Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308361273> ?p ?o ?g. }
- W4308361273 endingPage "1641" @default.
- W4308361273 startingPage "1634" @default.
- W4308361273 abstract "Abstract Pretrained neural network models for biological segmentation can provide good out-of-the-box results for many image types. However, such models do not allow users to adapt the segmentation style to their specific needs and can perform suboptimally for test images that are very different from the training images. Here we introduce Cellpose 2.0, a new package that includes an ensemble of diverse pretrained models as well as a human-in-the-loop pipeline for rapid prototyping of new custom models. We show that models pretrained on the Cellpose dataset can be fine-tuned with only 500–1,000 user-annotated regions of interest (ROI) to perform nearly as well as models trained on entire datasets with up to 200,000 ROI. A human-in-the-loop approach further reduced the required user annotation to 100–200 ROI, while maintaining high-quality segmentations. We provide software tools such as an annotation graphical user interface, a model zoo and a human-in-the-loop pipeline to facilitate the adoption of Cellpose 2.0." @default.
- W4308361273 created "2022-11-11" @default.
- W4308361273 creator A5044561730 @default.
- W4308361273 creator A5084844011 @default.
- W4308361273 date "2022-11-07" @default.
- W4308361273 modified "2023-10-10" @default.
- W4308361273 title "Cellpose 2.0: how to train your own model" @default.
- W4308361273 cites W1591540433 @default.
- W4308361273 cites W1861492603 @default.
- W4308361273 cites W1901129140 @default.
- W4308361273 cites W1999045972 @default.
- W4308361273 cites W2011301426 @default.
- W4308361273 cites W2019062120 @default.
- W4308361273 cites W2047759928 @default.
- W4308361273 cites W2072000804 @default.
- W4308361273 cites W2104311408 @default.
- W4308361273 cites W2111202632 @default.
- W4308361273 cites W2117539524 @default.
- W4308361273 cites W2146292423 @default.
- W4308361273 cites W2194775991 @default.
- W4308361273 cites W2245493112 @default.
- W4308361273 cites W2462710403 @default.
- W4308361273 cites W2475287302 @default.
- W4308361273 cites W2548342201 @default.
- W4308361273 cites W2602293332 @default.
- W4308361273 cites W2641905542 @default.
- W4308361273 cites W2793938489 @default.
- W4308361273 cites W2798643036 @default.
- W4308361273 cites W2946901414 @default.
- W4308361273 cites W2962770929 @default.
- W4308361273 cites W2962843773 @default.
- W4308361273 cites W2964185501 @default.
- W4308361273 cites W2975634117 @default.
- W4308361273 cites W2977942577 @default.
- W4308361273 cites W2980998394 @default.
- W4308361273 cites W2981994674 @default.
- W4308361273 cites W3020996329 @default.
- W4308361273 cites W3022215132 @default.
- W4308361273 cites W3035049382 @default.
- W4308361273 cites W3040784645 @default.
- W4308361273 cites W3100296314 @default.
- W4308361273 cites W3106188259 @default.
- W4308361273 cites W3111521801 @default.
- W4308361273 cites W3129809409 @default.
- W4308361273 cites W3153558340 @default.
- W4308361273 cites W3164885026 @default.
- W4308361273 cites W3196890347 @default.
- W4308361273 cites W3214596602 @default.
- W4308361273 cites W4200016501 @default.
- W4308361273 cites W4221064165 @default.
- W4308361273 cites W4281749985 @default.
- W4308361273 doi "https://doi.org/10.1038/s41592-022-01663-4" @default.
- W4308361273 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36344832" @default.
- W4308361273 hasPublicationYear "2022" @default.
- W4308361273 type Work @default.
- W4308361273 citedByCount "97" @default.
- W4308361273 countsByYear W43083612732022 @default.
- W4308361273 countsByYear W43083612732023 @default.
- W4308361273 crossrefType "journal-article" @default.
- W4308361273 hasAuthorship W4308361273A5044561730 @default.
- W4308361273 hasAuthorship W4308361273A5084844011 @default.
- W4308361273 hasBestOaLocation W43083612731 @default.
- W4308361273 hasConcept C119857082 @default.
- W4308361273 hasConcept C124101348 @default.
- W4308361273 hasConcept C153180895 @default.
- W4308361273 hasConcept C154945302 @default.
- W4308361273 hasConcept C19609008 @default.
- W4308361273 hasConcept C199360897 @default.
- W4308361273 hasConcept C2776321320 @default.
- W4308361273 hasConcept C2777904410 @default.
- W4308361273 hasConcept C41008148 @default.
- W4308361273 hasConcept C43521106 @default.
- W4308361273 hasConcept C50644808 @default.
- W4308361273 hasConcept C89600930 @default.
- W4308361273 hasConceptScore W4308361273C119857082 @default.
- W4308361273 hasConceptScore W4308361273C124101348 @default.
- W4308361273 hasConceptScore W4308361273C153180895 @default.
- W4308361273 hasConceptScore W4308361273C154945302 @default.
- W4308361273 hasConceptScore W4308361273C19609008 @default.
- W4308361273 hasConceptScore W4308361273C199360897 @default.
- W4308361273 hasConceptScore W4308361273C2776321320 @default.
- W4308361273 hasConceptScore W4308361273C2777904410 @default.
- W4308361273 hasConceptScore W4308361273C41008148 @default.
- W4308361273 hasConceptScore W4308361273C43521106 @default.
- W4308361273 hasConceptScore W4308361273C50644808 @default.
- W4308361273 hasConceptScore W4308361273C89600930 @default.
- W4308361273 hasFunder F4320306082 @default.
- W4308361273 hasIssue "12" @default.
- W4308361273 hasLocation W43083612731 @default.
- W4308361273 hasLocation W43083612732 @default.
- W4308361273 hasLocation W43083612733 @default.
- W4308361273 hasLocation W43083612734 @default.
- W4308361273 hasOpenAccess W4308361273 @default.
- W4308361273 hasPrimaryLocation W43083612731 @default.
- W4308361273 hasRelatedWork W1892467659 @default.
- W4308361273 hasRelatedWork W1988452762 @default.
- W4308361273 hasRelatedWork W2033000528 @default.
- W4308361273 hasRelatedWork W2354141538 @default.