Bayesian convolutional neural network based MRI brain extraction on nonhuman primates
Open accessAbstract
Brain extraction or skull stripping of magnetic resonance images (MRI) is an essential step in neuroimaging studies, the accuracy of which can severely affect subsequent image processing procedures. Current automatic brain extraction methods demonstrate good results on human brains, but are often far from satisfactory on nonhuman primates, which are a necessary part of neuroscience research. To overcome the challenges of brain extraction in nonhuman primates, we propose a fully-automated brain extraction pipeline combining deep Bayesian convolutional neural network (CNN) and fully connected three-dimensional (3D) conditional random field (CRF). The deep Bayesian CNN, Bayesian SegNet, is used as the core segmentation engine. As a probabilistic network, it is not only able to perform accurate high-resolution pixel-wise brain segmentation, but also capable of measuring the model uncertainty by Monte Carlo sampling with dropout in the testing stage. Then, fully connected 3D CRF is used to refine the probability result from Bayesian SegNet in the whole 3D context of the brain volume. The proposed method was evaluated with a manually brain-extracted dataset comprising T1w images of 100 nonhuman primates. Our method outperforms six popular publicly available brain extraction packages and three well-established deep learning based methods with a mean Dice coefficient of 0.985 and a mean average symmetric surface distance of 0.220 mm. A better performance against all the compared methods was verified by statistical tests (all p-values < 10-4, two-sided, Bonferroni corrected). The maximum uncertainty of the model on nonhuman primate brain extraction has a mean value of 0.116 across all the 100 subjects. The behavior of the uncertainty was also studied, which shows the uncertainty increases as the training set size decreases, the number of inconsistent labels in the training set increases, or the inconsistency between the training set and the testing set increases.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 intraobserver agreement of the cartilage lesion detection system was far from perfect, likely due to multiple factors including inherent model uncertainty of the network structure, the stochastic nature of network training, and variation between the training and testing image data sets.
“However, the intraobserver agreement was far from perfect, which is likely due to multiple factors, including the inherent model uncertainty of the network structure (43,44), the stochastic nature of network training, and the variation between the training and testing image data sets (24,45).”
From Deep learning approach for evaluating knee MR images: achieving high diagnostic performance for cartilage lesion detection. (2018) · cites this paper as [24]
The VGG16 network has proven to be an effective and efficient network of feature extraction in many medical image applications, including tissue segmentation and image contrast conversion.
“More recently, the VGG16 network has proven to be an effective and efficient network of feature extraction in many medical image applications, including tissue segmentation (14,24–26) and image contrast conversion (27,28).”
From Deep learning approach for evaluating knee MR images: achieving high diagnostic performance for cartilage lesion detection. (2018) · cites this paper as [24]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
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 · see citing works
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 · see citing works
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.10.004 · Cited by 3,498 · see citing works
Deep MRI brain extraction: A 3D convolutional neural network for skull stripping
Kleesiek, J., Urban, G., Hubert, A., Schwarz, D., Maier-Hein, K., Bendszus, M., & Biller, A. (2016) · NeuroImage · doi:10.1016/j.neuroimage.2016.01.024 · Cited by 505 · see citing works
Amygdalar and hippocampal substrates of anxious temperament differ in their heritability
Oler, J. A., Fox, A. S., Shelton, S. E., Rogers, J., Dyer, T. D., Davidson, R. J., Shelledy, W., Oakes, T. R., Blangero, J., & Kalin, N. H. (2010) · Nature · doi:10.1038/nature09282 · Cited by 208 · see citing works
Self-citationEvolutionarily conserved prefrontal-amygdalar dysfunction in early-life anxiety
Birn, R. M., Shackman, A. J., Oler, J. A., Williams, L. E., McFarlin, D. R., Rogers, G. M., Shelton, S. E., Alexander, A. L., Pine, D. S., Slattery, M. J., et al. (2014) · Molecular Psychiatry · doi:10.1038/mp.2014.46 · Cited by 159 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Balki, I., Amirabadi, A., Levman, J., Martel, A. L., Emersic, Z., Meden, B., Garcia-Pedrero, A., Ramirez, S. C., Kong, D., Moody, A. R., et al. (2019) · Canadian Association of Radiologists Journal · doi:10.1016/j.carj.2019.06.002 · Cited by 299 · see citing works
Liu, F., Zhou, Z., Samsonov, A., Blankenbaker, D., Larison, W., Kanarek, A., Lian, K., Kambhampati, S., & Kijowski, R. (2018) · Radiology · doi:10.1148/radiol.2018172986 · Cited by 297 · see citing works
“However, the intraobserver agreement was far from perfect, which is likely due to multiple factors, including the inherent model uncertainty of the network structure (43,44), the stochastic nature of network training, and the variation between the training and testing image data sets (24,45).”
Self-citationHe, T., Kong, R., Holmes, A. J., Nguyen, M., Sabuncu, M. R., Eickhoff, S. B., Bzdok, D., Feng, J., & Yeo, B. T. T. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2019.116276 · Cited by 271 · see citing works
Integrating uncertainty in deep neural networks for MRI based stroke analysis
Herzog, L., Murina, E., Dürr, O., Wegener, S., & Sick, B. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101790 · Cited by 66 · see citing works
- Authors
- Zhao, G., Liu, F., Oler, J. A., Meyerand, M. E., Kalin, N. H., & Birn, R. M.
- Affiliations
- University of Wisconsin–Madison (US)
- Corresponding author
- Zhao, Gengyan
- Venue
- NeuroImage
- Publisher
- Elsevier BV
- Published
- 2018-07
- Volume
- 175
- Pages
- 32-44
- ISSN
- 1053-8119 (ISSN-L)
- PMC
- PMC6095475
- OpenAlex
- W2794613614
- Cited by
- 68
- References
- 6
- Citations by year
- 2026: 3 · 2025: 2 · 2024: 4 · 2023: 6 · 2022: 11 · 2021: 11 · 2020: 7 · 2019: 16 · 2018: 8
- FWCI
- 5.25
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- NeuroImage (acceptedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Institutes of Health (P50-MH100031, P51-OD011106, R01-MH046729, R01-MH081884)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Life Sciences › Neuroscience › Neurology › Brain Tumor Detection and Classification
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced MRI Techniques and Applications
- Keywords
- brain extraction, skull stripping, non-human primates, Bayesian convolutional neural network, conditional random fields, probabilistic segmentation, model uncertainty, Monte Carlo dropout, T1-weighted imaging, automated brain segmentation
- MeSH terms
- Deep Learning, Animals, Bayes Theorem, Brain, Female, Image Processing, Computer-Assisted, Macaca mulatta, Magnetic Resonance Imaging, Male, Neuroimaging
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
