Abstract：Objective: To explore the diagnosis value of high-resolution computed tomography image texture analysis for solitary pulmonary solid nodule. Methods: A total of 98 patients with solitary pulmonary solid nodule were reviewed. Texture analysis was performed on high-resolution computed tomography image by software of Mazda to obtain the misclassification rate between benign and malignant pulmonary solid nodules. The procedure of texture analysis included analysis of texture parameters, selection of typical texture parameters(fisher coefficient, mutual information, classification error probability combined average correlation coefficients, and combined the three above(FPM)), and classification of the typical texture parameters(linear discriminant analysis, nonlinear discriminant analysis, raw data analysis). Then, the misclassification rate was compared between texture analysis and chest-radiologists. Results: The misclassification rate was the lowest with 6.1%(6/98) through FPM selection and nonlinear discriminant analysis statistical method, and was comparable with chest-radiologists(P<0.05). Conclusion: High-resolution computed tomography image texture analysis is a new important way for differential diagnosis of solitary pulmonary solid nodule.
徐志华，杨光钊，陈松宽，王 健，邵美华，贾玉柱. 高分辨率CT图像纹理分析对孤立性肺实性结节的诊断价值研究[J]. 中国临床医学影像杂志, 2020, 31(2): 98-101.
XU Zhi-hua, YANG Guang-zhao, CHEN Song-kuan, WANG Jian, SHAO Mei-hua, JIA Yu-zhu. The diagnosis value of high-resolution computed tomography image texture analysis for solitary pulmonary solid nodule. JOURNAL OF CHINA MEDICAL IMAGING, 2020, 31(2): 98-101.
[1]萧毅，刘士远. 肺结节影像人工智能技术现状与思考[J]. 肿瘤影像，2018，27（4）：249-252.
[2]李辉，阚晓婧，宁培刚，等. HRCT常见恶性征象对孤立性肺结节的定性诊断[J]. 放射学实践，2014，29（12）：1405-1408.
[3]白玥，辛秀琴，孟珊珊，等. 高分辨CT表现对孤立性肺结节良恶性鉴别的研究进展[J]. 中国老年学杂志，2015，35（19）：5670-5672.
[4]叶风平，许兵，孙高峰. 高分辨CT征象对肺内孤立结节良恶性的鉴别诊断价值分析[J]. 海军医学杂志，2015，36（6）：517-519.
[5]Castellano G, Bonilha L, Li LM, et al. Texture analysis of medical images[J]. Clinl Radiol, 2004, 59(12): 1061-1069.
[6]任采月，王升平，任敏，等. CT纹理分析在胃肠间质瘤危险度分级价值的初步研究[J]. 实用放射学杂志，2019，35（2）：228-231.
[7]Larroza A, Materka A, Lopez-Lereu MP, et al. Differentiation between acute and chronic myocardial infarction by means of texture analysis of late gadolinium enhancement and cine cardiac magnetic resonance imaging[J]. Eur J Radiol, 2017, 92(2017): 78-83.
[8]赵丽，梁萌，马霄虹，等. 增强MRI纹理分析技术对肝内胆管细胞癌术后早期复发的预测价值[J]. 实用放射学杂志，2018，34（7）：1039-1043.
[9]于浩鹏，李谋，张琳，等. CT图像纹理分析评估胰腺神经内分泌肿瘤的病理分级[J]. 中国临床医学影像杂志，2018，29（11）：788-791.
[10]Kocak B, Yardimci AH, Bektas CT, et al. Textural differences between renal cell carcinoma subtypes: Machine learning-based quantitative computed tomography texture analysis with independent external validation[J]. Eur J Radiol, 2018, 107(2018): 149-157.
[11]Marius EM. Texture-based classification of focal liver lesions on MRI at 3.0 Tesla: a feasibility study in cysts and hemangiomas[J]. J Magn Reson Imaging, 2010, 32(2): 352-359.
[12]Mayerhoefer ME, Breitenseher M, Amann G, et al. Are signal intensity and homogeneity useful parameters for distinguishing between benign and malignant soft tissue masses on MR images: Objective evaluation by means of texture analysis[J]. J Magn Reson Imaging, 2008, 26(9): 1316-1322.
[13]黎金葵，闫坤，杨品，等. PET/CT结合HRCT诊断孤立性肺结节的应用价值：Meta分析[J]. 中国CT和MRI杂志，2017，15（1）：41-44.
[14]张建功，史讯. PET/CT联合HRCT在诊断孤立性肺结节中的应用价值分析[J]. 中外医疗，2018，37（23）：185-187.
[15]李兰涛，林红雨，王海燕，等. HRCT与PET/CT联合诊断孤立性肺结节[J]. 中国医学影像技术，2013，29（3）：425-428.
2020, Vol. 31 
