Reza Forghani1,2,3,4, Avishek Chatterjee5, Caroline Reinhold6,7, Almudena Pérez-Lara8,9, Griselda Romero-Sanchez8, Yoshiko Ueno7,10, Maryam Bayat8, James W M Alexander8, Lynda Kadi8,11, Jeffrey Chankowsky7, Jan Seuntjens12,5, Behzad Forghani6,12. 1. Department of Radiology and Research Institute of the McGill University Health Centre, McGill University, Room C02.5821, 1001 Decarie Blvd, Montreal, QC, H4A 3J1, Canada. reza.forghani@mcgill.ca. 2. Segal Cancer Centre and Lady Davis Institute for Medical Research, Jewish General Hospital, Room C-212.1, 3755 Cote Ste-Catherine Road, Montreal, QC, H3T 1E2, Canada. reza.forghani@mcgill.ca. 3. Department of Radiology, Royal Victoria Hospital, McGill University Health Centre, 1001 Decarie Blvd, Montreal, QC, H4A 3J1, Canada. reza.forghani@mcgill.ca. 4. Gerald Bronfman Department of Oncology, McGill University, Montreal, QC, Canada. reza.forghani@mcgill.ca. 5. Medical Physics Unit, Cedars Cancer Centre, McGill University Health Centre, 1001 Decarie Blvd, Montreal, QC, H4A 3J1, Canada. 6. Department of Radiology and Research Institute of the McGill University Health Centre, McGill University, Room C02.5821, 1001 Decarie Blvd, Montreal, QC, H4A 3J1, Canada. 7. Department of Radiology, Royal Victoria Hospital, McGill University Health Centre, 1001 Decarie Blvd, Montreal, QC, H4A 3J1, Canada. 8. Segal Cancer Centre and Lady Davis Institute for Medical Research, Jewish General Hospital, Room C-212.1, 3755 Cote Ste-Catherine Road, Montreal, QC, H3T 1E2, Canada. 9. Department of Radiology, Hospital Regional Universitario de Málaga, Avenida Carlos Haya, S/N, 29010, Málaga, Spain. 10. Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2, Kusunoki-cho, Chuo-ku, Kobe, Hyogo, 650-0017, Japan. 11. Faculty of Medicine, Université de Montréal, Montreal, QC, Canada. 12. Gerald Bronfman Department of Oncology, McGill University, Montreal, QC, Canada.
Abstract
OBJECTIVES: This study was conducted in order to evaluate a novel risk stratification model using dual-energy CT (DECT) texture analysis of head and neck squamous cell carcinoma (HNSCC) with machine learning to (1) predict associated cervical lymphadenopathy and (2) compare the accuracy of spectral versus single-energy (65 keV) texture evaluation for endpoint prediction. METHODS: Eighty-seven patients with HNSCC were evaluated. Texture feature extraction was performed on virtual monochromatic images (VMIs) at 65 keV alone or different sets of multi-energy VMIs ranging from 40 to 140 keV, in addition to iodine material decomposition maps and other clinical information. Random forests (RF) models were constructed for outcome prediction with internal cross-validation in addition to the use of separate randomly selected training (70%) and testing (30%) sets. Accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were determined for predicting positive versus negative nodal status in the neck. RESULTS: Depending on the model used and subset of patients evaluated, an accuracy, sensitivity, specificity, PPV, and NPV of up to 88, 100, 67, 83, and 100%, respectively, could be achieved using multi-energy texture analysis. Texture evaluation of VMIs at 65 keV alone or in combination with only iodine maps had a much lower accuracy. CONCLUSIONS: Multi-energy DECT texture analysis of HNSCC is superior to texture analysis of 65 keV VMIs and iodine maps alone and can be used to predict cervical nodal metastases with relatively high accuracy, providing information not currently available by expert evaluation of the primary tumor alone. KEY POINTS: • Texture features of HNSCC tumor are predictive of nodal status. • Multi-energy texture analysis is superior to analysis of datasets at a single energy. • Dual-energy CT texture analysis with machine learning can enhance noninvasive diagnostic tumor evaluation.
OBJECTIVES: This study was conducted in order to evaluate a novel risk stratification model using dual-energy CT (DECT) texture analysis of head and neck squamous cell carcinoma (HNSCC) with machine learning to (1) predict associated cervical lymphadenopathy and (2) compare the accuracy of spectral versus single-energy (65 keV) texture evaluation for endpoint prediction. METHODS: Eighty-seven patients with HNSCC were evaluated. Texture feature extraction was performed on virtual monochromatic images (VMIs) at 65 keV alone or different sets of multi-energy VMIs ranging from 40 to 140 keV, in addition to iodine material decomposition maps and other clinical information. Random forests (RF) models were constructed for outcome prediction with internal cross-validation in addition to the use of separate randomly selected training (70%) and testing (30%) sets. Accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were determined for predicting positive versus negative nodal status in the neck. RESULTS: Depending on the model used and subset of patients evaluated, an accuracy, sensitivity, specificity, PPV, and NPV of up to 88, 100, 67, 83, and 100%, respectively, could be achieved using multi-energy texture analysis. Texture evaluation of VMIs at 65 keV alone or in combination with only iodine maps had a much lower accuracy. CONCLUSIONS: Multi-energy DECT texture analysis of HNSCC is superior to texture analysis of 65 keV VMIs and iodine maps alone and can be used to predict cervical nodal metastases with relatively high accuracy, providing information not currently available by expert evaluation of the primary tumor alone. KEY POINTS: • Texture features of HNSCC tumor are predictive of nodal status. • Multi-energy texture analysis is superior to analysis of datasets at a single energy. • Dual-energy CT texture analysis with machine learning can enhance noninvasive diagnostic tumor evaluation.
Entities:
Keywords:
Artificial intelligence; Computer-assisted diagnosis; Head and neck neoplasms; Machine learning; Multidetector computed tomography
Authors: Reza Assadsangabi; Rosa Babaei; Catherine Songco; Vladimir Ivanovic; Matthew Bobinski; Yin J Chen; Seyed Ali Nabavizadeh Journal: Radiol Med Date: 2021-05-16 Impact factor: 3.469
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