Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
Open accessThe DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Abstract
Diagnosis and treatment guidance are aided by detecting relevant biomarkers in medical images. Although supervised deep learning can perform accurate segmentation of pathological areas, it is limited by requiring a priori definitions of these regions, large-scale annotations, and a representative patient cohort in the training set. In contrast, anomaly detection is not limited to specific definitions of pathologies and allows for training on healthy samples without annotation. Anomalous regions can then serve as candidates for biomarker discovery. Knowledge about normal anatomical structure brings implicit information for detecting anomalies. We propose to take advantage of this property using Bayesian deep learning, based on the assumption that epistemic uncertainties will correlate with anatomical deviations from a normal training set. A Bayesian U-Net is trained on a well-defined healthy environment using weak labels of healthy anatomy produced by existing methods. At test time, we capture epistemic uncertainty estimates of our model using Monte Carlo dropout. A novel post-processing technique is then applied to exploit these estimates and transfer their layered appearance to smooth blob-shaped segmentations of the anomalies. We experimentally validated this approach in retinal optical coherence tomography (OCT) images, using weak labels of retinal layers. Our method achieved a Dice index of 0.789 in an independent anomaly test set of age-related macular degeneration (AMD) cases. The resulting segmentations allowed very high accuracy for separating healthy and diseased cases with late wet AMD, dry geographic atrophy (GA), diabetic macular edema (DME) and retinal vein occlusion (RVO). Finally, we qualitatively observed that our approach can also detect other deviations in normal scans such as cut edge artifacts.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Hiasa al. [684] | et | 2019 | Bayesian U-Net | Segmentation | Cancer | 2 | MC dropout”
From A review of uncertainty quantification in deep learning: Techniques, applications and challenges (2021) · cites this paper as [684]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We used Kaiming initialization [43], Adam optimization [44], and a learning rate of 1 × 10−4 (multiplied by 0.”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“applied after each convolutional block, which consists of two 3×3 convolutions, each followed by batch-normalization [40] and a rectified linear unit (ReLU).”
MethodDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“We used Kaiming initialization [43], Adam optimization [44], and a learning rate of 1 × 10−4 (multiplied by 0.”
MethodA survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · cited 1×
“Automated methods can partially address these issues by exploiting the potential of deep learning [3].”
BackgroundDermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · cited 2×
“markers such as disease lesions [4], [7], [8], [34].”
BackgroundBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Wong, W. L., Su, X., Li, X., Cheung, C. M. G., Klein, R., Cheng, C.-Y., & Wong, T. Y. (2014) · The Lancet Global Health · doi:10.1016/s2214-109x(13)70145-1 · Cited by 5,331 · cited 1×
“Age-related macular degeneration (AMD) is one of the leading causes of blindness in the world [26].”
BackgroundIdentifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., et al. (2018) · Cell · doi:10.1016/j.cell.2018.02.010 · Cited by 4,842
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Kendall, A., & Gal, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.04977 · Cited by 3,088 · cited 5×
“Bayesian deep learning has emerged as an active field of research that aims to develop efficient tools for quantifying uncertainties [18]–[20].”
BackgroundMethodInfluentialClinically applicable deep learning for diagnosis and referral in retinal disease
De Fauw, J., Ledsam, J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., Askham, H., Glorot, X., O’Donoghue, B., Visentin, D., et al. (2018) · Nature Medicine · doi:10.1038/s41591-018-0107-6 · Cited by 2,639 · cited 2×
“markers such as disease lesions [4], [7], [8], [34].”
BackgroundUnsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-59050-9_12 · Cited by 2,627
Self-citationA Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1610.02136 · Cited by 1,968 · cited 1×
“Using the soft predictions of neural networks directly has been previously explored as an alternative to identify out-of-distribution samples [45], [46].”
BackgroundPrediction of cardiovascular risk factors from retinal fundus photographs via deep learning
Poplin, R., Varadarajan, A. V., Blumer, K., Liu, Y., McConnell, M. V., Corrado, G. S., Peng, L., & Webster, D. R. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0195-0 · Cited by 1,865 · cited 4×
“the incorporation of deep learning [32].”
BackgroundInfluentialClinical Classification of Age-related Macular Degeneration
Ferris, F. L., Wilkinson, C. P., Bird, A., Chakravarthy, U., Chew, E., Csaky, K., & Sadda, S. R. (2013) · Ophthalmology · doi:10.1016/j.ophtha.2012.10.036 · Cited by 1,863 · cited 2×
“According to the Beckman Initiative Classification [31], we allowed drusen below 63 μm in size as only visible alteration, as they normally do not result in visual impairment.”
MethodPimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649
CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D. Y., Bagul, A., Langlotz, C. P., Shpanskaya, K. S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.05225 · Cited by 1,219
Large scale deep learning for computer aided detection of mammographic lesions
Kooi, T., Litjens, G., van Ginneken, B., Gubern-Mérida, A., Sánchez, C. I., Mann, R., den Heeten, A., & Karssemeijer, N. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.07.007 · Cited by 965
Kendall, A., Badrinarayanan, V., & Cipolla, R. (2017) · Procedings of the British Machine Vision Conference 2017 · doi:10.5244/c.31.57 · Cited by 784
Artificial intelligence in retina
Schmidt-Erfurth, U., Sadeghipour, A., Gerendas, B. S., Waldstein, S. M., & Bogunović, H. (2018) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2018.07.004 · Cited by 779 · cited 3×
“In retinal OCT imaging, supervised methods have been extensively used [8], e.”
BackgroundMethodSelf-citationGarvin, M. K., Abramoff, M. D., Wu, X., Russell, S. R., Burns, T. L., & Sonka, M. (2009) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2009.2016958 · Cited by 626 · cited 6×
“We also took advantage of weak supervision by training our segmentation model with labels provided by an existing automated approach [24], which is known to perform accurately in healthy scans.”
MethodInfluentialFully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning
Schlegl, T., Waldstein, S. M., Bogunovic, H., Endstraßer, F., Sadeghipour, A., Philip, A.-M., Podkowinski, D., Gerendas, B. S., Langs, G., & Schmidt-Erfurth, U. (2018) · Ophthalmology · doi:10.1016/j.ophtha.2017.10.031 · Cited by 597 · cited 1×
“for segmentation of fluid [9], [10], drusen [11], hyperreflective material [12] or photoreceptor”
BackgroundSelf-citationBayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
Gal, Y., & Ghahramani, Z. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.02158 · Cited by 563
Leveraging uncertainty information from deep neural networks for disease detection
Leibig, C., Allken, V., Ayhan, M. S., Berens, P., & Wahl, S. (2017) · Scientific Reports · doi:10.1038/s41598-017-17876-z · Cited by 510 · cited 1×
“Furthermore, disease classification methods based on deep learning were observed to be benefited by the usage of epistemic uncertainties [21].”
BackgroundThe Development, Commercialization, and Impact of Optical Coherence Tomography
Fujimoto, J., & Swanson, E. (2016) · Investigative Opthalmology & Visual Science · doi:10.1167/iovs.16-19963 · Cited by 472 · cited 2×
“OCT is a non-invasive volumetric imaging technique that provides high resolution images of the retina and is currently one of the most important diagnostic modalities in ophthalmology [25].”
BackgroundNair, T., Precup, D., Arnold, D. L., & Arbel, T. (2020) · Medical Image Analysis · doi:10.1016/j.media.2019.101557 · Cited by 451
A paradigm shift in imaging biomarkers in neovascular age-related macular degeneration
Schmidt-Erfurth, U., & Waldstein, S. M. (2016) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2015.07.007 · Cited by 390 · cited 1×
“Predictive capability however remains to be limited and underlying pathogenetic mechanisms are not yet fully understood [30], meaning that there might be other unknown structures or patterns that are still needed to”
BackgroundSelf-citationTan, G. S., Cheung, N., Simó, R., Cheung, G. C. M., & Wong, T. Y. (2017) · The Lancet Diabetes & Endocrinology · doi:10.1016/s2213-8587(16)30052-3 · Cited by 361 · cited 9×
“Qualitative results of the central B-scan of DME, RVO and GA cases, respectively, are presented in Fig.”
BackgroundInfluentialKendall, A., Badrinarayanan, V., & Cipolla, R. (2015) · arXiv · doi:10.48550/arxiv.1511.02680 · Cited by 292 · cited 3×
“means of Monte Carlo (MC) dropout [18], [19].”
MethodBiomarker detection technologies and future directions
Nimse, S. B., Sonawane, M. D., Song, K.-S., & Kim, T. (2016) · The Analyst · doi:10.1039/c5an01790d · Cited by 275 · cited 1×
“B IOMARKER detection in medical imaging data plays a critical role in the context of disease diagnosis and treatment planning [1].”
BackgroundA baseline for detecting misclassified and out-of-distribution examples in neural networks
Hendrycks, D. (2025) · arXiv (Cornell University) · doi:10.57702/9gs720u1 · Cited by 196
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker DiscoveryPreprint
Schlegl, T., Seeböck, P., Waldstein, S. M., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05921 · Cited by 145 · cited 3×
“therefore our knowledge about the underlying pathogenesis of diseases [14], [17], [36].”
BackgroundMethodSelf-citationBogunovic, H., Montuoro, A., Baratsits, M., Karantonis, M. G., Waldstein, S. M., Schlanitz, F., & Schmidt-Erfurth, U. (2017) · Investigative Opthalmology & Visual Science · doi:10.1167/iovs.17-21789 · Cited by 143 · cited 1×
“Such a method has proven to be effective in normal subjects and is widely applied in ophthalmological studies [41], [42].”
Self-citationAnatomy and Physiology of the Retina
Hildebrand, G. D., & Fielder, A. R. (2010) · Springer eBooks · doi:10.1007/978-3-642-12041-1_2 · Cited by 133 · cited 1×
“Considering the fact that the cellular components of the retina are arranged in a layer-wise manner [47] and pathologies alter their appearance, using retinal layer information proved to be a particularly appropriate way to incorporate anatomical knowledge into the model.”
BackgroundJonas, J. B., Monés, J., Glacet-Bernard, A., & COSCAS, G. J. (2017) · Developments in ophthalmology · doi:10.1159/000455278 · Cited by 126
Towards a Glaucoma Risk Index Based on Simulated Hemodynamics from Fundus Images
Orlando, J. I., Barbosa‐Breda, J., Keer, K. V., Blaschko, M. B., Blanco, P. J., & Bulant, C. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00934-2_8 · Cited by 113
Self-citationUnsupervised Lesion Detection in Brain CT using Bayesian Convolutional Autoencoders
Pawlowski, N., Lee, M. C. H., Rajchl, M., McDonagh, S., Ferrante, E., Kamnitsas, K., Cooke, S. F., Stevenson, S., Khetani, A., Newman, T., et al. (2018) · Cited by 103
Unsupervised Identification of Disease Marker Candidates in Retinal OCT Imaging Data
Seebock, P., Waldstein, S. M., Klimscha, S., Bogunovic, H., Schlegl, T., Gerendas, B. S., Donner, R., Schmidt-Erfurth, U., & Langs, G. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2877080 · Cited by 101 · cited 11×
“Our approach is able to obtain a clear performance improvement compared to previous state-of-the-art in anomaly detection in OCTs [14].”
BackgroundMethodInfluentialSelf-citationJoltikov, K. A., Sesi, C., Castro, V., Davila, J. R., Anand, R., Khan, S. M., Farbman, N., Jackson, G. R., Johnson, C. A., & Gardner, T. W. (2018) · Investigative Ophthalmology & Visual Science · doi:10.1167/iovs.18-24955 · Cited by 99 · cited 5×
“U-Net [22], [23] on a set of healthy images using weak labels of the retinal layers, provided by a standard graph-based method for layer segmentation [24].”
BackgroundMethodInfluentialAsman, A. J., & Landman, B. A. (2011) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2011.2147795 · Cited by 93 · cited 1×
“Moreover, as it requires experts in the field to know every possible visual appearance of the regions of interest, results may suffer from intra- and inter-grader variability [2].”
BackgroundNair, T., Precup, D., Arnold, D. L., & Arbel, T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00928-1_74 · Cited by 92
Jonas, J. B., Pâques, M., Monés, J., & Glacet-Bernard, A. (2010) · Developments in ophthalmology · doi:10.1159/000320076 · Cited by 87
Orlando, J. I., Seebock, P., Bogunovic, H., Klimscha, S., Grechenig, C., Waldstein, S., Gerendas, B. S., & Schmidt-Erfurth, U. (2019) · 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) · doi:10.1109/isbi.2019.8759581 · Cited by 65 · cited 1×
“drusen [11], hyperreflective material [12] or photoreceptor disruptions [13].”
BackgroundSelf-citationTowards trustable machine learning
(2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0315-x · Cited by 64
Sidibé, D., Sankar, S., Lemaître, G., Rastgoo, M., Massich, J., Cheung, C. Y.-L., Tan, G. S. W., Miléa, D., Lamoureux, E. L., Wong, T. Y., et al. (2016) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2016.11.001 · Cited by 63 · cited 2×
“Multiple techniques have been proposed in the past for automated anomaly detection in OCT images [14], [17], [37], [38].”
BackgroundMethodLee, H., Kang, K. E., Chung, H., & Kim, H. C. (2018) · American Journal of Ophthalmology · doi:10.1016/j.ajo.2018.04.007 · Cited by 58 · cited 1×
“for segmentation of fluid [9], [10], drusen [11], hyperreflective material [12] or photoreceptor”
BackgroundLeveraging uncertainty information from deep neural networks for disease detectionPreprint
Leibig, C., Allken, V., Ayhan, M. S., et al. (2016) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/084210 · Cited by 53
Sedai, S., Antony, B., Mahapatra, D., & Garnavi, R. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00949-6_26 · Cited by 44 · cited 1×
“in [39] the epistemic uncertainty was provided as qualitative feedback to users.”
CNNs Enable Accurate and Fast Segmentation of Drusen in Optical Coherence Tomography
Zadeh, S. G., Wintergerst, M. W. M., Wiens, V., Thiele, S., Holz, F. G., Finger, R. P., & Schultz, T. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67558-9_8 · Cited by 42 · cited 1×
“drusen [11], hyperreflective material [12] or photoreceptor disruptions [13].”
BackgroundVogl, W.-D., Waldstein, S. M., Gerendas, B. S., Schmidt-Erfurth, U., & Langs, G. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2700213 · Cited by 41 · cited 1×
“Such a method has proven to be effective in normal subjects and is widely applied in ophthalmological studies [41], [42].”
Self-citationVogl, W.-D., Waldstein, S. M., Gerendas, B. S., Schlegl, T., Langs, G., & Schmidt-Erfurth, U. (2017) · Investigative Opthalmology & Visual Science · doi:10.1167/iovs.17-21878 · Cited by 37 · cited 1×
“Presence or changes in some of these features have been shown to correlate with visual function or disease progression [29].”
BackgroundSelf-citationFully Automated Segmentation of Hyperreflective Foci in Optical Coherence Tomography ImagesPreprint
Schlegl, T., Bogunović, H., Klimscha, S., Seeböck, P., Sadeghipour, A., Gerendas, B. S., Waldstein, S. M., Langs, G., & Schmidt-Erfurth, U. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.03278 · Cited by 28 · cited 1×
“drusen [11], hyperreflective material [12] or photoreceptor disruptions [13].”
BackgroundSelf-citationSallam, A. B., & Ellabban, A. A. (2017) · doi:10.1002/9781119058984.ch7 · Cited by 21
Pathology Hinting as the Combination of Automatic Segmentation with a Statistical Shape Model
Dufour, P. A., Abdillahi, H., Ćeklić, L., Wolf-Schnurrbusch, U. E. K., & Kowal, J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33454-2_74 · Cited by 19 · cited 2×
“Shape models were used in [37] to perform drusen detection.”
MethodTowards a glaucoma risk index based on simulated hemodynamics from fundus imagesPreprint
Orlando, J. I., Barbosa‐Breda, J., Keer, K. V., Blaschko, M. B., Blanco, P. J., & Bulant, C. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10273 · Cited by 3 · cited 1×
“by means of linear discriminant analysis [33].”
Self-citationMethods for Detection and Recovery of Out-of-Distribution Examples
Ratzlaff, N. (2018) · Cited by 1
Cited by
A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., et al. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.05.008 · Cited by 3,111
A survey of uncertainty in deep neural networks
Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., Kruspe, A., Triebel, R., Jung, P., Roscher, R., et al. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10562-9 · Cited by 1,406
“uncertainty is estimated in segmentation tasks using approximates of Bayesian inference [1], [2], [4], [152], [261], [262], [263], [264] or test-time data augmentation techniques [249].”
MethodA Unifying Review of Deep and Shallow Anomaly Detection
Ruff, L., Kauffmann, J. R., Vandermeulen, R. A., Montavon, G., Samek, W., Kloft, M., Dietterich, T. G., & Muller, K.-R. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3052449 · Cited by 914
Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00424 · Cited by 990
Deep learning and medical image processing for coronavirus (COVID-19) pandemic: A survey
Bhattacharya, S., Reddy Maddikunta, P. K., Pham, Q.-V., Gadekallu, T. R., Krishnan S, S. R., Chowdhary, C. L., Alazab, M., & Jalil Piran, M. (2021) · Sustainable Cities and Society · doi:10.1016/j.scs.2020.102589 · Cited by 483
“The authors in Seeb ¨ ock et al. (2019) use this idea to implement a Bayesian DL technique assuming that the epistemic uncertainties would relate to the anatomical eccentricities from the training dataset.”
Metadata
- Authors
- Seebock, P., Orlando, J. I., Schlegl, T., Waldstein, S. M., Bogunovic, H., Klimscha, S., Langs, G., & Schmidt-Erfurth, U.
- Affiliations
- Medical University of Vienna (AT)
- ORCID
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2020-01
- Volume
- 39
- Issue
- 1
- Pages
- 87-98
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2947805333
- Cited by
- 164
- References
- 56
- Citations by year
- 2026: 13 · 2025: 17 · 2024: 25 · 2023: 31 · 2022: 30 · 2021: 32 · 2020: 14
- FWCI
- 12.86
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Christian Doppler Forschungsgesellschaft
- Nvidia
- National Foundation for Research, Technology, and Development
- Austrian Science Fund (FWF I2714-B31)
- Vienna Science and Technology Fund (FA7464A0249, VRG12-009)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- anomaly detection, retinal optical coherence tomography, epistemic uncertainty, Monte Carlo dropout, retinal layer segmentation, weak labels, age-related macular degeneration, geographic atrophy, diabetic macular edema, retinal vein occlusion, biomarker discovery
- MeSH terms
- Supervised Machine Learning, Algorithms, Humans, Image Processing, Computer-Assisted, Retina, Artifacts, Tomography, Optical Coherence
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.