Stochastic co-teaching for training neural networks with unknown levels of label noise

Autor: Bob D. de Vos, Gino E. Jansen, Ivana Išgum

Publikováno v: Scientific Reports, Vol 13, Iss 1, Pp 1-15 (2023)

Abstract Label noise hampers supervised training of neural networks. However, data without label noise is often infeasible to attain, especially for medical tasks. Attaining high-quality medical labels would require a pool of experts and their consen

Externí odkaz: https://doaj.org/article/3e6d116ef6854261b54045fedd718295

Automatic segmentation with detection of local segmentation failures in cardiac MRI

Autor: Jörg Sander, Bob D. de Vos, Ivana Išgum

Publikováno v: Scientific Reports, Vol 10, Iss 1, Pp 1-19 (2020)

Abstract Segmentation of cardiac anatomical structures in cardiac magnetic resonance images (CMRI) is a prerequisite for automatic diagnosis and prognosis of cardiovascular diseases. To increase robustness and performance of segmentation methods this

Externí odkaz: https://doaj.org/article/d0ad7ca897184f47b52c544724f78830

Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Images

Autor: Richard A.P. Takx, Max A. Viergever, Elbrich M. Postma, Bob D. de Vos, Jelmer M. Wolterink, Tim Leiner, Ivana Išgum, Julia M. H. Noothout, Paul A.M. Smeets

Publikováno v: IEEE Transactions on Medical Imaging, 39(12), 4011-4022
IEEE transactions on medical imaging, 39(12):9139480, 4011-4022. Institute of Electrical and Electronics Engineers Inc.
IEEE Transactions on Medical Imaging 39 (2020) 12
IEEE transactions on medical imaging, 39(12):9139480, 4011-4022. IEEE

In this study, we propose a fast and accurate method to automatically localize anatomical landmarks in medical images. We employ a global-to-local localization approach using fully convolutional neural networks (FCNNs). First, a global FCNN localizes

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a687107af5146ff744aa22c6d284d93
https://doi.org/10.1109/tmi.2020.3009002

Evaluation of a Fully Automatic Deep Learning-Based Method for the Measurement of Psoas Muscle Area

Autor: Dennis Van Erck, Pim Moeskops, Josje D. Schoufour, Peter J. M. Weijs, Wilma J. M. Scholte Op Reimer, Martijn S. Van Mourik, Yvonne C. Janmaat, R. Nils Planken, Marije Vis, Jan Baan, Robert Hemke, Ivana Išgum, José P. Henriques, Bob D. De Vos, Ronak Delewi

Publikováno v: Frontiers in Nutrition, 9:781860, 1-8. Frontiers Media S.A.
Frontiers in Nutrition, 9:781860. Frontiers Media S.A.
van Erck, D, Moeskops, P, Schoufour, J D, Weijs, P J M, Scholte op Reimer, W J M, van Mourik, M S, Janmaat, Y C, Planken, R N, Vis, M, Baan, J, Hemke, R, Išgum, I, Henriques, J P, de Vos, B D & Delewi, R 2022, ' Evaluation of a Fully Automatic Deep Learning-Based Method for the Measurement of Psoas Muscle Area ', Frontiers in Nutrition, vol. 9, 781860 . https://doi.org/10.3389/fnut.2022.781860

BackgroundManual muscle mass assessment based on Computed Tomography (CT) scans is recognized as a good marker for malnutrition, sarcopenia, and adverse outcomes. However, manual muscle mass analysis is cumbersome and time consuming. An accurate full

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::856f3fa6f8a517f2df07a565086b2352
https://pubmed.ncbi.nlm.nih.gov/35634380

Deep Learning-Quantified Calcium Scores for Automatic Cardiovascular Mortality Prediction at Lung Screening Low-Dose CT

Autor: Pim A. de Jong, Ivana Išgum, Bob D. de Vos, Nikolas Lessmann

Publikováno v: Radiology: Cardiothoracic Imaging, 3
Radiology: Cardiothoracic Imaging, 3(2):e190219. Radiological Society of North America Inc.
Radiol Cardiothorac Imaging
Radiology. Cardiothoracic imaging, 3(2):e190219. Radiological Society of North America Inc.
Radiology: Cardiothoracic Imaging, 3, 2

Contains fulltext : 235733.pdf (Publisher’s version ) (Closed access) Purpose: To examine the prognostic value of location-specific arterial calcification quantities at lung screening low-dose CT for the prediction of cardiovascular disease (CVD) m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a9c9c9a893d6b499ee9fbfc8c3a4ae2
http://hdl.handle.net/2066/235733