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].”
BackgroundMethodInfluential
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT. https://app.cochat.ai/papers/10.1109/tmi.2019.2919951
- The paper
- Seebock, P., Orlando, J. I., Schlegl, T., Waldstein, S. M., Bogunovic, H., Klimscha, S., Langs, G., & Schmidt-Erfurth, U. (2020). Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2019.2919951
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.