Automatic method for vertebral morphometry measurements

Torna indietro

Abstract

Aim of this study was to perform a detailed clinical validation of a novel fully automatic method for vertebralmorphometry. About 80 spine lateral radiographs were evaluated both automatically, by the proposed algorithm, andmanually, by an experienced radiologist. The following metrics were used for algorithm performance assessment:sensitivity and specificity in vertebra detection; errors in the localisation of characteristic points of vertebral border;errors in the measurement of six diagnostic parameters; level of agreement and correlation between manual andautomatic morphometric measurements; overall accuracy of automatic diagnoses with respect to manual ones.Obtained results showed a very good performance in vertebra detection (sensitivity = 89.1% and specificity = 100.0%).Average errors in the localisation of vertebral characteristic points were always smaller than 3 mm (range 0.85-2.79mm),causing relative errors in diagnostic parameter values ranging from -5.01 to +6.10%. Bland-Altman analysis documenteda mean error in automatic measurements of diagnostic ratios of 0.01 ± 0.18 (bias ± 2 SDs), while Pearson's correlationcoefficient resulted r = 0.71 (p < 0.001). Finally, an optimal diagnostic coincidence (92.8%) was found between automaticand manual diagnoses. Therefore, the adopted method has a potential for an effective employment in clinical routinefor reliable diagnosis of vertebral fractures.

Autore Pugliese

Tutti gli autori

  • R. Franchini; F. Conversano; P. Pisani; E. Casciaro; M. Peccarisi; E. Quarta; A. Grimaldi; M. Muratore; S. Casciaro

Titolo volume/Rivista

IET science, measurement & technology

Anno di pubblicazione

2016

ISSN

1751-8822

ISBN

Non Disponibile

Numero di citazioni Wos

Nessuna citazione

Ultimo Aggiornamento Citazioni

Non Disponibile

Numero di citazioni Scopus

Non Disponibile

Ultimo Aggiornamento Citazioni

Non Disponibile

Settori ERC

Non Disponibile

Codici ASJC

Non Disponibile