Brain Cell Laser Powered by Deep‐Learning‐Enhanced Laser Modes

AbstractCellular lasers are cutting-edge technologies for biomedical applications. Due to the enhanced interactions between light and cells in microcavities, cellular properties and subtle changes of cells can be significantly reflected by the laser emission characteristics. In particular, transverse laser modes from single-cell lasers which utilize Fabry–Pérot cavities are highly correlated to the spatial biophysical properties of cells. However, the high chaotic and complex variation of laser modes limits their practical applications for cell detections. Deep learning technique has demonstrated its powerful capability in solving complex imaging problems, which is expected to be applied for cell detections based on laser mode imaging. In this study, deep learning technique was applied to analyze laser modes generated from single-cell lasers, in which a correlation between laser modes and physical properties of cells was built. As a proof-of-concept, we demonstrated the predictions of cell sizes using deep learning based on laser mode imaging. In the first part, bioinspired cell models were fabricated to systematically study how cell sizes affect the characteristics of laser modes. By training a convolutional neuron network (CNN) model with laser mode images, predictions of cell model diameters with a sub-wavelength accuracy were achieved. In the second part, deep learning was employed to study laser modes generated from biological cells. By training a CNN model with laser mode images acquired from astrocyte cells, predictions of cell sizes with a sub-wavelength accuracy were also achieved. The results show the great potential of laser mode imaging integrated with deep learning for cell analysis and biophysical studies.

Download Full-text

Deep Learning

10.1017/cbo9780511780295 ◽

2009 ◽

Cited By ~ 94

Author(s):

Stellan Ohlsson

Keyword(s):

Deep Learning

Download Full-text

Intelligence artificielle : le futur de l’Orthodontie ?

Revue d Orthopédie Dento-Faciale ◽

10.1051/odf/2019026 ◽

2019 ◽

Vol 53 (3) ◽

pp. 281-294

Author(s):

Jean-Michel Foucart ◽

Augustin Chavanne ◽

Jérôme Bourriau

Keyword(s):

Big Data ◽

Deep Learning ◽

Intelligence Artificielle ◽

Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Download Full-text