Liliana Caldeira1, Thorsten Persigehl2, Simon Lennartz1,3,4, Alina Mager1, Nils Große Hokamp1, Sebastian Schäfer5, David Zopfs1, David Maintz1, Hans Christian Reinhardt6,7, Roman K Thomas8. 1. Department of Diagnostic and Interventional Radiology, University of Cologne, Faculty of Medicine and University Hospital Cologne, Kerpener Straße 62, 50937, Cologne, Germany. 2. Department of Diagnostic and Interventional Radiology, University of Cologne, Faculty of Medicine and University Hospital Cologne, Kerpener Straße 62, 50937, Cologne, Germany. thorsten.persigehl@uk-koeln.de. 3. Else Kröner Forschungskolleg Clonal Evolution in Cancer, University Hospital Cologne, Weyertal 115b, 50931, Cologne, Germany. 4. Department of Radiology, Massachusetts General Hospital, 55 Fruit St, White 270, Boston, MA, 02114, USA. 5. Mint Medical GmbH, Burgstraße 61, 69121, Heidelberg, Germany. 6. Clinic I of Internal Medicine, University Hospital Cologne, 50931, Cologne, Germany. 7. Department of Hematology and Stem Cell Transplantation, University Hospital Essen, University Duisburg-Essen, German Cancer Consortium (DKTK partner site Essen), Essen, Germany. 8. Department of Translational Genomics, Center of Integrated Oncology Cologne-Bonn, Medical Faculty, University of Cologne, 50931, Cologne, Germany.
Abstract
BACKGROUND: The purpose of this study was to analyze if the use of texture analysis on spectral detector CT (SDCT)-derived iodine maps (IM) in addition to conventional images (CI) improves lung nodule differentiation, when being applied to a k-nearest neighbor (KNN) classifier. METHODS: 183 cancer patients who underwent contrast-enhanced, venous phase SDCT of the chest were included: 85 patients with 146 benign lung nodules (BLN) confirmed by either prior/follow-up CT or histopathology and 98 patients with 425 lung metastases (LM) verified by histopathology, 18F-FDG-PET-CT or unequivocal change during treatment. Semi-automatic 3D segmentation of BLN/LM was performed, and volumetric HU attenuation and iodine concentration were acquired. For conventional images and iodine maps, average, standard deviation, entropy, kurtosis, mean of the positive pixels (MPP), skewness, uniformity and uniformity of the positive pixels (UPP) within the volumes of interests were calculated. All acquired parameters were transferred to a KNN classifier. RESULTS: Differentiation between BLN and LM was most accurate, when using all CI-derived features combined with the most significant IM-derived feature, entropy (Accuracy:0.87; F1/Dice:0.92). However, differentiation accuracy based on the 4 most powerful CI-derived features performed only slightly inferior (Accuracy:0.84; F1/Dice:0.89, p=0.125). Mono-parametric lung nodule differentiation based on either feature alone (i.e. attenuation or iodine concentration) was poor (AUC=0.65, 0.58, respectively). CONCLUSIONS: First-order texture feature analysis of contrast-enhanced staging SDCT scans of the chest yield accurate differentiation between benign and metastatic lung nodules. In our study cohort, the most powerful iodine map-derived feature slightly, yet insignificantly increased classification accuracy compared to classification based on conventional image features only.
BACKGROUND: The purpose of this study was to analyze if the use of texture analysis on spectral detector CT (SDCT)-derived iodine maps (IM) in addition to conventional images (CI) improves lung nodule differentiation, when being applied to a k-nearest neighbor (KNN) classifier. METHODS: 183 cancerpatients who underwent contrast-enhanced, venous phase SDCT of the chest were included: 85 patients with 146 benign lung nodules (BLN) confirmed by either prior/follow-up CT or histopathology and 98 patients with 425 lung metastases (LM) verified by histopathology, 18F-FDG-PET-CT or unequivocal change during treatment. Semi-automatic 3D segmentation of BLN/LM was performed, and volumetric HU attenuation and iodine concentration were acquired. For conventional images and iodine maps, average, standard deviation, entropy, kurtosis, mean of the positive pixels (MPP), skewness, uniformity and uniformity of the positive pixels (UPP) within the volumes of interests were calculated. All acquired parameters were transferred to a KNN classifier. RESULTS: Differentiation between BLN and LM was most accurate, when using all CI-derived features combined with the most significant IM-derived feature, entropy (Accuracy:0.87; F1/Dice:0.92). However, differentiation accuracy based on the 4 most powerful CI-derived features performed only slightly inferior (Accuracy:0.84; F1/Dice:0.89, p=0.125). Mono-parametric lung nodule differentiation based on either feature alone (i.e. attenuation or iodine concentration) was poor (AUC=0.65, 0.58, respectively). CONCLUSIONS: First-order texture feature analysis of contrast-enhanced staging SDCT scans of the chest yield accurate differentiation between benign and metastatic lung nodules. In our study cohort, the most powerful iodine map-derived feature slightly, yet insignificantly increased classification accuracy compared to classification based on conventional image features only.
Authors: M Beth McCarville; Henrique M Lederman; Victor M Santana; Najat C Daw; Stephen J Shochat; Chin-Shang Li; Robert A Kaufman Journal: Radiology Date: 2006-05 Impact factor: 11.105
Authors: Hee-Dong Chae; Chang Min Park; Sang Joon Park; Sang Min Lee; Kwang Gi Kim; Jin Mo Goo Journal: Radiology Date: 2014-08-01 Impact factor: 11.105
Authors: Samuel Hawkins; Hua Wang; Ying Liu; Alberto Garcia; Olya Stringfield; Henry Krewer; Qian Li; Dmitry Cherezov; Robert A Gatenby; Yoganand Balagurunathan; Dmitry Goldgof; Matthew B Schabath; Lawrence Hall; Robert J Gillies Journal: J Thorac Oncol Date: 2016-07-13 Impact factor: 15.609