Song Liu1, Huanhuan Zheng1, Xia Pan1, Ling Chen2, Minke Shi3, Yue Guan4, Yun Ge4, Jian He1, Zhengyang Zhou1. 1. Department of Radiology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, China. 2. Department of Pathology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, China. 3. Department of Thoracic and Cardiovascular Surgery, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, China. 4. School of Electronic Science and Engineering, Nanjing University, Nanjing 210046, China.
Abstract
BACKGROUND: To explore the role of texture analysis of computed tomography (CT) images in preoperative assessment of esophageal squamous cell carcinoma (ESCC) aggressiveness. METHODS: Seventy-three patients with pathologically confirmed ESCC underwent unenhanced and contrast enhanced CT imaging preoperatively. Texture analysis was performed on unenhanced and contrast enhanced CT images, respectively. Six CT texture parameters were obtained. One-way analysis of variance or independent-samples t-test (normality), independent-samples Kruskal-Wallis test or Mann-Whitney U test (non-normality), binary Logistic regression analysis (multivariable), Spearman correlation test, receiver operating characteristic (ROC) curve analysis and intraclass correlation coefficient (ICC) were used for statistical analyses. RESULTS: Kurtosis was an independent predictor for T stages (T1-2 vs. T3-4) as well as overall stages (I-II vs. III-IV) based on unenhanced CT images, while entropy was an independent predictor for T stages (T1-2 vs. T3-4), lymph node metastasis (N- vs. N+) and overall stages (I/II vs. III/IV). Skew and kurtosis based on unenhanced CT images showed significant differences among N stages (N0, N1, N2 and N3) as well as 90th percentile based on contrast enhanced CT images. In correlation with T stage of ESCC, kurtosis and entropy significantly correlated with T stage both on unenhanced and contrast enhanced CT images. Reversely, entropy and 90th percentile based on contrast enhanced CT images showed significant correlations with N stage (r: 0.526, 0.265; both P<0.05), as well as overall stage (r: 0.562, 0.315; both P<0.05). For identifying ESCC with different T stages (T1-2 vs. T3-4), lymph node metastasis (N- vs. N+) and overall stages (I/II vs. III/IV), entropy based on contrast enhanced CT images, showed good performance with area under ROC curve area under curve (AUC) of 0.637, 0.815 and 0.778, respectively. CONCLUSIONS: Texture analysis of CT images held great potential in differentiating different T, N and overall stages of ESCC preoperatively, while failed to assess the differentiation degrees.
BACKGROUND: To explore the role of texture analysis of computed tomography (CT) images in preoperative assessment of esophageal squamous cell carcinoma (ESCC) aggressiveness. METHODS: Seventy-three patients with pathologically confirmed ESCC underwent unenhanced and contrast enhanced CT imaging preoperatively. Texture analysis was performed on unenhanced and contrast enhanced CT images, respectively. Six CT texture parameters were obtained. One-way analysis of variance or independent-samples t-test (normality), independent-samples Kruskal-Wallis test or Mann-Whitney U test (non-normality), binary Logistic regression analysis (multivariable), Spearman correlation test, receiver operating characteristic (ROC) curve analysis and intraclass correlation coefficient (ICC) were used for statistical analyses. RESULTS: Kurtosis was an independent predictor for T stages (T1-2 vs. T3-4) as well as overall stages (I-II vs. III-IV) based on unenhanced CT images, while entropy was an independent predictor for T stages (T1-2 vs. T3-4), lymph node metastasis (N- vs. N+) and overall stages (I/II vs. III/IV). Skew and kurtosis based on unenhanced CT images showed significant differences among N stages (N0, N1, N2 and N3) as well as 90th percentile based on contrast enhanced CT images. In correlation with T stage of ESCC, kurtosis and entropy significantly correlated with T stage both on unenhanced and contrast enhanced CT images. Reversely, entropy and 90th percentile based on contrast enhanced CT images showed significant correlations with N stage (r: 0.526, 0.265; both P<0.05), as well as overall stage (r: 0.562, 0.315; both P<0.05). For identifying ESCC with different T stages (T1-2 vs. T3-4), lymph node metastasis (N- vs. N+) and overall stages (I/II vs. III/IV), entropy based on contrast enhanced CT images, showed good performance with area under ROC curve area under curve (AUC) of 0.637, 0.815 and 0.778, respectively. CONCLUSIONS: Texture analysis of CT images held great potential in differentiating different T, N and overall stages of ESCC preoperatively, while failed to assess the differentiation degrees.
Authors: Taryn Hodgdon; Matthew D F McInnes; Nicola Schieda; Trevor A Flood; Leslie Lamb; Rebecca E Thornhill Journal: Radiology Date: 2015-04-23 Impact factor: 11.105
Authors: Pablo G Cavalcanti; Shahram Shirani; Jacob Scharcanski; Crystal Fong; Jane Meng; Jane Castelli; David Koff Journal: Quant Imaging Med Surg Date: 2016-02
Authors: Sheng-Xiang Rao; Doenja Mj Lambregts; Roald S Schnerr; Wenzel van Ommen; Thiemo Ja van Nijnatten; Milou H Martens; Luc A Heijnen; Walter H Backes; Cornelis Verhoef; Meng-Su Zeng; Geerard L Beets; Regina Gh Beets-Tan Journal: United European Gastroenterol J Date: 2014-12 Impact factor: 4.623
Authors: Stephen S F Yip; Thibaud P Coroller; Nina N Sanford; Elizabeth Huynh; Harvey Mamon; Hugo J W L Aerts; Ross I Berbeco Journal: Phys Med Biol Date: 2016-01-07 Impact factor: 3.609