Explanation and Use of Uncertainty Quantified by Bayesian Neural Network Classifiers for Breast Histopathology Images
Open accessPublished version of a preprint
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Despite the promise of Convolutional neural network (CNN) based classification models for histopathological images, it is infeasible to quantify its uncertainties. Moreover, CNNs may suffer from overfitting when the data is biased. We show that Bayesian-CNN can overcome these limitations by regularizing automatically and by quantifying the uncertainty. We have developed a novel technique to utilize the uncertainties provided by the Bayesian-CNN that significantly improves the performance on a large fraction of the test data (about 6% improvement in accuracy on 77% of test data). Further, we provide a novel explanation for the uncertainty by projecting the data into a low dimensional space through a nonlinear dimensionality reduction technique. This dimensionality reduction enables interpretation of the test data through visualization and reveals the structure of the data in a low dimensional feature space. We show that the Bayesian-CNN can perform much better than the state-of-the-art transfer learning CNN (TL-CNN) by reducing the false negative and false positive by 11% and 7.7% respectively for the present data set. It achieves this performance with only 1.86 million parameters as compared to 134.33 million for TL-CNN. Besides, we modify the Bayesian-CNN by introducing a stochastic adaptive activation function. The modified Bayesian-CNN performs slightly better than Bayesian-CNN on all performance metrics and significantly reduces the number of false negatives and false positives (3% reduction for both). We also show that these results are statistically significant by performing McNemar's statistical significance test. This work shows the advantages of Bayesian-CNN against the state-of-the-art, explains and utilizes the uncertainties for histopathological images. It should find applications in various medical image classifications.
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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms
Dietterich, T. G. (1998) · Neural Computation · doi:10.1162/089976698300017197 · Cited by 3,840 · cited 1×
“The McNemar’s test [66] is performed and the results show that the difference in performance is statistically significant (p < 0.”
MethodA systematic study of the class imbalance problem in convolutional neural networks
Buda, M., Maki, A., & Mazurowski, M. A. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.011 · Cited by 3,088 · cited 1×
“CNN is known to perform poorly for biased data set [62].”
BackgroundWhat 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 1×
“[47] provided a Bayesian deep learning framework combining aleatoric and epistemic uncertainties.”
BackgroundHistopathological Image Analysis: A Review
Gurcan, M. N., Boucheron, L. E., Can, A., Madabhushi, A., Rajpoot, N. M., & Yener, B. (2009) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2009.2034865 · Cited by 2,052
Computer-aided diagnosis in medical imaging: historical review, current status and future potential
Doi, K. (2007) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2007.02.002 · Cited by 1,855
Weight Uncertainty in Neural Networks
Blundell, C., Cornebise, J., Kavukcuoglu, K., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1505.05424 · Cited by 1,342 · cited 4×
“[44] introduced an efficient algorithm called “Bayes by backprop”.”
BackgroundMethodInfluentialSirinukunwattana, K., Raza, S. E. A., Tsang, Y.-W., Snead, D. R. J., Cree, I. A., & Rajpoot, N. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2525803 · Cited by 1,224
The need for uncertainty quantification in machine-assisted medical decision making
Begoli, E., Bhattacharya, T., & Kusnezov, D. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-018-0004-1 · Cited by 597 · cited 1×
“To evaluate the confidence of predictions, uncertainty quantification is important [42].”
Background
Research works printed but not linked: 55
- Wild, 2014, World Cancer Report 2014
- 10.1001/jamaoncol.2018.2706 · DOI · Paper page
- 10.1186/bcr932 · DOI · Paper page
- 10.1038/s41598-017-04075-z · DOI · Paper page
- 10.1146/annurev-pathol-011811-120902 · DOI · Paper page
- 10.1111/j.1365-2559.2011.03814.x · DOI · Paper page
- 10.1016/j.compmedimag.2011.02.006 · DOI · Paper page
- 10.1016/j.imu.2016.11.001 · DOI · Paper page
- 10.1109/TMI.2013.2275151 · DOI · Paper page
- 10.1109/JSYST.2013.2279415 · DOI · Paper page
- 10.1016/j.compbiomed.2013.08.003 · DOI · Paper page
- 10.1016/j.procs.2016.04.224 · DOI · Paper page
- 10.1007/s00138-012-0459-8 · DOI
- 10.1109/TBME.2015.2496264 · DOI · Paper page
- 10.1109/TMI.2017.2758580 · DOI · Paper page
- 10.1109/ICPR.2016.7900002 · DOI · Paper page
- 10.1117/12.2043872 · DOI · Paper page
- 10.1109/IJCNN.2016.7727519 · DOI · Paper page
- 10.1371/journal.pone.0177544 · DOI · Paper page
- 10.1109/TMI.2019.2891305 · DOI · Paper page
- 10.1109/TPAMI.2016.2644615 · DOI · Paper page
- 10.1109/ACCESS.2019.2898044 · DOI · Paper page
- 10.1109/TMI.2019.2948026 · DOI · Paper page
- 10.1109/TMI.2019.2962013 · DOI
- 10.14569/IJACSA.2018.090645 · DOI
- Motlagh, 2018, Breast cancer histopathological image classification: A deep learning approach, Biorxiv
- 10.3389/fgene.2019.00080 · DOI · Paper page
- 10.1016/j.media.2019.05.010 · DOI · Paper page
- 10.1007/978-3-319-93000-8_91 · DOI
- 10.1007/978-3-319-93000-8_106 · DOI
- 10.1007/978-3-319-93000-8_87 · DOI
- 10.1109/CVPR.2017.243 · DOI · Paper page
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
- Simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556 · arXiv
- 10.5555/2999134.2999257 · doi:10.5555/2999134.2999257
- Shridhar, 2019, A comprehensive guide to Bayesian convolutional neural network with variational inference, arXiv:1901.02731 · arXiv
- Shridhar, 2018, Uncertainty estimations by softplus normalization in Bayesian convolutional neural networks with variational inference, arXiv:1806.05978 · arXiv
- 10.5555/3295222.3295309 · doi:10.5555/3295222.3295309
- Kwon, Uncertainty quantification using Bayesian neural networks in classification: Application to ischemic stroke lesion segmentation
- 10.1038/s41598-019-50587-1 · DOI · Paper page
- 10.1016/j.neucom.2017.06.070 · DOI · Paper page
- 10.1016/j.jcp.2019.109136 · DOI · Paper page
- 10.2352/ISSN.2470-1173.2016.19.COIMG-149 · DOI
- Mooney, 2017, Breast Histopathology Images
- Van der Maaten, 2008, Visualizing data using t-SNE, J. Mach. Learn. Res., 9, 1
- Bergstra, Algorithms for hyper-parameter optimization, 24, 1
- Bergstra, Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures, 115
- 10.1109/TMI.2016.2528162 · DOI · Paper page
- Bishop, 2006, Pattern Recognition and Machine Learning
- Orr, 2003, Neural Networks: Tricks of the Trade
- Friedman, 2001, The Elements of Statistical Learning, 1
- LeCun, 1998, The MNIST Database of Handwritten Digits
- 10.1177/001316446002000104 · DOI · Paper page
- 10.1371/journal.pone.0202121 · DOI · Paper page
- 10.1371/journal.pone.0242301 · DOI
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
Deep learning in cancer diagnosis, prognosis and treatment selection
Tran, K. A., Kondrashova, O., Bradley, A., Williams, E. D., Pearson, J. V., & Waddell, N. (2021) · Genome Medicine · doi:10.1186/s13073-021-00968-x · Cited by 932
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
Iacucci, M., Santacroce, G., Zammarchi, I., Maeda, Y., Del Amor, R., Meseguer, P., Kolawole, B. B., Chaudhari, U., Di Sabatino, A., Danese, S., et al. (2024) · The Lancet Gastroenterology & Hepatology · doi:10.1016/s2468-1253(24)00053-0 · Cited by 73
Self-citation
Metadata
- Authors
- Thiagarajan, P., Khairnar, P., & Ghosh, S.
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2022-04
- Volume
- 41
- Issue
- 4
- Pages
- 815-825
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W3211109300
- Cited by
- 57
- References
- 14
- FWCI
- 2.82
- Type
- journal article
- Language
- en
- Open access
- gold
- Licence
- Funders
- High Performance Computing (HPC) Facilities through SUPERIOR at Michigan Technological University
- Extreme Science and Engineering Discovery Environment (MSS200004)
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: Explanation and Use of Uncertainty Quantified by Bayesian Neural Network Classifiers for Breast Histopathology Images. https://app.cochat.ai/papers/10.1109/tmi.2021.3123300
- The paper
- Thiagarajan, P., Khairnar, P., & Ghosh, S. (2022). Explanation and Use of Uncertainty Quantified by Bayesian Neural Network Classifiers for Breast Histopathology Images. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2021.3123300
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.