On modelling label uncertainty in deep neural networks: Automatic estimation of intra-observer variability in 2d echocardiography quality assessment
Open accessThe DOI matches its Crossref record; 55 of the 56 references it cites were found in a registry or an index.
Abstract
Uncertainty of labels in clinical data resulting from intra-observer variability can have direct impact on the reliability of assessments made by deep neural networks. In this paper, we propose a method for modelling such uncertainty in the context of 2D echocardiography (echo), which is a routine procedure for detecting cardiovascular disease at point-of-care. Echo imaging quality and acquisition time is highly dependent on the operator's experience level. Recent developments have shown the possibility of automating echo image quality quantification by mapping an expert's assessment of quality to the echo image via deep learning techniques. Nevertheless, the observer variability in the expert's assessment can impact the quality quantification accuracy. Here, we aim to model the intra-observer variability in echo quality assessment as an aleatoric uncertainty modelling regression problem with the introduction of a novel method that handles the regression problem with categorical labels. A key feature of our design is that only a single forward pass is sufficient to estimate the level of uncertainty for the network output. Compared to the 0.11 ± 0.09 absolute error (in a scale from 0 to 1) archived by the conventional regression method, the proposed method brings the error down to 0.09 ± 0.08, where the improvement is statistically significant and equivalents to 5.7% test accuracy improvement. The simplicity of the proposed approach means that it could be generalized to other applications of deep learning in medical imaging, where there is often uncertainty in clinical labels.
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 cited source doesn’t support the claim as written.
In the citing paper
“Raghu al. [688] | et | 2019 | N/A | Classification | DR | 1 | DUP (Direct Uncertainty Pre- diction )”
From A review of uncertainty quantification in deep learning: Techniques, applications and challenges (2021) · cites this paper as [688]
Checked by a reasoning model — may be wrong.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 6×
“In parallel to the Mean and STD modules, the LSTM features are also fed to compute an additional value lambda (softmaxed over the 10 steps) to be the weighting parameter for each component.”
MethodInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 3×
“The Adam [52] optimizer is 1The symbols defined in Fig.”
MethodInfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
(2014) · Cited by 33,419
Batch 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×
“, 3 × 3 filter size with stride 1, no padding, batchnormalized [46], and use ReLU [47] activation function.”
MethodDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 2×
“The soft targets methods [41], [42] are used as regularization techniques for training a small model with the predictions inferred from a high complexity model or an ensemble of them (trained from the same dataset), for the purposes of capturing the knowledge of the high complexity models with fewer model parameters (…”
BackgroundMethod(2010) · International Conference on Machine Learning · Cited by 13,995
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 1×
“performance variations may be subtle when the deployed number of units/parameters are similar [49]–[51].”
BackgroundDropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471 · cited 2×
“is one of the commonly used Bayesian inference approximation method [36], which has been used in medical imaging to derive robust solutions for disease detection, lesion/organ segmentation [37]–[39].”
MethodBayesian Learning for Neural Networks
Neal, R. M. (1996) · Lecture Notes in Statistics · doi:10.1007/978-1-4612-0745-0 · Cited by 4,276 · cited 2×
“Several Bayesian inference approaches and more recent Bayesian neural networks (BNN) [25], [26], [27], [28] are designed to address the uncertainty in the induced classifier by imposing a prior distribution over model parameters.”
Method
Research works printed but not linked: 1
- 2019, Echocardiography in ICU—Main Views
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
Seoni, S., Jahmunah, V., Salvi, M., Barua, P. D., Molinari, F., & Acharya, U. R. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107441 · Cited by 239
Huang, L., Ruan, S., Xing, Y., & Feng, M. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103223 · Cited by 121
Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging
Komatsu, M., Sakai, A., Dozen, A., Shozu, K., Yasutomi, S., Machino, H., Asada, K., Kaneko, S., & Hamamoto, R. (2021) · Biomedicines · doi:10.3390/biomedicines9070720 · Cited by 114
“proposed a quality assessment method for cardiac US images through modeling the label uncertainty in CNNs resulting from intra-observer variability in the labeling [100].”
MethodUlloa, A., Jing, L., Good, C. W., vanMaanen, D. P., Raghunath, S. M., Suever, J. D., Nevius, C. D., Wehner, G. J., Hartzel, D. N., Leader, J. B., et al. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-020-00667-9 · Cited by 84
Metadata
- Authors
- Liao, Z., Girgis, H., Abdi, A., Vaseli, H., Hetherington, J., Rohling, R., Gin, K., Tsang, T., & Abolmaesumi, P.
- Affiliations
- University of British Columbia (CA)
- ORCID
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2020-06
- Volume
- 39
- Issue
- 6
- Pages
- 1868-1883
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2996089546
- Cited by
- 56
- References
- 56
- Citations by year
- 2026: 8 · 2025: 11 · 2024: 6 · 2023: 11 · 2022: 6 · 2021: 10 · 2020: 4
- FWCI
- 1.59
- 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
- Canadian Institutes of Health Research
- Natural Sciences and Engineering Research Council of Canada
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Keywords
- label uncertainty, intraobserver variability, two-dimensional echocardiography, aleatoric uncertainty, uncertainty estimation, categorical regression, single forward pass
- MeSH terms
- Echocardiography, Humans, Reproducibility of Results, Observer Variation, Neural Networks, Computer, Uncertainty
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: On modelling label uncertainty in deep neural networks: Automatic estimation of intra-observer variability in 2d echocardiography quality assessment. https://app.cochat.ai/papers/10.1109/tmi.2019.2959209
- The paper
- Liao, Z., Girgis, H., Abdi, A., Vaseli, H., Hetherington, J., Rohling, R., Gin, K., Tsang, T., & Abolmaesumi, P. (2020). On modelling label uncertainty in deep neural networks: Automatic estimation of intra-observer variability in 2d echocardiography quality assessment. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2019.2959209
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.