learning
en
dc.subject
computer vision
en
dc.subject
convolutional neural networks
en
dc.subject
digital imaging
en
dc.subject.ddc
600 Technik, Medizin, angewandte Wissenschaften::610 Medizin und Gesundheit::610 Medizin und Gesundheit
dc.title
Impact of Noisy Labels on Dental Deep Learning—Calculus Detection on Bitewing Radiographs
dc.type
Wissenschaftlicher Artikel
dcterms.bibliographicCitation.articlenumber
3058
dcterms.bibliographicCitation.doi
10.3390/jcm12093058
dcterms.bibliographicCitation.journaltitle
Journal of Clinical Medicine
dcterms.bibliographicCitation.number
9
dcterms.bibliographicCitation.originalpublishername
MDPI
dcterms.bibliographicCitation.volume
12
refubium.affiliation
Charité - Universitätsmedizin Berlin
refubium.resourceType.isindependentpub
no
dcterms.accessRights.openaire
open access
dcterms.bibliographicCitation.pmid
37176499
dcterms.isPartOf.eissn
2077-0383