The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction
Open accessAbstract
We present a method combining affinity prediction with region agglomeration, which improves significantly upon the state of the art of neuron segmentation from electron microscopy (EM) in accuracy and scalability. Our method consists of a 3D U-Net, trained to predict affinities between voxels, followed by iterative region agglomeration. We train using a structured loss based on Malis, encouraging topologically correct segmentations obtained from affinity thresholding. Our extension consists of two parts: First, we present a quasi-linear method to compute the loss gradient, improving over the original quadratic algorithm. Second, we compute the gradient in two separate passes to avoid spurious gradient contributions in early training stages. Our predictions are accurate enough that simple learning-free percentile-based agglomeration outperforms more involved methods used earlier on inferior predictions. We present results on three diverse EM datasets, achieving relative improvements over previous results of 27, 15, and 250 percent. Our findings suggest that a single method can be applied to both nearly isotropic block-face EM data and anisotropic serial sectioned EM data. The runtime of our method scales linearly with the size of the volume and achieves a throughput of $\sim$∼ 2.6 seconds per megavoxel, qualifying our method for the processing of very large datasets.
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
3D 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
Synaptic circuits and their variations within different columns in the visual system of Drosophila
Takemura, S.-Y., Xu, C. S., Lu, Z., Rivlin, P. K., Parag, T., Olbris, D. J., Plaza, S., Zhao, T., Katz, W. T., Umayam, L., et al. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1509820112 · Cited by 264
Research works printed but not linked: 14
- 10.2307/2033241 · doi:10.2307/2033241 · Paper page
- coelho, 2013, Mahotas: Open source software for scriptable computer vision, Journal of Open Research Software, 1
- 10.1016/j.ymeth.2016.12.013 · DOI
- 10.1016/j.neuron.2015.09.003 · DOI
- 10.1038/nmeth.2072 · DOI · Paper page
- zlateski, 2015, Image segmentation by size-dependent single linkage clustering of a watershed basin graph, CoRR, abs 1505 249
- januszewski, 2016, Flood-filling networks, CoRR, abs 1611 421
- maitin-shepard, 2016, Combinatorial energy learning for image segmentation, Proc Advances Neural Inf Process Syst, 1966
- 10.1007/978-3-642-33712-3_56 · DOI
- 10.3389/fninf.2014.00034 · DOI
- 10.1038/nmeth.4151 · DOI · Paper page
- 10.1109/ICCV.2015.204 · DOI
- briggman, 2009, Maximin affinity learning of image segmentation, Proc Advances Neural Inf Process Syst, 1865
- 10.1109/ICCV.2017.222 · DOI
Cited by
associated_data_Investigating the Effectiveness of clDice Loss for Road Crack Segmentation
Pereira, V. (2025) · arXiv (Cornell University) · doi:10.5281/zenodo.15696262 · Cited by 548
Accurate and versatile 3D segmentation of plant tissues at cellular resolution
Wolny, A., Cerrone, L., Vijayan, A., Tofanelli, R., Barro, A. V., Louveaux, M., Wenzl, C., Strauss, S., Wilson-Sánchez, D., Lymbouridou, R., et al. (2020) · eLife · doi:10.7554/elife.57613 · Cited by 326
Whole-cell organelle segmentation in volume electron microscopy
Heinrich, L., Bennett, D., Ackerman, D., Park, W., Bogovic, J., Eckstein, N., Petruncio, A., Clements, J., Pang, S., Xu, C. S., et al. (2021) · Nature · doi:10.1038/s41586-021-03977-3 · Cited by 292
Self-citationThe natverse, a versatile toolbox for combining and analysing neuroanatomical data
Bates, A. S., Manton, J. D., Jagannathan, S. R., Costa, M., Schlegel, P., Rohlfing, T., & Jefferis, G. S. (2020) · eLife · doi:10.7554/elife.53350 · Cited by 215
Eckstein, N., Bates, A. S., Champion, A., Du, M., Yin, Y., Schlegel, P., Lu, A. K.-Y., Rymer, T., Finley-May, S., Paterson, T., et al. (2024) · Cell · doi:10.1016/j.cell.2024.03.016 · Cited by 277
“…the 5 th and 95 th percentiles have been removed for ease of visualization. progress in the field, e.g. , to segment neurons (Berning et al., 2015; Funke et al., 2018; Januszewski et al., 2018; Lee et al., 2019; Sheridan et al., 2022; Schmidt et al., 2022; Dorkenwald et al., 2022; Svara et al.,…”
Self-citation
Metadata
- Authors
- Funke, J., Tschopp, F., Grisaitis, W., Sheridan, A., Singh, C., Saalfeld, S., & Turaga, S. C.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2019-07-01
- Volume
- 41
- Issue
- 7
- Pages
- 1669-1680
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W2803790834
- Cited by
- 218
- References
- 4
- FWCI
- 10.29
- Type
- journal article
- Language
- en
- Open access
- bronze
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (P2EZP2_165241)
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.