AUTHOR=Li Xin-xiang , Lin Ting-ting , Liu Bin , Wei Wei 

TITLE=Diagnosis of Cervical Cancer With Parametrial Invasion on Whole-Tumor Dynamic Contrast-Enhanced Magnetic Resonance Imaging Combined With Whole-Lesion Texture Analysis Based on T2- Weighted Images

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=8

YEAR=2020

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2020.00590

DOI=10.3389/fbioe.2020.00590

ISSN=2296-4185

ABSTRACT=<p><bold>Purpose:</bold> To evaluate the diagnostic value of the combination of whole-tumor dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and whole-lesion texture features based on T2–weighted images for cervical cancer with parametrial invasion.</p><p><bold>Materials and Methods:</bold> Sixty-two patients with cervical cancer (27 with parametrial invasion and 35 without invasion) preoperatively underwent routine MRI and DCE-MRI examinations. DCE-MRI parameters (K<sup>trans</sup>, K<sub>ep</sub>, and V<sub>e</sub>) and texture features (mean, skewness, kurtosis, uniformity, energy, and entropy) based on T2-weighted images were acquired by two observers. All parameters of parametrial invasion and non-invasion were analyzed by one-way analysis of variance. The diagnostic efficiency of significant variables was assessed using receiver operating characteristic analysis.</p><p><bold>Results:</bold> The invasion group of cervical cancer demonstrated significantly higher K<sup>trans</sup> (0.335 ± 0.050 vs. 0.269 ± 0.079; <italic>p</italic> &lt; 0.001), lower energy values (0.503 ± 0.093 vs. 0.602 ± 0.087; <italic>p</italic> &lt; 0.001), and higher entropy values (1.391 ± 0.193 vs. 1.24 ± 0.129; <italic>p</italic> &lt; 0.001) than those in the non-invasion group. Optimal diagnostic performance [area under curve [AUC], 0.925; sensitivity, 0.935; specificity, 0.829] could be obtained by the combination of K<sup>trans</sup>, energy, and entropy values. The AUC values of K<sup>trans</sup> (0.788), energy (0.761), entropy (0.749), the combination of K<sup>trans</sup> and energy (0.814), the combination of K<sup>trans</sup> and entropy (0.727), and the combination of energy and entropy (0.619) were lower than those of the combination of K<sup>trans</sup>, energy, and entropy values.</p><p><bold>Conclusion:</bold> The combination of DCE-MRI and texture analysis is a promising method for diagnosis cervical cancer with parametrial infiltration. Moreover, the combination of K<sup>trans</sup>, energy, and entropy is more valuable than any one alone, especially in improving diagnostic sensitivity.</p>