Eiman Al Ajmi1,2, Behzad Forghani2, Caroline Reinhold2,3, Maryam Bayat1, Reza Forghani4,5,6,7,8. 1. Department of Radiology, Jewish General Hospital, Room C-212.1, 3755 Cote Ste-Catherine Road, Montreal, Quebec, H3T 1E2, Canada. 2. Department of Diagnostic Radiology, McGill University, Montreal, Quebec, Canada. 3. Department of Radiology, Royal Victoria Hospital, McGill University Health Centre, 1001 Decarie Blvd, Montreal, Quebec, H4A 3J1, Canada. 4. Department of Radiology, Jewish General Hospital, Room C-212.1, 3755 Cote Ste-Catherine Road, Montreal, Quebec, H3T 1E2, Canada. rforghani@jgh.mcgill.ca. 5. Department of Diagnostic Radiology, McGill University, Montreal, Quebec, Canada. rforghani@jgh.mcgill.ca. 6. Department of Radiology, Royal Victoria Hospital, McGill University Health Centre, 1001 Decarie Blvd, Montreal, Quebec, H4A 3J1, Canada. rforghani@jgh.mcgill.ca. 7. Segal Cancer Centre and Lady Davis Institute for Medical Research, Jewish General Hospital, Montreal, Quebec, Canada. rforghani@jgh.mcgill.ca. 8. Department of Otolaryngology-Head and Neck Surgery, Jewish General Hospital, Montreal, Quebec, Canada. rforghani@jgh.mcgill.ca.
Abstract
OBJECTIVE: There is a rich amount of quantitative information in spectral datasets generated from dual-energy CT (DECT). In this study, we compare the performance of texture analysis performed on multi-energy datasets to that of virtual monochromatic images (VMIs) at 65 keV only, using classification of the two most common benign parotid neoplasms as a testing paradigm. METHODS: Forty-two patients with pathologically proven Warthin tumour (n = 25) or pleomorphic adenoma (n = 17) were evaluated. Texture analysis was performed on VMIs ranging from 40 to 140 keV in 5-keV increments (multi-energy analysis) or 65-keV VMIs only, which is typically considered equivalent to single-energy CT. Random forest (RF) models were constructed for outcome prediction using separate randomly selected training and testing sets or the entire patient set. RESULTS: Using multi-energy texture analysis, tumour classification in the independent testing set had accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 92%, 86%, 100%, 100%, and 83%, compared to 75%, 57%, 100%, 100%, and 63%, respectively, for single-energy analysis. CONCLUSIONS: Multi-energy texture analysis demonstrates superior performance compared to single-energy texture analysis of VMIs at 65 keV for classification of benign parotid tumours. KEY POINTS: • We present and validate a paradigm for texture analysis of DECT scans. • Multi-energy dataset texture analysis is superior to single-energy dataset texture analysis. • DECT texture analysis has high accura\cy for diagnosis of benign parotid tumours. • DECT texture analysis with machine learning can enhance non-invasive diagnostic tumour evaluation.
OBJECTIVE: There is a rich amount of quantitative information in spectral datasets generated from dual-energy CT (DECT). In this study, we compare the performance of texture analysis performed on multi-energy datasets to that of virtual monochromatic images (VMIs) at 65 keV only, using classification of the two most common benign parotid neoplasms as a testing paradigm. METHODS: Forty-two patients with pathologically proven Warthin tumour (n = 25) or pleomorphic adenoma (n = 17) were evaluated. Texture analysis was performed on VMIs ranging from 40 to 140 keV in 5-keV increments (multi-energy analysis) or 65-keV VMIs only, which is typically considered equivalent to single-energy CT. Random forest (RF) models were constructed for outcome prediction using separate randomly selected training and testing sets or the entire patient set. RESULTS: Using multi-energy texture analysis, tumour classification in the independent testing set had accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 92%, 86%, 100%, 100%, and 83%, compared to 75%, 57%, 100%, 100%, and 63%, respectively, for single-energy analysis. CONCLUSIONS: Multi-energy texture analysis demonstrates superior performance compared to single-energy texture analysis of VMIs at 65 keV for classification of benign parotid tumours. KEY POINTS: • We present and validate a paradigm for texture analysis of DECT scans. • Multi-energy dataset texture analysis is superior to single-energy dataset texture analysis. • DECT texture analysis has high accura\cy for diagnosis of benign parotid tumours. • DECT texture analysis with machine learning can enhance non-invasive diagnostic tumour evaluation.
Entities:
Keywords:
Artificial intelligence; Head and neck neoplasms; Multidetector computed tomography; Radiography; dual-energy scanned projection Computer-assisted diagnosis
Authors: M Dang; J T Lysack; T Wu; T W Matthews; S P Chandarana; N T Brockton; P Bose; G Bansal; H Cheng; J R Mitchell; J C Dort Journal: AJNR Am J Neuroradiol Date: 2014-09-25 Impact factor: 3.825
Authors: Julian L Wichmann; Eva-Maria Nöske; Johannes Kraft; Iris Burck; Jens Wagenblast; Anne Eckardt; Claudia Frellesen; J Matthias Kerl; Ralf W Bauer; Boris Bodelle; Thomas Lehnert; Thomas J Vogl; Boris Schulz Journal: Invest Radiol Date: 2014-11 Impact factor: 6.016
Authors: Marco A Mascarella; Nikesh Muthukrishnan; Farhad Maleki; Marie-Jeanne Kergoat; Keith Richardson; Alex Mlynarek; Veronique-Isabelle Forest; Caroline Reinhold; Diego R Martin; Michael Hier; Nader Sadeghi; Reza Forghani Journal: Ann Otol Rhinol Laryngol Date: 2021-08-20 Impact factor: 1.973