A classifier for dynamic thermal imaging

Tosun E., Dinc O. F., Arli B., Tozburun S.

Translational Biophotonics: Diagnostics and Therapeutics III 2023, Munich, Germany, 25 - 29 June 2023, vol.12627 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 12627
  • Doi Number: 10.1117/12.2672244
  • City: Munich
  • Country: Germany
  • Keywords: Artificial intelligence., Dynamic thermal imaging, Heterogeneity, Laser, Tissue phantom
  • Dokuz Eylül University Affiliated: Yes

Abstract

This study presents an artificial intelligence algorithm to classify the heterogeneity and homogeneity of ex vivo mouse liver tumor phantom using dynamic thermal imaging. The algorithm suggests that the phantom s temperature response to a 1340 nm collimated narrow laser beam results in a thermal pattern that may help separate tumor tissue from healthy tissue. The algorithm can classify homogeneity and heterogeneity with an accuracy of 98.6%.