Title: To get to the point, Neural Network application to key-point detection in radiographs
Authors: Schott, Constantin Tilman, Paul-Gerhardt-Schule Dassel, Dassel
Contributors: Editor: Physikalisch-Technische Bundesanstalt (PTB), ISNI: 0000 0001 2186 1887
HostingInstitution: Physikalisch-Technische Bundesanstalt (PTB), ISNI: 0000 0001 2186 1887
Pages:16
Language:en
DOI:10.7795/320.202106
Resource Type: Text / Article
Publisher: Physikalisch-Technische Bundesanstalt (PTB)
Rights: Download for personal/private use only, if your national copyright law allows this kind of use.
Dates: Available: 2021-09-13
Accepted: 2019-12-06
Submitted: 2019-10-06
File: Download File (application/pdf) 4.18 MB (4383661 Bytes)
MD5 Checksum: 6e64c07aa9500ba6374094338387e449
SHA256 Checksum: 368c6290d074b55dd543914c8d087631b600ff43d5ef003464cca86f14411f90
Keywords: artificial intelligence ; neural network ; deep learning ; key-point detection ; convolutional neural network ; cephalometry ; machine learning ; x-ray image ; radiograph ; automated analysis
Abstract: Physicians have to locate so called key-points e.g. for surgical procedures. Up to now, this was always done manually. In order to automate this process, innovative software was developed that uses artificial intelligence (AI)combining a clipping-window approach with the newly developed prediction shifting. The program can predict the key-points with a high degree of accuracy—making the AI as precise as a physician.
Series Information: Junge Wissenschaft. Paper 06/2021
Other: In der Jungen Wissenschaft werden Forschungsarbeiten von Schüler/innen, die selbstständig, z.B. in einer Schule oder einem Schülerforschungszentrum, durchgeführt wurden, veröffentlicht.
Citation: Schott, Constantin Tilman. To get to the point. Neural Network application to key-point detection in radiographs. Physikalisch-Technische Bundesanstalt (PTB), 2021. Verfügbar unter: https://doi.org/10.7795/320.202106