上海交通大学学报（医学版）

上海交通大学学报（医学版） ›› 2018, Vol. 38 ›› Issue (6): 624-.doi: 10.3969/j.issn.1674-8115.2018.06.007

• 论著·临床研究 • 上一篇    下一篇

肠道CT图像纹理分析和非线性判别分析在结直肠癌及溃疡性结肠炎判别诊断中的应用

王笑 1, 2，所世腾 1，朱炯 1，冯琦 1，华小兰 1，王伟中 2，龚建中 2，刘钧 1，路青 1   

  1. 1. 上海交通大学医学院附属仁济医院放射科，上海200127；2. 上海市浦东医院，复旦大学附属浦东医院放射科，上海201399
  • 出版日期:2018-06-28 发布日期:2018-07-03
  • 通讯作者: 路青，电子信箱：drluqing_rj@163.com。
  • 作者简介:王笑，男（1983—），主治医师，硕士生；电子信箱：radiologue@sina.com。
  • 基金资助:
    国家自然科学基金（81271638，81371622）；上海市浦江人才计划项目（15PJ1405200）

Application of intestinal CT texture analysis and nonlinear discriminant analysis in differential diagnosis of colorectal cancer and ulcerative colitis

WANG Xiao1, 2, SUO Shi-teng1, ZHU Jiong1, FENG Qi1, HUA Xiao-lan1, WANG Wei-zhong2, GONG Jian-zhong2, LIU Jun1, LU Qing1   

  1. 1.Department of Radiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200127, China; 2. Department of Radiology, Shanghai Pudong Hospital, Fudan University Pudong Medical Center, Shanghai 201399, China
  • Online:2018-06-28 Published:2018-07-03
  • Supported by:
    National Natural Science Foundation of China, 81271638,81371622); Shanghai Pujiang Talent Program, 15PJ1405200

PDF (PC)

670

摘要： 目的·探索肠道CT图像纹理分析在结直肠癌（colorectal cancer，CRC）与溃疡性结肠炎（ulcerative colitis，UC）中应用的可行性及其诊断价值。方法·回顾性分析61例CRC患者、62例UC患者及42例无任何肠道疾病者的腹部三期增强扫描CT图像，在不同扫描期采用MaZda软件手动勾画感兴趣区并选择纹理特征。分别使用3种特征筛选法筛选出最具有判别效能的纹理特征，并使用6种特征分类法判别这2种疾病。判别结果以错判率（misclassification rate，MCR）表示。同时由2名具有10年以上消化道疾病影像诊断经验的医师对疾病进行判别，将人眼视觉判别结果与纹理分类判别结果进行比较。结果·纹理分类鉴别CRC和UC在平扫期、动脉期、肠期的平均MCR分别为（28.42±6.89）%、（28.19±4.07）%、（19.10±3.58）%；非线性判别分析（nonlinear discriminant analysis，NDA）较其他分类法的准确性更高，特别在肠期结果最佳，MCR为12.61%。在平扫期、动脉期、肠期，纹理分类鉴别CRC和正常对照肠壁的平均MCR分别为（13.33±7.21）%、（15.49±5.47）%、（6.74±3.02）%，而纹理分类鉴别UC和正常对照肠壁的平均MCR分别为（19.26±4.68）%、（20.04±6.63）%、（16.74±6.36）%。在平扫期、动脉期、肠期，人眼视觉判别CRC和UC的平均MCR分别为（40.48±3.21）%、（35.71±1.60）%、（26.43±1.15）%，而纹理分类计算的MCR较人眼视觉判别的MCR低，计算机纹理分类有更高的鉴别诊断率。结论·肠道CT成像结合计算机纹理分析技术可以作为诊断CRC与UC的辅助手段。NDA分类法较其他分类法准确性更高，特别是在肠期的判别效果最优。

关键词: 体层摄影术, 螺旋计算机, 结直肠癌, 溃疡性结肠炎, 诊断

Abstract:

Objective · To evaluate the value of texture analysis in the discrimination of colorectal cancer (CRC) and ulcerative colitis (UC).Methods · The CT images of 61 CRC patients, 62 UC patients and 42 control objects were retrospectively analyzed. All the patients were pathologically proved and performed triphasic contrast-enhanced CT scan: non-enhanced phase (NP), the arterial phase (AP) and the enteric phase (EP). The region of interest was drawn along the abnormal bowel wall’s edge in each scan phase and texture features were generatedMaZda software. Based on 3 texture feature selection methods, the optimal subsets were generated and analyzed6 texture feature classification methods. The results were shownmisclassification rate (MCR). To compare the performance of texture-based classification and human visual classification, two radiologists with more than 10 years of gastrointestinal disease diagnostic experience analyzed the data. Results · The texture analysis based average MCR of differentiation between CRC and UC was (28.42±6.89)%, (28.19±4.07)%, (19.10±3.58)% in NP, AP, EP respectively. Compared with other texture feature classification methods, nonlinear discriminant analysis (NDA) was more accurate. In EP, NDA achieved an excellent classification result (MCR12.61%). The average MCR between CRC and normally dilated bowel wall (NOR) was (13.33±7.21)%, (15.49±5.47)%, (6.74±3.02)%, while the average MCR between UC and NOR was (19.26±4.68)%, (20.04±6.63)%, (16.74±6.36)% in NP, AP and EP respectively. For visual classification between CRC and UC, the average MCR was (40.48±3.21)%, (35.71±1.60)%, (26.43±1.15)% in NP, AP, EP respectively. But the MCR of texture classification was lower than that of human vision classification, and computer texture classification had higher differential diagnosis rate. Conclusion · The CT-based texture analysis could be a feasible supplementary method to differentiate CRC UC. NDA is more accurate than other classification methods, especially in EP.

Key words: tomography, spiral computed, colorectal neoplasm, ulcerative colitis, diagnosis

中图分类号: