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
Items 101–164 of 164
Xie, Q., Li, X., Li, Y., Lu, J., Ma, S., Zhao, Y., & Zhang, J. (2025) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2024.1532228 · Cited by 5
“…approaches have been explored to address the challenge of sparsely labeled medical image data (Perone and Cohen-Adad, 2018). extended the Mean Teacher method for MRI segmentation, while (Seeböck et al., 2019) proposed a Bayesian U-Net for abnormality detection in OCT image segmentation.”
PiPViT: Patch-based Visual Interpretable Prototypes for retinal image analysis
Oghbaie, M., Araújo, T., Reiter, G. S., & Bogunović, H. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109545 · Cited by 7
Alonso‐Caneiro, D., Kugelman, J., Tong, J., Kalloniatis, M., Chen, F. K., Read, S. A., & Collins, M. J. (2021) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta52665.2021.9647154 · Cited by 6
Saeedizadeh, N., Tajmirriahi, M., Haghani, A., Amini, Z., Pour, E. K., Esfahani, H. R., Fadakar, K., Kafieh, R., & Rabbani, H. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3185653 · Cited by 7
Emphasize of Deep CNN for Chest Radiology Images in the detection of COVID
Patil, P., & Narawade, V. E. (2022) · IEEE International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct54291.2022.9825370 · Cited by 4
Multi-resolution auto-encoder for anomaly detection of retinal imaging
Luo, Y., Ma, Y., & Yang, Z. (2024) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-023-01381-x · Cited by 5
“WeakAnD [11] applies a traditional image processing method to obtain an effective segmentation map of OCT data and uses the segmentation as the target to train a segmentation model with uncertainty.”
InfluentialMULTI-ATTENTION GHOSTNET FOR DEFORESTATION DETECTION IN THE AMAZON RAINFOREST
Ortega, M. X., da Costa, G. A. O. P., & Feitosa, R. Q. (2022) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-3-2022-657-2022 · Cited by 4
“Then, the final prediction μk(p) for pixel p and class k is the average over all n predictions y k(p) in a pixel-wise fashion (Seeböck et al., 2019):”
BackgroundMethodUncertainty Informed Anomaly Scores with Deep Learning: Robust Fault Detection with Limited Data
Zgraggen, J., Pizza, G., & Huber, L. G. (2022) · PHM Society European Conference · doi:10.36001/phme.2022.v7i1.3342 · Cited by 4
“The applications of uncertainty quantification (UQ) to machine learning anomaly detection are still rare, and these focus mostly on anomaly detection in images (Seeböck et al., 2019; Cai, Lu, & Sato, 2020; Sato, Hama, Matsubara, & Uehara, 2019).”
BackgroundED-AnoNet: Elastic Distortion-Based Unsupervised Network for OCT Image Anomaly Detection
Li, Y., Li, J., Shen, H., & Chen, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-18910-4_1 · Cited by 4
Xia, M., Yang, H., Huang, Y., Qu, Y., Zhou, G., Zhang, F., Wang, Y., & Guo, Y. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acb988 · Cited by 7
“TheMCUandDEUwere used in items like loss functions (Yu et al 2019), post-processing (Seebock et al 2020), guided backpropagation (Wickstrom et al 2020), iterative annotation suggestion (Li andYin 2020), etc.”
MethodFu, L.-W., Liu, C.-H., Jain, M., Chen, C. J., Wu, Y., Huang, S.-L. L., & Chen, H. H. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3327257 · Cited by 4
“OCTis an optical imaging technique widely adopted in the biomedical field [4], [5], [6], [7], [8], [9], [10].”
BackgroundJoy, T. T., Sedai, S., & Garnavi, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.08888 · Cited by 6
Uncertainty‐guided cross‐level fusion network for retinal OCT image segmentation
Wang, J., Zhu, W., Xiang, D., Chen, X., Peng, T., Peng, Q., Wang, M., & Shi, F. (2025) · Medical Physics · doi:10.1002/mp.18102 · Cited by 4
“Seebock et al. 20 proposed a Bayesian U-Net using weak supervision and Monte Carlo dropout to quantify uncertainty, which is transformed into anomaly segmentation results, later extended to multi-class segmentation.”
Improving Vision Anomaly Detection With the Guidance of Language Modality
Chen, D., Pan, K., Dai, G., Wang, G., Zhuang, Y., Tang, S., & Xu, M. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521813 · Cited by 12
“The wide applications of AD, such as event detection in earth fields [4], [5], medical diagnosis and disease detection [6]–[8], industrial defect detection [9], [10] and video surveillance [11]–[13], makes it a critical task and have attracted more and more attention.”
Lu, C.-G., Guo, Z.-T., Zhang, D., Mou, L., Yuan, J.-L., Ma, S.-D., Chen, D., Zhao, Y., Xia, K., & Zhang, J. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3531496 · Cited by 4
Li, S., Chen, W., Xing, K., Wang, H., Zhang, Y., & Kang, M. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113124 · Cited by 3
RDT-Net: A Novel Diffusion-Based Network for Intracranial Hemorrhage Segmentation
Zhang, F., Guo, J., Ma, Q., Zhang, X., & Zhang, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0030-7_12 · Cited by 3
Confidence-Aware and Self-supervised Image Anomaly Localisation
Müller, J. P., Baugh, M., Tan, J., Dombrowski, M., & Kainz, B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44336-7_18 · Cited by 9
Exploring Structure-Wise Uncertainty for 3D Medical Image Segmentation
Vasiliuk, A., Frolova, D., Belyaev, M., & Shirokikh, B. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-6775-6_2 · Cited by 5
Uncertainty-aware Generalized Adaptive CycleGANPreprint
Upadhyay, U., Chen, Y., & Akata, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11747 · Cited by 8
“However, for such critical applications, confidence in the network’s predictions is desirable (Mehta et al., 2020; Seeböck et al., 2019).”
BackgroundLi, Y., Yu, B., Zhao, X., Si, M., Yang, M., Cui, W., Zhou, Y., Fu, S., Wang, H., & Zhang, H. (2025) · Applied Optics · doi:10.1364/ao.547758 · Cited by 2
Quantifying Uncertainty in Deep Learning: Methods, Challenges, and Future Directions
Alaba, S. Y., & Motai, Y. (2026) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2026.3684025 · Cited by 3
Generative AI in different imaging modalities for disease diagnosis: A review
Ali, T. M., Zia‐ur‐Rehman, Hijji, M., Ayaz, M., Albelwi, S. A., & Ijaz, M. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131162 · Cited by 4
Shen, J. (2022) · Computational and Mathematical Methods in Medicine · doi:10.1155/2022/3235504 · Cited by 2
“How to segment medical image data accurately and quickly and optimize the segmentation effect is the key to image segmentation at the present stage [21].”
BackgroundAn improved dynamic-layered classification of retinal diseases
Nagamani, G. M., & Sudhakar, T. (2023) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v13.i1.pp417-429 · Cited by 2
“Seebock et al. [15] proposed the Bayesian deep learning approach which is used to detect the anomaly deviations from the training set.”
MethodA robust segmentation of retinal fluids from OCT images using MCFAR-net
Pavani, P. G., Biswal, B. B., Kandula, S. R., Biswal, P. K., Siddartha, G., Niranjan, T., & Bala Subrahmanyam, N. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128059 · Cited by 5
Jung, J., Yang, M., Won, H., Kim, J., Han, J. M., Hwang, J. S., Hwang, D. D.-J., & Han, J. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00867 · Cited by 3
“For instance, Seeböck et al. [54] proposed Bayesian U-Net with test-time Monte Carlo Dropout (MC Dropout) [15] for capturing epistemic uncertainty in OCT segmentation.”
Anomaly Detection Using Generative Models and Sum-Product Networks in Mammography Scans
Dietrichstein, M., Major, D., Trapp, M., Wimmer, M., Lenis, D., Winter, P., Berg, A., Neubauer, T., & Bühler, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-18576-2_8 · Cited by 5
“Examples are the application of Gaussian Mixture Models (GMMs) [2] for brain lesion detection as well as Bayesian U-Nets for OCT anomaly detection [15].”
MethodLightGBM-RF: A Hybrid Model for Anomaly Detection in Smart Building
Ekpo, O., Takyi, K., & Gyening, R.-M. O. M. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-8445-7_3 · Cited by 2
Shiihara, H., Sonoda, S., Terasaki, H., Fujiwara, K., Funatsu, R., Shiba, Y., Kumagai, Y., Honda, N., & Sakamoto, T. (2023) · PLoS ONE · doi:10.1371/journal.pone.0283214 · Cited by 2
“reported an AI algorithm for detecting abnormalities in OCT-B scan images of the retina [17].”
MethodSmida, J., Bose, A. S. C., Jarallah, N. A., Smida, A., & Koushaji, G. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10252324 · Cited by 2
Hybrid Dual-Heterogeneous Knowledge Distillation Network for Anomaly Detection in Retinal OCT Images
Xu, M., Wei, H., Nie, Z., Zhou, X., Fu, B., Yan, H., Wan, Y., & Song, W. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3650072 · Cited by 1
“This is particularly important for optical coherence tomography (OCT) [4], [5], a non-invasive volumetric modality widely used in ophthalmological diagnostics [6], [7], where annotation is especially challenging for rare or complex diseases and more demanding than for natural images [8], [9].”
A Lightweight Modified Adaptive UNet for Nucleus Segmentation
Khan, M. R. K., Mohaidat, T., & Khalil, K. (2026) · Sensors · doi:10.3390/s26020665 · Cited by 1
“This framework employs Bayesian optimization techniques [40], traversing the search space to identify promising operations, thus facilitating an efficient neural architecture search tailored to hyperparameter tuning.”
Li, J. W., Xie, Z., Shi, J., Chang, Y., & Chen, G. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115416 · Cited by 1
Predicting Visual Acuity in Patients Treated for AMD
Marginean, B.-A., Groza, A. P., Muntean, G. A., & Nicoară, S. (2022) · Diagnostics · doi:10.3390/diagnostics12061504 · Cited by 1
“performed segmentation of the areas that contained intraretinal cystoid fluid using an anomaly detection approach [20].”
MethodPipvit: Patch-Based Visual Interpretable Prototypes for Retinal Image AnalysisPreprint
Oghbaie, M., Araújo, T., & Bogunović, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5336537 · Cited by 1
Seeböck, P., Orlando, J. I., Schlegl, T., Waldstein, S. M., Bogunović, H., Klimscha, S., Langs, G., & Schmidt-Erfurth, U. M. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2972082
Self-citationVarious OCT Segmentation and Classification Techniques
Joy, N. (2020) · International Journal of Information Systems and Computer Sciences · doi:10.30534/ijiscs/2020/05932020
Tian, Y., Liu, F., Pang, G., Chen, Y., Liu, Y., Verjans, J. W. H., Singh, R., & Carneiro, G. (2021) · arXiv (Cornell University)
Joint Use of Skip Connections and Synthetic Corruption for Anomaly Detection with Autoencoders
Collin, A.-S., & Vleeschouwer, C. D. (2021) · Springer series in reliability engineering · doi:10.1007/978-3-030-83819-5_8 · Cited by 1
The anomaly segmentation via dynamic branch fusion
Liu, Z., Zhou, E., Yang, S., Zhuang, Z., & Ma, T. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671721
Elbarougy, R., Behery, G. M., Younes, Y. M., & Aboghrara, E. (2022) · International Journal of Computer Applications · doi:10.5120/ijca2022921943
(2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2980809
(2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2960787
Survey of Image Anomaly DetectionPreprint
Ghamry, F. M., El‐Banby, G. M., El‐Fishawy, A. S., El‐Samie, F. E. A., & Dessouky, M. I. (2022) · Research Square · doi:10.21203/rs.3.rs-1890977/v1
A Comprehensive Study of Machine Learning Techniques for Diabetic Retinopathy Detection
Kumari, R., Kumar, S., & Godara, S. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-3679-1_13
Normative Prior Network for Anomaly Segmentation in Retinal OCT Images
Zhou, X., Dong, J., Li, X., Han, T., Hou, Q., & Gao, X. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-0923-0_40
Anomaly Detection based on Broad Leaning System for Rolling Element Bearing Fault Diagnosis
Yang, L., Yang, Z., Zheng, Z., He, L., Li, F., & Chen, C. L. P. (2022) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3544793.3560408
“Anomaly detection (AD) [4, 24, 28] is one of the most important applications among many smart city applications [6–8, 35], and have been widely applied in a variety of domains, including cybersecurity [2, 32], medical diagnosis [9, 14, 30], fault and damage detection [1, 20, 34].”
BackgroundComparative Analysis on Deep Learning Algorithms for Detecting Retinal Diseases Using OCT Images
Nagamani, G. M., & Karthikeyan, S. (2023) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-99-0609-3_36
Hong-Jae, L., Cho, Y., Kwak, D.-Y., & Lee, J. (2023) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon51785.2023.10312549
“The authors in [17] introduced Bayesian bidirectional long short-term memory network (BLSTM) model for anomaly detection in satellite telemetry data.”
BackgroundPuri, A., & Krueger, R. R. (2024) · Research Square · doi:10.21203/rs.3.rs-4854925/v1
On The Local Geometry of the Pet Reconstruction Problem
Merabet, R., Sureau, F. C., & Trouvé, A. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635309
“While the former has been widely studied with techniques such as the so-called Monte-Carlo dropout [6] and its application in medical imaging [7], we focus in this work on aleatoric uncertainties, intrinsic to the PET reconstruction problem and source of instabilities and biases as shown in [3] in…”
MethodSelf-Healing Model from Uncertain Data
Ciu, A.-V., & Marginean, A. N. (2024) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp63557.2024.10793040
“Monte-Carlo (MC) Dropout is a technique used in machine learning to estimate model uncertainty ( [5], [8]).”
Out-of-distribution Detection via Nearest Neighbors and Null Vectors on Principal Feature Space
Nguyen, T., Tong, M. N., Lu, H. M., & Le, B. V. (2024) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc62082.2024.10826743
Smith, J. C., & Paraskevopoulou, C. (2025) · Infrastructures · doi:10.3390/infrastructures10040098 · Cited by 2
Sáez-Maldonado, F. J., García, L., Cooper, L., Goldstein, J. A., Molina, R., & Katsaggelos, A. K. (2025) · IEEE Access · doi:10.1109/access.2025.3593420 · Cited by 2
“Furthermore, a probabilistic uncertainty estimation is proposed in [33] using a Bayesian U-net to detect anomalies in OCT images.”
Unsupervised anomaly detection for medical image classification using masked denoising autoencoder
Qu, G., Pan, H., Yang, C., & Lin, Y. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114388 · Cited by 3
Yitao, 胡. H., Gongpu, 蓝. L., jingjiang, 许. X., Jia, 秦. Q., Lin, 安. A., & Yanping, 黄. H. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop251041
Zhang, Q., Chen, X., He, Z., Wang, K., Wu, L., Shen, H., & Sun, J. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.103939 · Cited by 2
Zhou, X., Niu, S., Han, X., Li, X., Gao, X., Feng, G., & Shi, J. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3667146
“UAD [23] is aimed at identifying unexpected behaviors by leveraging only normal data for model training, and it has been applied in various fields, such as defect detection [24], lesion detection [15] and tra ffi c monitoring [25].”
InfluentialExtraction automatique de biomarqueurs sur examens tomodensitométriques standards
Lartaud, P.-J. (2022) · theses.fr (ABES) · doi:10.70675/a41cd36fz1d22z4a94z96fcz5fa1cbe7c6c4
Wittmann, A. M., Seeböck, P., Heger, K. A., Egger, D., Langs, G., & Waldstein, S. M. (2026) · Journal of Ophthalmology · doi:10.1155/joph/9792133
“Well-defned hyporefective regions, such as IRF and SRF, and hyperrefective structures, such as DRIL, SHRM, ERM, HF, drusen, PED, and atrophy, were reliably identifed across multiple studies [6,12, 71, 78,123–125].”
InfluentialSelf-citationAnatomic-Decoupling Adaptation: A Unified Framework for Zero/Few-Shot Medical Anomaly Detection
Lin, Z., Wang, F., Cai, W., & Cai, H. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810835
“Standard visual encoders are prone to misjudge such high-frequency patterns as abnormalities, resulting in the masking of true lesions [5, 12, 29, 33].”
Tran, T. T., Do, M. K., Duy, P. N., & Lee, M. H. (2026) · doi:10.1109/cvprf71909.2026.00497 · Cited by 1
“For example, WeakAnD [33] leverages Bayes U-Net [32], which is trained on healthy data to model epistemic uncertainty as an indicator of anatomical deviations, while Han et al. proposed MADGAN [13], based on GAN [12] with adjacent slices, which enables better exploitation of 3D data to classify…”
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.