Svetlana: a Supervised Segmentation Classifier for Napari
Autor: | Cazorla, Clément, Morin, Renaud, Weiss, Pierre |
---|---|
Přispěvatelé: | Weiss, Pierre, Artificial and Natural Intelligence Toulouse Institute - - ANITI2019 - ANR-19-P3IA-0004 - P3IA - VALID, Problèmes inverses aveugles et microscopie optique - - MICROBLIND2021 - ANR-21-CE48-0008 - AAPG2021 - VALID, Institut de Mathématiques de Toulouse UMR5219 (IMT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS), Imactiv-3D, ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019), ANR-21-CE48-0008,MICROBLIND,Problèmes inverses aveugles et microscopie optique(2021) |
Jazyk: | angličtina |
Rok vydání: | 2023 |
Předmět: |
Microscopy
Frugal AI [SDV.BIBS] Life Sciences [q-bio]/Quantitative Methods [q-bio.QM] Convolutional Neural Networks Classification [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM] Image analysis Segmentation Biomedical imaging [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV] [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] Software [INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM] |
Popis: | We present Svetlana (SuperVised sEgmenTation cLAssifier for NapAri), an open-source Napari plugin dedicated to the manual or automatic classification of segmentation results. A few recent software have made it possible to automatically segment complex 2D and 3D objects such as cells in biology with unrivaled performance. However, the subsequent analysis of the results is oftentimes inaccessible to non-specialists. The Svetlana plugin aims at going one step further, by allowing end-users to label the segmented objects and to pick, train and run arbitrary neural network classifiers. The resulting network can then be used for the quantitative analysis of biophysical phenoma. We showcase its performance through challenging problems in 2D and3D. Comparisons with random forest classifiers, which are the only easily available alternative to date, show significant advantages for the proposed approach. |
Databáze: | OpenAIRE |
Externí odkaz: |