Wood identification based on longitudinal section images by using deep learning

2021 ◽  
Vol 55 (2) ◽  
pp. 553-563
Author(s):  
Fanyou Wu ◽  
Rado Gazo ◽  
Eva Haviarova ◽  
Bedrich Benes
2020 ◽  
Vol 4 (1) ◽  
pp. 70-76
Author(s):  
Hendriyana Hendriyana ◽  
Yazid Hilman Maulana

Indonesia is a wood producing with large number of forest and various type of trees in less than 4000 species of trees in Indonesia’s forest. The activity of wood identification is effort to get information about kind of wood. The identification type of wood that have similar characteristics, it is difficult to identify the right type of wood. The characteristic can be allotted to two group, general characteristic and anatomy characteristic. General characteristics can be seen directly by the senses without tools, while anatomy characteristics can be seen with tools such as loupe or microscope. Convolutional Neural Network with mobilenet architecture is a Deep Learning method that can be use identify and classifying an object. In this study, using 1000 images for 10 types of wood in each type. The images split into 90 images training dataset dan 10 images for validation datasets captured by mobilephone. Based on the result of research, the obtained level of accuracy 98% training, 93,3% testing, 28% recall, and 93% for precission. That result can be concluded that performance from this model in this research is optimal to classification the kind of wood.


Author(s):  
L. D. Ackerman ◽  
S. H. Y. Wei

Mature human dental enamel has presented investigators with several difficulties in ultramicrotomy of specimens for electron microscopy due to its high degree of mineralization. This study explores the possibility of combining ion-milling and high voltage electron microscopy as a means of circumventing the problems of ultramicrotomy.A longitudinal section of an extracted human third molar was ground to a thickness of about 30 um and polarized light micrographs were taken. The specimen was attached to a single hole grid and thinned by argon-ion bombardment at 15° incidence while rotating at 15 rpm. The beam current in each of two guns was 50 μA with an accelerating voltage of 4 kV. A 20 nm carbon coating was evaporated onto the specimen to prevent an electron charge from building up during electron microscopy.


Author(s):  
Matias Pardo ◽  
Malcolm Slifkin ◽  
Leonard Merkow ◽  
Marie Sanchez

The simian adenoviruses SV20, SV30 and SA7 have been found to be oncogenic in the Syrian hamster. The growth characteristics and replicative cycle of these viruses in tissue culture therefore appeared appropriate to investigate. Cesium chloride purified simian adenovirus with an infectivity titer of 100 TCID50, was inoculated into monolayers of LLC-MK2 cells. Cells were fixed in osmium tetroxide and embedded for ultrastructural studies at 1, 3, 6, 9, 18, 24, 48, 72, 120 and 192 hours post-infection.At the first hour post-infection, virus particles were adsorbed to the plasmalemma and found within the peripheral cytoplasm of many LLC-MK2 cells (Fig. 1). Although the first detection of infectious virus occurred at 14 hours and infectivity titers did not reach a maximum until 30 hours, intranuclear virus particles were observed by 3 hours in typical adenovirus crystalline array (Fig. 2) by means of electron microscopy. These typical honeycomb arrayed virus particles at 3 hours provided evidence of significant replication in approximately 5 percent of tissue culture cells examined. Simultaneously, a classical nuclear inclusion manifested by peripheral condensation of nuclear chromatin was evident by light microscopy. As early at 6 to 9 hours, unusual intranuclear concentric membranes formed “tubes” which contained linear arranged virus particles (Fig. 3). In transverse or tangential sections, these “tubes” appeared cochlear-like in shape. In longitudinal section, these intranuclear tubular structures contained individual virus particles at various stages of maturation in a linear arranged order. This arrangement resembled “peas in a pod”.


Author(s):  
Stellan Ohlsson
Keyword(s):  

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau

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.


1964 ◽  
Vol 04 (02) ◽  
pp. 186-192
Author(s):  
Leonel Costacurta

SummaryDental germs of the upper incisors of six-days old rats were studied for the uptake of leucine-H3 by different layers of the enamel organ in correlation to the various stages of the development of enamel.The longitudinal section of the tooth germ was divided into 15 zones of about equal length in order to facilitate the description and interpretation of results. Autoradiographic images of the histologic preparations from rats sacrificed 30 minutes, 1 hour, 1 day and 3 days after the injection were made. The strongest reactions were observed in dental germs of rats sacrificed 1 hour, and particularly one day, after the leucine-H3 injection.The uptake of this compound by the enamel matrix increases progressively up to the young enamel and then decreases to the distal extremity; the greatest quantity of this labeled amino-acid was observed in the primary and young enamel. The reactions were present in the transitional enamel only along a thin band close to the dentine-enamel junction.In the enamel organ leucine-H3 incorporation was greatest in the three layers, the zones corresponding to primary and young enamel. In zones corresponding to transitional enamel, the inner epithelium showed a small quantity, and the stellate reticulum a blackening only in its superficial part, were the blood vessels reach the enamel organ.


2020 ◽  
Author(s):  
L Pennig ◽  
L Lourenco Caldeira ◽  
C Hoyer ◽  
L Görtz ◽  
R Shahzad ◽  
...  
Keyword(s):  

2020 ◽  
Author(s):  
A Heinrich ◽  
M Engler ◽  
D Dachoua ◽  
U Teichgräber ◽  
F Güttler
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document