To assess the utility of histogram and texture analysis of magnetic resonance (MR) fat-suppressed T2-weighted imaging (Fs-T2WI) for the prediction of histological diagnosis of head and neck squamous cell carcinoma (SCC) and malignant lymphoma (ML). The cases of 57 patients with SCC (45 well/moderately and 12 poorly differentiated SCC) and 10 patients with ML were retrospectively analyzed. Quantitative parameters with histogram features (relative mean signal, coefficient of variation, kurtosis and skewness) and gray-level co-occurrence matrix (GLCM) features (contrast, correlation, energy and homogeneity) were calculated using Fs-T2WI data with a manual tumor region of interest (ROI). The following significantly different values were obtained for the total SCC versus ML groups: relative mean signal (3.65 ± 0.86 vs. 2.61 ± 0.49), contrast (72.9 ± 16.2 vs. 49.3 ± 8.7) and homogeneity (2.22 ± 0.25 × 10− 1 vs. 2.53 ± 0.12 × 10− 1). In the comparison of the SCC histological grades, the relative mean signal and contrast were significantly lower in the poorly differentiated SCC (2.89 ± 0.63, 56.2 ± 12.9) compared to the well/moderately SCC (3.85 ± 0.81, 77.5 ± 13.9). The homogeneity in poorly differentiated SCC (2.56 ± 0.15 × 10− 1) was higher than that of the well/moderately SCC (2.1 ± 0.18 × 10− 1). Parameters obtained by histogram and texture analysis of Fs-T2WI may be useful for noninvasive prediction of histological type and grade in head and neck malignancy.
19 April 2018 in International Journal of Clinical Oncology
The purpose of this study was to determine the predictive power for treatment outcome of a machine-learning algorithm combining magnetic resonance imaging (MRI)-derived data in patients with sinonasal squamous cell carcinomas (SCCs). Thirty-six primary lesions in 36 patients were evaluated. Quantitative morphological parameters and intratumoral characteristics from T2-weighted images, tumor perfusion parameters from arterial spin labeling (ASL) and tumor diffusion parameters of five diffusion models from multi-b-value diffusion-weighted imaging (DWI) were obtained. Machine learning by a non-linear support vector machine (SVM) was used to construct the best diagnostic algorithm for the prediction of local control and failure. The diagnostic accuracy was evaluated using a 9-fold cross-validation scheme, dividing patients into training and validation sets. Classification criteria for the division of local control and failure in nine training sets could be constructed with a mean sensitivity of 0.98, specificity of 0.91, positive predictive value (PPV) of 0.94, negative predictive value (NPV) of 0.97, and accuracy of 0.96. The nine validation data sets showed a mean sensitivity of 1.0, specificity of 0.82, PPV of 0.86, NPV of 1.0, and accuracy of 0.92. In conclusion, a machine-learning algorithm using various MR imaging-derived data can be helpful for the prediction of treatment outcomes in patients with sinonasal SCCs.
High-risk human papillomavirus (HPV) infection is associated with carcinogenesis in oropharyngeal squamous cell carcinoma (OPSCC) and patients with HPV-positive tumors have a significantly favorable prognosis. However, the underlying mechanism of this favorable clinical outcome remains unclear. Epithelial-mesenchymal transition (EMT) causes aggressiveness of cancer cells and we investigated the expression of the EMT markers and analyzed their correlation with HPV status and prognosis in order to examine the treatment response of HPV-positive OPSCCs. A total of 79 patients with OPSCC were examined in the present study. All high-risk HPV infections were determined with the multiplex PCR kit from each formalin-fixed paraffin-embedded (FFPE) sample. We performed immunohistochemical staining for E-cadherin and vimentin. Expression of the markers was graded and we statistically analyzed the correlation between tumor, node, metastasis (TNM) stages and prognosis. High-risk HPV-positive tumors were detected in 23 cases. The five‑year survival rate in HPV-positive and -negative tumors was 82.7 and 48.3%, respectively. High E-cadherin expression rate in HPV-negative samples was 76.7% and 43.4% in HPV-positive samples (p=0.007). Vimentin expression did not show a difference between HPV-positive and -negative tumors. HPV-negative patients presented significantly greater heterogeneity of E-cadherin expression compared to HPV-positive patients (p=0.0349). HPV-positive OPSCCs originally lost their epithelial cell phenotype compared with HPV-negative tumors. Therefore, the paradoxical favorable prognosis of HPV-positive OPSCC may be due to the intratumor homogeneity in EMT.
25 July 2012 in International Journal of Clinical Oncology