Matches in SemOpenAlex for { <https://semopenalex.org/work/W1898703532> ?p ?o ?g. }
- W1898703532 abstract "To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain. Participants submitted boundary maps predicted for a test set of images, and were scored based on their agreement with a consensus of human expert annotations. The winning team had no prior experience with EM images, and employed a convolutional network. This deep learning approach has since become accepted as a standard for segmentation of EM images. The challenge has continued to accept submissions, and the best so far has resulted from cooperation between two teams. The challenge has probably saturated, as algorithms cannot progress beyond limits set by ambiguities inherent in 2D scoring and the size of the test dataset. Retrospective evaluation of the challenge scoring system reveals that it was not sufficiently robust to variations in the widths of neurite borders. We propose a solution to this problem, which should be useful for a future 3D segmentation challenge." @default.
- W1898703532 created "2016-06-24" @default.
- W1898703532 creator A5001865165 @default.
- W1898703532 creator A5005339015 @default.
- W1898703532 creator A5005619868 @default.
- W1898703532 creator A5008113792 @default.
- W1898703532 creator A5009439842 @default.
- W1898703532 creator A5015329647 @default.
- W1898703532 creator A5021284069 @default.
- W1898703532 creator A5036042625 @default.
- W1898703532 creator A5038199211 @default.
- W1898703532 creator A5041589060 @default.
- W1898703532 creator A5042603640 @default.
- W1898703532 creator A5044273339 @default.
- W1898703532 creator A5044629673 @default.
- W1898703532 creator A5047671906 @default.
- W1898703532 creator A5049295603 @default.
- W1898703532 creator A5050085853 @default.
- W1898703532 creator A5052119291 @default.
- W1898703532 creator A5053494387 @default.
- W1898703532 creator A5058862171 @default.
- W1898703532 creator A5059125158 @default.
- W1898703532 creator A5063089557 @default.
- W1898703532 creator A5066189518 @default.
- W1898703532 creator A5073908382 @default.
- W1898703532 creator A5077436868 @default.
- W1898703532 date "2015-11-05" @default.
- W1898703532 modified "2023-10-09" @default.
- W1898703532 title "Crowdsourcing the creation of image segmentation algorithms for connectomics" @default.
- W1898703532 cites W1513082520 @default.
- W1898703532 cites W1545506100 @default.
- W1898703532 cites W1551114844 @default.
- W1898703532 cites W1969013163 @default.
- W1898703532 cites W1976032673 @default.
- W1898703532 cites W1977691361 @default.
- W1898703532 cites W1978700375 @default.
- W1898703532 cites W1989621138 @default.
- W1898703532 cites W2015574237 @default.
- W1898703532 cites W2026981426 @default.
- W1898703532 cites W2033403400 @default.
- W1898703532 cites W2033579242 @default.
- W1898703532 cites W2040156859 @default.
- W1898703532 cites W2076449818 @default.
- W1898703532 cites W2080858319 @default.
- W1898703532 cites W2087523977 @default.
- W1898703532 cites W2103706175 @default.
- W1898703532 cites W2104145949 @default.
- W1898703532 cites W2107833399 @default.
- W1898703532 cites W2110158442 @default.
- W1898703532 cites W2111987679 @default.
- W1898703532 cites W2114538750 @default.
- W1898703532 cites W2119823327 @default.
- W1898703532 cites W2121189958 @default.
- W1898703532 cites W2121289914 @default.
- W1898703532 cites W2141729166 @default.
- W1898703532 cites W2147762902 @default.
- W1898703532 cites W2147800946 @default.
- W1898703532 cites W2160938187 @default.
- W1898703532 cites W2166536682 @default.
- W1898703532 cites W2167279371 @default.
- W1898703532 doi "https://doi.org/10.3389/fnana.2015.00142" @default.
- W1898703532 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/4633678" @default.
- W1898703532 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26594156" @default.
- W1898703532 hasPublicationYear "2015" @default.
- W1898703532 type Work @default.
- W1898703532 sameAs 1898703532 @default.
- W1898703532 citedByCount "273" @default.
- W1898703532 countsByYear W18987035322012 @default.
- W1898703532 countsByYear W18987035322016 @default.
- W1898703532 countsByYear W18987035322017 @default.
- W1898703532 countsByYear W18987035322018 @default.
- W1898703532 countsByYear W18987035322019 @default.
- W1898703532 countsByYear W18987035322020 @default.
- W1898703532 countsByYear W18987035322021 @default.
- W1898703532 countsByYear W18987035322022 @default.
- W1898703532 countsByYear W18987035322023 @default.
- W1898703532 crossrefType "journal-article" @default.
- W1898703532 hasAuthorship W1898703532A5001865165 @default.
- W1898703532 hasAuthorship W1898703532A5005339015 @default.
- W1898703532 hasAuthorship W1898703532A5005619868 @default.
- W1898703532 hasAuthorship W1898703532A5008113792 @default.
- W1898703532 hasAuthorship W1898703532A5009439842 @default.
- W1898703532 hasAuthorship W1898703532A5015329647 @default.
- W1898703532 hasAuthorship W1898703532A5021284069 @default.
- W1898703532 hasAuthorship W1898703532A5036042625 @default.
- W1898703532 hasAuthorship W1898703532A5038199211 @default.
- W1898703532 hasAuthorship W1898703532A5041589060 @default.
- W1898703532 hasAuthorship W1898703532A5042603640 @default.
- W1898703532 hasAuthorship W1898703532A5044273339 @default.
- W1898703532 hasAuthorship W1898703532A5044629673 @default.
- W1898703532 hasAuthorship W1898703532A5047671906 @default.
- W1898703532 hasAuthorship W1898703532A5049295603 @default.
- W1898703532 hasAuthorship W1898703532A5050085853 @default.
- W1898703532 hasAuthorship W1898703532A5052119291 @default.
- W1898703532 hasAuthorship W1898703532A5053494387 @default.
- W1898703532 hasAuthorship W1898703532A5058862171 @default.
- W1898703532 hasAuthorship W1898703532A5059125158 @default.
- W1898703532 hasAuthorship W1898703532A5063089557 @default.
- W1898703532 hasAuthorship W1898703532A5066189518 @default.
- W1898703532 hasAuthorship W1898703532A5073908382 @default.