The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Asymmetric Loss Functions and Deep Densely-Connected Networks for Highly-Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection
Open accessAbstract
Fully convolutional deep neural networks have been asserted to be fast and precise frameworks with great potential in image segmentation. One of the major challenges in training such networks raises when the data are unbalanced, which is common in many medical imaging applications, such as lesion segmentation, where lesion class voxels are often much lower in numbers than non-lesion voxels. A trained network with unbalanced data may make predictions with high precision and low recall, being severely biased toward the non-lesion class which is particularly undesired in most medical applications where false negatives are actually more important than false positives. Various methods have been proposed to address this problem, including two-step training, sample re-weighting, balanced sampling, and more recently, similarity loss functions and focal loss. In this paper, we fully trained convolutional deep neural networks using an asymmetric similarity loss function to mitigate the issue of data imbalance and achieve much better tradeoff between precision and recall. To this end, we developed a 3D fully convolutional densely connected network (FC-DenseNet) with large overlapping image patches as input and an asymmetric similarity loss layer based on Tversky index (using$F_\beta $scores). We used large overlapping image patches as inputs for intrinsic and extrinsic data augmentation, a patch selection algorithm, and a patch prediction fusion strategy using B-spline weighted soft voting to account for the uncertainty of prediction in patch borders. We applied this method to multiple sclerosis (MS) lesion segmentation based on two different datasets of MSSEG 2016 and ISBI longitudinal MS lesion segmentation challenge, where we achieved average Dice similarity coefficients of 69.9% and 65.74%, respectively, achieving top performance in both the challenges. We compared the performance of our network trained with$F_\beta $loss, focal loss, and generalized Dice loss functions. Through September 2018, our network trained with focal loss ranked first according to the ISBI challenge overall score and resulted in the lowest reported lesion false positive rate among all submitted methods. Our network trained with the asymmetric similarity loss led to the lowest surface distance and the best lesion true positive rate that is arguably the most important performance metric in a clinical decision support system for lesion detection. The asymmetric similarity loss function based on$F_\beta $scores allows training networks that make a better balance between precision and recall in highly unbalanced image segmentation. We achieved superior performance in MS lesion segmentation using a patch-wise 3D FC-DenseNet with a patch prediction fusion strategy, trained with asymmetric similarity loss functions.
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
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
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931 · cited 15×
“To evaluate the effect of the asymmetric loss function in making the trade-off between precision and recall, and compare it with the Dice loss function (which is the harmonic mean of precision and recall) in MS lesion segmentation, we trained our FCNs with different β values on the MSSEG dataset.”
BackgroundMethodInfluential3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_49 · Cited by 7,945
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 · cited 1×
“Recent medical image processing literature shows significant progress towards automatic segmentation of brain lesions [1], [2], tumors [3]–[5], and neuroanatomy [6]–[8] using 2D networks [3], [6], [9], and more recently using 3D network architectures [2], [8].”
BackgroundBrain tumor segmentation with Deep Neural Networks
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., & Larochelle, H. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.05.004 · Cited by 3,278
Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations
Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S., & Jorge Cardoso, M. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-67558-9_28 · Cited by 2,829
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images
Pereira, S., Pinto, A., Alves, V., & Silva, C. A. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2538465 · Cited by 2,735
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
Luo, W., Li, Y., Urtasun, R., & Zemel, R. (2017) · arXiv · doi:10.48550/arxiv.1701.04128 · Cited by 1,575
Cited by
Medical Image Segmentation Review: The Success of U-Net
Azad, R., Aghdam, E. K., Rauland, A., Jia, Y., Avval, A. H., Bozorgpour, A., Karimijafarbigloo, S., Cohen, J. P., Adeli, E., & Merhof, D. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3435571 · Cited by 1,022
A survey of loss functions for semantic segmentation
Jadon, S. (2020) · 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb48159.2020.9277638 · Cited by 946
Yeung, M., Sala, E., Schönlieb, C.-B., & Rundo, L. (2022) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.102026 · Cited by 733
Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis
Karimi, D., Dou, H., Warfield, S. K., & Gholipour, A. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101759 · Cited by 706
Self-citationLoss odyssey in medical image segmentation
Ma, J., Chen, J., Ng, M., Huang, R., Li, Y., Li, C., Yang, X., & Martel, A. L. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102035 · Cited by 662
Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks
Karimi, D., & Salcudean, S. E. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2930068 · Cited by 635
Panda, A., Korfiatis, P., Suman, G., Garg, S. K., Polley, E. C., Singh, D. P., Chari, S. T., & Goenka, A. H. (2021) · Medical Physics · doi:10.1002/mp.14782 · Cited by 41
Metadata
- Authors
- Hashemi, S. R., Mohseni Salehi, S. S., Erdogmus, D., Prabhu, S. P., Warfield, S. K., & Gholipour, A.
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 1721-1735
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2903617078
- Cited by
- 212
- References
- 17
- FWCI
- 9.47
- Type
- journal article
- Language
- en
- Open access
- gold
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.