Vision Transformer for femur fracture classification.

Journal: Injury
PMID:

Abstract

INTRODUCTION: In recent years, the scientific community focused on developing Computer-Aided Diagnosis (CAD) tools that could improve clinicians' bone fractures diagnosis, primarily based on Convolutional Neural Networks (CNNs). However, the discerning accuracy of fractures' subtypes was far from optimal. The aim of the study was 1) to evaluate a new CAD system based on Vision Transformers (ViT), a very recent and powerful deep learning technique, and 2) to assess whether clinicians' diagnostic accuracy could be improved using this system.

Authors

  • Leonardo Tanzi
    DIGEP, Polytechnic University of Turin, Torino, Italy.
  • Andrea Audisio
    School of Medicine, University of Turin, Viale 25 Aprile 137 int 6, 10133, Torino, Italy. Electronic address: andrea.audisio384@edu.unito.it.
  • Giansalvo Cirrincione
    University of Picardie Jules Verne, Amiens, France; University of South Pacific, Suva, Fiji. Electronic address: giansalvo.cirrincione@u-picardie.fr.
  • Alessandro Aprato
    School of Medicine, University of Turin, Viale 25 Aprile 137 int 6, 10133, Torino, Italy. Electronic address: ale_aprato@hotmail.com.
  • Enrico Vezzetti
    Department of Management and Production Engineer, Politechnic University of Turin, Turin, Italy.