A Machine Learning Approach to Quantitative Analysis of Enamel Microstructure from Scanning Electron Microscopy Images DOI Creative Commons
Carli Marsico,

Cameron Renteria,

Jack Grimm

и другие.

Small Structures, Год журнала: 2024, Номер unknown

Опубликована: Дек. 25, 2024

Dental enamel, the outermost tissue of mammalian teeth, must withstand a lifetime wear and cyclic contact. To meet this demand, enamel possesses combination high hardness resistance to fracture, properties that are typically mutually exclusive. The impressive damage tolerance has been attributed largely decussation rods, principal unit its microstructure. As such, is inspiring design next‐generation structural materials. However, quantitative descriptions decussated rod microstructure remain limited due challenges encountered in applying computed tomography acquiring quality images appropriate for traditional digital processing methods. Here, machine learning segmentation method applied obtained using scanning electron microscopy support analysis A pretrained convolutional neural network used expand input training image dataset allow random forest classifier, which ultimately segments with very small set ( n = 3 images). validation presented, addition application calculate relevant microstructural parameters tooth from selected species. methodology here equally applicable other hard tissues.

Язык: Английский

High throughput automated characterization of enamel microstructure using synchrotron tomography and optical flow imaging DOI
Zherui Guo, Donna Post Guillen, Jack Grimm

и другие.

Acta Biomaterialia, Год журнала: 2024, Номер 181, С. 263 - 271

Опубликована: Апрель 25, 2024

Язык: Английский

Процитировано

4

Parthenocissus tricuspidata tendril: A mechanically robust structural design with multiple functions DOI
J H Zhou, Lin Zhang, Siyan Zhan

и другие.

Journal of the Mechanics and Physics of Solids, Год журнала: 2025, Номер unknown, С. 106065 - 106065

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0

Phase Contrast Based High Resolution X-Ray Desktop Tomography DOI
Alessandra Maia Marques Martinez Perez, D. Hampai,

A R Di Filippo

и другие.

Radiation Physics and Chemistry, Год журнала: 2025, Номер unknown, С. 112600 - 112600

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0

A Machine Learning Approach to Quantitative Analysis of Enamel Microstructure from Scanning Electron Microscopy Images DOI Creative Commons
Carli Marsico,

Cameron Renteria,

Jack Grimm

и другие.

Small Structures, Год журнала: 2024, Номер unknown

Опубликована: Дек. 25, 2024

Dental enamel, the outermost tissue of mammalian teeth, must withstand a lifetime wear and cyclic contact. To meet this demand, enamel possesses combination high hardness resistance to fracture, properties that are typically mutually exclusive. The impressive damage tolerance has been attributed largely decussation rods, principal unit its microstructure. As such, is inspiring design next‐generation structural materials. However, quantitative descriptions decussated rod microstructure remain limited due challenges encountered in applying computed tomography acquiring quality images appropriate for traditional digital processing methods. Here, machine learning segmentation method applied obtained using scanning electron microscopy support analysis A pretrained convolutional neural network used expand input training image dataset allow random forest classifier, which ultimately segments with very small set ( n = 3 images). validation presented, addition application calculate relevant microstructural parameters tooth from selected species. methodology here equally applicable other hard tissues.

Язык: Английский

Процитировано

0