/
/
Machine Learning et sans étiquette d’Identification des sous-types de lymphocytes à l’aide de l’imagerie tridimensionnelle Phase Quantitative
A subscription to JoVE is required to view this content. Sign in or start your free trial.
1Department of Physics,University of Cambridge, 2Department of Physics,Korea Advanced Institute of Science and Technology, 3KAIST Institute for Health Science and Technology,Korea Advanced Institute of Science and Technology, 4Tomocube, Inc., 5Department of Chemical and Biomolecular Engineering,Korea Advanced Institute of Science and Technology, 6Department of Biological Sciences,Korea Advanced Institute of Science and Technology, 7Department of Applied Physics,Stanford University
Chapters
- 00:04Title
- 01:173D Quantitative Phase Imaging
- 04:34Quantitative Morphological and Biochemical Feature Extraction and Supervised Learning and Identification
- 06:42Results: Representative Label-Free Lymphocyte Subtype 3D Phase Imaging Identification
- 07:56Conclusion
Les auteurs décrivent un protocole d’identification des sous-types de lymphocytes en utilisant l’imagerie quantitative phase et un algorithme d’apprentissage machine exempte d’étiquette. Mesures de l’indice de réfraction 3D tomographies des lymphocytes présentent 3D informations morphologiques et biochimiques des cellules individuelles, qui sont ensuite analysées grâce à un algorithme d’apprentissage automatique pour l’identification des types de cellules.
