Development of a Patient–Radiopharmaceutical Matching System Using Smartphone to Prevent Misadministration: Feasibility Study

We designed a patient–radiopharmaceutical matching system for preventing misadministration using smartphone, and developed a deep-learning model to identify radiopharmaceutical containers as an elemental technology for the system. As a result of the ResNet18 transfer learning and 10-fold cross-valid...

Full description

Saved in:
Bibliographic Details
Published inRADIOISOTOPES Vol. 73; no. 1; pp. 69 - 80
Main Authors Sato, Mitsuru, Hoshino, Hiromitsu, Shimizu, Masataka, Daisaki, Hiromitsu, Ichikawa, Shota, Kondo, Tatsuya, Okamoto, Masashi
Format Journal Article
LanguageEnglish
Japanese
Published Japan Radioisotope Association 15.03.2024
Subjects
deep learning
face recognition
prevention of misadministration
radiopharmaceutical identification
smartphone in hospital
Online AccessGet full text

Cover

More Information
Summary:We designed a patient–radiopharmaceutical matching system for preventing misadministration using smartphone, and developed a deep-learning model to identify radiopharmaceutical containers as an elemental technology for the system. As a result of the ResNet18 transfer learning and 10-fold cross-validation, this model achieved 100％ accuracy in classifying 15 different radiopharmaceutical containers. The feasibility of the proposed system was proven.
ISSN:0033-8303
1884-4111
DOI:10.3769/radioisotopes.73.69