OBJECTIVE: To assess the accuracy of CT texture and shape analysis in the differentiation of benign and malignant mediastinal nodes in lung cancer. METHODS: Forty-three patients with biopsy-proven primary lung malignancy with pathological mediastinal nodal staging and unenhanced CT of the thorax were studied retrospectively. Grey-level co-occurrence and run-length matrix textural features, as well as morphological features, were extracted from 72 nodes. Differences between benign and malignant features were assessed using Mann-Whitney U tests. Receiver operating characteristic (ROC) curves for each were constructed and the area under the curve (AUC) calculated with histopathology diagnosis as outcome. Combinations of features were also entered as predictors in logistic regression models and optimal threshold criteria were used to estimate sensitivity and specificity. RESULTS: Using optimum-threshold criteria, the combined textural and shape features identified malignant mediastinal nodes with 81% sensitivity and 80% specificity (AUC = 0.87, P < 0.0001). Using this combination, 84% malignant and 71% benign nodes were correctly classified. CONCLUSIONS: Quantitative CT texture and shape analysis has the potential to accurately differentiate malignant and benign mediastinal nodes in lung cancer. KEY POINTS: • Mediastinal nodal staging is crucial in the management of lung cancer • Mediastinal nodal metastasis affects prognosis and suitability for surgical treatment • Computed tomography (CT) is limited for mediastinal nodal staging • Texture analysis measures tissue heterogeneity not perceptible to human vision • CT texture analysis may accurately differentiate malignant and benign mediastinal nodes.
OBJECTIVE: To assess the accuracy of CT texture and shape analysis in the differentiation of benign and malignant mediastinal nodes in lung cancer. METHODS: Forty-three patients with biopsy-proven primary lung malignancy with pathological mediastinal nodal staging and unenhanced CT of the thorax were studied retrospectively. Grey-level co-occurrence and run-length matrix textural features, as well as morphological features, were extracted from 72 nodes. Differences between benign and malignant features were assessed using Mann-Whitney U tests. Receiver operating characteristic (ROC) curves for each were constructed and the area under the curve (AUC) calculated with histopathology diagnosis as outcome. Combinations of features were also entered as predictors in logistic regression models and optimal threshold criteria were used to estimate sensitivity and specificity. RESULTS: Using optimum-threshold criteria, the combined textural and shape features identified malignant mediastinal nodes with 81% sensitivity and 80% specificity (AUC = 0.87, P < 0.0001). Using this combination, 84% malignant and 71% benign nodes were correctly classified. CONCLUSIONS: Quantitative CT texture and shape analysis has the potential to accurately differentiate malignant and benign mediastinal nodes in lung cancer. KEY POINTS: • Mediastinal nodal staging is crucial in the management of lung cancer • Mediastinal nodal metastasis affects prognosis and suitability for surgical treatment • Computed tomography (CT) is limited for mediastinal nodal staging • Texture analysis measures tissue heterogeneity not perceptible to human vision • CT texture analysis may accurately differentiate malignant and benign mediastinal nodes.
Authors: Balaji Ganeshan; Vicky Goh; Henry C Mandeville; Quan Sing Ng; Peter J Hoskin; Kenneth A Miles Journal: Radiology Date: 2012-11-20 Impact factor: 11.105
Authors: T C McLoud; P M Bourgouin; R W Greenberg; J P Kosiuk; P A Templeton; J A Shepard; E H Moore; J C Wain; D J Mathisen; H C Grillo Journal: Radiology Date: 1992-02 Impact factor: 11.105
Authors: Fergus Davnall; Connie S P Yip; Gunnar Ljungqvist; Mariyah Selmi; Francesca Ng; Bal Sanghera; Balaji Ganeshan; Kenneth A Miles; Gary J Cook; Vicky Goh Journal: Insights Imaging Date: 2012-10-24
Authors: Christoph Frank Dietrich; Jouke Tabe Annema; Paul Clementsen; Xin Wu Cui; Mathias Maximilian Borst; Christian Jenssen Journal: J Thorac Dis Date: 2015-09 Impact factor: 2.895
Authors: He An; Yiang Wang; Esther M F Wong; Shanshan Lyu; Lujun Han; Jose A U Perucho; Peng Cao; Elaine Y P Lee Journal: Eur Radiol Date: 2021-01-06 Impact factor: 5.315
Authors: Raymond H Mak; Hugo J W L Aerts; Thibaud P Coroller; Vishesh Agrawal; Elizabeth Huynh; Vivek Narayan; Stephanie W Lee Journal: J Thorac Oncol Date: 2016-11-27 Impact factor: 15.609
Authors: Xenia Fave; Dennis Mackin; Jinzhong Yang; Joy Zhang; David Fried; Peter Balter; David Followill; Daniel Gomez; A Kyle Jones; Francesco Stingo; Jonas Fontenot; Laurence Court Journal: Med Phys Date: 2015-12 Impact factor: 4.071