Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223570418> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4223570418 abstract "Generalist models for cellular segmentation, like Cellpose, provide good out-of-the-box results for many types of images. However, such models do not allow users to adapt the segmentation style to their specific needs and may perform sub-optimally for test images that are very different from the training images. Here we introduce Cellpose 2.0, a new package which includes an ensemble of diverse pretrained models as well as a human-in-the-loop pipeline for quickly prototyping new specialist models. We show that specialist models pretrained on the Cellpose dataset can achieve state-of-the-art segmentation on new image categories with very little user-provided training data. Models trained on 500-1000 segmented regions-of-interest (ROIs) performed nearly as well as models trained on entire datasets with up to 200,000 ROIs. A human-in-the-loop approach further reduced the required user annotations to 100-200 ROIs, while maintaining state-of-the-art segmentation performance. This approach enables a new generation of specialist segmentation models that can be trained on new image types with only 1-2 hours of user effort. We provide software tools including an annotation GUI, a model zoo and a human-in-the-loop pipeline to facilitate the adoption of Cellpose 2.0." @default.
- W4223570418 created "2022-04-15" @default.
- W4223570418 creator A5044561730 @default.
- W4223570418 creator A5084844011 @default.
- W4223570418 date "2022-04-05" @default.
- W4223570418 modified "2023-10-16" @default.
- W4223570418 title "Cellpose 2.0: how to train your own model" @default.
- W4223570418 cites W1591540433 @default.
- W4223570418 cites W1999045972 @default.
- W4223570418 cites W2011301426 @default.
- W4223570418 cites W2015159529 @default.
- W4223570418 cites W2019062120 @default.
- W4223570418 cites W2047759928 @default.
- W4223570418 cites W2072000804 @default.
- W4223570418 cites W2104311408 @default.
- W4223570418 cites W2111202632 @default.
- W4223570418 cites W2146292423 @default.
- W4223570418 cites W2462710403 @default.
- W4223570418 cites W2475287302 @default.
- W4223570418 cites W2548342201 @default.
- W4223570418 cites W2602293332 @default.
- W4223570418 cites W2793938489 @default.
- W4223570418 cites W2798643036 @default.
- W4223570418 cites W2921955147 @default.
- W4223570418 cites W2946901414 @default.
- W4223570418 cites W2962770929 @default.
- W4223570418 cites W2962843773 @default.
- W4223570418 cites W2964185501 @default.
- W4223570418 cites W2975634117 @default.
- W4223570418 cites W2977942577 @default.
- W4223570418 cites W2980998394 @default.
- W4223570418 cites W2981994674 @default.
- W4223570418 cites W3020996329 @default.
- W4223570418 cites W3022215132 @default.
- W4223570418 cites W3040784645 @default.
- W4223570418 cites W3111521801 @default.
- W4223570418 cites W3135886608 @default.
- W4223570418 cites W3153558340 @default.
- W4223570418 cites W3164885026 @default.
- W4223570418 cites W3196890347 @default.
- W4223570418 cites W4200016501 @default.
- W4223570418 cites W4221064165 @default.
- W4223570418 doi "https://doi.org/10.1101/2022.04.01.486764" @default.
- W4223570418 hasPublicationYear "2022" @default.
- W4223570418 type Work @default.
- W4223570418 citedByCount "31" @default.
- W4223570418 countsByYear W42235704182021 @default.
- W4223570418 countsByYear W42235704182022 @default.
- W4223570418 countsByYear W42235704182023 @default.
- W4223570418 crossrefType "posted-content" @default.
- W4223570418 hasAuthorship W4223570418A5044561730 @default.
- W4223570418 hasAuthorship W4223570418A5084844011 @default.
- W4223570418 hasBestOaLocation W42235704181 @default.
- W4223570418 hasConcept C119857082 @default.
- W4223570418 hasConcept C124504099 @default.
- W4223570418 hasConcept C154945302 @default.
- W4223570418 hasConcept C199360897 @default.
- W4223570418 hasConcept C2776321320 @default.
- W4223570418 hasConcept C2777904410 @default.
- W4223570418 hasConcept C2780626000 @default.
- W4223570418 hasConcept C31972630 @default.
- W4223570418 hasConcept C41008148 @default.
- W4223570418 hasConcept C43521106 @default.
- W4223570418 hasConcept C89600930 @default.
- W4223570418 hasConceptScore W4223570418C119857082 @default.
- W4223570418 hasConceptScore W4223570418C124504099 @default.
- W4223570418 hasConceptScore W4223570418C154945302 @default.
- W4223570418 hasConceptScore W4223570418C199360897 @default.
- W4223570418 hasConceptScore W4223570418C2776321320 @default.
- W4223570418 hasConceptScore W4223570418C2777904410 @default.
- W4223570418 hasConceptScore W4223570418C2780626000 @default.
- W4223570418 hasConceptScore W4223570418C31972630 @default.
- W4223570418 hasConceptScore W4223570418C41008148 @default.
- W4223570418 hasConceptScore W4223570418C43521106 @default.
- W4223570418 hasConceptScore W4223570418C89600930 @default.
- W4223570418 hasLocation W42235704181 @default.
- W4223570418 hasOpenAccess W4223570418 @default.
- W4223570418 hasPrimaryLocation W42235704181 @default.
- W4223570418 hasRelatedWork W1669643531 @default.
- W4223570418 hasRelatedWork W1982826852 @default.
- W4223570418 hasRelatedWork W2005437358 @default.
- W4223570418 hasRelatedWork W2008656436 @default.
- W4223570418 hasRelatedWork W2023558673 @default.
- W4223570418 hasRelatedWork W2110230079 @default.
- W4223570418 hasRelatedWork W2134924024 @default.
- W4223570418 hasRelatedWork W2517104666 @default.
- W4223570418 hasRelatedWork W2613186388 @default.
- W4223570418 hasRelatedWork W2785003841 @default.
- W4223570418 isParatext "false" @default.
- W4223570418 isRetracted "false" @default.
- W4223570418 workType "article" @default.